agora inbox for [email protected]help / color / mirror / Atom feed
[PATCH 4/5] Change conversion function signature. 34+ messages / 6 participants [nested] [flat]
* [PATCH 4/5] Change conversion function signature. @ 2020-12-16 10:13 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 34+ messages in thread From: Heikki Linnakangas @ 2020-12-16 10:13 UTC (permalink / raw) Add a 'noError' argument, so that we can try to convert a buffer without knowing the character boundaries beforehand. The functions now need to return the number of input bytes successfully converted. TODO: Upgrade? --- doc/src/sgml/ref/create_conversion.sgml | 5 +- src/backend/commands/conversioncmds.c | 27 +- src/backend/utils/error/elog.c | 2 + src/backend/utils/mb/conv.c | 112 +++++- .../cyrillic_and_mic/cyrillic_and_mic.c | 127 ++++--- .../euc2004_sjis2004/euc2004_sjis2004.c | 96 ++++- .../euc_cn_and_mic/euc_cn_and_mic.c | 57 ++- .../euc_jp_and_sjis/euc_jp_and_sjis.c | 153 ++++++-- .../euc_kr_and_mic/euc_kr_and_mic.c | 57 ++- .../euc_tw_and_big5/euc_tw_and_big5.c | 165 +++++++-- .../latin2_and_win1250/latin2_and_win1250.c | 49 ++- .../latin_and_mic/latin_and_mic.c | 43 ++- .../utf8_and_big5/utf8_and_big5.c | 37 +- .../utf8_and_cyrillic/utf8_and_cyrillic.c | 67 ++-- .../utf8_and_euc2004/utf8_and_euc2004.c | 37 +- .../utf8_and_euc_cn/utf8_and_euc_cn.c | 37 +- .../utf8_and_euc_jp/utf8_and_euc_jp.c | 37 +- .../utf8_and_euc_kr/utf8_and_euc_kr.c | 37 +- .../utf8_and_euc_tw/utf8_and_euc_tw.c | 37 +- .../utf8_and_gb18030/utf8_and_gb18030.c | 37 +- .../utf8_and_gbk/utf8_and_gbk.c | 37 +- .../utf8_and_iso8859/utf8_and_iso8859.c | 43 ++- .../utf8_and_iso8859_1/utf8_and_iso8859_1.c | 27 +- .../utf8_and_johab/utf8_and_johab.c | 37 +- .../utf8_and_sjis/utf8_and_sjis.c | 37 +- .../utf8_and_sjis2004/utf8_and_sjis2004.c | 37 +- .../utf8_and_uhc/utf8_and_uhc.c | 37 +- .../utf8_and_win/utf8_and_win.c | 43 ++- src/backend/utils/mb/mbutils.c | 13 +- src/include/catalog/pg_proc.dat | 332 +++++++++--------- src/include/mb/pg_wchar.h | 49 +-- src/test/regress/expected/opr_sanity.out | 7 +- src/test/regress/sql/opr_sanity.sql | 7 +- 33 files changed, 1292 insertions(+), 633 deletions(-) diff --git a/doc/src/sgml/ref/create_conversion.sgml b/doc/src/sgml/ref/create_conversion.sgml index e7700fecfc5..f014a676c88 100644 --- a/doc/src/sgml/ref/create_conversion.sgml +++ b/doc/src/sgml/ref/create_conversion.sgml @@ -117,8 +117,9 @@ conv_proc( integer, -- destination encoding ID cstring, -- source string (null terminated C string) internal, -- destination (fill with a null terminated C string) - integer -- source string length -) RETURNS void; + integer, -- source string length + boolean -- if true, don't throw an error if conversion fails +) RETURNS integer; </programlisting></para> </listitem> </varlistentry> diff --git a/src/backend/commands/conversioncmds.c b/src/backend/commands/conversioncmds.c index 0ee3b6d19a3..2d032a802f5 100644 --- a/src/backend/commands/conversioncmds.c +++ b/src/backend/commands/conversioncmds.c @@ -45,8 +45,9 @@ CreateConversionCommand(CreateConversionStmt *stmt) const char *from_encoding_name = stmt->for_encoding_name; const char *to_encoding_name = stmt->to_encoding_name; List *func_name = stmt->func_name; - static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID}; + static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID, BOOLOID}; char result[1]; + Datum funcresult; /* Convert list of names to a name and namespace */ namespaceId = QualifiedNameGetCreationNamespace(stmt->conversion_name, @@ -92,8 +93,8 @@ CreateConversionCommand(CreateConversionStmt *stmt) funcoid = LookupFuncName(func_name, sizeof(funcargs) / sizeof(Oid), funcargs, false); - /* Check it returns VOID, else it's probably the wrong function */ - if (get_func_rettype(funcoid) != VOIDOID) + /* Check it returns int4, else it's probably the wrong function */ + if (get_func_rettype(funcoid) != INT4OID) ereport(ERROR, (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), errmsg("encoding conversion function %s must return type %s", @@ -111,12 +112,20 @@ CreateConversionCommand(CreateConversionStmt *stmt) * string; the conversion function should throw an error if it can't * perform the requested conversion. */ - OidFunctionCall5(funcoid, - Int32GetDatum(from_encoding), - Int32GetDatum(to_encoding), - CStringGetDatum(""), - CStringGetDatum(result), - Int32GetDatum(0)); + funcresult = OidFunctionCall6(funcoid, + Int32GetDatum(from_encoding), + Int32GetDatum(to_encoding), + CStringGetDatum(""), + CStringGetDatum(result), + Int32GetDatum(0), + BoolGetDatum(false)); + + /* The function should return 0 for empty input. Might as well check that, too. */ + if (DatumGetInt32(funcresult) != 0) + ereport(ERROR, + (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), + errmsg("encoding conversion function %s returned incorrect result for empty input", + NameListToString(func_name)))); /* * All seem ok, go ahead (possible failure would be a duplicate conversion diff --git a/src/backend/utils/error/elog.c b/src/backend/utils/error/elog.c index 3558e660c73..8b9d794dd33 100644 --- a/src/backend/utils/error/elog.c +++ b/src/backend/utils/error/elog.c @@ -2266,6 +2266,8 @@ write_console(const char *line, int len) * Conversion on non-win32 platforms is not implemented yet. It requires * non-throw version of pg_do_encoding_conversion(), that converts * unconvertable characters to '?' without errors. + * + * XXX: We have a no-throw version now. It doesn't convert to '?' though. */ #endif diff --git a/src/backend/utils/mb/conv.c b/src/backend/utils/mb/conv.c index 192948caad2..91251cf70e7 100644 --- a/src/backend/utils/mb/conv.c +++ b/src/backend/utils/mb/conv.c @@ -26,14 +26,16 @@ * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the target charset, or 0 if there is no equivalent code. */ -void +int local2local(const unsigned char *l, unsigned char *p, int len, int src_encoding, int dest_encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -41,7 +43,11 @@ local2local(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(src_encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -50,13 +56,19 @@ local2local(const unsigned char *l, if (c2) *p++ = c2; else + { + if (noError) + break; report_untranslatable_char(src_encoding, dest_encoding, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -67,17 +79,22 @@ local2local(const unsigned char *l, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = l; int c1; while (len > 0) { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (IS_HIGHBIT_SET(c1)) *p++ = lc; *p++ = c1; @@ -85,6 +102,8 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, len--; } *p = '\0'; + + return l - start; } /* @@ -95,17 +114,22 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -118,17 +142,27 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1])) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); + } *p++ = mic[1]; mic += 2; len -= 2; } } *p = '\0'; + + return mic - start; } @@ -144,14 +178,16 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the mule encoding, or 0 if there is no equivalent code. */ -void +int latin2mic_with_table(const unsigned char *l, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -159,7 +195,11 @@ latin2mic_with_table(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -171,13 +211,19 @@ latin2mic_with_table(const unsigned char *l, *p++ = c2; } else + { + if (noError) + break; report_untranslatable_char(encoding, PG_MULE_INTERNAL, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -192,14 +238,16 @@ latin2mic_with_table(const unsigned char *l, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the local charset, or 0 if there is no equivalent code. */ -void +int mic2latin_with_table(const unsigned char *mic, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = mic; unsigned char c1, c2; @@ -207,7 +255,11 @@ mic2latin_with_table(const unsigned char *mic, { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -220,11 +272,17 @@ mic2latin_with_table(const unsigned char *mic, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1]) || (c2 = tab[mic[1] - HIGHBIT]) == 0) { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); break; /* keep compiler quiet */ @@ -235,6 +293,8 @@ mic2latin_with_table(const unsigned char *mic, } } *p = '\0'; + + return mic - start; } /* @@ -425,17 +485,19 @@ pg_mb_radix_conv(const pg_mb_radix_tree *rt, * * See pg_wchar.h for more details about the data structures used here. */ -void +int UtfToLocal(const unsigned char *utf, int len, unsigned char *iso, const pg_mb_radix_tree *map, const pg_utf_to_local_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, bool noError) { uint32 iutf; int l; const pg_utf_to_local_combined *cp; + const unsigned char *start = utf; + const unsigned char *cur = utf; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -449,6 +511,8 @@ UtfToLocal(const unsigned char *utf, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*utf == '\0') break; @@ -584,15 +648,19 @@ UtfToLocal(const unsigned char *utf, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(PG_UTF8, encoding, (const char *) (utf - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(PG_UTF8, (const char *) utf, len); *iso = '\0'; + + return cur - start; } /* @@ -616,18 +684,24 @@ UtfToLocal(const unsigned char *utf, int len, * (if provided) is applied. An error is raised if no match is found. * * See pg_wchar.h for more details about the data structures used here. + * + * Returns the number of input bytes consumed. If noError is true, this can + * be less than 'len'. */ -void +int LocalToUtf(const unsigned char *iso, int len, unsigned char *utf, const pg_mb_radix_tree *map, const pg_local_to_utf_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, + bool noError) { uint32 iiso; int l; const pg_local_to_utf_combined *cp; + const unsigned char *start = iso; + const unsigned char *cur = iso; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -641,6 +715,8 @@ LocalToUtf(const unsigned char *iso, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*iso == '\0') break; @@ -723,13 +799,17 @@ LocalToUtf(const unsigned char *iso, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(encoding, PG_UTF8, (const char *) (iso - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(encoding, (const char *) iso, len); *utf = '\0'; + + return cur - start; } diff --git a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c index 376b48ca611..986c0c0c37d 100644 --- a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c @@ -44,8 +44,11 @@ PG_FUNCTION_INFO_V1(win866_to_iso); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -306,12 +309,14 @@ koi8r_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -320,12 +325,14 @@ mic_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_KOI8R); - mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -334,12 +341,14 @@ iso_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -348,12 +357,14 @@ mic_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_ISO_8859_5); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -362,12 +373,14 @@ win1251_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -376,12 +389,14 @@ mic_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1251); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -390,12 +405,14 @@ win866_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -404,12 +421,14 @@ mic_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN866); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -418,12 +437,14 @@ koi8r_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN1251); - local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -432,12 +453,14 @@ win1251_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_KOI8R); - local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi); + converted = local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -446,12 +469,14 @@ koi8r_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN866); - local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -460,12 +485,14 @@ win866_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_KOI8R); - local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi); + converted = local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -474,12 +501,14 @@ win866_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_WIN1251); - local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251); + converted = local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -488,12 +517,14 @@ win1251_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_WIN866); - local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866); + converted = local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -502,12 +533,14 @@ iso_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_KOI8R); - local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -516,12 +549,14 @@ koi8r_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_ISO_8859_5); - local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso); + converted = local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -530,12 +565,14 @@ iso_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN1251); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -544,12 +581,14 @@ win1251_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso); + converted = local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -558,12 +597,14 @@ iso_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN866); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -572,10 +613,12 @@ win866_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso); + converted = local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c index 3628e690aa1..40f231c12dc 100644 --- a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c @@ -19,8 +19,8 @@ PG_MODULE_MAGIC; PG_FUNCTION_INFO_V1(euc_jis_2004_to_shift_jis_2004); PG_FUNCTION_INFO_V1(shift_jis_2004_to_euc_jis_2004); -static void euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len); -static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len); +static int euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError); /* ---------- * conv_proc( @@ -28,8 +28,11 @@ static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -39,12 +42,14 @@ euc_jis_2004_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_SHIFT_JIS_2004); - euc_jis_20042shift_jis_2004(src, dest, len); + converted = euc_jis_20042shift_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -53,20 +58,23 @@ shift_jis_2004_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_EUC_JIS_2004); - shift_jis_20042euc_jis_2004(src, dest, len); + converted = shift_jis_20042euc_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_JIS_2004 -> SHIFT_JIS_2004 */ -static void -euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, ku, ten; @@ -79,8 +87,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -90,8 +102,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) l = pg_encoding_verifymbchar(PG_EUC_JIS_2004, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (c1 == SS2 && l == 2) /* JIS X 0201 kana? */ { @@ -121,8 +137,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) *p++ = (ku + 0x19b) >> 1; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } if (ku % 2) @@ -132,8 +152,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; @@ -149,8 +173,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ku >= 63 && ku <= 94) *p++ = (ku + 0x181) >> 1; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (ku % 2) { @@ -159,20 +187,30 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else - report_invalid_encoding(PG_EUC_JIS_2004, + { + if (noError) + break; + report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } euc += l; len -= l; } *p = '\0'; + + return euc - start; } /* @@ -212,9 +250,10 @@ get_ten(int b, int *ku) * SHIFT_JIS_2004 ---> EUC_JIS_2004 */ -static void -shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len) +static int +shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1; int ku, ten, @@ -230,8 +269,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -241,8 +284,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len l = pg_encoding_verifymbchar(PG_SHIFT_JIS_2004, (const char *) sjis, len); if (l < 0 || l > len) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf && l == 1) { @@ -266,8 +313,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x100; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xe0 && c1 <= 0xef) /* plane 1 62ku-94ku */ @@ -275,9 +326,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x180; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, - (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xf0 && c1 <= 0xf3) /* plane 2 @@ -286,8 +340,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } switch (c1) { case 0xf0: @@ -309,16 +367,24 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 == 0xf4 && kubun == 1) ku = 15; else ku = (c1 << 1) - 0x19a - kubun; } else + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (plane == 2) *p++ = SS3; @@ -330,4 +396,6 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c index 59c6c3bb129..ad9ebac39b1 100644 --- a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_cn2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_cn(const unsigned char *mic, unsigned char *p, int len); +static int euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_cn_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_cn_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_MULE_INTERNAL); - euc_cn2mic(src, dest, len); + converted = euc_cn2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_CN); - mic2euc_cn(src, dest, len); + converted = mic2euc_cn(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_CN ---> MIC */ -static void -euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; while (len > 0) @@ -76,7 +84,11 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (len < 2 || !IS_HIGHBIT_SET(euc[1])) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = LC_GB2312_80; *p++ = c1; *p++ = euc[1]; @@ -86,21 +98,28 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_CN */ -static void -mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) @@ -109,11 +128,19 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (c1 != LC_GB2312_80) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_CN, (const char *) mic, len); + } if (len < 3 || !IS_HIGHBIT_SET(mic[1]) || !IS_HIGHBIT_SET(mic[2])) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } mic++; *p++ = *mic++; *p++ = *mic++; @@ -122,12 +149,18 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; } } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c index ea05436596d..81064cb6e98 100644 --- a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c @@ -42,17 +42,20 @@ PG_FUNCTION_INFO_V1(mic_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void sjis2mic(const unsigned char *sjis, unsigned char *p, int len); -static void mic2sjis(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_jp(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len); -static void sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len); +static int sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError); +static int mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_jp_to_sjis(PG_FUNCTION_ARGS) @@ -60,12 +63,14 @@ euc_jp_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_SJIS); - euc_jp2sjis(src, dest, len); + converted = euc_jp2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -74,12 +79,14 @@ sjis_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_EUC_JP); - sjis2euc_jp(src, dest, len); + converted = sjis2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -88,12 +95,14 @@ euc_jp_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_MULE_INTERNAL); - euc_jp2mic(src, dest, len); + converted = euc_jp2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -102,12 +111,14 @@ mic_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_JP); - mic2euc_jp(src, dest, len); + converted = mic2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -116,12 +127,14 @@ sjis_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_MULE_INTERNAL); - sjis2mic(src, dest, len); + converted = sjis2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -130,20 +143,23 @@ mic_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_SJIS); - mic2sjis(src, dest, len); + converted = mic2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * SJIS ---> MIC */ -static void -sjis2mic(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -167,7 +183,11 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) * JIS X0208, X0212, user defined extended characters */ if (len < 2 || !ISSJISHEAD(c1) || !ISSJISTAIL(sjis[1])) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } c2 = sjis[1]; k = (c1 << 8) + c2; if (k >= 0xed40 && k < 0xf040) @@ -257,21 +277,28 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; } } *p = '\0'; + + return sjis - start; } /* * MIC ---> SJIS */ -static void -mic2sjis(const unsigned char *mic, unsigned char *p, int len) +static int +mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1, c2, k, @@ -284,8 +311,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -293,8 +324,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) *p++ = mic[1]; else if (c1 == LC_JISX0208) @@ -350,20 +385,27 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_SJIS, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP ---> MIC */ -static void -euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -374,8 +416,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -383,8 +429,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* 1 byte kana? */ *p++ = LC_JISX0201K; @@ -406,14 +456,17 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_JP */ -static void -mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -424,8 +477,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -433,8 +490,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) { *p++ = SS2; @@ -452,20 +513,27 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_JP, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP -> SJIS */ -static void -euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, c2, k; @@ -478,8 +546,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -487,8 +559,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* hankaku kana? */ @@ -551,14 +627,17 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * SJIS ---> EUC_JP */ -static void -sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -573,8 +652,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -582,8 +665,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_SJIS, (const char *) sjis, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf) { /* JIS X0201 (1 byte kana) */ @@ -680,4 +767,6 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c index 600c5cbc5cd..5a44262834a 100644 --- a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_kr2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_kr(const unsigned char *mic, unsigned char *p, int len); +static int euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_kr_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_kr_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_MULE_INTERNAL); - euc_kr2mic(src, dest, len); + converted = euc_kr2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_KR); - mic2euc_kr(src, dest, len); + converted = mic2euc_kr(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_KR ---> MIC */ -static void -euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -78,8 +86,12 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_KR, (const char *) euc, len); if (l != 2) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = LC_KS5601; *p++ = c1; *p++ = euc[1]; @@ -89,22 +101,29 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_KR */ -static void -mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -115,8 +134,12 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -124,18 +147,28 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_KS5601) { *p++ = mic[1]; *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_KR, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c index 7794d7ef8bf..bf87335c6a0 100644 --- a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c @@ -32,17 +32,20 @@ PG_FUNCTION_INFO_V1(mic_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_tw2big5(const unsigned char *euc, unsigned char *p, int len); -static void big52euc_tw(const unsigned char *euc, unsigned char *p, int len); -static void big52mic(const unsigned char *big5, unsigned char *p, int len); -static void mic2big5(const unsigned char *mic, unsigned char *p, int len); -static void euc_tw2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_tw(const unsigned char *mic, unsigned char *p, int len); +static int euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52euc_tw(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError); +static int mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_tw_to_big5(PG_FUNCTION_ARGS) @@ -50,12 +53,14 @@ euc_tw_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_BIG5); - euc_tw2big5(src, dest, len); + converted = euc_tw2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -64,12 +69,14 @@ big5_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_EUC_TW); - big52euc_tw(src, dest, len); + converted = big52euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -78,12 +85,14 @@ euc_tw_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_MULE_INTERNAL); - euc_tw2mic(src, dest, len); + converted = euc_tw2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -92,12 +101,14 @@ mic_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_TW); - mic2euc_tw(src, dest, len); + converted = mic2euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -106,12 +117,14 @@ big5_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_MULE_INTERNAL); - big52mic(src, dest, len); + converted = big52mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -120,21 +133,24 @@ mic_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_BIG5); - mic2big5(src, dest, len); + converted = mic2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_TW ---> Big5 */ -static void -euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; unsigned char c1; unsigned short big5buf, cnsBuf; @@ -149,8 +165,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Verify and decode the next EUC_TW input character */ l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -171,8 +191,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Write it out in Big5 */ big5buf = CNStoBIG5(cnsBuf, lc); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_EUC_TW, PG_BIG5, (const char *) euc, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; @@ -182,23 +206,30 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * Big5 ---> EUC_TW */ -static void -big52euc_tw(const unsigned char *big5, unsigned char *p, int len) +static int +big52euc_tw(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -213,8 +244,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); @@ -238,8 +273,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_EUC_TW, (const char *) big5, len); + } big5 += l; len -= l; @@ -257,15 +296,18 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) } } *p = '\0'; + + return big5 - start; } /* * EUC_TW ---> MIC */ -static void -euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -276,8 +318,12 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -306,22 +352,29 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_TW */ -static void -mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -332,8 +385,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -341,8 +398,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1) { *p++ = mic[1]; @@ -364,20 +425,27 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[3]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_TW, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * Big5 ---> MIC */ -static void -big52mic(const unsigned char *big5, unsigned char *p, int len) +static int +big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -391,8 +459,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } *p++ = c1; big5++; len--; @@ -400,8 +472,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); if (lc != 0) @@ -414,20 +490,27 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_MULE_INTERNAL, (const char *) big5, len); + } big5 += l; len -= l; } *p = '\0'; + + return big5 - start; } /* * MIC ---> Big5 */ -static void -mic2big5(const unsigned char *mic, unsigned char *p, int len) +static int +mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -440,8 +523,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -449,8 +536,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1 || c1 == LC_CNS11643_2 || c1 == LCPRV2_B) { if (c1 == LCPRV2_B) @@ -464,16 +555,26 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } big5buf = CNStoBIG5(cnsBuf, c1); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c index f424f881459..8752dcc09ac 100644 --- a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c +++ b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(win1250_to_latin2); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -82,12 +85,14 @@ latin2_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -96,12 +101,14 @@ mic_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN2); - mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -110,13 +117,15 @@ win1250_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - win1250_2_iso88592); + converted = latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -125,13 +134,15 @@ mic_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1250); - mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - iso88592_2_win1250); + converted = mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -140,12 +151,15 @@ latin2_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_WIN1250); - local2local(src, dest, len, PG_LATIN2, PG_WIN1250, iso88592_2_win1250); + converted = local2local(src, dest, len, PG_LATIN2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -154,10 +168,13 @@ win1250_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_LATIN2); - local2local(src, dest, len, PG_WIN1250, PG_LATIN2, win1250_2_iso88592); + converted = local2local(src, dest, len, PG_WIN1250, PG_LATIN2, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c index a358a707c11..431971c40cb 100644 --- a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(mic_to_latin4); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -42,12 +45,14 @@ latin1_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,12 +61,14 @@ mic_to_latin1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN1); - mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -70,12 +77,14 @@ latin3_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN3, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -84,12 +93,14 @@ mic_to_latin3(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN3); - mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,12 +109,14 @@ latin4_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN4, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -112,10 +125,12 @@ mic_to_latin4(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN4); - mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c index 75ed49ac54e..e45c7718945 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ big5_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_UTF8); - LocalToUtf(src, len, dest, - &big5_to_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = LocalToUtf(src, len, dest, + &big5_to_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_BIG5); - UtfToLocal(src, len, dest, - &big5_from_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = UtfToLocal(src, len, dest, + &big5_from_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c index 90ad316111a..e8303f38b68 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c @@ -33,8 +33,11 @@ PG_FUNCTION_INFO_V1(koi8u_to_utf8); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -44,16 +47,19 @@ utf8_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8R); - UtfToLocal(src, len, dest, - &koi8r_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = UtfToLocal(src, len, dest, + &koi8r_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -62,16 +68,19 @@ koi8r_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8r_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = LocalToUtf(src, len, dest, + &koi8r_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -80,16 +89,19 @@ utf8_to_koi8u(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8U); - UtfToLocal(src, len, dest, - &koi8u_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = UtfToLocal(src, len, dest, + &koi8u_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,14 +110,17 @@ koi8u_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8U, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8u_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = LocalToUtf(src, len, dest, + &koi8u_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c index 018312489cb..d2d9c44b3ff 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jis_2004_to_unicode_tree, - LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = LocalToUtf(src, len, dest, + &euc_jis_2004_to_unicode_tree, + LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JIS_2004); - UtfToLocal(src, len, dest, - &euc_jis_2004_from_unicode_tree, - ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = UtfToLocal(src, len, dest, + &euc_jis_2004_from_unicode_tree, + ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c index 62182a9ba8b..9892db0d102 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_cn_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_cn_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = LocalToUtf(src, len, dest, + &euc_cn_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_CN); - UtfToLocal(src, len, dest, - &euc_cn_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = UtfToLocal(src, len, dest, + &euc_cn_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c index dc5abb5dfd4..88ea32b74ba 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jp); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jp_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jp_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = LocalToUtf(src, len, dest, + &euc_jp_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JP); - UtfToLocal(src, len, dest, - &euc_jp_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = UtfToLocal(src, len, dest, + &euc_jp_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c index 088a38d8390..11dee117f47 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_kr_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_kr_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = LocalToUtf(src, len, dest, + &euc_kr_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_KR); - UtfToLocal(src, len, dest, - &euc_kr_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = UtfToLocal(src, len, dest, + &euc_kr_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c index a9fe94f88b8..29c03512819 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_tw); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_tw_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_tw_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = LocalToUtf(src, len, dest, + &euc_tw_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_TW); - UtfToLocal(src, len, dest, - &euc_tw_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = UtfToLocal(src, len, dest, + &euc_tw_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c index 96909b58859..72677fa6d40 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c @@ -183,8 +183,11 @@ conv_utf8_to_18030(uint32 code) * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -193,16 +196,19 @@ gb18030_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GB18030, PG_UTF8); - LocalToUtf(src, len, dest, - &gb18030_to_unicode_tree, - NULL, 0, - conv_18030_to_utf8, - PG_GB18030); + converted = LocalToUtf(src, len, dest, + &gb18030_to_unicode_tree, + NULL, 0, + conv_18030_to_utf8, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -211,14 +217,17 @@ utf8_to_gb18030(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GB18030); - UtfToLocal(src, len, dest, - &gb18030_from_unicode_tree, - NULL, 0, - conv_utf8_to_18030, - PG_GB18030); + converted = UtfToLocal(src, len, dest, + &gb18030_from_unicode_tree, + NULL, 0, + conv_utf8_to_18030, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c index 78bbcd3ce7d..057bc65e521 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_gbk); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ gbk_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GBK, PG_UTF8); - LocalToUtf(src, len, dest, - &gbk_to_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = LocalToUtf(src, len, dest, + &gbk_to_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_gbk(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GBK); - UtfToLocal(src, len, dest, - &gbk_from_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = UtfToLocal(src, len, dest, + &gbk_from_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c index 348524f4a2c..d16b6fe31d8 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c @@ -52,8 +52,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -100,6 +103,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -108,12 +112,15 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -122,7 +129,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -132,6 +139,7 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -140,12 +148,15 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -154,5 +165,5 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c index 2cdca9f780d..0bc08829657 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c @@ -26,8 +26,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859_1); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -37,6 +40,8 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_UTF8); @@ -45,7 +50,11 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_LATIN1, (const char *) src, len); + } if (!IS_HIGHBIT_SET(c)) *dest++ = c; else @@ -58,7 +67,7 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } Datum @@ -67,6 +76,8 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c, c1; @@ -76,7 +87,11 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_UTF8, (const char *) src, len); + } /* fast path for ASCII-subset characters */ if (!IS_HIGHBIT_SET(c)) { @@ -102,11 +117,15 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) len -= 2; } else + { + if (noError) + break; report_untranslatable_char(PG_UTF8, PG_LATIN1, (const char *) src, len); + } } } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c index e09a7c8e41e..a760ab54ab6 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_johab); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ johab_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_JOHAB, PG_UTF8); - LocalToUtf(src, len, dest, - &johab_to_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = LocalToUtf(src, len, dest, + &johab_to_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_johab(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_JOHAB); - UtfToLocal(src, len, dest, - &johab_from_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = UtfToLocal(src, len, dest, + &johab_from_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c index c56fa80a4bb..23892790730 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ sjis_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_UTF8); - LocalToUtf(src, len, dest, - &sjis_to_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = LocalToUtf(src, len, dest, + &sjis_to_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SJIS); - UtfToLocal(src, len, dest, - &sjis_from_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = UtfToLocal(src, len, dest, + &sjis_from_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c index 458500998d4..94930659347 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_shift_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ shift_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &shift_jis_2004_to_unicode_tree, - LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = LocalToUtf(src, len, dest, + &shift_jis_2004_to_unicode_tree, + LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SHIFT_JIS_2004); - UtfToLocal(src, len, dest, - &shift_jis_2004_from_unicode_tree, - ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = UtfToLocal(src, len, dest, + &shift_jis_2004_from_unicode_tree, + ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c index 3226ed03258..dfdc0dbfa2f 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_uhc); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ uhc_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UHC, PG_UTF8); - LocalToUtf(src, len, dest, - &uhc_to_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = LocalToUtf(src, len, dest, + &uhc_to_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_uhc(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_UHC); - UtfToLocal(src, len, dest, - &uhc_from_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = UtfToLocal(src, len, dest, + &uhc_from_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c index 1a0074d063c..8f046280029 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c @@ -48,8 +48,11 @@ PG_FUNCTION_INFO_V1(utf8_to_win); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -81,6 +84,7 @@ win_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -89,12 +93,15 @@ win_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -103,7 +110,7 @@ win_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -113,6 +120,7 @@ utf8_to_win(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -121,12 +129,15 @@ utf8_to_win(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -135,5 +146,5 @@ utf8_to_win(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/mbutils.c b/src/backend/utils/mb/mbutils.c index 67d1c4fc19f..a585e3a6f1e 100644 --- a/src/backend/utils/mb/mbutils.c +++ b/src/backend/utils/mb/mbutils.c @@ -406,12 +406,13 @@ pg_do_encoding_conversion(unsigned char *src, int len, MemoryContextAllocHuge(CurrentMemoryContext, (Size) len * MAX_CONVERSION_GROWTH + 1); - OidFunctionCall5(proc, - Int32GetDatum(src_encoding), - Int32GetDatum(dest_encoding), - CStringGetDatum(src), - CStringGetDatum(result), - Int32GetDatum(len)); + (void) OidFunctionCall6(proc, + Int32GetDatum(src_encoding), + Int32GetDatum(dest_encoding), + CStringGetDatum(src), + CStringGetDatum(result), + Int32GetDatum(len), + BoolGetDatum(false)); /* * If the result is large, it's worth repalloc'ing to release any extra diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index e6c7b070f64..1dd5558b078 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10409,388 +10409,388 @@ # conversion functions { oid => '4302', descr => 'internal conversion function for KOI8R to MULE_INTERNAL', - proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_mic', + proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4303', descr => 'internal conversion function for MULE_INTERNAL to KOI8R', - proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_koi8r', + proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4304', descr => 'internal conversion function for ISO-8859-5 to MULE_INTERNAL', - proname => 'iso_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_mic', + proname => 'iso_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4305', descr => 'internal conversion function for MULE_INTERNAL to ISO-8859-5', - proname => 'mic_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_iso', + proname => 'mic_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4306', descr => 'internal conversion function for WIN1251 to MULE_INTERNAL', - proname => 'win1251_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_mic', + proname => 'win1251_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4307', descr => 'internal conversion function for MULE_INTERNAL to WIN1251', - proname => 'mic_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1251', + proname => 'mic_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4308', descr => 'internal conversion function for WIN866 to MULE_INTERNAL', - proname => 'win866_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_mic', + proname => 'win866_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4309', descr => 'internal conversion function for MULE_INTERNAL to WIN866', - proname => 'mic_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win866', + proname => 'mic_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4310', descr => 'internal conversion function for KOI8R to WIN1251', - proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4311', descr => 'internal conversion function for WIN1251 to KOI8R', - proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4312', descr => 'internal conversion function for KOI8R to WIN866', - proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_win866', + proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4313', descr => 'internal conversion function for WIN866 to KOI8R', - proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_koi8r', + proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4314', descr => 'internal conversion function for WIN866 to WIN1251', - proname => 'win866_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win866_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4315', descr => 'internal conversion function for WIN1251 to WIN866', - proname => 'win1251_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4316', descr => 'internal conversion function for ISO-8859-5 to KOI8R', - proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_koi8r', + proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4317', descr => 'internal conversion function for KOI8R to ISO-8859-5', - proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_iso', + proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4318', descr => 'internal conversion function for ISO-8859-5 to WIN1251', - proname => 'iso_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win1251', + proname => 'iso_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4319', descr => 'internal conversion function for WIN1251 to ISO-8859-5', - proname => 'win1251_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_iso', + proname => 'win1251_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4320', descr => 'internal conversion function for ISO-8859-5 to WIN866', - proname => 'iso_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win866', + proname => 'iso_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4321', descr => 'internal conversion function for WIN866 to ISO-8859-5', - proname => 'win866_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_iso', + proname => 'win866_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4322', descr => 'internal conversion function for EUC_CN to MULE_INTERNAL', - proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_mic', + proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_mic', probin => '$libdir/euc_cn_and_mic' }, { oid => '4323', descr => 'internal conversion function for MULE_INTERNAL to EUC_CN', - proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_cn', + proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_cn', probin => '$libdir/euc_cn_and_mic' }, { oid => '4324', descr => 'internal conversion function for EUC_JP to SJIS', - proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_sjis', + proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4325', descr => 'internal conversion function for SJIS to EUC_JP', - proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_euc_jp', + proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4326', descr => 'internal conversion function for EUC_JP to MULE_INTERNAL', - proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_mic', + proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4327', descr => 'internal conversion function for SJIS to MULE_INTERNAL', - proname => 'sjis_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_mic', + proname => 'sjis_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4328', descr => 'internal conversion function for MULE_INTERNAL to EUC_JP', - proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_jp', + proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4329', descr => 'internal conversion function for MULE_INTERNAL to SJIS', - proname => 'mic_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_sjis', + proname => 'mic_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4330', descr => 'internal conversion function for EUC_KR to MULE_INTERNAL', - proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_mic', + proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_mic', probin => '$libdir/euc_kr_and_mic' }, { oid => '4331', descr => 'internal conversion function for MULE_INTERNAL to EUC_KR', - proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_kr', + proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_kr', probin => '$libdir/euc_kr_and_mic' }, { oid => '4332', descr => 'internal conversion function for EUC_TW to BIG5', - proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_big5', + proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4333', descr => 'internal conversion function for BIG5 to EUC_TW', - proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_euc_tw', + proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4334', descr => 'internal conversion function for EUC_TW to MULE_INTERNAL', - proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_mic', + proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4335', descr => 'internal conversion function for BIG5 to MULE_INTERNAL', - proname => 'big5_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_mic', + proname => 'big5_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4336', descr => 'internal conversion function for MULE_INTERNAL to EUC_TW', - proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_tw', + proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4337', descr => 'internal conversion function for MULE_INTERNAL to BIG5', - proname => 'mic_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_big5', + proname => 'mic_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4338', descr => 'internal conversion function for LATIN2 to MULE_INTERNAL', - proname => 'latin2_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin2_to_mic', + proname => 'latin2_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4339', descr => 'internal conversion function for MULE_INTERNAL to LATIN2', - proname => 'mic_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin2', + proname => 'mic_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4340', descr => 'internal conversion function for WIN1250 to MULE_INTERNAL', - proname => 'win1250_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1250_to_mic', + proname => 'win1250_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4341', descr => 'internal conversion function for MULE_INTERNAL to WIN1250', - proname => 'mic_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1250', + proname => 'mic_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4342', descr => 'internal conversion function for LATIN2 to WIN1250', - proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4343', descr => 'internal conversion function for WIN1250 to LATIN2', - proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4344', descr => 'internal conversion function for LATIN1 to MULE_INTERNAL', - proname => 'latin1_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin1_to_mic', + proname => 'latin1_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin1_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4345', descr => 'internal conversion function for MULE_INTERNAL to LATIN1', - proname => 'mic_to_latin1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin1', + proname => 'mic_to_latin1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin1', probin => '$libdir/latin_and_mic' }, { oid => '4346', descr => 'internal conversion function for LATIN3 to MULE_INTERNAL', - proname => 'latin3_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin3_to_mic', + proname => 'latin3_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin3_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4347', descr => 'internal conversion function for MULE_INTERNAL to LATIN3', - proname => 'mic_to_latin3', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin3', + proname => 'mic_to_latin3', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin3', probin => '$libdir/latin_and_mic' }, { oid => '4348', descr => 'internal conversion function for LATIN4 to MULE_INTERNAL', - proname => 'latin4_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin4_to_mic', + proname => 'latin4_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin4_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4349', descr => 'internal conversion function for MULE_INTERNAL to LATIN4', - proname => 'mic_to_latin4', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin4', + proname => 'mic_to_latin4', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin4', probin => '$libdir/latin_and_mic' }, { oid => '4352', descr => 'internal conversion function for BIG5 to UTF8', - proname => 'big5_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_utf8', + proname => 'big5_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_utf8', probin => '$libdir/utf8_and_big5' }, { oid => '4353', descr => 'internal conversion function for UTF8 to BIG5', - proname => 'utf8_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_big5', + proname => 'utf8_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_big5', probin => '$libdir/utf8_and_big5' }, { oid => '4354', descr => 'internal conversion function for UTF8 to KOI8R', - proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8r', + proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8r', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4355', descr => 'internal conversion function for KOI8R to UTF8', - proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_utf8', + proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4356', descr => 'internal conversion function for UTF8 to KOI8U', - proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8u', + proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8u', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4357', descr => 'internal conversion function for KOI8U to UTF8', - proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8u_to_utf8', + proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8u_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4358', descr => 'internal conversion function for UTF8 to WIN', - proname => 'utf8_to_win', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_win', + proname => 'utf8_to_win', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_win', probin => '$libdir/utf8_and_win' }, { oid => '4359', descr => 'internal conversion function for WIN to UTF8', - proname => 'win_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win_to_utf8', + proname => 'win_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win_to_utf8', probin => '$libdir/utf8_and_win' }, { oid => '4360', descr => 'internal conversion function for EUC_CN to UTF8', - proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_utf8', + proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_utf8', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4361', descr => 'internal conversion function for UTF8 to EUC_CN', - proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_cn', + proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_cn', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4362', descr => 'internal conversion function for EUC_JP to UTF8', - proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_utf8', + proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_utf8', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4363', descr => 'internal conversion function for UTF8 to EUC_JP', - proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_jp', + proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jp', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4364', descr => 'internal conversion function for EUC_KR to UTF8', - proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_utf8', + proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_utf8', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4365', descr => 'internal conversion function for UTF8 to EUC_KR', - proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_kr', + proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_kr', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4366', descr => 'internal conversion function for EUC_TW to UTF8', - proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_utf8', + proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_utf8', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4367', descr => 'internal conversion function for UTF8 to EUC_TW', - proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_tw', + proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_tw', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4368', descr => 'internal conversion function for GB18030 to UTF8', - proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gb18030_to_utf8', + proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gb18030_to_utf8', probin => '$libdir/utf8_and_gb18030' }, { oid => '4369', descr => 'internal conversion function for UTF8 to GB18030', - proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gb18030', + proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gb18030', probin => '$libdir/utf8_and_gb18030' }, { oid => '4370', descr => 'internal conversion function for GBK to UTF8', - proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gbk_to_utf8', + proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gbk_to_utf8', probin => '$libdir/utf8_and_gbk' }, { oid => '4371', descr => 'internal conversion function for UTF8 to GBK', - proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gbk', + proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gbk', probin => '$libdir/utf8_and_gbk' }, { oid => '4372', descr => 'internal conversion function for UTF8 to ISO-8859 2-16', - proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_iso8859', + proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859', probin => '$libdir/utf8_and_iso8859' }, { oid => '4373', descr => 'internal conversion function for ISO-8859 2-16 to UTF8', - proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso8859_to_utf8', + proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_to_utf8', probin => '$libdir/utf8_and_iso8859' }, { oid => '4374', descr => 'internal conversion function for LATIN1 to UTF8', - proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_1_to_utf8', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4375', descr => 'internal conversion function for UTF8 to LATIN1', - proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859_1', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4376', descr => 'internal conversion function for JOHAB to UTF8', - proname => 'johab_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'johab_to_utf8', + proname => 'johab_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'johab_to_utf8', probin => '$libdir/utf8_and_johab' }, { oid => '4377', descr => 'internal conversion function for UTF8 to JOHAB', - proname => 'utf8_to_johab', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_johab', + proname => 'utf8_to_johab', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_johab', probin => '$libdir/utf8_and_johab' }, { oid => '4378', descr => 'internal conversion function for SJIS to UTF8', - proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_utf8', + proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_utf8', probin => '$libdir/utf8_and_sjis' }, { oid => '4379', descr => 'internal conversion function for UTF8 to SJIS', - proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_sjis', + proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_sjis', probin => '$libdir/utf8_and_sjis' }, { oid => '4380', descr => 'internal conversion function for UHC to UTF8', - proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'uhc_to_utf8', + proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'uhc_to_utf8', probin => '$libdir/utf8_and_uhc' }, { oid => '4381', descr => 'internal conversion function for UTF8 to UHC', - proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_uhc', + proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_uhc', probin => '$libdir/utf8_and_uhc' }, { oid => '4382', descr => 'internal conversion function for EUC_JIS_2004 to UTF8', - proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_utf8', probin => '$libdir/utf8_and_euc2004' }, { oid => '4383', descr => 'internal conversion function for UTF8 to EUC_JIS_2004', - proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jis_2004', probin => '$libdir/utf8_and_euc2004' }, { oid => '4384', descr => 'internal conversion function for SHIFT_JIS_2004 to UTF8', - proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_utf8', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4385', descr => 'internal conversion function for UTF8 to SHIFT_JIS_2004', - proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_shift_jis_2004', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4386', descr => 'internal conversion function for EUC_JIS_2004 to SHIFT_JIS_2004', proname => 'euc_jis_2004_to_shift_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_shift_jis_2004', probin => '$libdir/euc2004_sjis2004' }, { oid => '4387', descr => 'internal conversion function for SHIFT_JIS_2004 to EUC_JIS_2004', proname => 'shift_jis_2004_to_euc_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_euc_jis_2004', probin => '$libdir/euc2004_sjis2004' }, diff --git a/src/include/mb/pg_wchar.h b/src/include/mb/pg_wchar.h index 549f2dd045d..4529a15a6ba 100644 --- a/src/include/mb/pg_wchar.h +++ b/src/include/mb/pg_wchar.h @@ -627,18 +627,18 @@ extern void pg_unicode_to_server(pg_wchar c, unsigned char *s); extern unsigned short BIG5toCNS(unsigned short big5, unsigned char *lc); extern unsigned short CNStoBIG5(unsigned short cns, unsigned char lc); -extern void UtfToLocal(const unsigned char *utf, int len, - unsigned char *iso, - const pg_mb_radix_tree *map, - const pg_utf_to_local_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); -extern void LocalToUtf(const unsigned char *iso, int len, - unsigned char *utf, - const pg_mb_radix_tree *map, - const pg_local_to_utf_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); +extern int UtfToLocal(const unsigned char *utf, int len, + unsigned char *iso, + const pg_mb_radix_tree *map, + const pg_utf_to_local_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); +extern int LocalToUtf(const unsigned char *iso, int len, + unsigned char *utf, + const pg_mb_radix_tree *map, + const pg_local_to_utf_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); extern bool pg_verifymbstr(const char *mbstr, int len, bool noError); extern bool pg_verify_mbstr(int encoding, const char *mbstr, int len, @@ -656,18 +656,19 @@ extern void report_invalid_encoding(int encoding, const char *mbstr, int len) pg extern void report_untranslatable_char(int src_encoding, int dest_encoding, const char *mbstr, int len) pg_attribute_noreturn(); -extern void local2local(const unsigned char *l, unsigned char *p, int len, - int src_encoding, int dest_encoding, const unsigned char *tab); -extern void latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding); -extern void mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding); -extern void latin2mic_with_table(const unsigned char *l, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); -extern void mic2latin_with_table(const unsigned char *mic, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); +extern int local2local(const unsigned char *l, unsigned char *p, int len, + int src_encoding, int dest_encoding, const unsigned char *tab, + bool noError); +extern int latin2mic(const unsigned char *l, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int mic2latin(const unsigned char *mic, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int latin2mic_with_table(const unsigned char *l, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); +extern int mic2latin_with_table(const unsigned char *mic, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); #ifdef WIN32 extern WCHAR *pgwin32_message_to_UTF16(const char *str, int len, int *utf16len); diff --git a/src/test/regress/expected/opr_sanity.out b/src/test/regress/expected/opr_sanity.out index 507b474b1bb..e4aab19ddaa 100644 --- a/src/test/regress/expected/opr_sanity.out +++ b/src/test/regress/expected/opr_sanity.out @@ -1035,13 +1035,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); oid | proname | oid | conname -----+---------+-----+--------- (0 rows) diff --git a/src/test/regress/sql/opr_sanity.sql b/src/test/regress/sql/opr_sanity.sql index 4189a5a4e09..90a735ea5c8 100644 --- a/src/test/regress/sql/opr_sanity.sql +++ b/src/test/regress/sql/opr_sanity.sql @@ -542,13 +542,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); -- Check for conprocs that don't perform the specific conversion that -- pg_conversion alleges they do, by trying to invoke each conversion -- 2.20.1 --------------28FF91F97438A3BA06B3DA61 Content-Type: text/x-patch; charset=UTF-8; name="0005-Do-COPY-FROM-encoding-conversion-verification-in-lar.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Do-COPY-FROM-encoding-conversion-verification-in-lar.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 34+ messages in thread
* [PATCH v3 2/5] Change conversion function signature. @ 2021-01-28 16:42 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 34+ messages in thread From: Heikki Linnakangas @ 2021-01-28 16:42 UTC (permalink / raw) Add a 'noError' argument, so that we can try to convert a buffer without knowing the character boundaries beforehand. The functions now need to return the number of input bytes successfully converted. This is is a backwards-incompatible change, if you have created a custom encoding conversion with CREATE CONVERSION. This adds a check to pg_upgrade for that, refusing the upgrade if there are any user-defined encoding conversions. --- doc/src/sgml/ref/create_conversion.sgml | 5 +- src/backend/commands/conversioncmds.c | 27 +- src/backend/utils/error/elog.c | 2 + src/backend/utils/mb/conv.c | 112 +++++- .../cyrillic_and_mic/cyrillic_and_mic.c | 127 ++++--- .../euc2004_sjis2004/euc2004_sjis2004.c | 96 ++++- .../euc_cn_and_mic/euc_cn_and_mic.c | 57 ++- .../euc_jp_and_sjis/euc_jp_and_sjis.c | 153 ++++++-- .../euc_kr_and_mic/euc_kr_and_mic.c | 57 ++- .../euc_tw_and_big5/euc_tw_and_big5.c | 165 +++++++-- .../latin2_and_win1250/latin2_and_win1250.c | 49 ++- .../latin_and_mic/latin_and_mic.c | 43 ++- .../utf8_and_big5/utf8_and_big5.c | 37 +- .../utf8_and_cyrillic/utf8_and_cyrillic.c | 67 ++-- .../utf8_and_euc2004/utf8_and_euc2004.c | 37 +- .../utf8_and_euc_cn/utf8_and_euc_cn.c | 37 +- .../utf8_and_euc_jp/utf8_and_euc_jp.c | 37 +- .../utf8_and_euc_kr/utf8_and_euc_kr.c | 37 +- .../utf8_and_euc_tw/utf8_and_euc_tw.c | 37 +- .../utf8_and_gb18030/utf8_and_gb18030.c | 37 +- .../utf8_and_gbk/utf8_and_gbk.c | 37 +- .../utf8_and_iso8859/utf8_and_iso8859.c | 43 ++- .../utf8_and_iso8859_1/utf8_and_iso8859_1.c | 27 +- .../utf8_and_johab/utf8_and_johab.c | 37 +- .../utf8_and_sjis/utf8_and_sjis.c | 37 +- .../utf8_and_sjis2004/utf8_and_sjis2004.c | 37 +- .../utf8_and_uhc/utf8_and_uhc.c | 37 +- .../utf8_and_win/utf8_and_win.c | 43 ++- src/backend/utils/mb/mbutils.c | 18 +- src/bin/pg_upgrade/check.c | 95 +++++ src/include/catalog/pg_proc.dat | 332 +++++++++--------- src/include/mb/pg_wchar.h | 49 +-- src/test/regress/expected/opr_sanity.out | 7 +- src/test/regress/sql/opr_sanity.sql | 7 +- 34 files changed, 1390 insertions(+), 635 deletions(-) diff --git a/doc/src/sgml/ref/create_conversion.sgml b/doc/src/sgml/ref/create_conversion.sgml index e7700fecfc5..f014a676c88 100644 --- a/doc/src/sgml/ref/create_conversion.sgml +++ b/doc/src/sgml/ref/create_conversion.sgml @@ -117,8 +117,9 @@ conv_proc( integer, -- destination encoding ID cstring, -- source string (null terminated C string) internal, -- destination (fill with a null terminated C string) - integer -- source string length -) RETURNS void; + integer, -- source string length + boolean -- if true, don't throw an error if conversion fails +) RETURNS integer; </programlisting></para> </listitem> </varlistentry> diff --git a/src/backend/commands/conversioncmds.c b/src/backend/commands/conversioncmds.c index f7ff321de71..d2041466911 100644 --- a/src/backend/commands/conversioncmds.c +++ b/src/backend/commands/conversioncmds.c @@ -45,8 +45,9 @@ CreateConversionCommand(CreateConversionStmt *stmt) const char *from_encoding_name = stmt->for_encoding_name; const char *to_encoding_name = stmt->to_encoding_name; List *func_name = stmt->func_name; - static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID}; + static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID, BOOLOID}; char result[1]; + Datum funcresult; /* Convert list of names to a name and namespace */ namespaceId = QualifiedNameGetCreationNamespace(stmt->conversion_name, @@ -92,8 +93,8 @@ CreateConversionCommand(CreateConversionStmt *stmt) funcoid = LookupFuncName(func_name, sizeof(funcargs) / sizeof(Oid), funcargs, false); - /* Check it returns VOID, else it's probably the wrong function */ - if (get_func_rettype(funcoid) != VOIDOID) + /* Check it returns int4, else it's probably the wrong function */ + if (get_func_rettype(funcoid) != INT4OID) ereport(ERROR, (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), errmsg("encoding conversion function %s must return type %s", @@ -111,12 +112,20 @@ CreateConversionCommand(CreateConversionStmt *stmt) * string; the conversion function should throw an error if it can't * perform the requested conversion. */ - OidFunctionCall5(funcoid, - Int32GetDatum(from_encoding), - Int32GetDatum(to_encoding), - CStringGetDatum(""), - CStringGetDatum(result), - Int32GetDatum(0)); + funcresult = OidFunctionCall6(funcoid, + Int32GetDatum(from_encoding), + Int32GetDatum(to_encoding), + CStringGetDatum(""), + CStringGetDatum(result), + Int32GetDatum(0), + BoolGetDatum(false)); + + /* The function should return 0 for empty input. Might as well check that, too. */ + if (DatumGetInt32(funcresult) != 0) + ereport(ERROR, + (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), + errmsg("encoding conversion function %s returned incorrect result for empty input", + NameListToString(func_name)))); /* * All seem ok, go ahead (possible failure would be a duplicate conversion diff --git a/src/backend/utils/error/elog.c b/src/backend/utils/error/elog.c index 80c26724612..762f77d533c 100644 --- a/src/backend/utils/error/elog.c +++ b/src/backend/utils/error/elog.c @@ -2280,6 +2280,8 @@ write_console(const char *line, int len) * Conversion on non-win32 platforms is not implemented yet. It requires * non-throw version of pg_do_encoding_conversion(), that converts * unconvertable characters to '?' without errors. + * + * XXX: We have a no-throw version now. It doesn't convert to '?' though. */ #endif diff --git a/src/backend/utils/mb/conv.c b/src/backend/utils/mb/conv.c index a07b54bd3b8..b83358bc7a5 100644 --- a/src/backend/utils/mb/conv.c +++ b/src/backend/utils/mb/conv.c @@ -26,14 +26,16 @@ * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the target charset, or 0 if there is no equivalent code. */ -void +int local2local(const unsigned char *l, unsigned char *p, int len, int src_encoding, int dest_encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -41,7 +43,11 @@ local2local(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(src_encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -50,13 +56,19 @@ local2local(const unsigned char *l, if (c2) *p++ = c2; else + { + if (noError) + break; report_untranslatable_char(src_encoding, dest_encoding, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -67,17 +79,22 @@ local2local(const unsigned char *l, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = l; int c1; while (len > 0) { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (IS_HIGHBIT_SET(c1)) *p++ = lc; *p++ = c1; @@ -85,6 +102,8 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, len--; } *p = '\0'; + + return l - start; } /* @@ -95,17 +114,22 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -118,17 +142,27 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1])) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); + } *p++ = mic[1]; mic += 2; len -= 2; } } *p = '\0'; + + return mic - start; } @@ -144,14 +178,16 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the mule encoding, or 0 if there is no equivalent code. */ -void +int latin2mic_with_table(const unsigned char *l, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -159,7 +195,11 @@ latin2mic_with_table(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -171,13 +211,19 @@ latin2mic_with_table(const unsigned char *l, *p++ = c2; } else + { + if (noError) + break; report_untranslatable_char(encoding, PG_MULE_INTERNAL, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -192,14 +238,16 @@ latin2mic_with_table(const unsigned char *l, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the local charset, or 0 if there is no equivalent code. */ -void +int mic2latin_with_table(const unsigned char *mic, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = mic; unsigned char c1, c2; @@ -207,7 +255,11 @@ mic2latin_with_table(const unsigned char *mic, { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -220,11 +272,17 @@ mic2latin_with_table(const unsigned char *mic, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1]) || (c2 = tab[mic[1] - HIGHBIT]) == 0) { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); break; /* keep compiler quiet */ @@ -235,6 +293,8 @@ mic2latin_with_table(const unsigned char *mic, } } *p = '\0'; + + return mic - start; } /* @@ -425,17 +485,19 @@ pg_mb_radix_conv(const pg_mb_radix_tree *rt, * * See pg_wchar.h for more details about the data structures used here. */ -void +int UtfToLocal(const unsigned char *utf, int len, unsigned char *iso, const pg_mb_radix_tree *map, const pg_utf_to_local_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, bool noError) { uint32 iutf; int l; const pg_utf_to_local_combined *cp; + const unsigned char *start = utf; + const unsigned char *cur = utf; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -449,6 +511,8 @@ UtfToLocal(const unsigned char *utf, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*utf == '\0') break; @@ -584,15 +648,19 @@ UtfToLocal(const unsigned char *utf, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(PG_UTF8, encoding, (const char *) (utf - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(PG_UTF8, (const char *) utf, len); *iso = '\0'; + + return cur - start; } /* @@ -616,18 +684,24 @@ UtfToLocal(const unsigned char *utf, int len, * (if provided) is applied. An error is raised if no match is found. * * See pg_wchar.h for more details about the data structures used here. + * + * Returns the number of input bytes consumed. If noError is true, this can + * be less than 'len'. */ -void +int LocalToUtf(const unsigned char *iso, int len, unsigned char *utf, const pg_mb_radix_tree *map, const pg_local_to_utf_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, + bool noError) { uint32 iiso; int l; const pg_local_to_utf_combined *cp; + const unsigned char *start = iso; + const unsigned char *cur = iso; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -641,6 +715,8 @@ LocalToUtf(const unsigned char *iso, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*iso == '\0') break; @@ -723,13 +799,17 @@ LocalToUtf(const unsigned char *iso, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(encoding, PG_UTF8, (const char *) (iso - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(encoding, (const char *) iso, len); *utf = '\0'; + + return cur - start; } diff --git a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c index 4c5b02654de..368c2deb5e4 100644 --- a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c @@ -44,8 +44,11 @@ PG_FUNCTION_INFO_V1(win866_to_iso); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -306,12 +309,14 @@ koi8r_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -320,12 +325,14 @@ mic_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_KOI8R); - mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -334,12 +341,14 @@ iso_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -348,12 +357,14 @@ mic_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_ISO_8859_5); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -362,12 +373,14 @@ win1251_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -376,12 +389,14 @@ mic_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1251); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -390,12 +405,14 @@ win866_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -404,12 +421,14 @@ mic_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN866); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -418,12 +437,14 @@ koi8r_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN1251); - local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -432,12 +453,14 @@ win1251_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_KOI8R); - local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi); + converted = local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -446,12 +469,14 @@ koi8r_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN866); - local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -460,12 +485,14 @@ win866_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_KOI8R); - local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi); + converted = local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -474,12 +501,14 @@ win866_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_WIN1251); - local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251); + converted = local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -488,12 +517,14 @@ win1251_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_WIN866); - local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866); + converted = local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -502,12 +533,14 @@ iso_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_KOI8R); - local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -516,12 +549,14 @@ koi8r_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_ISO_8859_5); - local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso); + converted = local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -530,12 +565,14 @@ iso_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN1251); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -544,12 +581,14 @@ win1251_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso); + converted = local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -558,12 +597,14 @@ iso_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN866); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -572,10 +613,12 @@ win866_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso); + converted = local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c index 4d7fb116cfd..88529c644cf 100644 --- a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c @@ -19,8 +19,8 @@ PG_MODULE_MAGIC; PG_FUNCTION_INFO_V1(euc_jis_2004_to_shift_jis_2004); PG_FUNCTION_INFO_V1(shift_jis_2004_to_euc_jis_2004); -static void euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len); -static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len); +static int euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError); /* ---------- * conv_proc( @@ -28,8 +28,11 @@ static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -39,12 +42,14 @@ euc_jis_2004_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_SHIFT_JIS_2004); - euc_jis_20042shift_jis_2004(src, dest, len); + converted = euc_jis_20042shift_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -53,20 +58,23 @@ shift_jis_2004_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_EUC_JIS_2004); - shift_jis_20042euc_jis_2004(src, dest, len); + converted = shift_jis_20042euc_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_JIS_2004 -> SHIFT_JIS_2004 */ -static void -euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, ku, ten; @@ -79,8 +87,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -90,8 +102,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) l = pg_encoding_verifymbchar(PG_EUC_JIS_2004, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (c1 == SS2 && l == 2) /* JIS X 0201 kana? */ { @@ -121,8 +137,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) *p++ = (ku + 0x19b) >> 1; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } if (ku % 2) @@ -132,8 +152,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; @@ -149,8 +173,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ku >= 63 && ku <= 94) *p++ = (ku + 0x181) >> 1; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (ku % 2) { @@ -159,20 +187,30 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else - report_invalid_encoding(PG_EUC_JIS_2004, + { + if (noError) + break; + report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } euc += l; len -= l; } *p = '\0'; + + return euc - start; } /* @@ -212,9 +250,10 @@ get_ten(int b, int *ku) * SHIFT_JIS_2004 ---> EUC_JIS_2004 */ -static void -shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len) +static int +shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1; int ku, ten, @@ -230,8 +269,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -241,8 +284,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len l = pg_encoding_verifymbchar(PG_SHIFT_JIS_2004, (const char *) sjis, len); if (l < 0 || l > len) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf && l == 1) { @@ -266,8 +313,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x100; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xe0 && c1 <= 0xef) /* plane 1 62ku-94ku */ @@ -275,9 +326,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x180; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, - (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xf0 && c1 <= 0xf3) /* plane 2 @@ -286,8 +340,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } switch (c1) { case 0xf0: @@ -309,16 +367,24 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 == 0xf4 && kubun == 1) ku = 15; else ku = (c1 << 1) - 0x19a - kubun; } else + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (plane == 2) *p++ = SS3; @@ -330,4 +396,6 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c index e9bb896935f..a8da733803d 100644 --- a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_cn2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_cn(const unsigned char *mic, unsigned char *p, int len); +static int euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_cn_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_cn_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_MULE_INTERNAL); - euc_cn2mic(src, dest, len); + converted = euc_cn2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_CN); - mic2euc_cn(src, dest, len); + converted = mic2euc_cn(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_CN ---> MIC */ -static void -euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; while (len > 0) @@ -76,7 +84,11 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (len < 2 || !IS_HIGHBIT_SET(euc[1])) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = LC_GB2312_80; *p++ = c1; *p++ = euc[1]; @@ -86,21 +98,28 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_CN */ -static void -mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) @@ -109,11 +128,19 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (c1 != LC_GB2312_80) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_CN, (const char *) mic, len); + } if (len < 3 || !IS_HIGHBIT_SET(mic[1]) || !IS_HIGHBIT_SET(mic[2])) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } mic++; *p++ = *mic++; *p++ = *mic++; @@ -122,12 +149,18 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; } } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c index 5059f917a98..cc4817dc4cd 100644 --- a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c @@ -42,17 +42,20 @@ PG_FUNCTION_INFO_V1(mic_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void sjis2mic(const unsigned char *sjis, unsigned char *p, int len); -static void mic2sjis(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_jp(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len); -static void sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len); +static int sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError); +static int mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_jp_to_sjis(PG_FUNCTION_ARGS) @@ -60,12 +63,14 @@ euc_jp_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_SJIS); - euc_jp2sjis(src, dest, len); + converted = euc_jp2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -74,12 +79,14 @@ sjis_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_EUC_JP); - sjis2euc_jp(src, dest, len); + converted = sjis2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -88,12 +95,14 @@ euc_jp_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_MULE_INTERNAL); - euc_jp2mic(src, dest, len); + converted = euc_jp2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -102,12 +111,14 @@ mic_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_JP); - mic2euc_jp(src, dest, len); + converted = mic2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -116,12 +127,14 @@ sjis_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_MULE_INTERNAL); - sjis2mic(src, dest, len); + converted = sjis2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -130,20 +143,23 @@ mic_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_SJIS); - mic2sjis(src, dest, len); + converted = mic2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * SJIS ---> MIC */ -static void -sjis2mic(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -167,7 +183,11 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) * JIS X0208, X0212, user defined extended characters */ if (len < 2 || !ISSJISHEAD(c1) || !ISSJISTAIL(sjis[1])) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } c2 = sjis[1]; k = (c1 << 8) + c2; if (k >= 0xed40 && k < 0xf040) @@ -257,21 +277,28 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; } } *p = '\0'; + + return sjis - start; } /* * MIC ---> SJIS */ -static void -mic2sjis(const unsigned char *mic, unsigned char *p, int len) +static int +mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1, c2, k, @@ -284,8 +311,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -293,8 +324,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) *p++ = mic[1]; else if (c1 == LC_JISX0208) @@ -350,20 +385,27 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_SJIS, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP ---> MIC */ -static void -euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -374,8 +416,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -383,8 +429,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* 1 byte kana? */ *p++ = LC_JISX0201K; @@ -406,14 +456,17 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_JP */ -static void -mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -424,8 +477,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -433,8 +490,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) { *p++ = SS2; @@ -452,20 +513,27 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_JP, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP -> SJIS */ -static void -euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, c2, k; @@ -478,8 +546,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -487,8 +559,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* hankaku kana? */ @@ -551,14 +627,17 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * SJIS ---> EUC_JP */ -static void -sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -573,8 +652,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -582,8 +665,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_SJIS, (const char *) sjis, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf) { /* JIS X0201 (1 byte kana) */ @@ -680,4 +767,6 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c index ac823d6c270..a5b51617e52 100644 --- a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_kr2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_kr(const unsigned char *mic, unsigned char *p, int len); +static int euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_kr_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_kr_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_MULE_INTERNAL); - euc_kr2mic(src, dest, len); + converted = euc_kr2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_KR); - mic2euc_kr(src, dest, len); + converted = mic2euc_kr(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_KR ---> MIC */ -static void -euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -78,8 +86,12 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_KR, (const char *) euc, len); if (l != 2) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = LC_KS5601; *p++ = c1; *p++ = euc[1]; @@ -89,22 +101,29 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_KR */ -static void -mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -115,8 +134,12 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -124,18 +147,28 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_KS5601) { *p++ = mic[1]; *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_KR, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c index 66c242d7f36..ebb4e0acd53 100644 --- a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c @@ -32,17 +32,20 @@ PG_FUNCTION_INFO_V1(mic_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_tw2big5(const unsigned char *euc, unsigned char *p, int len); -static void big52euc_tw(const unsigned char *euc, unsigned char *p, int len); -static void big52mic(const unsigned char *big5, unsigned char *p, int len); -static void mic2big5(const unsigned char *mic, unsigned char *p, int len); -static void euc_tw2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_tw(const unsigned char *mic, unsigned char *p, int len); +static int euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52euc_tw(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError); +static int mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_tw_to_big5(PG_FUNCTION_ARGS) @@ -50,12 +53,14 @@ euc_tw_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_BIG5); - euc_tw2big5(src, dest, len); + converted = euc_tw2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -64,12 +69,14 @@ big5_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_EUC_TW); - big52euc_tw(src, dest, len); + converted = big52euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -78,12 +85,14 @@ euc_tw_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_MULE_INTERNAL); - euc_tw2mic(src, dest, len); + converted = euc_tw2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -92,12 +101,14 @@ mic_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_TW); - mic2euc_tw(src, dest, len); + converted = mic2euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -106,12 +117,14 @@ big5_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_MULE_INTERNAL); - big52mic(src, dest, len); + converted = big52mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -120,21 +133,24 @@ mic_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_BIG5); - mic2big5(src, dest, len); + converted = mic2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_TW ---> Big5 */ -static void -euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; unsigned char c1; unsigned short big5buf, cnsBuf; @@ -149,8 +165,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Verify and decode the next EUC_TW input character */ l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -171,8 +191,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Write it out in Big5 */ big5buf = CNStoBIG5(cnsBuf, lc); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_EUC_TW, PG_BIG5, (const char *) euc, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; @@ -182,22 +206,29 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * Big5 ---> EUC_TW */ -static void -big52euc_tw(const unsigned char *big5, unsigned char *p, int len) +static int +big52euc_tw(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -212,8 +243,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); @@ -237,8 +272,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_EUC_TW, (const char *) big5, len); + } big5 += l; len -= l; @@ -256,14 +295,17 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) } } *p = '\0'; + + return big5 - start; } /* * EUC_TW ---> MIC */ -static void -euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -274,8 +316,12 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -304,22 +350,29 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_TW */ -static void -mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -330,8 +383,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -339,8 +396,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1) { *p++ = mic[1]; @@ -362,20 +423,27 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[3]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_TW, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * Big5 ---> MIC */ -static void -big52mic(const unsigned char *big5, unsigned char *p, int len) +static int +big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -389,8 +457,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } *p++ = c1; big5++; len--; @@ -398,8 +470,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); if (lc != 0) @@ -412,20 +488,27 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_MULE_INTERNAL, (const char *) big5, len); + } big5 += l; len -= l; } *p = '\0'; + + return big5 - start; } /* * MIC ---> Big5 */ -static void -mic2big5(const unsigned char *mic, unsigned char *p, int len) +static int +mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -438,8 +521,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -447,8 +534,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1 || c1 == LC_CNS11643_2 || c1 == LCPRV2_B) { if (c1 == LCPRV2_B) @@ -462,16 +553,26 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } big5buf = CNStoBIG5(cnsBuf, c1); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c index 2e28e6780a5..8610fcb69aa 100644 --- a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c +++ b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(win1250_to_latin2); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -82,12 +85,14 @@ latin2_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -96,12 +101,14 @@ mic_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN2); - mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -110,13 +117,15 @@ win1250_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - win1250_2_iso88592); + converted = latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -125,13 +134,15 @@ mic_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1250); - mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - iso88592_2_win1250); + converted = mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -140,12 +151,15 @@ latin2_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_WIN1250); - local2local(src, dest, len, PG_LATIN2, PG_WIN1250, iso88592_2_win1250); + converted = local2local(src, dest, len, PG_LATIN2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -154,10 +168,13 @@ win1250_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_LATIN2); - local2local(src, dest, len, PG_WIN1250, PG_LATIN2, win1250_2_iso88592); + converted = local2local(src, dest, len, PG_WIN1250, PG_LATIN2, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c index bc651410f21..bff27d1c295 100644 --- a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(mic_to_latin4); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -42,12 +45,14 @@ latin1_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,12 +61,14 @@ mic_to_latin1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN1); - mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -70,12 +77,14 @@ latin3_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN3, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -84,12 +93,14 @@ mic_to_latin3(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN3); - mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,12 +109,14 @@ latin4_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN4, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -112,10 +125,12 @@ mic_to_latin4(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN4); - mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c index d6067cdc24e..3838b15cab9 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ big5_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_UTF8); - LocalToUtf(src, len, dest, - &big5_to_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = LocalToUtf(src, len, dest, + &big5_to_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_BIG5); - UtfToLocal(src, len, dest, - &big5_from_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = UtfToLocal(src, len, dest, + &big5_from_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c index ed90e8e682e..75719fe5f1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c @@ -33,8 +33,11 @@ PG_FUNCTION_INFO_V1(koi8u_to_utf8); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -44,16 +47,19 @@ utf8_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8R); - UtfToLocal(src, len, dest, - &koi8r_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = UtfToLocal(src, len, dest, + &koi8r_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -62,16 +68,19 @@ koi8r_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8r_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = LocalToUtf(src, len, dest, + &koi8r_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -80,16 +89,19 @@ utf8_to_koi8u(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8U); - UtfToLocal(src, len, dest, - &koi8u_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = UtfToLocal(src, len, dest, + &koi8u_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,14 +110,17 @@ koi8u_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8U, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8u_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = LocalToUtf(src, len, dest, + &koi8u_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c index d699affce47..5391001951a 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jis_2004_to_unicode_tree, - LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = LocalToUtf(src, len, dest, + &euc_jis_2004_to_unicode_tree, + LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JIS_2004); - UtfToLocal(src, len, dest, - &euc_jis_2004_from_unicode_tree, - ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = UtfToLocal(src, len, dest, + &euc_jis_2004_from_unicode_tree, + ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c index d7c0ba6a58b..c87d1bf2398 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_cn_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_cn_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = LocalToUtf(src, len, dest, + &euc_cn_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_CN); - UtfToLocal(src, len, dest, - &euc_cn_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = UtfToLocal(src, len, dest, + &euc_cn_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c index 13a3a23e77b..6a55134db21 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jp); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jp_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jp_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = LocalToUtf(src, len, dest, + &euc_jp_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JP); - UtfToLocal(src, len, dest, - &euc_jp_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = UtfToLocal(src, len, dest, + &euc_jp_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c index 1bbb8aaef7b..fe1924e2fec 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_kr_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_kr_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = LocalToUtf(src, len, dest, + &euc_kr_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_KR); - UtfToLocal(src, len, dest, - &euc_kr_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = UtfToLocal(src, len, dest, + &euc_kr_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c index 9830045dccd..68215659b57 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_tw); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_tw_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_tw_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = LocalToUtf(src, len, dest, + &euc_tw_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_TW); - UtfToLocal(src, len, dest, - &euc_tw_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = UtfToLocal(src, len, dest, + &euc_tw_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c index f86ecf27424..e1a59c39a4d 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c @@ -183,8 +183,11 @@ conv_utf8_to_18030(uint32 code) * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -193,16 +196,19 @@ gb18030_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GB18030, PG_UTF8); - LocalToUtf(src, len, dest, - &gb18030_to_unicode_tree, - NULL, 0, - conv_18030_to_utf8, - PG_GB18030); + converted = LocalToUtf(src, len, dest, + &gb18030_to_unicode_tree, + NULL, 0, + conv_18030_to_utf8, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -211,14 +217,17 @@ utf8_to_gb18030(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GB18030); - UtfToLocal(src, len, dest, - &gb18030_from_unicode_tree, - NULL, 0, - conv_utf8_to_18030, - PG_GB18030); + converted = UtfToLocal(src, len, dest, + &gb18030_from_unicode_tree, + NULL, 0, + conv_utf8_to_18030, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c index 2ab8b16c8a8..881386d5347 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_gbk); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ gbk_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GBK, PG_UTF8); - LocalToUtf(src, len, dest, - &gbk_to_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = LocalToUtf(src, len, dest, + &gbk_to_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_gbk(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GBK); - UtfToLocal(src, len, dest, - &gbk_from_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = UtfToLocal(src, len, dest, + &gbk_from_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c index 3e49f67ea2f..d93a521badf 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c @@ -52,8 +52,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -100,6 +103,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -108,12 +112,15 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -122,7 +129,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -132,6 +139,7 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -140,12 +148,15 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -154,5 +165,5 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c index 67e713cca11..8ac93604a1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c @@ -26,8 +26,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859_1); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -37,6 +40,8 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_UTF8); @@ -45,7 +50,11 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_LATIN1, (const char *) src, len); + } if (!IS_HIGHBIT_SET(c)) *dest++ = c; else @@ -58,7 +67,7 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } Datum @@ -67,6 +76,8 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c, c1; @@ -76,7 +87,11 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_UTF8, (const char *) src, len); + } /* fast path for ASCII-subset characters */ if (!IS_HIGHBIT_SET(c)) { @@ -102,11 +117,15 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) len -= 2; } else + { + if (noError) + break; report_untranslatable_char(PG_UTF8, PG_LATIN1, (const char *) src, len); + } } } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c index 578f5df4e7f..317daa2d5ee 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_johab); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ johab_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_JOHAB, PG_UTF8); - LocalToUtf(src, len, dest, - &johab_to_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = LocalToUtf(src, len, dest, + &johab_to_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_johab(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_JOHAB); - UtfToLocal(src, len, dest, - &johab_from_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = UtfToLocal(src, len, dest, + &johab_from_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c index dd9fc2975ad..4c9348aba59 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ sjis_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_UTF8); - LocalToUtf(src, len, dest, - &sjis_to_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = LocalToUtf(src, len, dest, + &sjis_to_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SJIS); - UtfToLocal(src, len, dest, - &sjis_from_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = UtfToLocal(src, len, dest, + &sjis_from_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c index 4bcc886d674..1fffdc5930c 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_shift_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ shift_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &shift_jis_2004_to_unicode_tree, - LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = LocalToUtf(src, len, dest, + &shift_jis_2004_to_unicode_tree, + LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SHIFT_JIS_2004); - UtfToLocal(src, len, dest, - &shift_jis_2004_from_unicode_tree, - ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = UtfToLocal(src, len, dest, + &shift_jis_2004_from_unicode_tree, + ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c index c8e512994a1..d9471dad097 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_uhc); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ uhc_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UHC, PG_UTF8); - LocalToUtf(src, len, dest, - &uhc_to_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = LocalToUtf(src, len, dest, + &uhc_to_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_uhc(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_UHC); - UtfToLocal(src, len, dest, - &uhc_from_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = UtfToLocal(src, len, dest, + &uhc_from_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c index 0c9493dee56..110ba5677d0 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c @@ -48,8 +48,11 @@ PG_FUNCTION_INFO_V1(utf8_to_win); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -81,6 +84,7 @@ win_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -89,12 +93,15 @@ win_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -103,7 +110,7 @@ win_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -113,6 +120,7 @@ utf8_to_win(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -121,12 +129,15 @@ utf8_to_win(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -135,5 +146,5 @@ utf8_to_win(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/mbutils.c b/src/backend/utils/mb/mbutils.c index 2578573b0ab..65753860e35 100644 --- a/src/backend/utils/mb/mbutils.c +++ b/src/backend/utils/mb/mbutils.c @@ -406,12 +406,13 @@ pg_do_encoding_conversion(unsigned char *src, int len, MemoryContextAllocHuge(CurrentMemoryContext, (Size) len * MAX_CONVERSION_GROWTH + 1); - OidFunctionCall5(proc, - Int32GetDatum(src_encoding), - Int32GetDatum(dest_encoding), - CStringGetDatum(src), - CStringGetDatum(result), - Int32GetDatum(len)); + (void) OidFunctionCall6(proc, + Int32GetDatum(src_encoding), + Int32GetDatum(dest_encoding), + CStringGetDatum(src), + CStringGetDatum(result), + Int32GetDatum(len), + BoolGetDatum(false)); /* * If the result is large, it's worth repalloc'ing to release any extra @@ -849,12 +850,13 @@ pg_unicode_to_server(pg_wchar c, unsigned char *s) c_as_utf8[c_as_utf8_len] = '\0'; /* Convert, or throw error if we can't */ - FunctionCall5(Utf8ToServerConvProc, + FunctionCall6(Utf8ToServerConvProc, Int32GetDatum(PG_UTF8), Int32GetDatum(server_encoding), CStringGetDatum(c_as_utf8), CStringGetDatum(s), - Int32GetDatum(c_as_utf8_len)); + Int32GetDatum(c_as_utf8_len), + BoolGetDatum(false)); } diff --git a/src/bin/pg_upgrade/check.c b/src/bin/pg_upgrade/check.c index 43fc297eb69..ee6be95b08d 100644 --- a/src/bin/pg_upgrade/check.c +++ b/src/bin/pg_upgrade/check.c @@ -28,6 +28,7 @@ static void check_for_reg_data_type_usage(ClusterInfo *cluster); static void check_for_jsonb_9_4_usage(ClusterInfo *cluster); static void check_for_pg_role_prefix(ClusterInfo *cluster); static void check_for_new_tablespace_dir(ClusterInfo *new_cluster); +static void check_for_user_defined_encoding_conversions(ClusterInfo *cluster); static char *get_canonical_locale_name(int category, const char *locale); @@ -102,6 +103,15 @@ check_and_dump_old_cluster(bool live_check) check_for_reg_data_type_usage(&old_cluster); check_for_isn_and_int8_passing_mismatch(&old_cluster); + /* + * PG 14 changed the function signature of encoding conversion functions. + * Conversions from older versions cannot be upgraded automatically + * because the user-defined functions used by the encoding conversions + * need to changed to match the new signature. + */ + if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1300) + check_for_user_defined_encoding_conversions(&old_cluster); + /* * Pre-PG 14 allowed user defined postfix operators, which are not * supported anymore. Verify there are none, iff applicable. @@ -1268,6 +1278,91 @@ check_for_pg_role_prefix(ClusterInfo *cluster) check_ok(); } +/* + * Verify that no user-defined encoding conversions exist. + */ +static void +check_for_user_defined_encoding_conversions(ClusterInfo *cluster) +{ + int dbnum; + FILE *script = NULL; + bool found = false; + char output_path[MAXPGPATH]; + + prep_status("Checking for user-defined encoding conversions"); + + snprintf(output_path, sizeof(output_path), + "encoding_conversions.txt"); + + /* Find any user defined encoding conversions */ + for (dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++) + { + PGresult *res; + bool db_used = false; + int ntups; + int rowno; + int i_conoid, + i_conname, + i_nspname; + DbInfo *active_db = &cluster->dbarr.dbs[dbnum]; + PGconn *conn = connectToServer(cluster, active_db->db_name); + + /* + * The query below hardcodes FirstNormalObjectId as 16384 rather than + * interpolating that C #define into the query because, if that + * #define is ever changed, the cutoff we want to use is the value + * used by pre-version 14 servers, not that of some future version. + */ + res = executeQueryOrDie(conn, + "SELECT c.oid as conoid, c.conname, n.nspname " + "FROM pg_catalog.pg_conversion c, " + " pg_catalog.pg_namespace n " + "WHERE c.connamespace = n.oid AND " + " c.oid >= 16384"); + ntups = PQntuples(res); + i_conoid = PQfnumber(res, "conoid"); + i_conname = PQfnumber(res, "conname"); + i_nspname = PQfnumber(res, "nspname"); + for (rowno = 0; rowno < ntups; rowno++) + { + found = true; + if (script == NULL && + (script = fopen_priv(output_path, "w")) == NULL) + pg_fatal("could not open file \"%s\": %s\n", + output_path, strerror(errno)); + if (!db_used) + { + fprintf(script, "In database: %s\n", active_db->db_name); + db_used = true; + } + fprintf(script, " (oid=%s) %s.%s\n", + PQgetvalue(res, rowno, i_conoid), + PQgetvalue(res, rowno, i_nspname), + PQgetvalue(res, rowno, i_conname)); + } + + PQclear(res); + + PQfinish(conn); + } + + if (script) + fclose(script); + + if (found) + { + pg_log(PG_REPORT, "fatal\n"); + pg_fatal("Your installation contains user-defined encoding conversions.\n" + "The conversion function parameters changed in PostgreSQL version 14\n" + "so this cluster cannot currently be upgraded. You can remove the\n" + "encoding conversions in the old cluster and restart the upgrade.\n" + "A list of user-defined encoding conversions is in the file:\n" + " %s\n\n", output_path); + } + else + check_ok(); +} + /* * get_canonical_locale_name diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index f8174061ef3..75b829e8514 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10766,388 +10766,388 @@ # conversion functions { oid => '4302', descr => 'internal conversion function for KOI8R to MULE_INTERNAL', - proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_mic', + proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4303', descr => 'internal conversion function for MULE_INTERNAL to KOI8R', - proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_koi8r', + proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4304', descr => 'internal conversion function for ISO-8859-5 to MULE_INTERNAL', - proname => 'iso_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_mic', + proname => 'iso_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4305', descr => 'internal conversion function for MULE_INTERNAL to ISO-8859-5', - proname => 'mic_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_iso', + proname => 'mic_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4306', descr => 'internal conversion function for WIN1251 to MULE_INTERNAL', - proname => 'win1251_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_mic', + proname => 'win1251_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4307', descr => 'internal conversion function for MULE_INTERNAL to WIN1251', - proname => 'mic_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1251', + proname => 'mic_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4308', descr => 'internal conversion function for WIN866 to MULE_INTERNAL', - proname => 'win866_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_mic', + proname => 'win866_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4309', descr => 'internal conversion function for MULE_INTERNAL to WIN866', - proname => 'mic_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win866', + proname => 'mic_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4310', descr => 'internal conversion function for KOI8R to WIN1251', - proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4311', descr => 'internal conversion function for WIN1251 to KOI8R', - proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4312', descr => 'internal conversion function for KOI8R to WIN866', - proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_win866', + proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4313', descr => 'internal conversion function for WIN866 to KOI8R', - proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_koi8r', + proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4314', descr => 'internal conversion function for WIN866 to WIN1251', - proname => 'win866_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win866_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4315', descr => 'internal conversion function for WIN1251 to WIN866', - proname => 'win1251_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4316', descr => 'internal conversion function for ISO-8859-5 to KOI8R', - proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_koi8r', + proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4317', descr => 'internal conversion function for KOI8R to ISO-8859-5', - proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_iso', + proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4318', descr => 'internal conversion function for ISO-8859-5 to WIN1251', - proname => 'iso_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win1251', + proname => 'iso_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4319', descr => 'internal conversion function for WIN1251 to ISO-8859-5', - proname => 'win1251_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_iso', + proname => 'win1251_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4320', descr => 'internal conversion function for ISO-8859-5 to WIN866', - proname => 'iso_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win866', + proname => 'iso_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4321', descr => 'internal conversion function for WIN866 to ISO-8859-5', - proname => 'win866_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_iso', + proname => 'win866_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4322', descr => 'internal conversion function for EUC_CN to MULE_INTERNAL', - proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_mic', + proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_mic', probin => '$libdir/euc_cn_and_mic' }, { oid => '4323', descr => 'internal conversion function for MULE_INTERNAL to EUC_CN', - proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_cn', + proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_cn', probin => '$libdir/euc_cn_and_mic' }, { oid => '4324', descr => 'internal conversion function for EUC_JP to SJIS', - proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_sjis', + proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4325', descr => 'internal conversion function for SJIS to EUC_JP', - proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_euc_jp', + proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4326', descr => 'internal conversion function for EUC_JP to MULE_INTERNAL', - proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_mic', + proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4327', descr => 'internal conversion function for SJIS to MULE_INTERNAL', - proname => 'sjis_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_mic', + proname => 'sjis_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4328', descr => 'internal conversion function for MULE_INTERNAL to EUC_JP', - proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_jp', + proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4329', descr => 'internal conversion function for MULE_INTERNAL to SJIS', - proname => 'mic_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_sjis', + proname => 'mic_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4330', descr => 'internal conversion function for EUC_KR to MULE_INTERNAL', - proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_mic', + proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_mic', probin => '$libdir/euc_kr_and_mic' }, { oid => '4331', descr => 'internal conversion function for MULE_INTERNAL to EUC_KR', - proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_kr', + proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_kr', probin => '$libdir/euc_kr_and_mic' }, { oid => '4332', descr => 'internal conversion function for EUC_TW to BIG5', - proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_big5', + proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4333', descr => 'internal conversion function for BIG5 to EUC_TW', - proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_euc_tw', + proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4334', descr => 'internal conversion function for EUC_TW to MULE_INTERNAL', - proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_mic', + proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4335', descr => 'internal conversion function for BIG5 to MULE_INTERNAL', - proname => 'big5_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_mic', + proname => 'big5_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4336', descr => 'internal conversion function for MULE_INTERNAL to EUC_TW', - proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_tw', + proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4337', descr => 'internal conversion function for MULE_INTERNAL to BIG5', - proname => 'mic_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_big5', + proname => 'mic_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4338', descr => 'internal conversion function for LATIN2 to MULE_INTERNAL', - proname => 'latin2_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin2_to_mic', + proname => 'latin2_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4339', descr => 'internal conversion function for MULE_INTERNAL to LATIN2', - proname => 'mic_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin2', + proname => 'mic_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4340', descr => 'internal conversion function for WIN1250 to MULE_INTERNAL', - proname => 'win1250_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1250_to_mic', + proname => 'win1250_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4341', descr => 'internal conversion function for MULE_INTERNAL to WIN1250', - proname => 'mic_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1250', + proname => 'mic_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4342', descr => 'internal conversion function for LATIN2 to WIN1250', - proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4343', descr => 'internal conversion function for WIN1250 to LATIN2', - proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4344', descr => 'internal conversion function for LATIN1 to MULE_INTERNAL', - proname => 'latin1_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin1_to_mic', + proname => 'latin1_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin1_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4345', descr => 'internal conversion function for MULE_INTERNAL to LATIN1', - proname => 'mic_to_latin1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin1', + proname => 'mic_to_latin1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin1', probin => '$libdir/latin_and_mic' }, { oid => '4346', descr => 'internal conversion function for LATIN3 to MULE_INTERNAL', - proname => 'latin3_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin3_to_mic', + proname => 'latin3_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin3_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4347', descr => 'internal conversion function for MULE_INTERNAL to LATIN3', - proname => 'mic_to_latin3', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin3', + proname => 'mic_to_latin3', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin3', probin => '$libdir/latin_and_mic' }, { oid => '4348', descr => 'internal conversion function for LATIN4 to MULE_INTERNAL', - proname => 'latin4_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin4_to_mic', + proname => 'latin4_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin4_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4349', descr => 'internal conversion function for MULE_INTERNAL to LATIN4', - proname => 'mic_to_latin4', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin4', + proname => 'mic_to_latin4', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin4', probin => '$libdir/latin_and_mic' }, { oid => '4352', descr => 'internal conversion function for BIG5 to UTF8', - proname => 'big5_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_utf8', + proname => 'big5_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_utf8', probin => '$libdir/utf8_and_big5' }, { oid => '4353', descr => 'internal conversion function for UTF8 to BIG5', - proname => 'utf8_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_big5', + proname => 'utf8_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_big5', probin => '$libdir/utf8_and_big5' }, { oid => '4354', descr => 'internal conversion function for UTF8 to KOI8R', - proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8r', + proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8r', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4355', descr => 'internal conversion function for KOI8R to UTF8', - proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_utf8', + proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4356', descr => 'internal conversion function for UTF8 to KOI8U', - proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8u', + proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8u', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4357', descr => 'internal conversion function for KOI8U to UTF8', - proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8u_to_utf8', + proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8u_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4358', descr => 'internal conversion function for UTF8 to WIN', - proname => 'utf8_to_win', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_win', + proname => 'utf8_to_win', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_win', probin => '$libdir/utf8_and_win' }, { oid => '4359', descr => 'internal conversion function for WIN to UTF8', - proname => 'win_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win_to_utf8', + proname => 'win_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win_to_utf8', probin => '$libdir/utf8_and_win' }, { oid => '4360', descr => 'internal conversion function for EUC_CN to UTF8', - proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_utf8', + proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_utf8', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4361', descr => 'internal conversion function for UTF8 to EUC_CN', - proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_cn', + proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_cn', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4362', descr => 'internal conversion function for EUC_JP to UTF8', - proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_utf8', + proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_utf8', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4363', descr => 'internal conversion function for UTF8 to EUC_JP', - proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_jp', + proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jp', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4364', descr => 'internal conversion function for EUC_KR to UTF8', - proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_utf8', + proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_utf8', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4365', descr => 'internal conversion function for UTF8 to EUC_KR', - proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_kr', + proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_kr', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4366', descr => 'internal conversion function for EUC_TW to UTF8', - proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_utf8', + proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_utf8', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4367', descr => 'internal conversion function for UTF8 to EUC_TW', - proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_tw', + proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_tw', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4368', descr => 'internal conversion function for GB18030 to UTF8', - proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gb18030_to_utf8', + proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gb18030_to_utf8', probin => '$libdir/utf8_and_gb18030' }, { oid => '4369', descr => 'internal conversion function for UTF8 to GB18030', - proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gb18030', + proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gb18030', probin => '$libdir/utf8_and_gb18030' }, { oid => '4370', descr => 'internal conversion function for GBK to UTF8', - proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gbk_to_utf8', + proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gbk_to_utf8', probin => '$libdir/utf8_and_gbk' }, { oid => '4371', descr => 'internal conversion function for UTF8 to GBK', - proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gbk', + proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gbk', probin => '$libdir/utf8_and_gbk' }, { oid => '4372', descr => 'internal conversion function for UTF8 to ISO-8859 2-16', - proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_iso8859', + proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859', probin => '$libdir/utf8_and_iso8859' }, { oid => '4373', descr => 'internal conversion function for ISO-8859 2-16 to UTF8', - proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso8859_to_utf8', + proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_to_utf8', probin => '$libdir/utf8_and_iso8859' }, { oid => '4374', descr => 'internal conversion function for LATIN1 to UTF8', - proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_1_to_utf8', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4375', descr => 'internal conversion function for UTF8 to LATIN1', - proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859_1', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4376', descr => 'internal conversion function for JOHAB to UTF8', - proname => 'johab_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'johab_to_utf8', + proname => 'johab_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'johab_to_utf8', probin => '$libdir/utf8_and_johab' }, { oid => '4377', descr => 'internal conversion function for UTF8 to JOHAB', - proname => 'utf8_to_johab', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_johab', + proname => 'utf8_to_johab', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_johab', probin => '$libdir/utf8_and_johab' }, { oid => '4378', descr => 'internal conversion function for SJIS to UTF8', - proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_utf8', + proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_utf8', probin => '$libdir/utf8_and_sjis' }, { oid => '4379', descr => 'internal conversion function for UTF8 to SJIS', - proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_sjis', + proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_sjis', probin => '$libdir/utf8_and_sjis' }, { oid => '4380', descr => 'internal conversion function for UHC to UTF8', - proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'uhc_to_utf8', + proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'uhc_to_utf8', probin => '$libdir/utf8_and_uhc' }, { oid => '4381', descr => 'internal conversion function for UTF8 to UHC', - proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_uhc', + proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_uhc', probin => '$libdir/utf8_and_uhc' }, { oid => '4382', descr => 'internal conversion function for EUC_JIS_2004 to UTF8', - proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_utf8', probin => '$libdir/utf8_and_euc2004' }, { oid => '4383', descr => 'internal conversion function for UTF8 to EUC_JIS_2004', - proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jis_2004', probin => '$libdir/utf8_and_euc2004' }, { oid => '4384', descr => 'internal conversion function for SHIFT_JIS_2004 to UTF8', - proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_utf8', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4385', descr => 'internal conversion function for UTF8 to SHIFT_JIS_2004', - proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_shift_jis_2004', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4386', descr => 'internal conversion function for EUC_JIS_2004 to SHIFT_JIS_2004', proname => 'euc_jis_2004_to_shift_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_shift_jis_2004', probin => '$libdir/euc2004_sjis2004' }, { oid => '4387', descr => 'internal conversion function for SHIFT_JIS_2004 to EUC_JIS_2004', proname => 'shift_jis_2004_to_euc_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_euc_jis_2004', probin => '$libdir/euc2004_sjis2004' }, diff --git a/src/include/mb/pg_wchar.h b/src/include/mb/pg_wchar.h index 64b22e4b0d4..346a41a1f3d 100644 --- a/src/include/mb/pg_wchar.h +++ b/src/include/mb/pg_wchar.h @@ -627,18 +627,18 @@ extern void pg_unicode_to_server(pg_wchar c, unsigned char *s); extern unsigned short BIG5toCNS(unsigned short big5, unsigned char *lc); extern unsigned short CNStoBIG5(unsigned short cns, unsigned char lc); -extern void UtfToLocal(const unsigned char *utf, int len, - unsigned char *iso, - const pg_mb_radix_tree *map, - const pg_utf_to_local_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); -extern void LocalToUtf(const unsigned char *iso, int len, - unsigned char *utf, - const pg_mb_radix_tree *map, - const pg_local_to_utf_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); +extern int UtfToLocal(const unsigned char *utf, int len, + unsigned char *iso, + const pg_mb_radix_tree *map, + const pg_utf_to_local_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); +extern int LocalToUtf(const unsigned char *iso, int len, + unsigned char *utf, + const pg_mb_radix_tree *map, + const pg_local_to_utf_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); extern bool pg_verifymbstr(const char *mbstr, int len, bool noError); extern bool pg_verify_mbstr(int encoding, const char *mbstr, int len, @@ -656,18 +656,19 @@ extern void report_invalid_encoding(int encoding, const char *mbstr, int len) pg extern void report_untranslatable_char(int src_encoding, int dest_encoding, const char *mbstr, int len) pg_attribute_noreturn(); -extern void local2local(const unsigned char *l, unsigned char *p, int len, - int src_encoding, int dest_encoding, const unsigned char *tab); -extern void latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding); -extern void mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding); -extern void latin2mic_with_table(const unsigned char *l, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); -extern void mic2latin_with_table(const unsigned char *mic, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); +extern int local2local(const unsigned char *l, unsigned char *p, int len, + int src_encoding, int dest_encoding, const unsigned char *tab, + bool noError); +extern int latin2mic(const unsigned char *l, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int mic2latin(const unsigned char *mic, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int latin2mic_with_table(const unsigned char *l, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); +extern int mic2latin_with_table(const unsigned char *mic, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); #ifdef WIN32 extern WCHAR *pgwin32_message_to_UTF16(const char *str, int len, int *utf16len); diff --git a/src/test/regress/expected/opr_sanity.out b/src/test/regress/expected/opr_sanity.out index 254ca06d3dd..23ba60e395f 100644 --- a/src/test/regress/expected/opr_sanity.out +++ b/src/test/regress/expected/opr_sanity.out @@ -1052,13 +1052,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); oid | proname | oid | conname -----+---------+-----+--------- (0 rows) diff --git a/src/test/regress/sql/opr_sanity.sql b/src/test/regress/sql/opr_sanity.sql index bbd3834b634..04691745981 100644 --- a/src/test/regress/sql/opr_sanity.sql +++ b/src/test/regress/sql/opr_sanity.sql @@ -556,13 +556,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); -- Check for conprocs that don't perform the specific conversion that -- pg_conversion alleges they do, by trying to invoke each conversion -- 2.29.2 --------------39E46EF15EBFAA37D53332E5 Content-Type: text/x-patch; charset=UTF-8; name="v3-0003-Add-tests-for-the-new-noError-variants-of-built-i.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="v3-0003-Add-tests-for-the-new-noError-variants-of-built-i.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 34+ messages in thread
* [PATCH v3 2/5] Change conversion function signature. @ 2021-01-28 16:42 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 34+ messages in thread From: Heikki Linnakangas @ 2021-01-28 16:42 UTC (permalink / raw) Add a 'noError' argument, so that we can try to convert a buffer without knowing the character boundaries beforehand. The functions now need to return the number of input bytes successfully converted. This is is a backwards-incompatible change, if you have created a custom encoding conversion with CREATE CONVERSION. This adds a check to pg_upgrade for that, refusing the upgrade if there are any user-defined encoding conversions. --- doc/src/sgml/ref/create_conversion.sgml | 5 +- src/backend/commands/conversioncmds.c | 27 +- src/backend/utils/error/elog.c | 2 + src/backend/utils/mb/conv.c | 112 +++++- .../cyrillic_and_mic/cyrillic_and_mic.c | 127 ++++--- .../euc2004_sjis2004/euc2004_sjis2004.c | 96 ++++- .../euc_cn_and_mic/euc_cn_and_mic.c | 57 ++- .../euc_jp_and_sjis/euc_jp_and_sjis.c | 153 ++++++-- .../euc_kr_and_mic/euc_kr_and_mic.c | 57 ++- .../euc_tw_and_big5/euc_tw_and_big5.c | 165 +++++++-- .../latin2_and_win1250/latin2_and_win1250.c | 49 ++- .../latin_and_mic/latin_and_mic.c | 43 ++- .../utf8_and_big5/utf8_and_big5.c | 37 +- .../utf8_and_cyrillic/utf8_and_cyrillic.c | 67 ++-- .../utf8_and_euc2004/utf8_and_euc2004.c | 37 +- .../utf8_and_euc_cn/utf8_and_euc_cn.c | 37 +- .../utf8_and_euc_jp/utf8_and_euc_jp.c | 37 +- .../utf8_and_euc_kr/utf8_and_euc_kr.c | 37 +- .../utf8_and_euc_tw/utf8_and_euc_tw.c | 37 +- .../utf8_and_gb18030/utf8_and_gb18030.c | 37 +- .../utf8_and_gbk/utf8_and_gbk.c | 37 +- .../utf8_and_iso8859/utf8_and_iso8859.c | 43 ++- .../utf8_and_iso8859_1/utf8_and_iso8859_1.c | 27 +- .../utf8_and_johab/utf8_and_johab.c | 37 +- .../utf8_and_sjis/utf8_and_sjis.c | 37 +- .../utf8_and_sjis2004/utf8_and_sjis2004.c | 37 +- .../utf8_and_uhc/utf8_and_uhc.c | 37 +- .../utf8_and_win/utf8_and_win.c | 43 ++- src/backend/utils/mb/mbutils.c | 18 +- src/bin/pg_upgrade/check.c | 95 +++++ src/include/catalog/pg_proc.dat | 332 +++++++++--------- src/include/mb/pg_wchar.h | 49 +-- src/test/regress/expected/opr_sanity.out | 7 +- src/test/regress/sql/opr_sanity.sql | 7 +- 34 files changed, 1390 insertions(+), 635 deletions(-) diff --git a/doc/src/sgml/ref/create_conversion.sgml b/doc/src/sgml/ref/create_conversion.sgml index e7700fecfc5..f014a676c88 100644 --- a/doc/src/sgml/ref/create_conversion.sgml +++ b/doc/src/sgml/ref/create_conversion.sgml @@ -117,8 +117,9 @@ conv_proc( integer, -- destination encoding ID cstring, -- source string (null terminated C string) internal, -- destination (fill with a null terminated C string) - integer -- source string length -) RETURNS void; + integer, -- source string length + boolean -- if true, don't throw an error if conversion fails +) RETURNS integer; </programlisting></para> </listitem> </varlistentry> diff --git a/src/backend/commands/conversioncmds.c b/src/backend/commands/conversioncmds.c index f7ff321de71..d2041466911 100644 --- a/src/backend/commands/conversioncmds.c +++ b/src/backend/commands/conversioncmds.c @@ -45,8 +45,9 @@ CreateConversionCommand(CreateConversionStmt *stmt) const char *from_encoding_name = stmt->for_encoding_name; const char *to_encoding_name = stmt->to_encoding_name; List *func_name = stmt->func_name; - static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID}; + static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID, BOOLOID}; char result[1]; + Datum funcresult; /* Convert list of names to a name and namespace */ namespaceId = QualifiedNameGetCreationNamespace(stmt->conversion_name, @@ -92,8 +93,8 @@ CreateConversionCommand(CreateConversionStmt *stmt) funcoid = LookupFuncName(func_name, sizeof(funcargs) / sizeof(Oid), funcargs, false); - /* Check it returns VOID, else it's probably the wrong function */ - if (get_func_rettype(funcoid) != VOIDOID) + /* Check it returns int4, else it's probably the wrong function */ + if (get_func_rettype(funcoid) != INT4OID) ereport(ERROR, (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), errmsg("encoding conversion function %s must return type %s", @@ -111,12 +112,20 @@ CreateConversionCommand(CreateConversionStmt *stmt) * string; the conversion function should throw an error if it can't * perform the requested conversion. */ - OidFunctionCall5(funcoid, - Int32GetDatum(from_encoding), - Int32GetDatum(to_encoding), - CStringGetDatum(""), - CStringGetDatum(result), - Int32GetDatum(0)); + funcresult = OidFunctionCall6(funcoid, + Int32GetDatum(from_encoding), + Int32GetDatum(to_encoding), + CStringGetDatum(""), + CStringGetDatum(result), + Int32GetDatum(0), + BoolGetDatum(false)); + + /* The function should return 0 for empty input. Might as well check that, too. */ + if (DatumGetInt32(funcresult) != 0) + ereport(ERROR, + (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), + errmsg("encoding conversion function %s returned incorrect result for empty input", + NameListToString(func_name)))); /* * All seem ok, go ahead (possible failure would be a duplicate conversion diff --git a/src/backend/utils/error/elog.c b/src/backend/utils/error/elog.c index 80c26724612..762f77d533c 100644 --- a/src/backend/utils/error/elog.c +++ b/src/backend/utils/error/elog.c @@ -2280,6 +2280,8 @@ write_console(const char *line, int len) * Conversion on non-win32 platforms is not implemented yet. It requires * non-throw version of pg_do_encoding_conversion(), that converts * unconvertable characters to '?' without errors. + * + * XXX: We have a no-throw version now. It doesn't convert to '?' though. */ #endif diff --git a/src/backend/utils/mb/conv.c b/src/backend/utils/mb/conv.c index a07b54bd3b8..b83358bc7a5 100644 --- a/src/backend/utils/mb/conv.c +++ b/src/backend/utils/mb/conv.c @@ -26,14 +26,16 @@ * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the target charset, or 0 if there is no equivalent code. */ -void +int local2local(const unsigned char *l, unsigned char *p, int len, int src_encoding, int dest_encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -41,7 +43,11 @@ local2local(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(src_encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -50,13 +56,19 @@ local2local(const unsigned char *l, if (c2) *p++ = c2; else + { + if (noError) + break; report_untranslatable_char(src_encoding, dest_encoding, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -67,17 +79,22 @@ local2local(const unsigned char *l, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = l; int c1; while (len > 0) { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (IS_HIGHBIT_SET(c1)) *p++ = lc; *p++ = c1; @@ -85,6 +102,8 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, len--; } *p = '\0'; + + return l - start; } /* @@ -95,17 +114,22 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -118,17 +142,27 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1])) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); + } *p++ = mic[1]; mic += 2; len -= 2; } } *p = '\0'; + + return mic - start; } @@ -144,14 +178,16 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the mule encoding, or 0 if there is no equivalent code. */ -void +int latin2mic_with_table(const unsigned char *l, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -159,7 +195,11 @@ latin2mic_with_table(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -171,13 +211,19 @@ latin2mic_with_table(const unsigned char *l, *p++ = c2; } else + { + if (noError) + break; report_untranslatable_char(encoding, PG_MULE_INTERNAL, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -192,14 +238,16 @@ latin2mic_with_table(const unsigned char *l, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the local charset, or 0 if there is no equivalent code. */ -void +int mic2latin_with_table(const unsigned char *mic, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = mic; unsigned char c1, c2; @@ -207,7 +255,11 @@ mic2latin_with_table(const unsigned char *mic, { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -220,11 +272,17 @@ mic2latin_with_table(const unsigned char *mic, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1]) || (c2 = tab[mic[1] - HIGHBIT]) == 0) { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); break; /* keep compiler quiet */ @@ -235,6 +293,8 @@ mic2latin_with_table(const unsigned char *mic, } } *p = '\0'; + + return mic - start; } /* @@ -425,17 +485,19 @@ pg_mb_radix_conv(const pg_mb_radix_tree *rt, * * See pg_wchar.h for more details about the data structures used here. */ -void +int UtfToLocal(const unsigned char *utf, int len, unsigned char *iso, const pg_mb_radix_tree *map, const pg_utf_to_local_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, bool noError) { uint32 iutf; int l; const pg_utf_to_local_combined *cp; + const unsigned char *start = utf; + const unsigned char *cur = utf; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -449,6 +511,8 @@ UtfToLocal(const unsigned char *utf, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*utf == '\0') break; @@ -584,15 +648,19 @@ UtfToLocal(const unsigned char *utf, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(PG_UTF8, encoding, (const char *) (utf - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(PG_UTF8, (const char *) utf, len); *iso = '\0'; + + return cur - start; } /* @@ -616,18 +684,24 @@ UtfToLocal(const unsigned char *utf, int len, * (if provided) is applied. An error is raised if no match is found. * * See pg_wchar.h for more details about the data structures used here. + * + * Returns the number of input bytes consumed. If noError is true, this can + * be less than 'len'. */ -void +int LocalToUtf(const unsigned char *iso, int len, unsigned char *utf, const pg_mb_radix_tree *map, const pg_local_to_utf_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, + bool noError) { uint32 iiso; int l; const pg_local_to_utf_combined *cp; + const unsigned char *start = iso; + const unsigned char *cur = iso; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -641,6 +715,8 @@ LocalToUtf(const unsigned char *iso, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*iso == '\0') break; @@ -723,13 +799,17 @@ LocalToUtf(const unsigned char *iso, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(encoding, PG_UTF8, (const char *) (iso - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(encoding, (const char *) iso, len); *utf = '\0'; + + return cur - start; } diff --git a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c index 4c5b02654de..368c2deb5e4 100644 --- a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c @@ -44,8 +44,11 @@ PG_FUNCTION_INFO_V1(win866_to_iso); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -306,12 +309,14 @@ koi8r_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -320,12 +325,14 @@ mic_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_KOI8R); - mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -334,12 +341,14 @@ iso_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -348,12 +357,14 @@ mic_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_ISO_8859_5); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -362,12 +373,14 @@ win1251_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -376,12 +389,14 @@ mic_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1251); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -390,12 +405,14 @@ win866_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -404,12 +421,14 @@ mic_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN866); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -418,12 +437,14 @@ koi8r_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN1251); - local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -432,12 +453,14 @@ win1251_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_KOI8R); - local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi); + converted = local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -446,12 +469,14 @@ koi8r_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN866); - local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -460,12 +485,14 @@ win866_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_KOI8R); - local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi); + converted = local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -474,12 +501,14 @@ win866_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_WIN1251); - local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251); + converted = local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -488,12 +517,14 @@ win1251_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_WIN866); - local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866); + converted = local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -502,12 +533,14 @@ iso_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_KOI8R); - local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -516,12 +549,14 @@ koi8r_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_ISO_8859_5); - local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso); + converted = local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -530,12 +565,14 @@ iso_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN1251); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -544,12 +581,14 @@ win1251_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso); + converted = local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -558,12 +597,14 @@ iso_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN866); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -572,10 +613,12 @@ win866_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso); + converted = local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c index 4d7fb116cfd..88529c644cf 100644 --- a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c @@ -19,8 +19,8 @@ PG_MODULE_MAGIC; PG_FUNCTION_INFO_V1(euc_jis_2004_to_shift_jis_2004); PG_FUNCTION_INFO_V1(shift_jis_2004_to_euc_jis_2004); -static void euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len); -static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len); +static int euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError); /* ---------- * conv_proc( @@ -28,8 +28,11 @@ static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -39,12 +42,14 @@ euc_jis_2004_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_SHIFT_JIS_2004); - euc_jis_20042shift_jis_2004(src, dest, len); + converted = euc_jis_20042shift_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -53,20 +58,23 @@ shift_jis_2004_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_EUC_JIS_2004); - shift_jis_20042euc_jis_2004(src, dest, len); + converted = shift_jis_20042euc_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_JIS_2004 -> SHIFT_JIS_2004 */ -static void -euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, ku, ten; @@ -79,8 +87,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -90,8 +102,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) l = pg_encoding_verifymbchar(PG_EUC_JIS_2004, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (c1 == SS2 && l == 2) /* JIS X 0201 kana? */ { @@ -121,8 +137,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) *p++ = (ku + 0x19b) >> 1; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } if (ku % 2) @@ -132,8 +152,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; @@ -149,8 +173,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ku >= 63 && ku <= 94) *p++ = (ku + 0x181) >> 1; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (ku % 2) { @@ -159,20 +187,30 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else - report_invalid_encoding(PG_EUC_JIS_2004, + { + if (noError) + break; + report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } euc += l; len -= l; } *p = '\0'; + + return euc - start; } /* @@ -212,9 +250,10 @@ get_ten(int b, int *ku) * SHIFT_JIS_2004 ---> EUC_JIS_2004 */ -static void -shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len) +static int +shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1; int ku, ten, @@ -230,8 +269,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -241,8 +284,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len l = pg_encoding_verifymbchar(PG_SHIFT_JIS_2004, (const char *) sjis, len); if (l < 0 || l > len) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf && l == 1) { @@ -266,8 +313,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x100; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xe0 && c1 <= 0xef) /* plane 1 62ku-94ku */ @@ -275,9 +326,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x180; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, - (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xf0 && c1 <= 0xf3) /* plane 2 @@ -286,8 +340,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } switch (c1) { case 0xf0: @@ -309,16 +367,24 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 == 0xf4 && kubun == 1) ku = 15; else ku = (c1 << 1) - 0x19a - kubun; } else + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (plane == 2) *p++ = SS3; @@ -330,4 +396,6 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c index e9bb896935f..a8da733803d 100644 --- a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_cn2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_cn(const unsigned char *mic, unsigned char *p, int len); +static int euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_cn_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_cn_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_MULE_INTERNAL); - euc_cn2mic(src, dest, len); + converted = euc_cn2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_CN); - mic2euc_cn(src, dest, len); + converted = mic2euc_cn(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_CN ---> MIC */ -static void -euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; while (len > 0) @@ -76,7 +84,11 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (len < 2 || !IS_HIGHBIT_SET(euc[1])) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = LC_GB2312_80; *p++ = c1; *p++ = euc[1]; @@ -86,21 +98,28 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_CN */ -static void -mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) @@ -109,11 +128,19 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (c1 != LC_GB2312_80) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_CN, (const char *) mic, len); + } if (len < 3 || !IS_HIGHBIT_SET(mic[1]) || !IS_HIGHBIT_SET(mic[2])) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } mic++; *p++ = *mic++; *p++ = *mic++; @@ -122,12 +149,18 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; } } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c index 5059f917a98..cc4817dc4cd 100644 --- a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c @@ -42,17 +42,20 @@ PG_FUNCTION_INFO_V1(mic_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void sjis2mic(const unsigned char *sjis, unsigned char *p, int len); -static void mic2sjis(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_jp(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len); -static void sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len); +static int sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError); +static int mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_jp_to_sjis(PG_FUNCTION_ARGS) @@ -60,12 +63,14 @@ euc_jp_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_SJIS); - euc_jp2sjis(src, dest, len); + converted = euc_jp2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -74,12 +79,14 @@ sjis_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_EUC_JP); - sjis2euc_jp(src, dest, len); + converted = sjis2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -88,12 +95,14 @@ euc_jp_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_MULE_INTERNAL); - euc_jp2mic(src, dest, len); + converted = euc_jp2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -102,12 +111,14 @@ mic_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_JP); - mic2euc_jp(src, dest, len); + converted = mic2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -116,12 +127,14 @@ sjis_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_MULE_INTERNAL); - sjis2mic(src, dest, len); + converted = sjis2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -130,20 +143,23 @@ mic_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_SJIS); - mic2sjis(src, dest, len); + converted = mic2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * SJIS ---> MIC */ -static void -sjis2mic(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -167,7 +183,11 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) * JIS X0208, X0212, user defined extended characters */ if (len < 2 || !ISSJISHEAD(c1) || !ISSJISTAIL(sjis[1])) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } c2 = sjis[1]; k = (c1 << 8) + c2; if (k >= 0xed40 && k < 0xf040) @@ -257,21 +277,28 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; } } *p = '\0'; + + return sjis - start; } /* * MIC ---> SJIS */ -static void -mic2sjis(const unsigned char *mic, unsigned char *p, int len) +static int +mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1, c2, k, @@ -284,8 +311,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -293,8 +324,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) *p++ = mic[1]; else if (c1 == LC_JISX0208) @@ -350,20 +385,27 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_SJIS, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP ---> MIC */ -static void -euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -374,8 +416,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -383,8 +429,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* 1 byte kana? */ *p++ = LC_JISX0201K; @@ -406,14 +456,17 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_JP */ -static void -mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -424,8 +477,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -433,8 +490,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) { *p++ = SS2; @@ -452,20 +513,27 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_JP, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP -> SJIS */ -static void -euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, c2, k; @@ -478,8 +546,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -487,8 +559,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* hankaku kana? */ @@ -551,14 +627,17 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * SJIS ---> EUC_JP */ -static void -sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -573,8 +652,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -582,8 +665,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_SJIS, (const char *) sjis, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf) { /* JIS X0201 (1 byte kana) */ @@ -680,4 +767,6 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c index ac823d6c270..a5b51617e52 100644 --- a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_kr2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_kr(const unsigned char *mic, unsigned char *p, int len); +static int euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_kr_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_kr_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_MULE_INTERNAL); - euc_kr2mic(src, dest, len); + converted = euc_kr2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_KR); - mic2euc_kr(src, dest, len); + converted = mic2euc_kr(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_KR ---> MIC */ -static void -euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -78,8 +86,12 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_KR, (const char *) euc, len); if (l != 2) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = LC_KS5601; *p++ = c1; *p++ = euc[1]; @@ -89,22 +101,29 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_KR */ -static void -mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -115,8 +134,12 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -124,18 +147,28 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_KS5601) { *p++ = mic[1]; *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_KR, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c index 66c242d7f36..ebb4e0acd53 100644 --- a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c @@ -32,17 +32,20 @@ PG_FUNCTION_INFO_V1(mic_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_tw2big5(const unsigned char *euc, unsigned char *p, int len); -static void big52euc_tw(const unsigned char *euc, unsigned char *p, int len); -static void big52mic(const unsigned char *big5, unsigned char *p, int len); -static void mic2big5(const unsigned char *mic, unsigned char *p, int len); -static void euc_tw2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_tw(const unsigned char *mic, unsigned char *p, int len); +static int euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52euc_tw(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError); +static int mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_tw_to_big5(PG_FUNCTION_ARGS) @@ -50,12 +53,14 @@ euc_tw_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_BIG5); - euc_tw2big5(src, dest, len); + converted = euc_tw2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -64,12 +69,14 @@ big5_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_EUC_TW); - big52euc_tw(src, dest, len); + converted = big52euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -78,12 +85,14 @@ euc_tw_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_MULE_INTERNAL); - euc_tw2mic(src, dest, len); + converted = euc_tw2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -92,12 +101,14 @@ mic_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_TW); - mic2euc_tw(src, dest, len); + converted = mic2euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -106,12 +117,14 @@ big5_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_MULE_INTERNAL); - big52mic(src, dest, len); + converted = big52mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -120,21 +133,24 @@ mic_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_BIG5); - mic2big5(src, dest, len); + converted = mic2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_TW ---> Big5 */ -static void -euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; unsigned char c1; unsigned short big5buf, cnsBuf; @@ -149,8 +165,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Verify and decode the next EUC_TW input character */ l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -171,8 +191,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Write it out in Big5 */ big5buf = CNStoBIG5(cnsBuf, lc); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_EUC_TW, PG_BIG5, (const char *) euc, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; @@ -182,22 +206,29 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * Big5 ---> EUC_TW */ -static void -big52euc_tw(const unsigned char *big5, unsigned char *p, int len) +static int +big52euc_tw(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -212,8 +243,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); @@ -237,8 +272,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_EUC_TW, (const char *) big5, len); + } big5 += l; len -= l; @@ -256,14 +295,17 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) } } *p = '\0'; + + return big5 - start; } /* * EUC_TW ---> MIC */ -static void -euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -274,8 +316,12 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -304,22 +350,29 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_TW */ -static void -mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -330,8 +383,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -339,8 +396,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1) { *p++ = mic[1]; @@ -362,20 +423,27 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[3]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_TW, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * Big5 ---> MIC */ -static void -big52mic(const unsigned char *big5, unsigned char *p, int len) +static int +big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -389,8 +457,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } *p++ = c1; big5++; len--; @@ -398,8 +470,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); if (lc != 0) @@ -412,20 +488,27 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_MULE_INTERNAL, (const char *) big5, len); + } big5 += l; len -= l; } *p = '\0'; + + return big5 - start; } /* * MIC ---> Big5 */ -static void -mic2big5(const unsigned char *mic, unsigned char *p, int len) +static int +mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -438,8 +521,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -447,8 +534,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1 || c1 == LC_CNS11643_2 || c1 == LCPRV2_B) { if (c1 == LCPRV2_B) @@ -462,16 +553,26 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } big5buf = CNStoBIG5(cnsBuf, c1); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c index 2e28e6780a5..8610fcb69aa 100644 --- a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c +++ b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(win1250_to_latin2); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -82,12 +85,14 @@ latin2_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -96,12 +101,14 @@ mic_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN2); - mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -110,13 +117,15 @@ win1250_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - win1250_2_iso88592); + converted = latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -125,13 +134,15 @@ mic_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1250); - mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - iso88592_2_win1250); + converted = mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -140,12 +151,15 @@ latin2_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_WIN1250); - local2local(src, dest, len, PG_LATIN2, PG_WIN1250, iso88592_2_win1250); + converted = local2local(src, dest, len, PG_LATIN2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -154,10 +168,13 @@ win1250_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_LATIN2); - local2local(src, dest, len, PG_WIN1250, PG_LATIN2, win1250_2_iso88592); + converted = local2local(src, dest, len, PG_WIN1250, PG_LATIN2, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c index bc651410f21..bff27d1c295 100644 --- a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(mic_to_latin4); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -42,12 +45,14 @@ latin1_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,12 +61,14 @@ mic_to_latin1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN1); - mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -70,12 +77,14 @@ latin3_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN3, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -84,12 +93,14 @@ mic_to_latin3(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN3); - mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,12 +109,14 @@ latin4_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN4, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -112,10 +125,12 @@ mic_to_latin4(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN4); - mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c index d6067cdc24e..3838b15cab9 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ big5_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_UTF8); - LocalToUtf(src, len, dest, - &big5_to_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = LocalToUtf(src, len, dest, + &big5_to_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_BIG5); - UtfToLocal(src, len, dest, - &big5_from_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = UtfToLocal(src, len, dest, + &big5_from_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c index ed90e8e682e..75719fe5f1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c @@ -33,8 +33,11 @@ PG_FUNCTION_INFO_V1(koi8u_to_utf8); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -44,16 +47,19 @@ utf8_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8R); - UtfToLocal(src, len, dest, - &koi8r_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = UtfToLocal(src, len, dest, + &koi8r_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -62,16 +68,19 @@ koi8r_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8r_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = LocalToUtf(src, len, dest, + &koi8r_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -80,16 +89,19 @@ utf8_to_koi8u(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8U); - UtfToLocal(src, len, dest, - &koi8u_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = UtfToLocal(src, len, dest, + &koi8u_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,14 +110,17 @@ koi8u_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8U, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8u_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = LocalToUtf(src, len, dest, + &koi8u_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c index d699affce47..5391001951a 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jis_2004_to_unicode_tree, - LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = LocalToUtf(src, len, dest, + &euc_jis_2004_to_unicode_tree, + LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JIS_2004); - UtfToLocal(src, len, dest, - &euc_jis_2004_from_unicode_tree, - ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = UtfToLocal(src, len, dest, + &euc_jis_2004_from_unicode_tree, + ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c index d7c0ba6a58b..c87d1bf2398 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_cn_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_cn_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = LocalToUtf(src, len, dest, + &euc_cn_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_CN); - UtfToLocal(src, len, dest, - &euc_cn_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = UtfToLocal(src, len, dest, + &euc_cn_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c index 13a3a23e77b..6a55134db21 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jp); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jp_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jp_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = LocalToUtf(src, len, dest, + &euc_jp_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JP); - UtfToLocal(src, len, dest, - &euc_jp_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = UtfToLocal(src, len, dest, + &euc_jp_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c index 1bbb8aaef7b..fe1924e2fec 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_kr_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_kr_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = LocalToUtf(src, len, dest, + &euc_kr_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_KR); - UtfToLocal(src, len, dest, - &euc_kr_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = UtfToLocal(src, len, dest, + &euc_kr_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c index 9830045dccd..68215659b57 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_tw); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_tw_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_tw_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = LocalToUtf(src, len, dest, + &euc_tw_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_TW); - UtfToLocal(src, len, dest, - &euc_tw_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = UtfToLocal(src, len, dest, + &euc_tw_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c index f86ecf27424..e1a59c39a4d 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c @@ -183,8 +183,11 @@ conv_utf8_to_18030(uint32 code) * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -193,16 +196,19 @@ gb18030_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GB18030, PG_UTF8); - LocalToUtf(src, len, dest, - &gb18030_to_unicode_tree, - NULL, 0, - conv_18030_to_utf8, - PG_GB18030); + converted = LocalToUtf(src, len, dest, + &gb18030_to_unicode_tree, + NULL, 0, + conv_18030_to_utf8, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -211,14 +217,17 @@ utf8_to_gb18030(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GB18030); - UtfToLocal(src, len, dest, - &gb18030_from_unicode_tree, - NULL, 0, - conv_utf8_to_18030, - PG_GB18030); + converted = UtfToLocal(src, len, dest, + &gb18030_from_unicode_tree, + NULL, 0, + conv_utf8_to_18030, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c index 2ab8b16c8a8..881386d5347 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_gbk); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ gbk_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GBK, PG_UTF8); - LocalToUtf(src, len, dest, - &gbk_to_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = LocalToUtf(src, len, dest, + &gbk_to_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_gbk(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GBK); - UtfToLocal(src, len, dest, - &gbk_from_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = UtfToLocal(src, len, dest, + &gbk_from_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c index 3e49f67ea2f..d93a521badf 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c @@ -52,8 +52,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -100,6 +103,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -108,12 +112,15 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -122,7 +129,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -132,6 +139,7 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -140,12 +148,15 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -154,5 +165,5 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c index 67e713cca11..8ac93604a1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c @@ -26,8 +26,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859_1); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -37,6 +40,8 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_UTF8); @@ -45,7 +50,11 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_LATIN1, (const char *) src, len); + } if (!IS_HIGHBIT_SET(c)) *dest++ = c; else @@ -58,7 +67,7 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } Datum @@ -67,6 +76,8 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c, c1; @@ -76,7 +87,11 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_UTF8, (const char *) src, len); + } /* fast path for ASCII-subset characters */ if (!IS_HIGHBIT_SET(c)) { @@ -102,11 +117,15 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) len -= 2; } else + { + if (noError) + break; report_untranslatable_char(PG_UTF8, PG_LATIN1, (const char *) src, len); + } } } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c index 578f5df4e7f..317daa2d5ee 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_johab); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ johab_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_JOHAB, PG_UTF8); - LocalToUtf(src, len, dest, - &johab_to_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = LocalToUtf(src, len, dest, + &johab_to_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_johab(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_JOHAB); - UtfToLocal(src, len, dest, - &johab_from_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = UtfToLocal(src, len, dest, + &johab_from_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c index dd9fc2975ad..4c9348aba59 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ sjis_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_UTF8); - LocalToUtf(src, len, dest, - &sjis_to_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = LocalToUtf(src, len, dest, + &sjis_to_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SJIS); - UtfToLocal(src, len, dest, - &sjis_from_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = UtfToLocal(src, len, dest, + &sjis_from_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c index 4bcc886d674..1fffdc5930c 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_shift_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ shift_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &shift_jis_2004_to_unicode_tree, - LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = LocalToUtf(src, len, dest, + &shift_jis_2004_to_unicode_tree, + LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SHIFT_JIS_2004); - UtfToLocal(src, len, dest, - &shift_jis_2004_from_unicode_tree, - ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = UtfToLocal(src, len, dest, + &shift_jis_2004_from_unicode_tree, + ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c index c8e512994a1..d9471dad097 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_uhc); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ uhc_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UHC, PG_UTF8); - LocalToUtf(src, len, dest, - &uhc_to_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = LocalToUtf(src, len, dest, + &uhc_to_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_uhc(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_UHC); - UtfToLocal(src, len, dest, - &uhc_from_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = UtfToLocal(src, len, dest, + &uhc_from_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c index 0c9493dee56..110ba5677d0 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c @@ -48,8 +48,11 @@ PG_FUNCTION_INFO_V1(utf8_to_win); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -81,6 +84,7 @@ win_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -89,12 +93,15 @@ win_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -103,7 +110,7 @@ win_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -113,6 +120,7 @@ utf8_to_win(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -121,12 +129,15 @@ utf8_to_win(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -135,5 +146,5 @@ utf8_to_win(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/mbutils.c b/src/backend/utils/mb/mbutils.c index 2578573b0ab..65753860e35 100644 --- a/src/backend/utils/mb/mbutils.c +++ b/src/backend/utils/mb/mbutils.c @@ -406,12 +406,13 @@ pg_do_encoding_conversion(unsigned char *src, int len, MemoryContextAllocHuge(CurrentMemoryContext, (Size) len * MAX_CONVERSION_GROWTH + 1); - OidFunctionCall5(proc, - Int32GetDatum(src_encoding), - Int32GetDatum(dest_encoding), - CStringGetDatum(src), - CStringGetDatum(result), - Int32GetDatum(len)); + (void) OidFunctionCall6(proc, + Int32GetDatum(src_encoding), + Int32GetDatum(dest_encoding), + CStringGetDatum(src), + CStringGetDatum(result), + Int32GetDatum(len), + BoolGetDatum(false)); /* * If the result is large, it's worth repalloc'ing to release any extra @@ -849,12 +850,13 @@ pg_unicode_to_server(pg_wchar c, unsigned char *s) c_as_utf8[c_as_utf8_len] = '\0'; /* Convert, or throw error if we can't */ - FunctionCall5(Utf8ToServerConvProc, + FunctionCall6(Utf8ToServerConvProc, Int32GetDatum(PG_UTF8), Int32GetDatum(server_encoding), CStringGetDatum(c_as_utf8), CStringGetDatum(s), - Int32GetDatum(c_as_utf8_len)); + Int32GetDatum(c_as_utf8_len), + BoolGetDatum(false)); } diff --git a/src/bin/pg_upgrade/check.c b/src/bin/pg_upgrade/check.c index 43fc297eb69..ee6be95b08d 100644 --- a/src/bin/pg_upgrade/check.c +++ b/src/bin/pg_upgrade/check.c @@ -28,6 +28,7 @@ static void check_for_reg_data_type_usage(ClusterInfo *cluster); static void check_for_jsonb_9_4_usage(ClusterInfo *cluster); static void check_for_pg_role_prefix(ClusterInfo *cluster); static void check_for_new_tablespace_dir(ClusterInfo *new_cluster); +static void check_for_user_defined_encoding_conversions(ClusterInfo *cluster); static char *get_canonical_locale_name(int category, const char *locale); @@ -102,6 +103,15 @@ check_and_dump_old_cluster(bool live_check) check_for_reg_data_type_usage(&old_cluster); check_for_isn_and_int8_passing_mismatch(&old_cluster); + /* + * PG 14 changed the function signature of encoding conversion functions. + * Conversions from older versions cannot be upgraded automatically + * because the user-defined functions used by the encoding conversions + * need to changed to match the new signature. + */ + if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1300) + check_for_user_defined_encoding_conversions(&old_cluster); + /* * Pre-PG 14 allowed user defined postfix operators, which are not * supported anymore. Verify there are none, iff applicable. @@ -1268,6 +1278,91 @@ check_for_pg_role_prefix(ClusterInfo *cluster) check_ok(); } +/* + * Verify that no user-defined encoding conversions exist. + */ +static void +check_for_user_defined_encoding_conversions(ClusterInfo *cluster) +{ + int dbnum; + FILE *script = NULL; + bool found = false; + char output_path[MAXPGPATH]; + + prep_status("Checking for user-defined encoding conversions"); + + snprintf(output_path, sizeof(output_path), + "encoding_conversions.txt"); + + /* Find any user defined encoding conversions */ + for (dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++) + { + PGresult *res; + bool db_used = false; + int ntups; + int rowno; + int i_conoid, + i_conname, + i_nspname; + DbInfo *active_db = &cluster->dbarr.dbs[dbnum]; + PGconn *conn = connectToServer(cluster, active_db->db_name); + + /* + * The query below hardcodes FirstNormalObjectId as 16384 rather than + * interpolating that C #define into the query because, if that + * #define is ever changed, the cutoff we want to use is the value + * used by pre-version 14 servers, not that of some future version. + */ + res = executeQueryOrDie(conn, + "SELECT c.oid as conoid, c.conname, n.nspname " + "FROM pg_catalog.pg_conversion c, " + " pg_catalog.pg_namespace n " + "WHERE c.connamespace = n.oid AND " + " c.oid >= 16384"); + ntups = PQntuples(res); + i_conoid = PQfnumber(res, "conoid"); + i_conname = PQfnumber(res, "conname"); + i_nspname = PQfnumber(res, "nspname"); + for (rowno = 0; rowno < ntups; rowno++) + { + found = true; + if (script == NULL && + (script = fopen_priv(output_path, "w")) == NULL) + pg_fatal("could not open file \"%s\": %s\n", + output_path, strerror(errno)); + if (!db_used) + { + fprintf(script, "In database: %s\n", active_db->db_name); + db_used = true; + } + fprintf(script, " (oid=%s) %s.%s\n", + PQgetvalue(res, rowno, i_conoid), + PQgetvalue(res, rowno, i_nspname), + PQgetvalue(res, rowno, i_conname)); + } + + PQclear(res); + + PQfinish(conn); + } + + if (script) + fclose(script); + + if (found) + { + pg_log(PG_REPORT, "fatal\n"); + pg_fatal("Your installation contains user-defined encoding conversions.\n" + "The conversion function parameters changed in PostgreSQL version 14\n" + "so this cluster cannot currently be upgraded. You can remove the\n" + "encoding conversions in the old cluster and restart the upgrade.\n" + "A list of user-defined encoding conversions is in the file:\n" + " %s\n\n", output_path); + } + else + check_ok(); +} + /* * get_canonical_locale_name diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index f8174061ef3..75b829e8514 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10766,388 +10766,388 @@ # conversion functions { oid => '4302', descr => 'internal conversion function for KOI8R to MULE_INTERNAL', - proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_mic', + proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4303', descr => 'internal conversion function for MULE_INTERNAL to KOI8R', - proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_koi8r', + proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4304', descr => 'internal conversion function for ISO-8859-5 to MULE_INTERNAL', - proname => 'iso_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_mic', + proname => 'iso_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4305', descr => 'internal conversion function for MULE_INTERNAL to ISO-8859-5', - proname => 'mic_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_iso', + proname => 'mic_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4306', descr => 'internal conversion function for WIN1251 to MULE_INTERNAL', - proname => 'win1251_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_mic', + proname => 'win1251_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4307', descr => 'internal conversion function for MULE_INTERNAL to WIN1251', - proname => 'mic_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1251', + proname => 'mic_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4308', descr => 'internal conversion function for WIN866 to MULE_INTERNAL', - proname => 'win866_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_mic', + proname => 'win866_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4309', descr => 'internal conversion function for MULE_INTERNAL to WIN866', - proname => 'mic_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win866', + proname => 'mic_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4310', descr => 'internal conversion function for KOI8R to WIN1251', - proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4311', descr => 'internal conversion function for WIN1251 to KOI8R', - proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4312', descr => 'internal conversion function for KOI8R to WIN866', - proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_win866', + proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4313', descr => 'internal conversion function for WIN866 to KOI8R', - proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_koi8r', + proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4314', descr => 'internal conversion function for WIN866 to WIN1251', - proname => 'win866_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win866_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4315', descr => 'internal conversion function for WIN1251 to WIN866', - proname => 'win1251_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4316', descr => 'internal conversion function for ISO-8859-5 to KOI8R', - proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_koi8r', + proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4317', descr => 'internal conversion function for KOI8R to ISO-8859-5', - proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_iso', + proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4318', descr => 'internal conversion function for ISO-8859-5 to WIN1251', - proname => 'iso_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win1251', + proname => 'iso_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4319', descr => 'internal conversion function for WIN1251 to ISO-8859-5', - proname => 'win1251_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_iso', + proname => 'win1251_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4320', descr => 'internal conversion function for ISO-8859-5 to WIN866', - proname => 'iso_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win866', + proname => 'iso_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4321', descr => 'internal conversion function for WIN866 to ISO-8859-5', - proname => 'win866_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_iso', + proname => 'win866_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4322', descr => 'internal conversion function for EUC_CN to MULE_INTERNAL', - proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_mic', + proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_mic', probin => '$libdir/euc_cn_and_mic' }, { oid => '4323', descr => 'internal conversion function for MULE_INTERNAL to EUC_CN', - proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_cn', + proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_cn', probin => '$libdir/euc_cn_and_mic' }, { oid => '4324', descr => 'internal conversion function for EUC_JP to SJIS', - proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_sjis', + proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4325', descr => 'internal conversion function for SJIS to EUC_JP', - proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_euc_jp', + proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4326', descr => 'internal conversion function for EUC_JP to MULE_INTERNAL', - proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_mic', + proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4327', descr => 'internal conversion function for SJIS to MULE_INTERNAL', - proname => 'sjis_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_mic', + proname => 'sjis_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4328', descr => 'internal conversion function for MULE_INTERNAL to EUC_JP', - proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_jp', + proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4329', descr => 'internal conversion function for MULE_INTERNAL to SJIS', - proname => 'mic_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_sjis', + proname => 'mic_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4330', descr => 'internal conversion function for EUC_KR to MULE_INTERNAL', - proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_mic', + proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_mic', probin => '$libdir/euc_kr_and_mic' }, { oid => '4331', descr => 'internal conversion function for MULE_INTERNAL to EUC_KR', - proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_kr', + proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_kr', probin => '$libdir/euc_kr_and_mic' }, { oid => '4332', descr => 'internal conversion function for EUC_TW to BIG5', - proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_big5', + proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4333', descr => 'internal conversion function for BIG5 to EUC_TW', - proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_euc_tw', + proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4334', descr => 'internal conversion function for EUC_TW to MULE_INTERNAL', - proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_mic', + proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4335', descr => 'internal conversion function for BIG5 to MULE_INTERNAL', - proname => 'big5_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_mic', + proname => 'big5_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4336', descr => 'internal conversion function for MULE_INTERNAL to EUC_TW', - proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_tw', + proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4337', descr => 'internal conversion function for MULE_INTERNAL to BIG5', - proname => 'mic_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_big5', + proname => 'mic_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4338', descr => 'internal conversion function for LATIN2 to MULE_INTERNAL', - proname => 'latin2_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin2_to_mic', + proname => 'latin2_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4339', descr => 'internal conversion function for MULE_INTERNAL to LATIN2', - proname => 'mic_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin2', + proname => 'mic_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4340', descr => 'internal conversion function for WIN1250 to MULE_INTERNAL', - proname => 'win1250_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1250_to_mic', + proname => 'win1250_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4341', descr => 'internal conversion function for MULE_INTERNAL to WIN1250', - proname => 'mic_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1250', + proname => 'mic_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4342', descr => 'internal conversion function for LATIN2 to WIN1250', - proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4343', descr => 'internal conversion function for WIN1250 to LATIN2', - proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4344', descr => 'internal conversion function for LATIN1 to MULE_INTERNAL', - proname => 'latin1_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin1_to_mic', + proname => 'latin1_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin1_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4345', descr => 'internal conversion function for MULE_INTERNAL to LATIN1', - proname => 'mic_to_latin1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin1', + proname => 'mic_to_latin1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin1', probin => '$libdir/latin_and_mic' }, { oid => '4346', descr => 'internal conversion function for LATIN3 to MULE_INTERNAL', - proname => 'latin3_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin3_to_mic', + proname => 'latin3_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin3_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4347', descr => 'internal conversion function for MULE_INTERNAL to LATIN3', - proname => 'mic_to_latin3', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin3', + proname => 'mic_to_latin3', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin3', probin => '$libdir/latin_and_mic' }, { oid => '4348', descr => 'internal conversion function for LATIN4 to MULE_INTERNAL', - proname => 'latin4_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin4_to_mic', + proname => 'latin4_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin4_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4349', descr => 'internal conversion function for MULE_INTERNAL to LATIN4', - proname => 'mic_to_latin4', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin4', + proname => 'mic_to_latin4', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin4', probin => '$libdir/latin_and_mic' }, { oid => '4352', descr => 'internal conversion function for BIG5 to UTF8', - proname => 'big5_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_utf8', + proname => 'big5_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_utf8', probin => '$libdir/utf8_and_big5' }, { oid => '4353', descr => 'internal conversion function for UTF8 to BIG5', - proname => 'utf8_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_big5', + proname => 'utf8_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_big5', probin => '$libdir/utf8_and_big5' }, { oid => '4354', descr => 'internal conversion function for UTF8 to KOI8R', - proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8r', + proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8r', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4355', descr => 'internal conversion function for KOI8R to UTF8', - proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_utf8', + proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4356', descr => 'internal conversion function for UTF8 to KOI8U', - proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8u', + proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8u', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4357', descr => 'internal conversion function for KOI8U to UTF8', - proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8u_to_utf8', + proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8u_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4358', descr => 'internal conversion function for UTF8 to WIN', - proname => 'utf8_to_win', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_win', + proname => 'utf8_to_win', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_win', probin => '$libdir/utf8_and_win' }, { oid => '4359', descr => 'internal conversion function for WIN to UTF8', - proname => 'win_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win_to_utf8', + proname => 'win_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win_to_utf8', probin => '$libdir/utf8_and_win' }, { oid => '4360', descr => 'internal conversion function for EUC_CN to UTF8', - proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_utf8', + proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_utf8', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4361', descr => 'internal conversion function for UTF8 to EUC_CN', - proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_cn', + proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_cn', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4362', descr => 'internal conversion function for EUC_JP to UTF8', - proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_utf8', + proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_utf8', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4363', descr => 'internal conversion function for UTF8 to EUC_JP', - proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_jp', + proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jp', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4364', descr => 'internal conversion function for EUC_KR to UTF8', - proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_utf8', + proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_utf8', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4365', descr => 'internal conversion function for UTF8 to EUC_KR', - proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_kr', + proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_kr', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4366', descr => 'internal conversion function for EUC_TW to UTF8', - proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_utf8', + proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_utf8', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4367', descr => 'internal conversion function for UTF8 to EUC_TW', - proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_tw', + proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_tw', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4368', descr => 'internal conversion function for GB18030 to UTF8', - proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gb18030_to_utf8', + proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gb18030_to_utf8', probin => '$libdir/utf8_and_gb18030' }, { oid => '4369', descr => 'internal conversion function for UTF8 to GB18030', - proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gb18030', + proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gb18030', probin => '$libdir/utf8_and_gb18030' }, { oid => '4370', descr => 'internal conversion function for GBK to UTF8', - proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gbk_to_utf8', + proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gbk_to_utf8', probin => '$libdir/utf8_and_gbk' }, { oid => '4371', descr => 'internal conversion function for UTF8 to GBK', - proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gbk', + proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gbk', probin => '$libdir/utf8_and_gbk' }, { oid => '4372', descr => 'internal conversion function for UTF8 to ISO-8859 2-16', - proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_iso8859', + proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859', probin => '$libdir/utf8_and_iso8859' }, { oid => '4373', descr => 'internal conversion function for ISO-8859 2-16 to UTF8', - proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso8859_to_utf8', + proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_to_utf8', probin => '$libdir/utf8_and_iso8859' }, { oid => '4374', descr => 'internal conversion function for LATIN1 to UTF8', - proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_1_to_utf8', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4375', descr => 'internal conversion function for UTF8 to LATIN1', - proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859_1', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4376', descr => 'internal conversion function for JOHAB to UTF8', - proname => 'johab_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'johab_to_utf8', + proname => 'johab_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'johab_to_utf8', probin => '$libdir/utf8_and_johab' }, { oid => '4377', descr => 'internal conversion function for UTF8 to JOHAB', - proname => 'utf8_to_johab', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_johab', + proname => 'utf8_to_johab', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_johab', probin => '$libdir/utf8_and_johab' }, { oid => '4378', descr => 'internal conversion function for SJIS to UTF8', - proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_utf8', + proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_utf8', probin => '$libdir/utf8_and_sjis' }, { oid => '4379', descr => 'internal conversion function for UTF8 to SJIS', - proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_sjis', + proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_sjis', probin => '$libdir/utf8_and_sjis' }, { oid => '4380', descr => 'internal conversion function for UHC to UTF8', - proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'uhc_to_utf8', + proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'uhc_to_utf8', probin => '$libdir/utf8_and_uhc' }, { oid => '4381', descr => 'internal conversion function for UTF8 to UHC', - proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_uhc', + proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_uhc', probin => '$libdir/utf8_and_uhc' }, { oid => '4382', descr => 'internal conversion function for EUC_JIS_2004 to UTF8', - proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_utf8', probin => '$libdir/utf8_and_euc2004' }, { oid => '4383', descr => 'internal conversion function for UTF8 to EUC_JIS_2004', - proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jis_2004', probin => '$libdir/utf8_and_euc2004' }, { oid => '4384', descr => 'internal conversion function for SHIFT_JIS_2004 to UTF8', - proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_utf8', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4385', descr => 'internal conversion function for UTF8 to SHIFT_JIS_2004', - proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_shift_jis_2004', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4386', descr => 'internal conversion function for EUC_JIS_2004 to SHIFT_JIS_2004', proname => 'euc_jis_2004_to_shift_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_shift_jis_2004', probin => '$libdir/euc2004_sjis2004' }, { oid => '4387', descr => 'internal conversion function for SHIFT_JIS_2004 to EUC_JIS_2004', proname => 'shift_jis_2004_to_euc_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_euc_jis_2004', probin => '$libdir/euc2004_sjis2004' }, diff --git a/src/include/mb/pg_wchar.h b/src/include/mb/pg_wchar.h index 64b22e4b0d4..346a41a1f3d 100644 --- a/src/include/mb/pg_wchar.h +++ b/src/include/mb/pg_wchar.h @@ -627,18 +627,18 @@ extern void pg_unicode_to_server(pg_wchar c, unsigned char *s); extern unsigned short BIG5toCNS(unsigned short big5, unsigned char *lc); extern unsigned short CNStoBIG5(unsigned short cns, unsigned char lc); -extern void UtfToLocal(const unsigned char *utf, int len, - unsigned char *iso, - const pg_mb_radix_tree *map, - const pg_utf_to_local_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); -extern void LocalToUtf(const unsigned char *iso, int len, - unsigned char *utf, - const pg_mb_radix_tree *map, - const pg_local_to_utf_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); +extern int UtfToLocal(const unsigned char *utf, int len, + unsigned char *iso, + const pg_mb_radix_tree *map, + const pg_utf_to_local_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); +extern int LocalToUtf(const unsigned char *iso, int len, + unsigned char *utf, + const pg_mb_radix_tree *map, + const pg_local_to_utf_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); extern bool pg_verifymbstr(const char *mbstr, int len, bool noError); extern bool pg_verify_mbstr(int encoding, const char *mbstr, int len, @@ -656,18 +656,19 @@ extern void report_invalid_encoding(int encoding, const char *mbstr, int len) pg extern void report_untranslatable_char(int src_encoding, int dest_encoding, const char *mbstr, int len) pg_attribute_noreturn(); -extern void local2local(const unsigned char *l, unsigned char *p, int len, - int src_encoding, int dest_encoding, const unsigned char *tab); -extern void latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding); -extern void mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding); -extern void latin2mic_with_table(const unsigned char *l, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); -extern void mic2latin_with_table(const unsigned char *mic, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); +extern int local2local(const unsigned char *l, unsigned char *p, int len, + int src_encoding, int dest_encoding, const unsigned char *tab, + bool noError); +extern int latin2mic(const unsigned char *l, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int mic2latin(const unsigned char *mic, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int latin2mic_with_table(const unsigned char *l, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); +extern int mic2latin_with_table(const unsigned char *mic, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); #ifdef WIN32 extern WCHAR *pgwin32_message_to_UTF16(const char *str, int len, int *utf16len); diff --git a/src/test/regress/expected/opr_sanity.out b/src/test/regress/expected/opr_sanity.out index 254ca06d3dd..23ba60e395f 100644 --- a/src/test/regress/expected/opr_sanity.out +++ b/src/test/regress/expected/opr_sanity.out @@ -1052,13 +1052,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); oid | proname | oid | conname -----+---------+-----+--------- (0 rows) diff --git a/src/test/regress/sql/opr_sanity.sql b/src/test/regress/sql/opr_sanity.sql index bbd3834b634..04691745981 100644 --- a/src/test/regress/sql/opr_sanity.sql +++ b/src/test/regress/sql/opr_sanity.sql @@ -556,13 +556,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); -- Check for conprocs that don't perform the specific conversion that -- pg_conversion alleges they do, by trying to invoke each conversion -- 2.29.2 --------------39E46EF15EBFAA37D53332E5 Content-Type: text/x-patch; charset=UTF-8; name="v3-0003-Add-tests-for-the-new-noError-variants-of-built-i.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="v3-0003-Add-tests-for-the-new-noError-variants-of-built-i.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 34+ messages in thread
* [PATCH v3 2/5] Change conversion function signature. @ 2021-01-28 16:42 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 34+ messages in thread From: Heikki Linnakangas @ 2021-01-28 16:42 UTC (permalink / raw) Add a 'noError' argument, so that we can try to convert a buffer without knowing the character boundaries beforehand. The functions now need to return the number of input bytes successfully converted. This is is a backwards-incompatible change, if you have created a custom encoding conversion with CREATE CONVERSION. This adds a check to pg_upgrade for that, refusing the upgrade if there are any user-defined encoding conversions. --- doc/src/sgml/ref/create_conversion.sgml | 5 +- src/backend/commands/conversioncmds.c | 27 +- src/backend/utils/error/elog.c | 2 + src/backend/utils/mb/conv.c | 112 +++++- .../cyrillic_and_mic/cyrillic_and_mic.c | 127 ++++--- .../euc2004_sjis2004/euc2004_sjis2004.c | 96 ++++- .../euc_cn_and_mic/euc_cn_and_mic.c | 57 ++- .../euc_jp_and_sjis/euc_jp_and_sjis.c | 153 ++++++-- .../euc_kr_and_mic/euc_kr_and_mic.c | 57 ++- .../euc_tw_and_big5/euc_tw_and_big5.c | 165 +++++++-- .../latin2_and_win1250/latin2_and_win1250.c | 49 ++- .../latin_and_mic/latin_and_mic.c | 43 ++- .../utf8_and_big5/utf8_and_big5.c | 37 +- .../utf8_and_cyrillic/utf8_and_cyrillic.c | 67 ++-- .../utf8_and_euc2004/utf8_and_euc2004.c | 37 +- .../utf8_and_euc_cn/utf8_and_euc_cn.c | 37 +- .../utf8_and_euc_jp/utf8_and_euc_jp.c | 37 +- .../utf8_and_euc_kr/utf8_and_euc_kr.c | 37 +- .../utf8_and_euc_tw/utf8_and_euc_tw.c | 37 +- .../utf8_and_gb18030/utf8_and_gb18030.c | 37 +- .../utf8_and_gbk/utf8_and_gbk.c | 37 +- .../utf8_and_iso8859/utf8_and_iso8859.c | 43 ++- .../utf8_and_iso8859_1/utf8_and_iso8859_1.c | 27 +- .../utf8_and_johab/utf8_and_johab.c | 37 +- .../utf8_and_sjis/utf8_and_sjis.c | 37 +- .../utf8_and_sjis2004/utf8_and_sjis2004.c | 37 +- .../utf8_and_uhc/utf8_and_uhc.c | 37 +- .../utf8_and_win/utf8_and_win.c | 43 ++- src/backend/utils/mb/mbutils.c | 18 +- src/bin/pg_upgrade/check.c | 95 +++++ src/include/catalog/pg_proc.dat | 332 +++++++++--------- src/include/mb/pg_wchar.h | 49 +-- src/test/regress/expected/opr_sanity.out | 7 +- src/test/regress/sql/opr_sanity.sql | 7 +- 34 files changed, 1390 insertions(+), 635 deletions(-) diff --git a/doc/src/sgml/ref/create_conversion.sgml b/doc/src/sgml/ref/create_conversion.sgml index e7700fecfc5..f014a676c88 100644 --- a/doc/src/sgml/ref/create_conversion.sgml +++ b/doc/src/sgml/ref/create_conversion.sgml @@ -117,8 +117,9 @@ conv_proc( integer, -- destination encoding ID cstring, -- source string (null terminated C string) internal, -- destination (fill with a null terminated C string) - integer -- source string length -) RETURNS void; + integer, -- source string length + boolean -- if true, don't throw an error if conversion fails +) RETURNS integer; </programlisting></para> </listitem> </varlistentry> diff --git a/src/backend/commands/conversioncmds.c b/src/backend/commands/conversioncmds.c index f7ff321de71..d2041466911 100644 --- a/src/backend/commands/conversioncmds.c +++ b/src/backend/commands/conversioncmds.c @@ -45,8 +45,9 @@ CreateConversionCommand(CreateConversionStmt *stmt) const char *from_encoding_name = stmt->for_encoding_name; const char *to_encoding_name = stmt->to_encoding_name; List *func_name = stmt->func_name; - static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID}; + static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID, BOOLOID}; char result[1]; + Datum funcresult; /* Convert list of names to a name and namespace */ namespaceId = QualifiedNameGetCreationNamespace(stmt->conversion_name, @@ -92,8 +93,8 @@ CreateConversionCommand(CreateConversionStmt *stmt) funcoid = LookupFuncName(func_name, sizeof(funcargs) / sizeof(Oid), funcargs, false); - /* Check it returns VOID, else it's probably the wrong function */ - if (get_func_rettype(funcoid) != VOIDOID) + /* Check it returns int4, else it's probably the wrong function */ + if (get_func_rettype(funcoid) != INT4OID) ereport(ERROR, (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), errmsg("encoding conversion function %s must return type %s", @@ -111,12 +112,20 @@ CreateConversionCommand(CreateConversionStmt *stmt) * string; the conversion function should throw an error if it can't * perform the requested conversion. */ - OidFunctionCall5(funcoid, - Int32GetDatum(from_encoding), - Int32GetDatum(to_encoding), - CStringGetDatum(""), - CStringGetDatum(result), - Int32GetDatum(0)); + funcresult = OidFunctionCall6(funcoid, + Int32GetDatum(from_encoding), + Int32GetDatum(to_encoding), + CStringGetDatum(""), + CStringGetDatum(result), + Int32GetDatum(0), + BoolGetDatum(false)); + + /* The function should return 0 for empty input. Might as well check that, too. */ + if (DatumGetInt32(funcresult) != 0) + ereport(ERROR, + (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), + errmsg("encoding conversion function %s returned incorrect result for empty input", + NameListToString(func_name)))); /* * All seem ok, go ahead (possible failure would be a duplicate conversion diff --git a/src/backend/utils/error/elog.c b/src/backend/utils/error/elog.c index 80c26724612..762f77d533c 100644 --- a/src/backend/utils/error/elog.c +++ b/src/backend/utils/error/elog.c @@ -2280,6 +2280,8 @@ write_console(const char *line, int len) * Conversion on non-win32 platforms is not implemented yet. It requires * non-throw version of pg_do_encoding_conversion(), that converts * unconvertable characters to '?' without errors. + * + * XXX: We have a no-throw version now. It doesn't convert to '?' though. */ #endif diff --git a/src/backend/utils/mb/conv.c b/src/backend/utils/mb/conv.c index a07b54bd3b8..b83358bc7a5 100644 --- a/src/backend/utils/mb/conv.c +++ b/src/backend/utils/mb/conv.c @@ -26,14 +26,16 @@ * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the target charset, or 0 if there is no equivalent code. */ -void +int local2local(const unsigned char *l, unsigned char *p, int len, int src_encoding, int dest_encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -41,7 +43,11 @@ local2local(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(src_encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -50,13 +56,19 @@ local2local(const unsigned char *l, if (c2) *p++ = c2; else + { + if (noError) + break; report_untranslatable_char(src_encoding, dest_encoding, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -67,17 +79,22 @@ local2local(const unsigned char *l, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = l; int c1; while (len > 0) { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (IS_HIGHBIT_SET(c1)) *p++ = lc; *p++ = c1; @@ -85,6 +102,8 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, len--; } *p = '\0'; + + return l - start; } /* @@ -95,17 +114,22 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -118,17 +142,27 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1])) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); + } *p++ = mic[1]; mic += 2; len -= 2; } } *p = '\0'; + + return mic - start; } @@ -144,14 +178,16 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the mule encoding, or 0 if there is no equivalent code. */ -void +int latin2mic_with_table(const unsigned char *l, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -159,7 +195,11 @@ latin2mic_with_table(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -171,13 +211,19 @@ latin2mic_with_table(const unsigned char *l, *p++ = c2; } else + { + if (noError) + break; report_untranslatable_char(encoding, PG_MULE_INTERNAL, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -192,14 +238,16 @@ latin2mic_with_table(const unsigned char *l, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the local charset, or 0 if there is no equivalent code. */ -void +int mic2latin_with_table(const unsigned char *mic, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = mic; unsigned char c1, c2; @@ -207,7 +255,11 @@ mic2latin_with_table(const unsigned char *mic, { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -220,11 +272,17 @@ mic2latin_with_table(const unsigned char *mic, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1]) || (c2 = tab[mic[1] - HIGHBIT]) == 0) { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); break; /* keep compiler quiet */ @@ -235,6 +293,8 @@ mic2latin_with_table(const unsigned char *mic, } } *p = '\0'; + + return mic - start; } /* @@ -425,17 +485,19 @@ pg_mb_radix_conv(const pg_mb_radix_tree *rt, * * See pg_wchar.h for more details about the data structures used here. */ -void +int UtfToLocal(const unsigned char *utf, int len, unsigned char *iso, const pg_mb_radix_tree *map, const pg_utf_to_local_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, bool noError) { uint32 iutf; int l; const pg_utf_to_local_combined *cp; + const unsigned char *start = utf; + const unsigned char *cur = utf; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -449,6 +511,8 @@ UtfToLocal(const unsigned char *utf, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*utf == '\0') break; @@ -584,15 +648,19 @@ UtfToLocal(const unsigned char *utf, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(PG_UTF8, encoding, (const char *) (utf - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(PG_UTF8, (const char *) utf, len); *iso = '\0'; + + return cur - start; } /* @@ -616,18 +684,24 @@ UtfToLocal(const unsigned char *utf, int len, * (if provided) is applied. An error is raised if no match is found. * * See pg_wchar.h for more details about the data structures used here. + * + * Returns the number of input bytes consumed. If noError is true, this can + * be less than 'len'. */ -void +int LocalToUtf(const unsigned char *iso, int len, unsigned char *utf, const pg_mb_radix_tree *map, const pg_local_to_utf_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, + bool noError) { uint32 iiso; int l; const pg_local_to_utf_combined *cp; + const unsigned char *start = iso; + const unsigned char *cur = iso; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -641,6 +715,8 @@ LocalToUtf(const unsigned char *iso, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*iso == '\0') break; @@ -723,13 +799,17 @@ LocalToUtf(const unsigned char *iso, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(encoding, PG_UTF8, (const char *) (iso - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(encoding, (const char *) iso, len); *utf = '\0'; + + return cur - start; } diff --git a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c index 4c5b02654de..368c2deb5e4 100644 --- a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c @@ -44,8 +44,11 @@ PG_FUNCTION_INFO_V1(win866_to_iso); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -306,12 +309,14 @@ koi8r_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -320,12 +325,14 @@ mic_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_KOI8R); - mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -334,12 +341,14 @@ iso_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -348,12 +357,14 @@ mic_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_ISO_8859_5); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -362,12 +373,14 @@ win1251_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -376,12 +389,14 @@ mic_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1251); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -390,12 +405,14 @@ win866_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -404,12 +421,14 @@ mic_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN866); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -418,12 +437,14 @@ koi8r_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN1251); - local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -432,12 +453,14 @@ win1251_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_KOI8R); - local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi); + converted = local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -446,12 +469,14 @@ koi8r_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN866); - local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -460,12 +485,14 @@ win866_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_KOI8R); - local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi); + converted = local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -474,12 +501,14 @@ win866_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_WIN1251); - local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251); + converted = local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -488,12 +517,14 @@ win1251_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_WIN866); - local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866); + converted = local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -502,12 +533,14 @@ iso_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_KOI8R); - local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -516,12 +549,14 @@ koi8r_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_ISO_8859_5); - local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso); + converted = local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -530,12 +565,14 @@ iso_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN1251); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -544,12 +581,14 @@ win1251_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso); + converted = local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -558,12 +597,14 @@ iso_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN866); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -572,10 +613,12 @@ win866_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso); + converted = local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c index 4d7fb116cfd..88529c644cf 100644 --- a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c @@ -19,8 +19,8 @@ PG_MODULE_MAGIC; PG_FUNCTION_INFO_V1(euc_jis_2004_to_shift_jis_2004); PG_FUNCTION_INFO_V1(shift_jis_2004_to_euc_jis_2004); -static void euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len); -static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len); +static int euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError); /* ---------- * conv_proc( @@ -28,8 +28,11 @@ static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -39,12 +42,14 @@ euc_jis_2004_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_SHIFT_JIS_2004); - euc_jis_20042shift_jis_2004(src, dest, len); + converted = euc_jis_20042shift_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -53,20 +58,23 @@ shift_jis_2004_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_EUC_JIS_2004); - shift_jis_20042euc_jis_2004(src, dest, len); + converted = shift_jis_20042euc_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_JIS_2004 -> SHIFT_JIS_2004 */ -static void -euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, ku, ten; @@ -79,8 +87,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -90,8 +102,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) l = pg_encoding_verifymbchar(PG_EUC_JIS_2004, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (c1 == SS2 && l == 2) /* JIS X 0201 kana? */ { @@ -121,8 +137,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) *p++ = (ku + 0x19b) >> 1; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } if (ku % 2) @@ -132,8 +152,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; @@ -149,8 +173,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ku >= 63 && ku <= 94) *p++ = (ku + 0x181) >> 1; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (ku % 2) { @@ -159,20 +187,30 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else - report_invalid_encoding(PG_EUC_JIS_2004, + { + if (noError) + break; + report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } euc += l; len -= l; } *p = '\0'; + + return euc - start; } /* @@ -212,9 +250,10 @@ get_ten(int b, int *ku) * SHIFT_JIS_2004 ---> EUC_JIS_2004 */ -static void -shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len) +static int +shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1; int ku, ten, @@ -230,8 +269,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -241,8 +284,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len l = pg_encoding_verifymbchar(PG_SHIFT_JIS_2004, (const char *) sjis, len); if (l < 0 || l > len) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf && l == 1) { @@ -266,8 +313,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x100; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xe0 && c1 <= 0xef) /* plane 1 62ku-94ku */ @@ -275,9 +326,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x180; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, - (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xf0 && c1 <= 0xf3) /* plane 2 @@ -286,8 +340,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } switch (c1) { case 0xf0: @@ -309,16 +367,24 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 == 0xf4 && kubun == 1) ku = 15; else ku = (c1 << 1) - 0x19a - kubun; } else + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (plane == 2) *p++ = SS3; @@ -330,4 +396,6 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c index e9bb896935f..a8da733803d 100644 --- a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_cn2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_cn(const unsigned char *mic, unsigned char *p, int len); +static int euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_cn_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_cn_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_MULE_INTERNAL); - euc_cn2mic(src, dest, len); + converted = euc_cn2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_CN); - mic2euc_cn(src, dest, len); + converted = mic2euc_cn(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_CN ---> MIC */ -static void -euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; while (len > 0) @@ -76,7 +84,11 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (len < 2 || !IS_HIGHBIT_SET(euc[1])) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = LC_GB2312_80; *p++ = c1; *p++ = euc[1]; @@ -86,21 +98,28 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_CN */ -static void -mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) @@ -109,11 +128,19 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (c1 != LC_GB2312_80) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_CN, (const char *) mic, len); + } if (len < 3 || !IS_HIGHBIT_SET(mic[1]) || !IS_HIGHBIT_SET(mic[2])) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } mic++; *p++ = *mic++; *p++ = *mic++; @@ -122,12 +149,18 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; } } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c index 5059f917a98..cc4817dc4cd 100644 --- a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c @@ -42,17 +42,20 @@ PG_FUNCTION_INFO_V1(mic_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void sjis2mic(const unsigned char *sjis, unsigned char *p, int len); -static void mic2sjis(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_jp(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len); -static void sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len); +static int sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError); +static int mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_jp_to_sjis(PG_FUNCTION_ARGS) @@ -60,12 +63,14 @@ euc_jp_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_SJIS); - euc_jp2sjis(src, dest, len); + converted = euc_jp2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -74,12 +79,14 @@ sjis_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_EUC_JP); - sjis2euc_jp(src, dest, len); + converted = sjis2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -88,12 +95,14 @@ euc_jp_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_MULE_INTERNAL); - euc_jp2mic(src, dest, len); + converted = euc_jp2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -102,12 +111,14 @@ mic_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_JP); - mic2euc_jp(src, dest, len); + converted = mic2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -116,12 +127,14 @@ sjis_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_MULE_INTERNAL); - sjis2mic(src, dest, len); + converted = sjis2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -130,20 +143,23 @@ mic_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_SJIS); - mic2sjis(src, dest, len); + converted = mic2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * SJIS ---> MIC */ -static void -sjis2mic(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -167,7 +183,11 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) * JIS X0208, X0212, user defined extended characters */ if (len < 2 || !ISSJISHEAD(c1) || !ISSJISTAIL(sjis[1])) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } c2 = sjis[1]; k = (c1 << 8) + c2; if (k >= 0xed40 && k < 0xf040) @@ -257,21 +277,28 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; } } *p = '\0'; + + return sjis - start; } /* * MIC ---> SJIS */ -static void -mic2sjis(const unsigned char *mic, unsigned char *p, int len) +static int +mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1, c2, k, @@ -284,8 +311,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -293,8 +324,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) *p++ = mic[1]; else if (c1 == LC_JISX0208) @@ -350,20 +385,27 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_SJIS, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP ---> MIC */ -static void -euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -374,8 +416,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -383,8 +429,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* 1 byte kana? */ *p++ = LC_JISX0201K; @@ -406,14 +456,17 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_JP */ -static void -mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -424,8 +477,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -433,8 +490,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) { *p++ = SS2; @@ -452,20 +513,27 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_JP, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP -> SJIS */ -static void -euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, c2, k; @@ -478,8 +546,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -487,8 +559,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* hankaku kana? */ @@ -551,14 +627,17 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * SJIS ---> EUC_JP */ -static void -sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -573,8 +652,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -582,8 +665,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_SJIS, (const char *) sjis, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf) { /* JIS X0201 (1 byte kana) */ @@ -680,4 +767,6 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c index ac823d6c270..a5b51617e52 100644 --- a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_kr2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_kr(const unsigned char *mic, unsigned char *p, int len); +static int euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_kr_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_kr_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_MULE_INTERNAL); - euc_kr2mic(src, dest, len); + converted = euc_kr2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_KR); - mic2euc_kr(src, dest, len); + converted = mic2euc_kr(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_KR ---> MIC */ -static void -euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -78,8 +86,12 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_KR, (const char *) euc, len); if (l != 2) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = LC_KS5601; *p++ = c1; *p++ = euc[1]; @@ -89,22 +101,29 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_KR */ -static void -mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -115,8 +134,12 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -124,18 +147,28 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_KS5601) { *p++ = mic[1]; *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_KR, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c index 66c242d7f36..ebb4e0acd53 100644 --- a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c @@ -32,17 +32,20 @@ PG_FUNCTION_INFO_V1(mic_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_tw2big5(const unsigned char *euc, unsigned char *p, int len); -static void big52euc_tw(const unsigned char *euc, unsigned char *p, int len); -static void big52mic(const unsigned char *big5, unsigned char *p, int len); -static void mic2big5(const unsigned char *mic, unsigned char *p, int len); -static void euc_tw2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_tw(const unsigned char *mic, unsigned char *p, int len); +static int euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52euc_tw(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError); +static int mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_tw_to_big5(PG_FUNCTION_ARGS) @@ -50,12 +53,14 @@ euc_tw_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_BIG5); - euc_tw2big5(src, dest, len); + converted = euc_tw2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -64,12 +69,14 @@ big5_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_EUC_TW); - big52euc_tw(src, dest, len); + converted = big52euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -78,12 +85,14 @@ euc_tw_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_MULE_INTERNAL); - euc_tw2mic(src, dest, len); + converted = euc_tw2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -92,12 +101,14 @@ mic_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_TW); - mic2euc_tw(src, dest, len); + converted = mic2euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -106,12 +117,14 @@ big5_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_MULE_INTERNAL); - big52mic(src, dest, len); + converted = big52mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -120,21 +133,24 @@ mic_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_BIG5); - mic2big5(src, dest, len); + converted = mic2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_TW ---> Big5 */ -static void -euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; unsigned char c1; unsigned short big5buf, cnsBuf; @@ -149,8 +165,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Verify and decode the next EUC_TW input character */ l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -171,8 +191,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Write it out in Big5 */ big5buf = CNStoBIG5(cnsBuf, lc); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_EUC_TW, PG_BIG5, (const char *) euc, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; @@ -182,22 +206,29 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * Big5 ---> EUC_TW */ -static void -big52euc_tw(const unsigned char *big5, unsigned char *p, int len) +static int +big52euc_tw(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -212,8 +243,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); @@ -237,8 +272,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_EUC_TW, (const char *) big5, len); + } big5 += l; len -= l; @@ -256,14 +295,17 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) } } *p = '\0'; + + return big5 - start; } /* * EUC_TW ---> MIC */ -static void -euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -274,8 +316,12 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -304,22 +350,29 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_TW */ -static void -mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -330,8 +383,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -339,8 +396,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1) { *p++ = mic[1]; @@ -362,20 +423,27 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[3]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_TW, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * Big5 ---> MIC */ -static void -big52mic(const unsigned char *big5, unsigned char *p, int len) +static int +big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -389,8 +457,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } *p++ = c1; big5++; len--; @@ -398,8 +470,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); if (lc != 0) @@ -412,20 +488,27 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_MULE_INTERNAL, (const char *) big5, len); + } big5 += l; len -= l; } *p = '\0'; + + return big5 - start; } /* * MIC ---> Big5 */ -static void -mic2big5(const unsigned char *mic, unsigned char *p, int len) +static int +mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -438,8 +521,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -447,8 +534,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1 || c1 == LC_CNS11643_2 || c1 == LCPRV2_B) { if (c1 == LCPRV2_B) @@ -462,16 +553,26 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } big5buf = CNStoBIG5(cnsBuf, c1); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c index 2e28e6780a5..8610fcb69aa 100644 --- a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c +++ b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(win1250_to_latin2); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -82,12 +85,14 @@ latin2_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -96,12 +101,14 @@ mic_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN2); - mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -110,13 +117,15 @@ win1250_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - win1250_2_iso88592); + converted = latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -125,13 +134,15 @@ mic_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1250); - mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - iso88592_2_win1250); + converted = mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -140,12 +151,15 @@ latin2_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_WIN1250); - local2local(src, dest, len, PG_LATIN2, PG_WIN1250, iso88592_2_win1250); + converted = local2local(src, dest, len, PG_LATIN2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -154,10 +168,13 @@ win1250_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_LATIN2); - local2local(src, dest, len, PG_WIN1250, PG_LATIN2, win1250_2_iso88592); + converted = local2local(src, dest, len, PG_WIN1250, PG_LATIN2, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c index bc651410f21..bff27d1c295 100644 --- a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(mic_to_latin4); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -42,12 +45,14 @@ latin1_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,12 +61,14 @@ mic_to_latin1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN1); - mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -70,12 +77,14 @@ latin3_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN3, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -84,12 +93,14 @@ mic_to_latin3(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN3); - mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,12 +109,14 @@ latin4_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN4, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -112,10 +125,12 @@ mic_to_latin4(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN4); - mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c index d6067cdc24e..3838b15cab9 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ big5_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_UTF8); - LocalToUtf(src, len, dest, - &big5_to_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = LocalToUtf(src, len, dest, + &big5_to_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_BIG5); - UtfToLocal(src, len, dest, - &big5_from_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = UtfToLocal(src, len, dest, + &big5_from_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c index ed90e8e682e..75719fe5f1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c @@ -33,8 +33,11 @@ PG_FUNCTION_INFO_V1(koi8u_to_utf8); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -44,16 +47,19 @@ utf8_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8R); - UtfToLocal(src, len, dest, - &koi8r_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = UtfToLocal(src, len, dest, + &koi8r_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -62,16 +68,19 @@ koi8r_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8r_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = LocalToUtf(src, len, dest, + &koi8r_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -80,16 +89,19 @@ utf8_to_koi8u(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8U); - UtfToLocal(src, len, dest, - &koi8u_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = UtfToLocal(src, len, dest, + &koi8u_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,14 +110,17 @@ koi8u_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8U, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8u_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = LocalToUtf(src, len, dest, + &koi8u_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c index d699affce47..5391001951a 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jis_2004_to_unicode_tree, - LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = LocalToUtf(src, len, dest, + &euc_jis_2004_to_unicode_tree, + LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JIS_2004); - UtfToLocal(src, len, dest, - &euc_jis_2004_from_unicode_tree, - ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = UtfToLocal(src, len, dest, + &euc_jis_2004_from_unicode_tree, + ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c index d7c0ba6a58b..c87d1bf2398 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_cn_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_cn_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = LocalToUtf(src, len, dest, + &euc_cn_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_CN); - UtfToLocal(src, len, dest, - &euc_cn_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = UtfToLocal(src, len, dest, + &euc_cn_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c index 13a3a23e77b..6a55134db21 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jp); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jp_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jp_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = LocalToUtf(src, len, dest, + &euc_jp_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JP); - UtfToLocal(src, len, dest, - &euc_jp_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = UtfToLocal(src, len, dest, + &euc_jp_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c index 1bbb8aaef7b..fe1924e2fec 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_kr_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_kr_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = LocalToUtf(src, len, dest, + &euc_kr_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_KR); - UtfToLocal(src, len, dest, - &euc_kr_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = UtfToLocal(src, len, dest, + &euc_kr_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c index 9830045dccd..68215659b57 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_tw); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_tw_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_tw_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = LocalToUtf(src, len, dest, + &euc_tw_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_TW); - UtfToLocal(src, len, dest, - &euc_tw_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = UtfToLocal(src, len, dest, + &euc_tw_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c index f86ecf27424..e1a59c39a4d 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c @@ -183,8 +183,11 @@ conv_utf8_to_18030(uint32 code) * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -193,16 +196,19 @@ gb18030_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GB18030, PG_UTF8); - LocalToUtf(src, len, dest, - &gb18030_to_unicode_tree, - NULL, 0, - conv_18030_to_utf8, - PG_GB18030); + converted = LocalToUtf(src, len, dest, + &gb18030_to_unicode_tree, + NULL, 0, + conv_18030_to_utf8, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -211,14 +217,17 @@ utf8_to_gb18030(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GB18030); - UtfToLocal(src, len, dest, - &gb18030_from_unicode_tree, - NULL, 0, - conv_utf8_to_18030, - PG_GB18030); + converted = UtfToLocal(src, len, dest, + &gb18030_from_unicode_tree, + NULL, 0, + conv_utf8_to_18030, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c index 2ab8b16c8a8..881386d5347 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_gbk); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ gbk_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GBK, PG_UTF8); - LocalToUtf(src, len, dest, - &gbk_to_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = LocalToUtf(src, len, dest, + &gbk_to_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_gbk(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GBK); - UtfToLocal(src, len, dest, - &gbk_from_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = UtfToLocal(src, len, dest, + &gbk_from_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c index 3e49f67ea2f..d93a521badf 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c @@ -52,8 +52,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -100,6 +103,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -108,12 +112,15 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -122,7 +129,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -132,6 +139,7 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -140,12 +148,15 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -154,5 +165,5 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c index 67e713cca11..8ac93604a1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c @@ -26,8 +26,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859_1); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -37,6 +40,8 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_UTF8); @@ -45,7 +50,11 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_LATIN1, (const char *) src, len); + } if (!IS_HIGHBIT_SET(c)) *dest++ = c; else @@ -58,7 +67,7 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } Datum @@ -67,6 +76,8 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c, c1; @@ -76,7 +87,11 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_UTF8, (const char *) src, len); + } /* fast path for ASCII-subset characters */ if (!IS_HIGHBIT_SET(c)) { @@ -102,11 +117,15 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) len -= 2; } else + { + if (noError) + break; report_untranslatable_char(PG_UTF8, PG_LATIN1, (const char *) src, len); + } } } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c index 578f5df4e7f..317daa2d5ee 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_johab); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ johab_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_JOHAB, PG_UTF8); - LocalToUtf(src, len, dest, - &johab_to_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = LocalToUtf(src, len, dest, + &johab_to_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_johab(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_JOHAB); - UtfToLocal(src, len, dest, - &johab_from_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = UtfToLocal(src, len, dest, + &johab_from_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c index dd9fc2975ad..4c9348aba59 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ sjis_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_UTF8); - LocalToUtf(src, len, dest, - &sjis_to_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = LocalToUtf(src, len, dest, + &sjis_to_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SJIS); - UtfToLocal(src, len, dest, - &sjis_from_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = UtfToLocal(src, len, dest, + &sjis_from_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c index 4bcc886d674..1fffdc5930c 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_shift_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ shift_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &shift_jis_2004_to_unicode_tree, - LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = LocalToUtf(src, len, dest, + &shift_jis_2004_to_unicode_tree, + LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SHIFT_JIS_2004); - UtfToLocal(src, len, dest, - &shift_jis_2004_from_unicode_tree, - ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = UtfToLocal(src, len, dest, + &shift_jis_2004_from_unicode_tree, + ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c index c8e512994a1..d9471dad097 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_uhc); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ uhc_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UHC, PG_UTF8); - LocalToUtf(src, len, dest, - &uhc_to_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = LocalToUtf(src, len, dest, + &uhc_to_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_uhc(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_UHC); - UtfToLocal(src, len, dest, - &uhc_from_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = UtfToLocal(src, len, dest, + &uhc_from_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c index 0c9493dee56..110ba5677d0 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c @@ -48,8 +48,11 @@ PG_FUNCTION_INFO_V1(utf8_to_win); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -81,6 +84,7 @@ win_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -89,12 +93,15 @@ win_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -103,7 +110,7 @@ win_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -113,6 +120,7 @@ utf8_to_win(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -121,12 +129,15 @@ utf8_to_win(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -135,5 +146,5 @@ utf8_to_win(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/mbutils.c b/src/backend/utils/mb/mbutils.c index 2578573b0ab..65753860e35 100644 --- a/src/backend/utils/mb/mbutils.c +++ b/src/backend/utils/mb/mbutils.c @@ -406,12 +406,13 @@ pg_do_encoding_conversion(unsigned char *src, int len, MemoryContextAllocHuge(CurrentMemoryContext, (Size) len * MAX_CONVERSION_GROWTH + 1); - OidFunctionCall5(proc, - Int32GetDatum(src_encoding), - Int32GetDatum(dest_encoding), - CStringGetDatum(src), - CStringGetDatum(result), - Int32GetDatum(len)); + (void) OidFunctionCall6(proc, + Int32GetDatum(src_encoding), + Int32GetDatum(dest_encoding), + CStringGetDatum(src), + CStringGetDatum(result), + Int32GetDatum(len), + BoolGetDatum(false)); /* * If the result is large, it's worth repalloc'ing to release any extra @@ -849,12 +850,13 @@ pg_unicode_to_server(pg_wchar c, unsigned char *s) c_as_utf8[c_as_utf8_len] = '\0'; /* Convert, or throw error if we can't */ - FunctionCall5(Utf8ToServerConvProc, + FunctionCall6(Utf8ToServerConvProc, Int32GetDatum(PG_UTF8), Int32GetDatum(server_encoding), CStringGetDatum(c_as_utf8), CStringGetDatum(s), - Int32GetDatum(c_as_utf8_len)); + Int32GetDatum(c_as_utf8_len), + BoolGetDatum(false)); } diff --git a/src/bin/pg_upgrade/check.c b/src/bin/pg_upgrade/check.c index 43fc297eb69..ee6be95b08d 100644 --- a/src/bin/pg_upgrade/check.c +++ b/src/bin/pg_upgrade/check.c @@ -28,6 +28,7 @@ static void check_for_reg_data_type_usage(ClusterInfo *cluster); static void check_for_jsonb_9_4_usage(ClusterInfo *cluster); static void check_for_pg_role_prefix(ClusterInfo *cluster); static void check_for_new_tablespace_dir(ClusterInfo *new_cluster); +static void check_for_user_defined_encoding_conversions(ClusterInfo *cluster); static char *get_canonical_locale_name(int category, const char *locale); @@ -102,6 +103,15 @@ check_and_dump_old_cluster(bool live_check) check_for_reg_data_type_usage(&old_cluster); check_for_isn_and_int8_passing_mismatch(&old_cluster); + /* + * PG 14 changed the function signature of encoding conversion functions. + * Conversions from older versions cannot be upgraded automatically + * because the user-defined functions used by the encoding conversions + * need to changed to match the new signature. + */ + if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1300) + check_for_user_defined_encoding_conversions(&old_cluster); + /* * Pre-PG 14 allowed user defined postfix operators, which are not * supported anymore. Verify there are none, iff applicable. @@ -1268,6 +1278,91 @@ check_for_pg_role_prefix(ClusterInfo *cluster) check_ok(); } +/* + * Verify that no user-defined encoding conversions exist. + */ +static void +check_for_user_defined_encoding_conversions(ClusterInfo *cluster) +{ + int dbnum; + FILE *script = NULL; + bool found = false; + char output_path[MAXPGPATH]; + + prep_status("Checking for user-defined encoding conversions"); + + snprintf(output_path, sizeof(output_path), + "encoding_conversions.txt"); + + /* Find any user defined encoding conversions */ + for (dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++) + { + PGresult *res; + bool db_used = false; + int ntups; + int rowno; + int i_conoid, + i_conname, + i_nspname; + DbInfo *active_db = &cluster->dbarr.dbs[dbnum]; + PGconn *conn = connectToServer(cluster, active_db->db_name); + + /* + * The query below hardcodes FirstNormalObjectId as 16384 rather than + * interpolating that C #define into the query because, if that + * #define is ever changed, the cutoff we want to use is the value + * used by pre-version 14 servers, not that of some future version. + */ + res = executeQueryOrDie(conn, + "SELECT c.oid as conoid, c.conname, n.nspname " + "FROM pg_catalog.pg_conversion c, " + " pg_catalog.pg_namespace n " + "WHERE c.connamespace = n.oid AND " + " c.oid >= 16384"); + ntups = PQntuples(res); + i_conoid = PQfnumber(res, "conoid"); + i_conname = PQfnumber(res, "conname"); + i_nspname = PQfnumber(res, "nspname"); + for (rowno = 0; rowno < ntups; rowno++) + { + found = true; + if (script == NULL && + (script = fopen_priv(output_path, "w")) == NULL) + pg_fatal("could not open file \"%s\": %s\n", + output_path, strerror(errno)); + if (!db_used) + { + fprintf(script, "In database: %s\n", active_db->db_name); + db_used = true; + } + fprintf(script, " (oid=%s) %s.%s\n", + PQgetvalue(res, rowno, i_conoid), + PQgetvalue(res, rowno, i_nspname), + PQgetvalue(res, rowno, i_conname)); + } + + PQclear(res); + + PQfinish(conn); + } + + if (script) + fclose(script); + + if (found) + { + pg_log(PG_REPORT, "fatal\n"); + pg_fatal("Your installation contains user-defined encoding conversions.\n" + "The conversion function parameters changed in PostgreSQL version 14\n" + "so this cluster cannot currently be upgraded. You can remove the\n" + "encoding conversions in the old cluster and restart the upgrade.\n" + "A list of user-defined encoding conversions is in the file:\n" + " %s\n\n", output_path); + } + else + check_ok(); +} + /* * get_canonical_locale_name diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index f8174061ef3..75b829e8514 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10766,388 +10766,388 @@ # conversion functions { oid => '4302', descr => 'internal conversion function for KOI8R to MULE_INTERNAL', - proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_mic', + proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4303', descr => 'internal conversion function for MULE_INTERNAL to KOI8R', - proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_koi8r', + proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4304', descr => 'internal conversion function for ISO-8859-5 to MULE_INTERNAL', - proname => 'iso_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_mic', + proname => 'iso_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4305', descr => 'internal conversion function for MULE_INTERNAL to ISO-8859-5', - proname => 'mic_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_iso', + proname => 'mic_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4306', descr => 'internal conversion function for WIN1251 to MULE_INTERNAL', - proname => 'win1251_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_mic', + proname => 'win1251_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4307', descr => 'internal conversion function for MULE_INTERNAL to WIN1251', - proname => 'mic_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1251', + proname => 'mic_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4308', descr => 'internal conversion function for WIN866 to MULE_INTERNAL', - proname => 'win866_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_mic', + proname => 'win866_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4309', descr => 'internal conversion function for MULE_INTERNAL to WIN866', - proname => 'mic_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win866', + proname => 'mic_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4310', descr => 'internal conversion function for KOI8R to WIN1251', - proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4311', descr => 'internal conversion function for WIN1251 to KOI8R', - proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4312', descr => 'internal conversion function for KOI8R to WIN866', - proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_win866', + proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4313', descr => 'internal conversion function for WIN866 to KOI8R', - proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_koi8r', + proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4314', descr => 'internal conversion function for WIN866 to WIN1251', - proname => 'win866_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win866_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4315', descr => 'internal conversion function for WIN1251 to WIN866', - proname => 'win1251_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4316', descr => 'internal conversion function for ISO-8859-5 to KOI8R', - proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_koi8r', + proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4317', descr => 'internal conversion function for KOI8R to ISO-8859-5', - proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_iso', + proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4318', descr => 'internal conversion function for ISO-8859-5 to WIN1251', - proname => 'iso_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win1251', + proname => 'iso_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4319', descr => 'internal conversion function for WIN1251 to ISO-8859-5', - proname => 'win1251_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_iso', + proname => 'win1251_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4320', descr => 'internal conversion function for ISO-8859-5 to WIN866', - proname => 'iso_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win866', + proname => 'iso_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4321', descr => 'internal conversion function for WIN866 to ISO-8859-5', - proname => 'win866_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_iso', + proname => 'win866_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4322', descr => 'internal conversion function for EUC_CN to MULE_INTERNAL', - proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_mic', + proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_mic', probin => '$libdir/euc_cn_and_mic' }, { oid => '4323', descr => 'internal conversion function for MULE_INTERNAL to EUC_CN', - proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_cn', + proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_cn', probin => '$libdir/euc_cn_and_mic' }, { oid => '4324', descr => 'internal conversion function for EUC_JP to SJIS', - proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_sjis', + proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4325', descr => 'internal conversion function for SJIS to EUC_JP', - proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_euc_jp', + proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4326', descr => 'internal conversion function for EUC_JP to MULE_INTERNAL', - proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_mic', + proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4327', descr => 'internal conversion function for SJIS to MULE_INTERNAL', - proname => 'sjis_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_mic', + proname => 'sjis_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4328', descr => 'internal conversion function for MULE_INTERNAL to EUC_JP', - proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_jp', + proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4329', descr => 'internal conversion function for MULE_INTERNAL to SJIS', - proname => 'mic_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_sjis', + proname => 'mic_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4330', descr => 'internal conversion function for EUC_KR to MULE_INTERNAL', - proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_mic', + proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_mic', probin => '$libdir/euc_kr_and_mic' }, { oid => '4331', descr => 'internal conversion function for MULE_INTERNAL to EUC_KR', - proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_kr', + proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_kr', probin => '$libdir/euc_kr_and_mic' }, { oid => '4332', descr => 'internal conversion function for EUC_TW to BIG5', - proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_big5', + proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4333', descr => 'internal conversion function for BIG5 to EUC_TW', - proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_euc_tw', + proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4334', descr => 'internal conversion function for EUC_TW to MULE_INTERNAL', - proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_mic', + proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4335', descr => 'internal conversion function for BIG5 to MULE_INTERNAL', - proname => 'big5_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_mic', + proname => 'big5_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4336', descr => 'internal conversion function for MULE_INTERNAL to EUC_TW', - proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_tw', + proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4337', descr => 'internal conversion function for MULE_INTERNAL to BIG5', - proname => 'mic_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_big5', + proname => 'mic_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4338', descr => 'internal conversion function for LATIN2 to MULE_INTERNAL', - proname => 'latin2_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin2_to_mic', + proname => 'latin2_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4339', descr => 'internal conversion function for MULE_INTERNAL to LATIN2', - proname => 'mic_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin2', + proname => 'mic_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4340', descr => 'internal conversion function for WIN1250 to MULE_INTERNAL', - proname => 'win1250_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1250_to_mic', + proname => 'win1250_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4341', descr => 'internal conversion function for MULE_INTERNAL to WIN1250', - proname => 'mic_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1250', + proname => 'mic_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4342', descr => 'internal conversion function for LATIN2 to WIN1250', - proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4343', descr => 'internal conversion function for WIN1250 to LATIN2', - proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4344', descr => 'internal conversion function for LATIN1 to MULE_INTERNAL', - proname => 'latin1_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin1_to_mic', + proname => 'latin1_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin1_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4345', descr => 'internal conversion function for MULE_INTERNAL to LATIN1', - proname => 'mic_to_latin1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin1', + proname => 'mic_to_latin1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin1', probin => '$libdir/latin_and_mic' }, { oid => '4346', descr => 'internal conversion function for LATIN3 to MULE_INTERNAL', - proname => 'latin3_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin3_to_mic', + proname => 'latin3_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin3_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4347', descr => 'internal conversion function for MULE_INTERNAL to LATIN3', - proname => 'mic_to_latin3', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin3', + proname => 'mic_to_latin3', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin3', probin => '$libdir/latin_and_mic' }, { oid => '4348', descr => 'internal conversion function for LATIN4 to MULE_INTERNAL', - proname => 'latin4_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin4_to_mic', + proname => 'latin4_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin4_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4349', descr => 'internal conversion function for MULE_INTERNAL to LATIN4', - proname => 'mic_to_latin4', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin4', + proname => 'mic_to_latin4', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin4', probin => '$libdir/latin_and_mic' }, { oid => '4352', descr => 'internal conversion function for BIG5 to UTF8', - proname => 'big5_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_utf8', + proname => 'big5_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_utf8', probin => '$libdir/utf8_and_big5' }, { oid => '4353', descr => 'internal conversion function for UTF8 to BIG5', - proname => 'utf8_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_big5', + proname => 'utf8_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_big5', probin => '$libdir/utf8_and_big5' }, { oid => '4354', descr => 'internal conversion function for UTF8 to KOI8R', - proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8r', + proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8r', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4355', descr => 'internal conversion function for KOI8R to UTF8', - proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_utf8', + proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4356', descr => 'internal conversion function for UTF8 to KOI8U', - proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8u', + proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8u', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4357', descr => 'internal conversion function for KOI8U to UTF8', - proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8u_to_utf8', + proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8u_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4358', descr => 'internal conversion function for UTF8 to WIN', - proname => 'utf8_to_win', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_win', + proname => 'utf8_to_win', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_win', probin => '$libdir/utf8_and_win' }, { oid => '4359', descr => 'internal conversion function for WIN to UTF8', - proname => 'win_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win_to_utf8', + proname => 'win_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win_to_utf8', probin => '$libdir/utf8_and_win' }, { oid => '4360', descr => 'internal conversion function for EUC_CN to UTF8', - proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_utf8', + proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_utf8', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4361', descr => 'internal conversion function for UTF8 to EUC_CN', - proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_cn', + proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_cn', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4362', descr => 'internal conversion function for EUC_JP to UTF8', - proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_utf8', + proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_utf8', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4363', descr => 'internal conversion function for UTF8 to EUC_JP', - proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_jp', + proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jp', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4364', descr => 'internal conversion function for EUC_KR to UTF8', - proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_utf8', + proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_utf8', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4365', descr => 'internal conversion function for UTF8 to EUC_KR', - proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_kr', + proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_kr', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4366', descr => 'internal conversion function for EUC_TW to UTF8', - proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_utf8', + proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_utf8', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4367', descr => 'internal conversion function for UTF8 to EUC_TW', - proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_tw', + proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_tw', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4368', descr => 'internal conversion function for GB18030 to UTF8', - proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gb18030_to_utf8', + proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gb18030_to_utf8', probin => '$libdir/utf8_and_gb18030' }, { oid => '4369', descr => 'internal conversion function for UTF8 to GB18030', - proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gb18030', + proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gb18030', probin => '$libdir/utf8_and_gb18030' }, { oid => '4370', descr => 'internal conversion function for GBK to UTF8', - proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gbk_to_utf8', + proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gbk_to_utf8', probin => '$libdir/utf8_and_gbk' }, { oid => '4371', descr => 'internal conversion function for UTF8 to GBK', - proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gbk', + proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gbk', probin => '$libdir/utf8_and_gbk' }, { oid => '4372', descr => 'internal conversion function for UTF8 to ISO-8859 2-16', - proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_iso8859', + proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859', probin => '$libdir/utf8_and_iso8859' }, { oid => '4373', descr => 'internal conversion function for ISO-8859 2-16 to UTF8', - proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso8859_to_utf8', + proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_to_utf8', probin => '$libdir/utf8_and_iso8859' }, { oid => '4374', descr => 'internal conversion function for LATIN1 to UTF8', - proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_1_to_utf8', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4375', descr => 'internal conversion function for UTF8 to LATIN1', - proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859_1', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4376', descr => 'internal conversion function for JOHAB to UTF8', - proname => 'johab_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'johab_to_utf8', + proname => 'johab_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'johab_to_utf8', probin => '$libdir/utf8_and_johab' }, { oid => '4377', descr => 'internal conversion function for UTF8 to JOHAB', - proname => 'utf8_to_johab', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_johab', + proname => 'utf8_to_johab', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_johab', probin => '$libdir/utf8_and_johab' }, { oid => '4378', descr => 'internal conversion function for SJIS to UTF8', - proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_utf8', + proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_utf8', probin => '$libdir/utf8_and_sjis' }, { oid => '4379', descr => 'internal conversion function for UTF8 to SJIS', - proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_sjis', + proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_sjis', probin => '$libdir/utf8_and_sjis' }, { oid => '4380', descr => 'internal conversion function for UHC to UTF8', - proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'uhc_to_utf8', + proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'uhc_to_utf8', probin => '$libdir/utf8_and_uhc' }, { oid => '4381', descr => 'internal conversion function for UTF8 to UHC', - proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_uhc', + proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_uhc', probin => '$libdir/utf8_and_uhc' }, { oid => '4382', descr => 'internal conversion function for EUC_JIS_2004 to UTF8', - proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_utf8', probin => '$libdir/utf8_and_euc2004' }, { oid => '4383', descr => 'internal conversion function for UTF8 to EUC_JIS_2004', - proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jis_2004', probin => '$libdir/utf8_and_euc2004' }, { oid => '4384', descr => 'internal conversion function for SHIFT_JIS_2004 to UTF8', - proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_utf8', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4385', descr => 'internal conversion function for UTF8 to SHIFT_JIS_2004', - proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_shift_jis_2004', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4386', descr => 'internal conversion function for EUC_JIS_2004 to SHIFT_JIS_2004', proname => 'euc_jis_2004_to_shift_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_shift_jis_2004', probin => '$libdir/euc2004_sjis2004' }, { oid => '4387', descr => 'internal conversion function for SHIFT_JIS_2004 to EUC_JIS_2004', proname => 'shift_jis_2004_to_euc_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_euc_jis_2004', probin => '$libdir/euc2004_sjis2004' }, diff --git a/src/include/mb/pg_wchar.h b/src/include/mb/pg_wchar.h index 64b22e4b0d4..346a41a1f3d 100644 --- a/src/include/mb/pg_wchar.h +++ b/src/include/mb/pg_wchar.h @@ -627,18 +627,18 @@ extern void pg_unicode_to_server(pg_wchar c, unsigned char *s); extern unsigned short BIG5toCNS(unsigned short big5, unsigned char *lc); extern unsigned short CNStoBIG5(unsigned short cns, unsigned char lc); -extern void UtfToLocal(const unsigned char *utf, int len, - unsigned char *iso, - const pg_mb_radix_tree *map, - const pg_utf_to_local_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); -extern void LocalToUtf(const unsigned char *iso, int len, - unsigned char *utf, - const pg_mb_radix_tree *map, - const pg_local_to_utf_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); +extern int UtfToLocal(const unsigned char *utf, int len, + unsigned char *iso, + const pg_mb_radix_tree *map, + const pg_utf_to_local_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); +extern int LocalToUtf(const unsigned char *iso, int len, + unsigned char *utf, + const pg_mb_radix_tree *map, + const pg_local_to_utf_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); extern bool pg_verifymbstr(const char *mbstr, int len, bool noError); extern bool pg_verify_mbstr(int encoding, const char *mbstr, int len, @@ -656,18 +656,19 @@ extern void report_invalid_encoding(int encoding, const char *mbstr, int len) pg extern void report_untranslatable_char(int src_encoding, int dest_encoding, const char *mbstr, int len) pg_attribute_noreturn(); -extern void local2local(const unsigned char *l, unsigned char *p, int len, - int src_encoding, int dest_encoding, const unsigned char *tab); -extern void latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding); -extern void mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding); -extern void latin2mic_with_table(const unsigned char *l, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); -extern void mic2latin_with_table(const unsigned char *mic, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); +extern int local2local(const unsigned char *l, unsigned char *p, int len, + int src_encoding, int dest_encoding, const unsigned char *tab, + bool noError); +extern int latin2mic(const unsigned char *l, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int mic2latin(const unsigned char *mic, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int latin2mic_with_table(const unsigned char *l, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); +extern int mic2latin_with_table(const unsigned char *mic, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); #ifdef WIN32 extern WCHAR *pgwin32_message_to_UTF16(const char *str, int len, int *utf16len); diff --git a/src/test/regress/expected/opr_sanity.out b/src/test/regress/expected/opr_sanity.out index 254ca06d3dd..23ba60e395f 100644 --- a/src/test/regress/expected/opr_sanity.out +++ b/src/test/regress/expected/opr_sanity.out @@ -1052,13 +1052,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); oid | proname | oid | conname -----+---------+-----+--------- (0 rows) diff --git a/src/test/regress/sql/opr_sanity.sql b/src/test/regress/sql/opr_sanity.sql index bbd3834b634..04691745981 100644 --- a/src/test/regress/sql/opr_sanity.sql +++ b/src/test/regress/sql/opr_sanity.sql @@ -556,13 +556,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); -- Check for conprocs that don't perform the specific conversion that -- pg_conversion alleges they do, by trying to invoke each conversion -- 2.29.2 --------------39E46EF15EBFAA37D53332E5 Content-Type: text/x-patch; charset=UTF-8; name="v3-0003-Add-tests-for-the-new-noError-variants-of-built-i.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="v3-0003-Add-tests-for-the-new-noError-variants-of-built-i.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 34+ messages in thread
* [PATCH v3 2/5] Change conversion function signature. @ 2021-01-28 16:42 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 34+ messages in thread From: Heikki Linnakangas @ 2021-01-28 16:42 UTC (permalink / raw) Add a 'noError' argument, so that we can try to convert a buffer without knowing the character boundaries beforehand. The functions now need to return the number of input bytes successfully converted. This is is a backwards-incompatible change, if you have created a custom encoding conversion with CREATE CONVERSION. This adds a check to pg_upgrade for that, refusing the upgrade if there are any user-defined encoding conversions. --- doc/src/sgml/ref/create_conversion.sgml | 5 +- src/backend/commands/conversioncmds.c | 27 +- src/backend/utils/error/elog.c | 2 + src/backend/utils/mb/conv.c | 112 +++++- .../cyrillic_and_mic/cyrillic_and_mic.c | 127 ++++--- .../euc2004_sjis2004/euc2004_sjis2004.c | 96 ++++- .../euc_cn_and_mic/euc_cn_and_mic.c | 57 ++- .../euc_jp_and_sjis/euc_jp_and_sjis.c | 153 ++++++-- .../euc_kr_and_mic/euc_kr_and_mic.c | 57 ++- .../euc_tw_and_big5/euc_tw_and_big5.c | 165 +++++++-- .../latin2_and_win1250/latin2_and_win1250.c | 49 ++- .../latin_and_mic/latin_and_mic.c | 43 ++- .../utf8_and_big5/utf8_and_big5.c | 37 +- .../utf8_and_cyrillic/utf8_and_cyrillic.c | 67 ++-- .../utf8_and_euc2004/utf8_and_euc2004.c | 37 +- .../utf8_and_euc_cn/utf8_and_euc_cn.c | 37 +- .../utf8_and_euc_jp/utf8_and_euc_jp.c | 37 +- .../utf8_and_euc_kr/utf8_and_euc_kr.c | 37 +- .../utf8_and_euc_tw/utf8_and_euc_tw.c | 37 +- .../utf8_and_gb18030/utf8_and_gb18030.c | 37 +- .../utf8_and_gbk/utf8_and_gbk.c | 37 +- .../utf8_and_iso8859/utf8_and_iso8859.c | 43 ++- .../utf8_and_iso8859_1/utf8_and_iso8859_1.c | 27 +- .../utf8_and_johab/utf8_and_johab.c | 37 +- .../utf8_and_sjis/utf8_and_sjis.c | 37 +- .../utf8_and_sjis2004/utf8_and_sjis2004.c | 37 +- .../utf8_and_uhc/utf8_and_uhc.c | 37 +- .../utf8_and_win/utf8_and_win.c | 43 ++- src/backend/utils/mb/mbutils.c | 18 +- src/bin/pg_upgrade/check.c | 95 +++++ src/include/catalog/pg_proc.dat | 332 +++++++++--------- src/include/mb/pg_wchar.h | 49 +-- src/test/regress/expected/opr_sanity.out | 7 +- src/test/regress/sql/opr_sanity.sql | 7 +- 34 files changed, 1390 insertions(+), 635 deletions(-) diff --git a/doc/src/sgml/ref/create_conversion.sgml b/doc/src/sgml/ref/create_conversion.sgml index e7700fecfc5..f014a676c88 100644 --- a/doc/src/sgml/ref/create_conversion.sgml +++ b/doc/src/sgml/ref/create_conversion.sgml @@ -117,8 +117,9 @@ conv_proc( integer, -- destination encoding ID cstring, -- source string (null terminated C string) internal, -- destination (fill with a null terminated C string) - integer -- source string length -) RETURNS void; + integer, -- source string length + boolean -- if true, don't throw an error if conversion fails +) RETURNS integer; </programlisting></para> </listitem> </varlistentry> diff --git a/src/backend/commands/conversioncmds.c b/src/backend/commands/conversioncmds.c index f7ff321de71..d2041466911 100644 --- a/src/backend/commands/conversioncmds.c +++ b/src/backend/commands/conversioncmds.c @@ -45,8 +45,9 @@ CreateConversionCommand(CreateConversionStmt *stmt) const char *from_encoding_name = stmt->for_encoding_name; const char *to_encoding_name = stmt->to_encoding_name; List *func_name = stmt->func_name; - static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID}; + static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID, BOOLOID}; char result[1]; + Datum funcresult; /* Convert list of names to a name and namespace */ namespaceId = QualifiedNameGetCreationNamespace(stmt->conversion_name, @@ -92,8 +93,8 @@ CreateConversionCommand(CreateConversionStmt *stmt) funcoid = LookupFuncName(func_name, sizeof(funcargs) / sizeof(Oid), funcargs, false); - /* Check it returns VOID, else it's probably the wrong function */ - if (get_func_rettype(funcoid) != VOIDOID) + /* Check it returns int4, else it's probably the wrong function */ + if (get_func_rettype(funcoid) != INT4OID) ereport(ERROR, (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), errmsg("encoding conversion function %s must return type %s", @@ -111,12 +112,20 @@ CreateConversionCommand(CreateConversionStmt *stmt) * string; the conversion function should throw an error if it can't * perform the requested conversion. */ - OidFunctionCall5(funcoid, - Int32GetDatum(from_encoding), - Int32GetDatum(to_encoding), - CStringGetDatum(""), - CStringGetDatum(result), - Int32GetDatum(0)); + funcresult = OidFunctionCall6(funcoid, + Int32GetDatum(from_encoding), + Int32GetDatum(to_encoding), + CStringGetDatum(""), + CStringGetDatum(result), + Int32GetDatum(0), + BoolGetDatum(false)); + + /* The function should return 0 for empty input. Might as well check that, too. */ + if (DatumGetInt32(funcresult) != 0) + ereport(ERROR, + (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), + errmsg("encoding conversion function %s returned incorrect result for empty input", + NameListToString(func_name)))); /* * All seem ok, go ahead (possible failure would be a duplicate conversion diff --git a/src/backend/utils/error/elog.c b/src/backend/utils/error/elog.c index 80c26724612..762f77d533c 100644 --- a/src/backend/utils/error/elog.c +++ b/src/backend/utils/error/elog.c @@ -2280,6 +2280,8 @@ write_console(const char *line, int len) * Conversion on non-win32 platforms is not implemented yet. It requires * non-throw version of pg_do_encoding_conversion(), that converts * unconvertable characters to '?' without errors. + * + * XXX: We have a no-throw version now. It doesn't convert to '?' though. */ #endif diff --git a/src/backend/utils/mb/conv.c b/src/backend/utils/mb/conv.c index a07b54bd3b8..b83358bc7a5 100644 --- a/src/backend/utils/mb/conv.c +++ b/src/backend/utils/mb/conv.c @@ -26,14 +26,16 @@ * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the target charset, or 0 if there is no equivalent code. */ -void +int local2local(const unsigned char *l, unsigned char *p, int len, int src_encoding, int dest_encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -41,7 +43,11 @@ local2local(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(src_encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -50,13 +56,19 @@ local2local(const unsigned char *l, if (c2) *p++ = c2; else + { + if (noError) + break; report_untranslatable_char(src_encoding, dest_encoding, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -67,17 +79,22 @@ local2local(const unsigned char *l, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = l; int c1; while (len > 0) { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (IS_HIGHBIT_SET(c1)) *p++ = lc; *p++ = c1; @@ -85,6 +102,8 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, len--; } *p = '\0'; + + return l - start; } /* @@ -95,17 +114,22 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -118,17 +142,27 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1])) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); + } *p++ = mic[1]; mic += 2; len -= 2; } } *p = '\0'; + + return mic - start; } @@ -144,14 +178,16 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the mule encoding, or 0 if there is no equivalent code. */ -void +int latin2mic_with_table(const unsigned char *l, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -159,7 +195,11 @@ latin2mic_with_table(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -171,13 +211,19 @@ latin2mic_with_table(const unsigned char *l, *p++ = c2; } else + { + if (noError) + break; report_untranslatable_char(encoding, PG_MULE_INTERNAL, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -192,14 +238,16 @@ latin2mic_with_table(const unsigned char *l, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the local charset, or 0 if there is no equivalent code. */ -void +int mic2latin_with_table(const unsigned char *mic, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = mic; unsigned char c1, c2; @@ -207,7 +255,11 @@ mic2latin_with_table(const unsigned char *mic, { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -220,11 +272,17 @@ mic2latin_with_table(const unsigned char *mic, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1]) || (c2 = tab[mic[1] - HIGHBIT]) == 0) { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); break; /* keep compiler quiet */ @@ -235,6 +293,8 @@ mic2latin_with_table(const unsigned char *mic, } } *p = '\0'; + + return mic - start; } /* @@ -425,17 +485,19 @@ pg_mb_radix_conv(const pg_mb_radix_tree *rt, * * See pg_wchar.h for more details about the data structures used here. */ -void +int UtfToLocal(const unsigned char *utf, int len, unsigned char *iso, const pg_mb_radix_tree *map, const pg_utf_to_local_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, bool noError) { uint32 iutf; int l; const pg_utf_to_local_combined *cp; + const unsigned char *start = utf; + const unsigned char *cur = utf; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -449,6 +511,8 @@ UtfToLocal(const unsigned char *utf, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*utf == '\0') break; @@ -584,15 +648,19 @@ UtfToLocal(const unsigned char *utf, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(PG_UTF8, encoding, (const char *) (utf - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(PG_UTF8, (const char *) utf, len); *iso = '\0'; + + return cur - start; } /* @@ -616,18 +684,24 @@ UtfToLocal(const unsigned char *utf, int len, * (if provided) is applied. An error is raised if no match is found. * * See pg_wchar.h for more details about the data structures used here. + * + * Returns the number of input bytes consumed. If noError is true, this can + * be less than 'len'. */ -void +int LocalToUtf(const unsigned char *iso, int len, unsigned char *utf, const pg_mb_radix_tree *map, const pg_local_to_utf_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, + bool noError) { uint32 iiso; int l; const pg_local_to_utf_combined *cp; + const unsigned char *start = iso; + const unsigned char *cur = iso; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -641,6 +715,8 @@ LocalToUtf(const unsigned char *iso, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*iso == '\0') break; @@ -723,13 +799,17 @@ LocalToUtf(const unsigned char *iso, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(encoding, PG_UTF8, (const char *) (iso - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(encoding, (const char *) iso, len); *utf = '\0'; + + return cur - start; } diff --git a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c index 4c5b02654de..368c2deb5e4 100644 --- a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c @@ -44,8 +44,11 @@ PG_FUNCTION_INFO_V1(win866_to_iso); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -306,12 +309,14 @@ koi8r_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -320,12 +325,14 @@ mic_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_KOI8R); - mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -334,12 +341,14 @@ iso_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -348,12 +357,14 @@ mic_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_ISO_8859_5); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -362,12 +373,14 @@ win1251_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -376,12 +389,14 @@ mic_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1251); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -390,12 +405,14 @@ win866_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -404,12 +421,14 @@ mic_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN866); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -418,12 +437,14 @@ koi8r_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN1251); - local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -432,12 +453,14 @@ win1251_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_KOI8R); - local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi); + converted = local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -446,12 +469,14 @@ koi8r_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN866); - local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -460,12 +485,14 @@ win866_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_KOI8R); - local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi); + converted = local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -474,12 +501,14 @@ win866_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_WIN1251); - local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251); + converted = local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -488,12 +517,14 @@ win1251_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_WIN866); - local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866); + converted = local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -502,12 +533,14 @@ iso_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_KOI8R); - local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -516,12 +549,14 @@ koi8r_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_ISO_8859_5); - local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso); + converted = local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -530,12 +565,14 @@ iso_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN1251); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -544,12 +581,14 @@ win1251_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso); + converted = local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -558,12 +597,14 @@ iso_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN866); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -572,10 +613,12 @@ win866_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso); + converted = local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c index 4d7fb116cfd..88529c644cf 100644 --- a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c @@ -19,8 +19,8 @@ PG_MODULE_MAGIC; PG_FUNCTION_INFO_V1(euc_jis_2004_to_shift_jis_2004); PG_FUNCTION_INFO_V1(shift_jis_2004_to_euc_jis_2004); -static void euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len); -static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len); +static int euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError); /* ---------- * conv_proc( @@ -28,8 +28,11 @@ static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -39,12 +42,14 @@ euc_jis_2004_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_SHIFT_JIS_2004); - euc_jis_20042shift_jis_2004(src, dest, len); + converted = euc_jis_20042shift_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -53,20 +58,23 @@ shift_jis_2004_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_EUC_JIS_2004); - shift_jis_20042euc_jis_2004(src, dest, len); + converted = shift_jis_20042euc_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_JIS_2004 -> SHIFT_JIS_2004 */ -static void -euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, ku, ten; @@ -79,8 +87,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -90,8 +102,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) l = pg_encoding_verifymbchar(PG_EUC_JIS_2004, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (c1 == SS2 && l == 2) /* JIS X 0201 kana? */ { @@ -121,8 +137,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) *p++ = (ku + 0x19b) >> 1; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } if (ku % 2) @@ -132,8 +152,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; @@ -149,8 +173,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ku >= 63 && ku <= 94) *p++ = (ku + 0x181) >> 1; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (ku % 2) { @@ -159,20 +187,30 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else - report_invalid_encoding(PG_EUC_JIS_2004, + { + if (noError) + break; + report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } euc += l; len -= l; } *p = '\0'; + + return euc - start; } /* @@ -212,9 +250,10 @@ get_ten(int b, int *ku) * SHIFT_JIS_2004 ---> EUC_JIS_2004 */ -static void -shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len) +static int +shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1; int ku, ten, @@ -230,8 +269,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -241,8 +284,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len l = pg_encoding_verifymbchar(PG_SHIFT_JIS_2004, (const char *) sjis, len); if (l < 0 || l > len) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf && l == 1) { @@ -266,8 +313,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x100; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xe0 && c1 <= 0xef) /* plane 1 62ku-94ku */ @@ -275,9 +326,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x180; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, - (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xf0 && c1 <= 0xf3) /* plane 2 @@ -286,8 +340,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } switch (c1) { case 0xf0: @@ -309,16 +367,24 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 == 0xf4 && kubun == 1) ku = 15; else ku = (c1 << 1) - 0x19a - kubun; } else + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (plane == 2) *p++ = SS3; @@ -330,4 +396,6 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c index e9bb896935f..a8da733803d 100644 --- a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_cn2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_cn(const unsigned char *mic, unsigned char *p, int len); +static int euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_cn_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_cn_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_MULE_INTERNAL); - euc_cn2mic(src, dest, len); + converted = euc_cn2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_CN); - mic2euc_cn(src, dest, len); + converted = mic2euc_cn(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_CN ---> MIC */ -static void -euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; while (len > 0) @@ -76,7 +84,11 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (len < 2 || !IS_HIGHBIT_SET(euc[1])) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = LC_GB2312_80; *p++ = c1; *p++ = euc[1]; @@ -86,21 +98,28 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_CN */ -static void -mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) @@ -109,11 +128,19 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (c1 != LC_GB2312_80) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_CN, (const char *) mic, len); + } if (len < 3 || !IS_HIGHBIT_SET(mic[1]) || !IS_HIGHBIT_SET(mic[2])) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } mic++; *p++ = *mic++; *p++ = *mic++; @@ -122,12 +149,18 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; } } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c index 5059f917a98..cc4817dc4cd 100644 --- a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c @@ -42,17 +42,20 @@ PG_FUNCTION_INFO_V1(mic_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void sjis2mic(const unsigned char *sjis, unsigned char *p, int len); -static void mic2sjis(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_jp(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len); -static void sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len); +static int sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError); +static int mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_jp_to_sjis(PG_FUNCTION_ARGS) @@ -60,12 +63,14 @@ euc_jp_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_SJIS); - euc_jp2sjis(src, dest, len); + converted = euc_jp2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -74,12 +79,14 @@ sjis_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_EUC_JP); - sjis2euc_jp(src, dest, len); + converted = sjis2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -88,12 +95,14 @@ euc_jp_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_MULE_INTERNAL); - euc_jp2mic(src, dest, len); + converted = euc_jp2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -102,12 +111,14 @@ mic_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_JP); - mic2euc_jp(src, dest, len); + converted = mic2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -116,12 +127,14 @@ sjis_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_MULE_INTERNAL); - sjis2mic(src, dest, len); + converted = sjis2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -130,20 +143,23 @@ mic_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_SJIS); - mic2sjis(src, dest, len); + converted = mic2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * SJIS ---> MIC */ -static void -sjis2mic(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -167,7 +183,11 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) * JIS X0208, X0212, user defined extended characters */ if (len < 2 || !ISSJISHEAD(c1) || !ISSJISTAIL(sjis[1])) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } c2 = sjis[1]; k = (c1 << 8) + c2; if (k >= 0xed40 && k < 0xf040) @@ -257,21 +277,28 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; } } *p = '\0'; + + return sjis - start; } /* * MIC ---> SJIS */ -static void -mic2sjis(const unsigned char *mic, unsigned char *p, int len) +static int +mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1, c2, k, @@ -284,8 +311,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -293,8 +324,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) *p++ = mic[1]; else if (c1 == LC_JISX0208) @@ -350,20 +385,27 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_SJIS, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP ---> MIC */ -static void -euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -374,8 +416,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -383,8 +429,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* 1 byte kana? */ *p++ = LC_JISX0201K; @@ -406,14 +456,17 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_JP */ -static void -mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -424,8 +477,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -433,8 +490,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) { *p++ = SS2; @@ -452,20 +513,27 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_JP, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP -> SJIS */ -static void -euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, c2, k; @@ -478,8 +546,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -487,8 +559,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* hankaku kana? */ @@ -551,14 +627,17 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * SJIS ---> EUC_JP */ -static void -sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -573,8 +652,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -582,8 +665,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_SJIS, (const char *) sjis, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf) { /* JIS X0201 (1 byte kana) */ @@ -680,4 +767,6 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c index ac823d6c270..a5b51617e52 100644 --- a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_kr2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_kr(const unsigned char *mic, unsigned char *p, int len); +static int euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_kr_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_kr_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_MULE_INTERNAL); - euc_kr2mic(src, dest, len); + converted = euc_kr2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_KR); - mic2euc_kr(src, dest, len); + converted = mic2euc_kr(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_KR ---> MIC */ -static void -euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -78,8 +86,12 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_KR, (const char *) euc, len); if (l != 2) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = LC_KS5601; *p++ = c1; *p++ = euc[1]; @@ -89,22 +101,29 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_KR */ -static void -mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -115,8 +134,12 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -124,18 +147,28 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_KS5601) { *p++ = mic[1]; *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_KR, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c index 66c242d7f36..ebb4e0acd53 100644 --- a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c @@ -32,17 +32,20 @@ PG_FUNCTION_INFO_V1(mic_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_tw2big5(const unsigned char *euc, unsigned char *p, int len); -static void big52euc_tw(const unsigned char *euc, unsigned char *p, int len); -static void big52mic(const unsigned char *big5, unsigned char *p, int len); -static void mic2big5(const unsigned char *mic, unsigned char *p, int len); -static void euc_tw2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_tw(const unsigned char *mic, unsigned char *p, int len); +static int euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52euc_tw(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError); +static int mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_tw_to_big5(PG_FUNCTION_ARGS) @@ -50,12 +53,14 @@ euc_tw_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_BIG5); - euc_tw2big5(src, dest, len); + converted = euc_tw2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -64,12 +69,14 @@ big5_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_EUC_TW); - big52euc_tw(src, dest, len); + converted = big52euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -78,12 +85,14 @@ euc_tw_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_MULE_INTERNAL); - euc_tw2mic(src, dest, len); + converted = euc_tw2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -92,12 +101,14 @@ mic_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_TW); - mic2euc_tw(src, dest, len); + converted = mic2euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -106,12 +117,14 @@ big5_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_MULE_INTERNAL); - big52mic(src, dest, len); + converted = big52mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -120,21 +133,24 @@ mic_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_BIG5); - mic2big5(src, dest, len); + converted = mic2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_TW ---> Big5 */ -static void -euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; unsigned char c1; unsigned short big5buf, cnsBuf; @@ -149,8 +165,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Verify and decode the next EUC_TW input character */ l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -171,8 +191,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Write it out in Big5 */ big5buf = CNStoBIG5(cnsBuf, lc); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_EUC_TW, PG_BIG5, (const char *) euc, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; @@ -182,22 +206,29 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * Big5 ---> EUC_TW */ -static void -big52euc_tw(const unsigned char *big5, unsigned char *p, int len) +static int +big52euc_tw(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -212,8 +243,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); @@ -237,8 +272,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_EUC_TW, (const char *) big5, len); + } big5 += l; len -= l; @@ -256,14 +295,17 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) } } *p = '\0'; + + return big5 - start; } /* * EUC_TW ---> MIC */ -static void -euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -274,8 +316,12 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -304,22 +350,29 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_TW */ -static void -mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -330,8 +383,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -339,8 +396,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1) { *p++ = mic[1]; @@ -362,20 +423,27 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[3]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_TW, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * Big5 ---> MIC */ -static void -big52mic(const unsigned char *big5, unsigned char *p, int len) +static int +big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -389,8 +457,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } *p++ = c1; big5++; len--; @@ -398,8 +470,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); if (lc != 0) @@ -412,20 +488,27 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_MULE_INTERNAL, (const char *) big5, len); + } big5 += l; len -= l; } *p = '\0'; + + return big5 - start; } /* * MIC ---> Big5 */ -static void -mic2big5(const unsigned char *mic, unsigned char *p, int len) +static int +mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -438,8 +521,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -447,8 +534,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1 || c1 == LC_CNS11643_2 || c1 == LCPRV2_B) { if (c1 == LCPRV2_B) @@ -462,16 +553,26 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } big5buf = CNStoBIG5(cnsBuf, c1); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c index 2e28e6780a5..8610fcb69aa 100644 --- a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c +++ b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(win1250_to_latin2); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -82,12 +85,14 @@ latin2_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -96,12 +101,14 @@ mic_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN2); - mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -110,13 +117,15 @@ win1250_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - win1250_2_iso88592); + converted = latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -125,13 +134,15 @@ mic_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1250); - mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - iso88592_2_win1250); + converted = mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -140,12 +151,15 @@ latin2_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_WIN1250); - local2local(src, dest, len, PG_LATIN2, PG_WIN1250, iso88592_2_win1250); + converted = local2local(src, dest, len, PG_LATIN2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -154,10 +168,13 @@ win1250_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_LATIN2); - local2local(src, dest, len, PG_WIN1250, PG_LATIN2, win1250_2_iso88592); + converted = local2local(src, dest, len, PG_WIN1250, PG_LATIN2, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c index bc651410f21..bff27d1c295 100644 --- a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(mic_to_latin4); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -42,12 +45,14 @@ latin1_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,12 +61,14 @@ mic_to_latin1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN1); - mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -70,12 +77,14 @@ latin3_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN3, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -84,12 +93,14 @@ mic_to_latin3(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN3); - mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,12 +109,14 @@ latin4_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN4, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -112,10 +125,12 @@ mic_to_latin4(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN4); - mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c index d6067cdc24e..3838b15cab9 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ big5_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_UTF8); - LocalToUtf(src, len, dest, - &big5_to_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = LocalToUtf(src, len, dest, + &big5_to_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_BIG5); - UtfToLocal(src, len, dest, - &big5_from_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = UtfToLocal(src, len, dest, + &big5_from_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c index ed90e8e682e..75719fe5f1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c @@ -33,8 +33,11 @@ PG_FUNCTION_INFO_V1(koi8u_to_utf8); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -44,16 +47,19 @@ utf8_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8R); - UtfToLocal(src, len, dest, - &koi8r_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = UtfToLocal(src, len, dest, + &koi8r_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -62,16 +68,19 @@ koi8r_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8r_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = LocalToUtf(src, len, dest, + &koi8r_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -80,16 +89,19 @@ utf8_to_koi8u(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8U); - UtfToLocal(src, len, dest, - &koi8u_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = UtfToLocal(src, len, dest, + &koi8u_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,14 +110,17 @@ koi8u_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8U, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8u_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = LocalToUtf(src, len, dest, + &koi8u_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c index d699affce47..5391001951a 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jis_2004_to_unicode_tree, - LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = LocalToUtf(src, len, dest, + &euc_jis_2004_to_unicode_tree, + LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JIS_2004); - UtfToLocal(src, len, dest, - &euc_jis_2004_from_unicode_tree, - ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = UtfToLocal(src, len, dest, + &euc_jis_2004_from_unicode_tree, + ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c index d7c0ba6a58b..c87d1bf2398 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_cn_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_cn_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = LocalToUtf(src, len, dest, + &euc_cn_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_CN); - UtfToLocal(src, len, dest, - &euc_cn_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = UtfToLocal(src, len, dest, + &euc_cn_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c index 13a3a23e77b..6a55134db21 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jp); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jp_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jp_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = LocalToUtf(src, len, dest, + &euc_jp_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JP); - UtfToLocal(src, len, dest, - &euc_jp_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = UtfToLocal(src, len, dest, + &euc_jp_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c index 1bbb8aaef7b..fe1924e2fec 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_kr_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_kr_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = LocalToUtf(src, len, dest, + &euc_kr_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_KR); - UtfToLocal(src, len, dest, - &euc_kr_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = UtfToLocal(src, len, dest, + &euc_kr_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c index 9830045dccd..68215659b57 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_tw); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_tw_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_tw_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = LocalToUtf(src, len, dest, + &euc_tw_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_TW); - UtfToLocal(src, len, dest, - &euc_tw_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = UtfToLocal(src, len, dest, + &euc_tw_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c index f86ecf27424..e1a59c39a4d 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c @@ -183,8 +183,11 @@ conv_utf8_to_18030(uint32 code) * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -193,16 +196,19 @@ gb18030_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GB18030, PG_UTF8); - LocalToUtf(src, len, dest, - &gb18030_to_unicode_tree, - NULL, 0, - conv_18030_to_utf8, - PG_GB18030); + converted = LocalToUtf(src, len, dest, + &gb18030_to_unicode_tree, + NULL, 0, + conv_18030_to_utf8, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -211,14 +217,17 @@ utf8_to_gb18030(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GB18030); - UtfToLocal(src, len, dest, - &gb18030_from_unicode_tree, - NULL, 0, - conv_utf8_to_18030, - PG_GB18030); + converted = UtfToLocal(src, len, dest, + &gb18030_from_unicode_tree, + NULL, 0, + conv_utf8_to_18030, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c index 2ab8b16c8a8..881386d5347 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_gbk); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ gbk_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GBK, PG_UTF8); - LocalToUtf(src, len, dest, - &gbk_to_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = LocalToUtf(src, len, dest, + &gbk_to_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_gbk(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GBK); - UtfToLocal(src, len, dest, - &gbk_from_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = UtfToLocal(src, len, dest, + &gbk_from_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c index 3e49f67ea2f..d93a521badf 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c @@ -52,8 +52,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -100,6 +103,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -108,12 +112,15 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -122,7 +129,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -132,6 +139,7 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -140,12 +148,15 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -154,5 +165,5 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c index 67e713cca11..8ac93604a1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c @@ -26,8 +26,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859_1); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -37,6 +40,8 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_UTF8); @@ -45,7 +50,11 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_LATIN1, (const char *) src, len); + } if (!IS_HIGHBIT_SET(c)) *dest++ = c; else @@ -58,7 +67,7 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } Datum @@ -67,6 +76,8 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c, c1; @@ -76,7 +87,11 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_UTF8, (const char *) src, len); + } /* fast path for ASCII-subset characters */ if (!IS_HIGHBIT_SET(c)) { @@ -102,11 +117,15 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) len -= 2; } else + { + if (noError) + break; report_untranslatable_char(PG_UTF8, PG_LATIN1, (const char *) src, len); + } } } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c index 578f5df4e7f..317daa2d5ee 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_johab); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ johab_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_JOHAB, PG_UTF8); - LocalToUtf(src, len, dest, - &johab_to_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = LocalToUtf(src, len, dest, + &johab_to_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_johab(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_JOHAB); - UtfToLocal(src, len, dest, - &johab_from_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = UtfToLocal(src, len, dest, + &johab_from_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c index dd9fc2975ad..4c9348aba59 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ sjis_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_UTF8); - LocalToUtf(src, len, dest, - &sjis_to_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = LocalToUtf(src, len, dest, + &sjis_to_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SJIS); - UtfToLocal(src, len, dest, - &sjis_from_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = UtfToLocal(src, len, dest, + &sjis_from_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c index 4bcc886d674..1fffdc5930c 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_shift_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ shift_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &shift_jis_2004_to_unicode_tree, - LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = LocalToUtf(src, len, dest, + &shift_jis_2004_to_unicode_tree, + LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SHIFT_JIS_2004); - UtfToLocal(src, len, dest, - &shift_jis_2004_from_unicode_tree, - ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = UtfToLocal(src, len, dest, + &shift_jis_2004_from_unicode_tree, + ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c index c8e512994a1..d9471dad097 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_uhc); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ uhc_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UHC, PG_UTF8); - LocalToUtf(src, len, dest, - &uhc_to_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = LocalToUtf(src, len, dest, + &uhc_to_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_uhc(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_UHC); - UtfToLocal(src, len, dest, - &uhc_from_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = UtfToLocal(src, len, dest, + &uhc_from_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c index 0c9493dee56..110ba5677d0 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c @@ -48,8 +48,11 @@ PG_FUNCTION_INFO_V1(utf8_to_win); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -81,6 +84,7 @@ win_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -89,12 +93,15 @@ win_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -103,7 +110,7 @@ win_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -113,6 +120,7 @@ utf8_to_win(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -121,12 +129,15 @@ utf8_to_win(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -135,5 +146,5 @@ utf8_to_win(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/mbutils.c b/src/backend/utils/mb/mbutils.c index 2578573b0ab..65753860e35 100644 --- a/src/backend/utils/mb/mbutils.c +++ b/src/backend/utils/mb/mbutils.c @@ -406,12 +406,13 @@ pg_do_encoding_conversion(unsigned char *src, int len, MemoryContextAllocHuge(CurrentMemoryContext, (Size) len * MAX_CONVERSION_GROWTH + 1); - OidFunctionCall5(proc, - Int32GetDatum(src_encoding), - Int32GetDatum(dest_encoding), - CStringGetDatum(src), - CStringGetDatum(result), - Int32GetDatum(len)); + (void) OidFunctionCall6(proc, + Int32GetDatum(src_encoding), + Int32GetDatum(dest_encoding), + CStringGetDatum(src), + CStringGetDatum(result), + Int32GetDatum(len), + BoolGetDatum(false)); /* * If the result is large, it's worth repalloc'ing to release any extra @@ -849,12 +850,13 @@ pg_unicode_to_server(pg_wchar c, unsigned char *s) c_as_utf8[c_as_utf8_len] = '\0'; /* Convert, or throw error if we can't */ - FunctionCall5(Utf8ToServerConvProc, + FunctionCall6(Utf8ToServerConvProc, Int32GetDatum(PG_UTF8), Int32GetDatum(server_encoding), CStringGetDatum(c_as_utf8), CStringGetDatum(s), - Int32GetDatum(c_as_utf8_len)); + Int32GetDatum(c_as_utf8_len), + BoolGetDatum(false)); } diff --git a/src/bin/pg_upgrade/check.c b/src/bin/pg_upgrade/check.c index 43fc297eb69..ee6be95b08d 100644 --- a/src/bin/pg_upgrade/check.c +++ b/src/bin/pg_upgrade/check.c @@ -28,6 +28,7 @@ static void check_for_reg_data_type_usage(ClusterInfo *cluster); static void check_for_jsonb_9_4_usage(ClusterInfo *cluster); static void check_for_pg_role_prefix(ClusterInfo *cluster); static void check_for_new_tablespace_dir(ClusterInfo *new_cluster); +static void check_for_user_defined_encoding_conversions(ClusterInfo *cluster); static char *get_canonical_locale_name(int category, const char *locale); @@ -102,6 +103,15 @@ check_and_dump_old_cluster(bool live_check) check_for_reg_data_type_usage(&old_cluster); check_for_isn_and_int8_passing_mismatch(&old_cluster); + /* + * PG 14 changed the function signature of encoding conversion functions. + * Conversions from older versions cannot be upgraded automatically + * because the user-defined functions used by the encoding conversions + * need to changed to match the new signature. + */ + if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1300) + check_for_user_defined_encoding_conversions(&old_cluster); + /* * Pre-PG 14 allowed user defined postfix operators, which are not * supported anymore. Verify there are none, iff applicable. @@ -1268,6 +1278,91 @@ check_for_pg_role_prefix(ClusterInfo *cluster) check_ok(); } +/* + * Verify that no user-defined encoding conversions exist. + */ +static void +check_for_user_defined_encoding_conversions(ClusterInfo *cluster) +{ + int dbnum; + FILE *script = NULL; + bool found = false; + char output_path[MAXPGPATH]; + + prep_status("Checking for user-defined encoding conversions"); + + snprintf(output_path, sizeof(output_path), + "encoding_conversions.txt"); + + /* Find any user defined encoding conversions */ + for (dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++) + { + PGresult *res; + bool db_used = false; + int ntups; + int rowno; + int i_conoid, + i_conname, + i_nspname; + DbInfo *active_db = &cluster->dbarr.dbs[dbnum]; + PGconn *conn = connectToServer(cluster, active_db->db_name); + + /* + * The query below hardcodes FirstNormalObjectId as 16384 rather than + * interpolating that C #define into the query because, if that + * #define is ever changed, the cutoff we want to use is the value + * used by pre-version 14 servers, not that of some future version. + */ + res = executeQueryOrDie(conn, + "SELECT c.oid as conoid, c.conname, n.nspname " + "FROM pg_catalog.pg_conversion c, " + " pg_catalog.pg_namespace n " + "WHERE c.connamespace = n.oid AND " + " c.oid >= 16384"); + ntups = PQntuples(res); + i_conoid = PQfnumber(res, "conoid"); + i_conname = PQfnumber(res, "conname"); + i_nspname = PQfnumber(res, "nspname"); + for (rowno = 0; rowno < ntups; rowno++) + { + found = true; + if (script == NULL && + (script = fopen_priv(output_path, "w")) == NULL) + pg_fatal("could not open file \"%s\": %s\n", + output_path, strerror(errno)); + if (!db_used) + { + fprintf(script, "In database: %s\n", active_db->db_name); + db_used = true; + } + fprintf(script, " (oid=%s) %s.%s\n", + PQgetvalue(res, rowno, i_conoid), + PQgetvalue(res, rowno, i_nspname), + PQgetvalue(res, rowno, i_conname)); + } + + PQclear(res); + + PQfinish(conn); + } + + if (script) + fclose(script); + + if (found) + { + pg_log(PG_REPORT, "fatal\n"); + pg_fatal("Your installation contains user-defined encoding conversions.\n" + "The conversion function parameters changed in PostgreSQL version 14\n" + "so this cluster cannot currently be upgraded. You can remove the\n" + "encoding conversions in the old cluster and restart the upgrade.\n" + "A list of user-defined encoding conversions is in the file:\n" + " %s\n\n", output_path); + } + else + check_ok(); +} + /* * get_canonical_locale_name diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index f8174061ef3..75b829e8514 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10766,388 +10766,388 @@ # conversion functions { oid => '4302', descr => 'internal conversion function for KOI8R to MULE_INTERNAL', - proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_mic', + proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4303', descr => 'internal conversion function for MULE_INTERNAL to KOI8R', - proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_koi8r', + proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4304', descr => 'internal conversion function for ISO-8859-5 to MULE_INTERNAL', - proname => 'iso_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_mic', + proname => 'iso_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4305', descr => 'internal conversion function for MULE_INTERNAL to ISO-8859-5', - proname => 'mic_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_iso', + proname => 'mic_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4306', descr => 'internal conversion function for WIN1251 to MULE_INTERNAL', - proname => 'win1251_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_mic', + proname => 'win1251_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4307', descr => 'internal conversion function for MULE_INTERNAL to WIN1251', - proname => 'mic_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1251', + proname => 'mic_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4308', descr => 'internal conversion function for WIN866 to MULE_INTERNAL', - proname => 'win866_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_mic', + proname => 'win866_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4309', descr => 'internal conversion function for MULE_INTERNAL to WIN866', - proname => 'mic_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win866', + proname => 'mic_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4310', descr => 'internal conversion function for KOI8R to WIN1251', - proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4311', descr => 'internal conversion function for WIN1251 to KOI8R', - proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4312', descr => 'internal conversion function for KOI8R to WIN866', - proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_win866', + proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4313', descr => 'internal conversion function for WIN866 to KOI8R', - proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_koi8r', + proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4314', descr => 'internal conversion function for WIN866 to WIN1251', - proname => 'win866_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win866_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4315', descr => 'internal conversion function for WIN1251 to WIN866', - proname => 'win1251_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4316', descr => 'internal conversion function for ISO-8859-5 to KOI8R', - proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_koi8r', + proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4317', descr => 'internal conversion function for KOI8R to ISO-8859-5', - proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_iso', + proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4318', descr => 'internal conversion function for ISO-8859-5 to WIN1251', - proname => 'iso_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win1251', + proname => 'iso_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4319', descr => 'internal conversion function for WIN1251 to ISO-8859-5', - proname => 'win1251_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_iso', + proname => 'win1251_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4320', descr => 'internal conversion function for ISO-8859-5 to WIN866', - proname => 'iso_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win866', + proname => 'iso_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4321', descr => 'internal conversion function for WIN866 to ISO-8859-5', - proname => 'win866_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_iso', + proname => 'win866_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4322', descr => 'internal conversion function for EUC_CN to MULE_INTERNAL', - proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_mic', + proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_mic', probin => '$libdir/euc_cn_and_mic' }, { oid => '4323', descr => 'internal conversion function for MULE_INTERNAL to EUC_CN', - proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_cn', + proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_cn', probin => '$libdir/euc_cn_and_mic' }, { oid => '4324', descr => 'internal conversion function for EUC_JP to SJIS', - proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_sjis', + proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4325', descr => 'internal conversion function for SJIS to EUC_JP', - proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_euc_jp', + proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4326', descr => 'internal conversion function for EUC_JP to MULE_INTERNAL', - proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_mic', + proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4327', descr => 'internal conversion function for SJIS to MULE_INTERNAL', - proname => 'sjis_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_mic', + proname => 'sjis_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4328', descr => 'internal conversion function for MULE_INTERNAL to EUC_JP', - proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_jp', + proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4329', descr => 'internal conversion function for MULE_INTERNAL to SJIS', - proname => 'mic_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_sjis', + proname => 'mic_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4330', descr => 'internal conversion function for EUC_KR to MULE_INTERNAL', - proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_mic', + proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_mic', probin => '$libdir/euc_kr_and_mic' }, { oid => '4331', descr => 'internal conversion function for MULE_INTERNAL to EUC_KR', - proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_kr', + proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_kr', probin => '$libdir/euc_kr_and_mic' }, { oid => '4332', descr => 'internal conversion function for EUC_TW to BIG5', - proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_big5', + proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4333', descr => 'internal conversion function for BIG5 to EUC_TW', - proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_euc_tw', + proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4334', descr => 'internal conversion function for EUC_TW to MULE_INTERNAL', - proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_mic', + proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4335', descr => 'internal conversion function for BIG5 to MULE_INTERNAL', - proname => 'big5_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_mic', + proname => 'big5_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4336', descr => 'internal conversion function for MULE_INTERNAL to EUC_TW', - proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_tw', + proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4337', descr => 'internal conversion function for MULE_INTERNAL to BIG5', - proname => 'mic_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_big5', + proname => 'mic_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4338', descr => 'internal conversion function for LATIN2 to MULE_INTERNAL', - proname => 'latin2_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin2_to_mic', + proname => 'latin2_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4339', descr => 'internal conversion function for MULE_INTERNAL to LATIN2', - proname => 'mic_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin2', + proname => 'mic_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4340', descr => 'internal conversion function for WIN1250 to MULE_INTERNAL', - proname => 'win1250_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1250_to_mic', + proname => 'win1250_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4341', descr => 'internal conversion function for MULE_INTERNAL to WIN1250', - proname => 'mic_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1250', + proname => 'mic_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4342', descr => 'internal conversion function for LATIN2 to WIN1250', - proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4343', descr => 'internal conversion function for WIN1250 to LATIN2', - proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4344', descr => 'internal conversion function for LATIN1 to MULE_INTERNAL', - proname => 'latin1_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin1_to_mic', + proname => 'latin1_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin1_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4345', descr => 'internal conversion function for MULE_INTERNAL to LATIN1', - proname => 'mic_to_latin1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin1', + proname => 'mic_to_latin1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin1', probin => '$libdir/latin_and_mic' }, { oid => '4346', descr => 'internal conversion function for LATIN3 to MULE_INTERNAL', - proname => 'latin3_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin3_to_mic', + proname => 'latin3_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin3_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4347', descr => 'internal conversion function for MULE_INTERNAL to LATIN3', - proname => 'mic_to_latin3', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin3', + proname => 'mic_to_latin3', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin3', probin => '$libdir/latin_and_mic' }, { oid => '4348', descr => 'internal conversion function for LATIN4 to MULE_INTERNAL', - proname => 'latin4_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin4_to_mic', + proname => 'latin4_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin4_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4349', descr => 'internal conversion function for MULE_INTERNAL to LATIN4', - proname => 'mic_to_latin4', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin4', + proname => 'mic_to_latin4', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin4', probin => '$libdir/latin_and_mic' }, { oid => '4352', descr => 'internal conversion function for BIG5 to UTF8', - proname => 'big5_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_utf8', + proname => 'big5_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_utf8', probin => '$libdir/utf8_and_big5' }, { oid => '4353', descr => 'internal conversion function for UTF8 to BIG5', - proname => 'utf8_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_big5', + proname => 'utf8_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_big5', probin => '$libdir/utf8_and_big5' }, { oid => '4354', descr => 'internal conversion function for UTF8 to KOI8R', - proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8r', + proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8r', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4355', descr => 'internal conversion function for KOI8R to UTF8', - proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_utf8', + proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4356', descr => 'internal conversion function for UTF8 to KOI8U', - proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8u', + proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8u', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4357', descr => 'internal conversion function for KOI8U to UTF8', - proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8u_to_utf8', + proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8u_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4358', descr => 'internal conversion function for UTF8 to WIN', - proname => 'utf8_to_win', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_win', + proname => 'utf8_to_win', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_win', probin => '$libdir/utf8_and_win' }, { oid => '4359', descr => 'internal conversion function for WIN to UTF8', - proname => 'win_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win_to_utf8', + proname => 'win_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win_to_utf8', probin => '$libdir/utf8_and_win' }, { oid => '4360', descr => 'internal conversion function for EUC_CN to UTF8', - proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_utf8', + proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_utf8', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4361', descr => 'internal conversion function for UTF8 to EUC_CN', - proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_cn', + proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_cn', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4362', descr => 'internal conversion function for EUC_JP to UTF8', - proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_utf8', + proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_utf8', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4363', descr => 'internal conversion function for UTF8 to EUC_JP', - proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_jp', + proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jp', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4364', descr => 'internal conversion function for EUC_KR to UTF8', - proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_utf8', + proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_utf8', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4365', descr => 'internal conversion function for UTF8 to EUC_KR', - proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_kr', + proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_kr', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4366', descr => 'internal conversion function for EUC_TW to UTF8', - proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_utf8', + proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_utf8', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4367', descr => 'internal conversion function for UTF8 to EUC_TW', - proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_tw', + proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_tw', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4368', descr => 'internal conversion function for GB18030 to UTF8', - proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gb18030_to_utf8', + proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gb18030_to_utf8', probin => '$libdir/utf8_and_gb18030' }, { oid => '4369', descr => 'internal conversion function for UTF8 to GB18030', - proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gb18030', + proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gb18030', probin => '$libdir/utf8_and_gb18030' }, { oid => '4370', descr => 'internal conversion function for GBK to UTF8', - proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gbk_to_utf8', + proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gbk_to_utf8', probin => '$libdir/utf8_and_gbk' }, { oid => '4371', descr => 'internal conversion function for UTF8 to GBK', - proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gbk', + proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gbk', probin => '$libdir/utf8_and_gbk' }, { oid => '4372', descr => 'internal conversion function for UTF8 to ISO-8859 2-16', - proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_iso8859', + proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859', probin => '$libdir/utf8_and_iso8859' }, { oid => '4373', descr => 'internal conversion function for ISO-8859 2-16 to UTF8', - proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso8859_to_utf8', + proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_to_utf8', probin => '$libdir/utf8_and_iso8859' }, { oid => '4374', descr => 'internal conversion function for LATIN1 to UTF8', - proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_1_to_utf8', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4375', descr => 'internal conversion function for UTF8 to LATIN1', - proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859_1', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4376', descr => 'internal conversion function for JOHAB to UTF8', - proname => 'johab_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'johab_to_utf8', + proname => 'johab_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'johab_to_utf8', probin => '$libdir/utf8_and_johab' }, { oid => '4377', descr => 'internal conversion function for UTF8 to JOHAB', - proname => 'utf8_to_johab', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_johab', + proname => 'utf8_to_johab', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_johab', probin => '$libdir/utf8_and_johab' }, { oid => '4378', descr => 'internal conversion function for SJIS to UTF8', - proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_utf8', + proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_utf8', probin => '$libdir/utf8_and_sjis' }, { oid => '4379', descr => 'internal conversion function for UTF8 to SJIS', - proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_sjis', + proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_sjis', probin => '$libdir/utf8_and_sjis' }, { oid => '4380', descr => 'internal conversion function for UHC to UTF8', - proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'uhc_to_utf8', + proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'uhc_to_utf8', probin => '$libdir/utf8_and_uhc' }, { oid => '4381', descr => 'internal conversion function for UTF8 to UHC', - proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_uhc', + proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_uhc', probin => '$libdir/utf8_and_uhc' }, { oid => '4382', descr => 'internal conversion function for EUC_JIS_2004 to UTF8', - proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_utf8', probin => '$libdir/utf8_and_euc2004' }, { oid => '4383', descr => 'internal conversion function for UTF8 to EUC_JIS_2004', - proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jis_2004', probin => '$libdir/utf8_and_euc2004' }, { oid => '4384', descr => 'internal conversion function for SHIFT_JIS_2004 to UTF8', - proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_utf8', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4385', descr => 'internal conversion function for UTF8 to SHIFT_JIS_2004', - proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_shift_jis_2004', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4386', descr => 'internal conversion function for EUC_JIS_2004 to SHIFT_JIS_2004', proname => 'euc_jis_2004_to_shift_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_shift_jis_2004', probin => '$libdir/euc2004_sjis2004' }, { oid => '4387', descr => 'internal conversion function for SHIFT_JIS_2004 to EUC_JIS_2004', proname => 'shift_jis_2004_to_euc_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_euc_jis_2004', probin => '$libdir/euc2004_sjis2004' }, diff --git a/src/include/mb/pg_wchar.h b/src/include/mb/pg_wchar.h index 64b22e4b0d4..346a41a1f3d 100644 --- a/src/include/mb/pg_wchar.h +++ b/src/include/mb/pg_wchar.h @@ -627,18 +627,18 @@ extern void pg_unicode_to_server(pg_wchar c, unsigned char *s); extern unsigned short BIG5toCNS(unsigned short big5, unsigned char *lc); extern unsigned short CNStoBIG5(unsigned short cns, unsigned char lc); -extern void UtfToLocal(const unsigned char *utf, int len, - unsigned char *iso, - const pg_mb_radix_tree *map, - const pg_utf_to_local_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); -extern void LocalToUtf(const unsigned char *iso, int len, - unsigned char *utf, - const pg_mb_radix_tree *map, - const pg_local_to_utf_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); +extern int UtfToLocal(const unsigned char *utf, int len, + unsigned char *iso, + const pg_mb_radix_tree *map, + const pg_utf_to_local_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); +extern int LocalToUtf(const unsigned char *iso, int len, + unsigned char *utf, + const pg_mb_radix_tree *map, + const pg_local_to_utf_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); extern bool pg_verifymbstr(const char *mbstr, int len, bool noError); extern bool pg_verify_mbstr(int encoding, const char *mbstr, int len, @@ -656,18 +656,19 @@ extern void report_invalid_encoding(int encoding, const char *mbstr, int len) pg extern void report_untranslatable_char(int src_encoding, int dest_encoding, const char *mbstr, int len) pg_attribute_noreturn(); -extern void local2local(const unsigned char *l, unsigned char *p, int len, - int src_encoding, int dest_encoding, const unsigned char *tab); -extern void latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding); -extern void mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding); -extern void latin2mic_with_table(const unsigned char *l, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); -extern void mic2latin_with_table(const unsigned char *mic, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); +extern int local2local(const unsigned char *l, unsigned char *p, int len, + int src_encoding, int dest_encoding, const unsigned char *tab, + bool noError); +extern int latin2mic(const unsigned char *l, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int mic2latin(const unsigned char *mic, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int latin2mic_with_table(const unsigned char *l, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); +extern int mic2latin_with_table(const unsigned char *mic, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); #ifdef WIN32 extern WCHAR *pgwin32_message_to_UTF16(const char *str, int len, int *utf16len); diff --git a/src/test/regress/expected/opr_sanity.out b/src/test/regress/expected/opr_sanity.out index 254ca06d3dd..23ba60e395f 100644 --- a/src/test/regress/expected/opr_sanity.out +++ b/src/test/regress/expected/opr_sanity.out @@ -1052,13 +1052,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); oid | proname | oid | conname -----+---------+-----+--------- (0 rows) diff --git a/src/test/regress/sql/opr_sanity.sql b/src/test/regress/sql/opr_sanity.sql index bbd3834b634..04691745981 100644 --- a/src/test/regress/sql/opr_sanity.sql +++ b/src/test/regress/sql/opr_sanity.sql @@ -556,13 +556,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); -- Check for conprocs that don't perform the specific conversion that -- pg_conversion alleges they do, by trying to invoke each conversion -- 2.29.2 --------------39E46EF15EBFAA37D53332E5 Content-Type: text/x-patch; charset=UTF-8; name="v3-0003-Add-tests-for-the-new-noError-variants-of-built-i.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="v3-0003-Add-tests-for-the-new-noError-variants-of-built-i.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 34+ messages in thread
* [PATCH v3 2/5] Change conversion function signature. @ 2021-01-28 16:42 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 34+ messages in thread From: Heikki Linnakangas @ 2021-01-28 16:42 UTC (permalink / raw) Add a 'noError' argument, so that we can try to convert a buffer without knowing the character boundaries beforehand. The functions now need to return the number of input bytes successfully converted. This is is a backwards-incompatible change, if you have created a custom encoding conversion with CREATE CONVERSION. This adds a check to pg_upgrade for that, refusing the upgrade if there are any user-defined encoding conversions. --- doc/src/sgml/ref/create_conversion.sgml | 5 +- src/backend/commands/conversioncmds.c | 27 +- src/backend/utils/error/elog.c | 2 + src/backend/utils/mb/conv.c | 112 +++++- .../cyrillic_and_mic/cyrillic_and_mic.c | 127 ++++--- .../euc2004_sjis2004/euc2004_sjis2004.c | 96 ++++- .../euc_cn_and_mic/euc_cn_and_mic.c | 57 ++- .../euc_jp_and_sjis/euc_jp_and_sjis.c | 153 ++++++-- .../euc_kr_and_mic/euc_kr_and_mic.c | 57 ++- .../euc_tw_and_big5/euc_tw_and_big5.c | 165 +++++++-- .../latin2_and_win1250/latin2_and_win1250.c | 49 ++- .../latin_and_mic/latin_and_mic.c | 43 ++- .../utf8_and_big5/utf8_and_big5.c | 37 +- .../utf8_and_cyrillic/utf8_and_cyrillic.c | 67 ++-- .../utf8_and_euc2004/utf8_and_euc2004.c | 37 +- .../utf8_and_euc_cn/utf8_and_euc_cn.c | 37 +- .../utf8_and_euc_jp/utf8_and_euc_jp.c | 37 +- .../utf8_and_euc_kr/utf8_and_euc_kr.c | 37 +- .../utf8_and_euc_tw/utf8_and_euc_tw.c | 37 +- .../utf8_and_gb18030/utf8_and_gb18030.c | 37 +- .../utf8_and_gbk/utf8_and_gbk.c | 37 +- .../utf8_and_iso8859/utf8_and_iso8859.c | 43 ++- .../utf8_and_iso8859_1/utf8_and_iso8859_1.c | 27 +- .../utf8_and_johab/utf8_and_johab.c | 37 +- .../utf8_and_sjis/utf8_and_sjis.c | 37 +- .../utf8_and_sjis2004/utf8_and_sjis2004.c | 37 +- .../utf8_and_uhc/utf8_and_uhc.c | 37 +- .../utf8_and_win/utf8_and_win.c | 43 ++- src/backend/utils/mb/mbutils.c | 18 +- src/bin/pg_upgrade/check.c | 95 +++++ src/include/catalog/pg_proc.dat | 332 +++++++++--------- src/include/mb/pg_wchar.h | 49 +-- src/test/regress/expected/opr_sanity.out | 7 +- src/test/regress/sql/opr_sanity.sql | 7 +- 34 files changed, 1390 insertions(+), 635 deletions(-) diff --git a/doc/src/sgml/ref/create_conversion.sgml b/doc/src/sgml/ref/create_conversion.sgml index e7700fecfc5..f014a676c88 100644 --- a/doc/src/sgml/ref/create_conversion.sgml +++ b/doc/src/sgml/ref/create_conversion.sgml @@ -117,8 +117,9 @@ conv_proc( integer, -- destination encoding ID cstring, -- source string (null terminated C string) internal, -- destination (fill with a null terminated C string) - integer -- source string length -) RETURNS void; + integer, -- source string length + boolean -- if true, don't throw an error if conversion fails +) RETURNS integer; </programlisting></para> </listitem> </varlistentry> diff --git a/src/backend/commands/conversioncmds.c b/src/backend/commands/conversioncmds.c index f7ff321de71..d2041466911 100644 --- a/src/backend/commands/conversioncmds.c +++ b/src/backend/commands/conversioncmds.c @@ -45,8 +45,9 @@ CreateConversionCommand(CreateConversionStmt *stmt) const char *from_encoding_name = stmt->for_encoding_name; const char *to_encoding_name = stmt->to_encoding_name; List *func_name = stmt->func_name; - static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID}; + static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID, BOOLOID}; char result[1]; + Datum funcresult; /* Convert list of names to a name and namespace */ namespaceId = QualifiedNameGetCreationNamespace(stmt->conversion_name, @@ -92,8 +93,8 @@ CreateConversionCommand(CreateConversionStmt *stmt) funcoid = LookupFuncName(func_name, sizeof(funcargs) / sizeof(Oid), funcargs, false); - /* Check it returns VOID, else it's probably the wrong function */ - if (get_func_rettype(funcoid) != VOIDOID) + /* Check it returns int4, else it's probably the wrong function */ + if (get_func_rettype(funcoid) != INT4OID) ereport(ERROR, (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), errmsg("encoding conversion function %s must return type %s", @@ -111,12 +112,20 @@ CreateConversionCommand(CreateConversionStmt *stmt) * string; the conversion function should throw an error if it can't * perform the requested conversion. */ - OidFunctionCall5(funcoid, - Int32GetDatum(from_encoding), - Int32GetDatum(to_encoding), - CStringGetDatum(""), - CStringGetDatum(result), - Int32GetDatum(0)); + funcresult = OidFunctionCall6(funcoid, + Int32GetDatum(from_encoding), + Int32GetDatum(to_encoding), + CStringGetDatum(""), + CStringGetDatum(result), + Int32GetDatum(0), + BoolGetDatum(false)); + + /* The function should return 0 for empty input. Might as well check that, too. */ + if (DatumGetInt32(funcresult) != 0) + ereport(ERROR, + (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), + errmsg("encoding conversion function %s returned incorrect result for empty input", + NameListToString(func_name)))); /* * All seem ok, go ahead (possible failure would be a duplicate conversion diff --git a/src/backend/utils/error/elog.c b/src/backend/utils/error/elog.c index 80c26724612..762f77d533c 100644 --- a/src/backend/utils/error/elog.c +++ b/src/backend/utils/error/elog.c @@ -2280,6 +2280,8 @@ write_console(const char *line, int len) * Conversion on non-win32 platforms is not implemented yet. It requires * non-throw version of pg_do_encoding_conversion(), that converts * unconvertable characters to '?' without errors. + * + * XXX: We have a no-throw version now. It doesn't convert to '?' though. */ #endif diff --git a/src/backend/utils/mb/conv.c b/src/backend/utils/mb/conv.c index a07b54bd3b8..b83358bc7a5 100644 --- a/src/backend/utils/mb/conv.c +++ b/src/backend/utils/mb/conv.c @@ -26,14 +26,16 @@ * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the target charset, or 0 if there is no equivalent code. */ -void +int local2local(const unsigned char *l, unsigned char *p, int len, int src_encoding, int dest_encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -41,7 +43,11 @@ local2local(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(src_encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -50,13 +56,19 @@ local2local(const unsigned char *l, if (c2) *p++ = c2; else + { + if (noError) + break; report_untranslatable_char(src_encoding, dest_encoding, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -67,17 +79,22 @@ local2local(const unsigned char *l, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = l; int c1; while (len > 0) { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (IS_HIGHBIT_SET(c1)) *p++ = lc; *p++ = c1; @@ -85,6 +102,8 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, len--; } *p = '\0'; + + return l - start; } /* @@ -95,17 +114,22 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -118,17 +142,27 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1])) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); + } *p++ = mic[1]; mic += 2; len -= 2; } } *p = '\0'; + + return mic - start; } @@ -144,14 +178,16 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the mule encoding, or 0 if there is no equivalent code. */ -void +int latin2mic_with_table(const unsigned char *l, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -159,7 +195,11 @@ latin2mic_with_table(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -171,13 +211,19 @@ latin2mic_with_table(const unsigned char *l, *p++ = c2; } else + { + if (noError) + break; report_untranslatable_char(encoding, PG_MULE_INTERNAL, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -192,14 +238,16 @@ latin2mic_with_table(const unsigned char *l, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the local charset, or 0 if there is no equivalent code. */ -void +int mic2latin_with_table(const unsigned char *mic, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = mic; unsigned char c1, c2; @@ -207,7 +255,11 @@ mic2latin_with_table(const unsigned char *mic, { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -220,11 +272,17 @@ mic2latin_with_table(const unsigned char *mic, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1]) || (c2 = tab[mic[1] - HIGHBIT]) == 0) { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); break; /* keep compiler quiet */ @@ -235,6 +293,8 @@ mic2latin_with_table(const unsigned char *mic, } } *p = '\0'; + + return mic - start; } /* @@ -425,17 +485,19 @@ pg_mb_radix_conv(const pg_mb_radix_tree *rt, * * See pg_wchar.h for more details about the data structures used here. */ -void +int UtfToLocal(const unsigned char *utf, int len, unsigned char *iso, const pg_mb_radix_tree *map, const pg_utf_to_local_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, bool noError) { uint32 iutf; int l; const pg_utf_to_local_combined *cp; + const unsigned char *start = utf; + const unsigned char *cur = utf; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -449,6 +511,8 @@ UtfToLocal(const unsigned char *utf, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*utf == '\0') break; @@ -584,15 +648,19 @@ UtfToLocal(const unsigned char *utf, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(PG_UTF8, encoding, (const char *) (utf - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(PG_UTF8, (const char *) utf, len); *iso = '\0'; + + return cur - start; } /* @@ -616,18 +684,24 @@ UtfToLocal(const unsigned char *utf, int len, * (if provided) is applied. An error is raised if no match is found. * * See pg_wchar.h for more details about the data structures used here. + * + * Returns the number of input bytes consumed. If noError is true, this can + * be less than 'len'. */ -void +int LocalToUtf(const unsigned char *iso, int len, unsigned char *utf, const pg_mb_radix_tree *map, const pg_local_to_utf_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, + bool noError) { uint32 iiso; int l; const pg_local_to_utf_combined *cp; + const unsigned char *start = iso; + const unsigned char *cur = iso; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -641,6 +715,8 @@ LocalToUtf(const unsigned char *iso, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*iso == '\0') break; @@ -723,13 +799,17 @@ LocalToUtf(const unsigned char *iso, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(encoding, PG_UTF8, (const char *) (iso - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(encoding, (const char *) iso, len); *utf = '\0'; + + return cur - start; } diff --git a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c index 4c5b02654de..368c2deb5e4 100644 --- a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c @@ -44,8 +44,11 @@ PG_FUNCTION_INFO_V1(win866_to_iso); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -306,12 +309,14 @@ koi8r_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -320,12 +325,14 @@ mic_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_KOI8R); - mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -334,12 +341,14 @@ iso_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -348,12 +357,14 @@ mic_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_ISO_8859_5); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -362,12 +373,14 @@ win1251_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -376,12 +389,14 @@ mic_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1251); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -390,12 +405,14 @@ win866_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -404,12 +421,14 @@ mic_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN866); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -418,12 +437,14 @@ koi8r_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN1251); - local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -432,12 +453,14 @@ win1251_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_KOI8R); - local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi); + converted = local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -446,12 +469,14 @@ koi8r_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN866); - local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -460,12 +485,14 @@ win866_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_KOI8R); - local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi); + converted = local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -474,12 +501,14 @@ win866_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_WIN1251); - local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251); + converted = local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -488,12 +517,14 @@ win1251_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_WIN866); - local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866); + converted = local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -502,12 +533,14 @@ iso_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_KOI8R); - local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -516,12 +549,14 @@ koi8r_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_ISO_8859_5); - local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso); + converted = local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -530,12 +565,14 @@ iso_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN1251); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -544,12 +581,14 @@ win1251_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso); + converted = local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -558,12 +597,14 @@ iso_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN866); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -572,10 +613,12 @@ win866_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso); + converted = local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c index 4d7fb116cfd..88529c644cf 100644 --- a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c @@ -19,8 +19,8 @@ PG_MODULE_MAGIC; PG_FUNCTION_INFO_V1(euc_jis_2004_to_shift_jis_2004); PG_FUNCTION_INFO_V1(shift_jis_2004_to_euc_jis_2004); -static void euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len); -static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len); +static int euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError); /* ---------- * conv_proc( @@ -28,8 +28,11 @@ static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -39,12 +42,14 @@ euc_jis_2004_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_SHIFT_JIS_2004); - euc_jis_20042shift_jis_2004(src, dest, len); + converted = euc_jis_20042shift_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -53,20 +58,23 @@ shift_jis_2004_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_EUC_JIS_2004); - shift_jis_20042euc_jis_2004(src, dest, len); + converted = shift_jis_20042euc_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_JIS_2004 -> SHIFT_JIS_2004 */ -static void -euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, ku, ten; @@ -79,8 +87,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -90,8 +102,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) l = pg_encoding_verifymbchar(PG_EUC_JIS_2004, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (c1 == SS2 && l == 2) /* JIS X 0201 kana? */ { @@ -121,8 +137,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) *p++ = (ku + 0x19b) >> 1; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } if (ku % 2) @@ -132,8 +152,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; @@ -149,8 +173,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ku >= 63 && ku <= 94) *p++ = (ku + 0x181) >> 1; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (ku % 2) { @@ -159,20 +187,30 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else - report_invalid_encoding(PG_EUC_JIS_2004, + { + if (noError) + break; + report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } euc += l; len -= l; } *p = '\0'; + + return euc - start; } /* @@ -212,9 +250,10 @@ get_ten(int b, int *ku) * SHIFT_JIS_2004 ---> EUC_JIS_2004 */ -static void -shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len) +static int +shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1; int ku, ten, @@ -230,8 +269,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -241,8 +284,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len l = pg_encoding_verifymbchar(PG_SHIFT_JIS_2004, (const char *) sjis, len); if (l < 0 || l > len) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf && l == 1) { @@ -266,8 +313,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x100; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xe0 && c1 <= 0xef) /* plane 1 62ku-94ku */ @@ -275,9 +326,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x180; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, - (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xf0 && c1 <= 0xf3) /* plane 2 @@ -286,8 +340,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } switch (c1) { case 0xf0: @@ -309,16 +367,24 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 == 0xf4 && kubun == 1) ku = 15; else ku = (c1 << 1) - 0x19a - kubun; } else + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (plane == 2) *p++ = SS3; @@ -330,4 +396,6 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c index e9bb896935f..a8da733803d 100644 --- a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_cn2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_cn(const unsigned char *mic, unsigned char *p, int len); +static int euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_cn_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_cn_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_MULE_INTERNAL); - euc_cn2mic(src, dest, len); + converted = euc_cn2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_CN); - mic2euc_cn(src, dest, len); + converted = mic2euc_cn(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_CN ---> MIC */ -static void -euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; while (len > 0) @@ -76,7 +84,11 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (len < 2 || !IS_HIGHBIT_SET(euc[1])) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = LC_GB2312_80; *p++ = c1; *p++ = euc[1]; @@ -86,21 +98,28 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_CN */ -static void -mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) @@ -109,11 +128,19 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (c1 != LC_GB2312_80) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_CN, (const char *) mic, len); + } if (len < 3 || !IS_HIGHBIT_SET(mic[1]) || !IS_HIGHBIT_SET(mic[2])) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } mic++; *p++ = *mic++; *p++ = *mic++; @@ -122,12 +149,18 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; } } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c index 5059f917a98..cc4817dc4cd 100644 --- a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c @@ -42,17 +42,20 @@ PG_FUNCTION_INFO_V1(mic_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void sjis2mic(const unsigned char *sjis, unsigned char *p, int len); -static void mic2sjis(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_jp(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len); -static void sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len); +static int sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError); +static int mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_jp_to_sjis(PG_FUNCTION_ARGS) @@ -60,12 +63,14 @@ euc_jp_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_SJIS); - euc_jp2sjis(src, dest, len); + converted = euc_jp2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -74,12 +79,14 @@ sjis_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_EUC_JP); - sjis2euc_jp(src, dest, len); + converted = sjis2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -88,12 +95,14 @@ euc_jp_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_MULE_INTERNAL); - euc_jp2mic(src, dest, len); + converted = euc_jp2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -102,12 +111,14 @@ mic_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_JP); - mic2euc_jp(src, dest, len); + converted = mic2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -116,12 +127,14 @@ sjis_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_MULE_INTERNAL); - sjis2mic(src, dest, len); + converted = sjis2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -130,20 +143,23 @@ mic_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_SJIS); - mic2sjis(src, dest, len); + converted = mic2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * SJIS ---> MIC */ -static void -sjis2mic(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -167,7 +183,11 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) * JIS X0208, X0212, user defined extended characters */ if (len < 2 || !ISSJISHEAD(c1) || !ISSJISTAIL(sjis[1])) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } c2 = sjis[1]; k = (c1 << 8) + c2; if (k >= 0xed40 && k < 0xf040) @@ -257,21 +277,28 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; } } *p = '\0'; + + return sjis - start; } /* * MIC ---> SJIS */ -static void -mic2sjis(const unsigned char *mic, unsigned char *p, int len) +static int +mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1, c2, k, @@ -284,8 +311,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -293,8 +324,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) *p++ = mic[1]; else if (c1 == LC_JISX0208) @@ -350,20 +385,27 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_SJIS, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP ---> MIC */ -static void -euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -374,8 +416,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -383,8 +429,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* 1 byte kana? */ *p++ = LC_JISX0201K; @@ -406,14 +456,17 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_JP */ -static void -mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -424,8 +477,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -433,8 +490,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) { *p++ = SS2; @@ -452,20 +513,27 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_JP, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP -> SJIS */ -static void -euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, c2, k; @@ -478,8 +546,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -487,8 +559,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* hankaku kana? */ @@ -551,14 +627,17 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * SJIS ---> EUC_JP */ -static void -sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -573,8 +652,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -582,8 +665,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_SJIS, (const char *) sjis, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf) { /* JIS X0201 (1 byte kana) */ @@ -680,4 +767,6 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c index ac823d6c270..a5b51617e52 100644 --- a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_kr2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_kr(const unsigned char *mic, unsigned char *p, int len); +static int euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_kr_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_kr_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_MULE_INTERNAL); - euc_kr2mic(src, dest, len); + converted = euc_kr2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_KR); - mic2euc_kr(src, dest, len); + converted = mic2euc_kr(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_KR ---> MIC */ -static void -euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -78,8 +86,12 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_KR, (const char *) euc, len); if (l != 2) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = LC_KS5601; *p++ = c1; *p++ = euc[1]; @@ -89,22 +101,29 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_KR */ -static void -mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -115,8 +134,12 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -124,18 +147,28 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_KS5601) { *p++ = mic[1]; *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_KR, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c index 66c242d7f36..ebb4e0acd53 100644 --- a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c @@ -32,17 +32,20 @@ PG_FUNCTION_INFO_V1(mic_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_tw2big5(const unsigned char *euc, unsigned char *p, int len); -static void big52euc_tw(const unsigned char *euc, unsigned char *p, int len); -static void big52mic(const unsigned char *big5, unsigned char *p, int len); -static void mic2big5(const unsigned char *mic, unsigned char *p, int len); -static void euc_tw2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_tw(const unsigned char *mic, unsigned char *p, int len); +static int euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52euc_tw(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError); +static int mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_tw_to_big5(PG_FUNCTION_ARGS) @@ -50,12 +53,14 @@ euc_tw_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_BIG5); - euc_tw2big5(src, dest, len); + converted = euc_tw2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -64,12 +69,14 @@ big5_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_EUC_TW); - big52euc_tw(src, dest, len); + converted = big52euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -78,12 +85,14 @@ euc_tw_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_MULE_INTERNAL); - euc_tw2mic(src, dest, len); + converted = euc_tw2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -92,12 +101,14 @@ mic_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_TW); - mic2euc_tw(src, dest, len); + converted = mic2euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -106,12 +117,14 @@ big5_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_MULE_INTERNAL); - big52mic(src, dest, len); + converted = big52mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -120,21 +133,24 @@ mic_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_BIG5); - mic2big5(src, dest, len); + converted = mic2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_TW ---> Big5 */ -static void -euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; unsigned char c1; unsigned short big5buf, cnsBuf; @@ -149,8 +165,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Verify and decode the next EUC_TW input character */ l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -171,8 +191,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Write it out in Big5 */ big5buf = CNStoBIG5(cnsBuf, lc); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_EUC_TW, PG_BIG5, (const char *) euc, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; @@ -182,22 +206,29 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * Big5 ---> EUC_TW */ -static void -big52euc_tw(const unsigned char *big5, unsigned char *p, int len) +static int +big52euc_tw(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -212,8 +243,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); @@ -237,8 +272,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_EUC_TW, (const char *) big5, len); + } big5 += l; len -= l; @@ -256,14 +295,17 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) } } *p = '\0'; + + return big5 - start; } /* * EUC_TW ---> MIC */ -static void -euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -274,8 +316,12 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -304,22 +350,29 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_TW */ -static void -mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -330,8 +383,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -339,8 +396,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1) { *p++ = mic[1]; @@ -362,20 +423,27 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[3]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_TW, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * Big5 ---> MIC */ -static void -big52mic(const unsigned char *big5, unsigned char *p, int len) +static int +big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -389,8 +457,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } *p++ = c1; big5++; len--; @@ -398,8 +470,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); if (lc != 0) @@ -412,20 +488,27 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_MULE_INTERNAL, (const char *) big5, len); + } big5 += l; len -= l; } *p = '\0'; + + return big5 - start; } /* * MIC ---> Big5 */ -static void -mic2big5(const unsigned char *mic, unsigned char *p, int len) +static int +mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -438,8 +521,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -447,8 +534,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1 || c1 == LC_CNS11643_2 || c1 == LCPRV2_B) { if (c1 == LCPRV2_B) @@ -462,16 +553,26 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } big5buf = CNStoBIG5(cnsBuf, c1); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c index 2e28e6780a5..8610fcb69aa 100644 --- a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c +++ b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(win1250_to_latin2); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -82,12 +85,14 @@ latin2_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -96,12 +101,14 @@ mic_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN2); - mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -110,13 +117,15 @@ win1250_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - win1250_2_iso88592); + converted = latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -125,13 +134,15 @@ mic_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1250); - mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - iso88592_2_win1250); + converted = mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -140,12 +151,15 @@ latin2_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_WIN1250); - local2local(src, dest, len, PG_LATIN2, PG_WIN1250, iso88592_2_win1250); + converted = local2local(src, dest, len, PG_LATIN2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -154,10 +168,13 @@ win1250_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_LATIN2); - local2local(src, dest, len, PG_WIN1250, PG_LATIN2, win1250_2_iso88592); + converted = local2local(src, dest, len, PG_WIN1250, PG_LATIN2, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c index bc651410f21..bff27d1c295 100644 --- a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(mic_to_latin4); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -42,12 +45,14 @@ latin1_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,12 +61,14 @@ mic_to_latin1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN1); - mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -70,12 +77,14 @@ latin3_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN3, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -84,12 +93,14 @@ mic_to_latin3(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN3); - mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,12 +109,14 @@ latin4_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN4, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -112,10 +125,12 @@ mic_to_latin4(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN4); - mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c index d6067cdc24e..3838b15cab9 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ big5_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_UTF8); - LocalToUtf(src, len, dest, - &big5_to_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = LocalToUtf(src, len, dest, + &big5_to_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_BIG5); - UtfToLocal(src, len, dest, - &big5_from_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = UtfToLocal(src, len, dest, + &big5_from_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c index ed90e8e682e..75719fe5f1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c @@ -33,8 +33,11 @@ PG_FUNCTION_INFO_V1(koi8u_to_utf8); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -44,16 +47,19 @@ utf8_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8R); - UtfToLocal(src, len, dest, - &koi8r_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = UtfToLocal(src, len, dest, + &koi8r_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -62,16 +68,19 @@ koi8r_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8r_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = LocalToUtf(src, len, dest, + &koi8r_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -80,16 +89,19 @@ utf8_to_koi8u(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8U); - UtfToLocal(src, len, dest, - &koi8u_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = UtfToLocal(src, len, dest, + &koi8u_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,14 +110,17 @@ koi8u_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8U, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8u_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = LocalToUtf(src, len, dest, + &koi8u_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c index d699affce47..5391001951a 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jis_2004_to_unicode_tree, - LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = LocalToUtf(src, len, dest, + &euc_jis_2004_to_unicode_tree, + LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JIS_2004); - UtfToLocal(src, len, dest, - &euc_jis_2004_from_unicode_tree, - ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = UtfToLocal(src, len, dest, + &euc_jis_2004_from_unicode_tree, + ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c index d7c0ba6a58b..c87d1bf2398 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_cn_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_cn_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = LocalToUtf(src, len, dest, + &euc_cn_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_CN); - UtfToLocal(src, len, dest, - &euc_cn_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = UtfToLocal(src, len, dest, + &euc_cn_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c index 13a3a23e77b..6a55134db21 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jp); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jp_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jp_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = LocalToUtf(src, len, dest, + &euc_jp_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JP); - UtfToLocal(src, len, dest, - &euc_jp_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = UtfToLocal(src, len, dest, + &euc_jp_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c index 1bbb8aaef7b..fe1924e2fec 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_kr_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_kr_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = LocalToUtf(src, len, dest, + &euc_kr_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_KR); - UtfToLocal(src, len, dest, - &euc_kr_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = UtfToLocal(src, len, dest, + &euc_kr_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c index 9830045dccd..68215659b57 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_tw); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_tw_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_tw_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = LocalToUtf(src, len, dest, + &euc_tw_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_TW); - UtfToLocal(src, len, dest, - &euc_tw_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = UtfToLocal(src, len, dest, + &euc_tw_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c index f86ecf27424..e1a59c39a4d 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c @@ -183,8 +183,11 @@ conv_utf8_to_18030(uint32 code) * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -193,16 +196,19 @@ gb18030_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GB18030, PG_UTF8); - LocalToUtf(src, len, dest, - &gb18030_to_unicode_tree, - NULL, 0, - conv_18030_to_utf8, - PG_GB18030); + converted = LocalToUtf(src, len, dest, + &gb18030_to_unicode_tree, + NULL, 0, + conv_18030_to_utf8, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -211,14 +217,17 @@ utf8_to_gb18030(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GB18030); - UtfToLocal(src, len, dest, - &gb18030_from_unicode_tree, - NULL, 0, - conv_utf8_to_18030, - PG_GB18030); + converted = UtfToLocal(src, len, dest, + &gb18030_from_unicode_tree, + NULL, 0, + conv_utf8_to_18030, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c index 2ab8b16c8a8..881386d5347 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_gbk); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ gbk_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GBK, PG_UTF8); - LocalToUtf(src, len, dest, - &gbk_to_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = LocalToUtf(src, len, dest, + &gbk_to_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_gbk(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GBK); - UtfToLocal(src, len, dest, - &gbk_from_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = UtfToLocal(src, len, dest, + &gbk_from_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c index 3e49f67ea2f..d93a521badf 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c @@ -52,8 +52,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -100,6 +103,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -108,12 +112,15 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -122,7 +129,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -132,6 +139,7 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -140,12 +148,15 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -154,5 +165,5 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c index 67e713cca11..8ac93604a1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c @@ -26,8 +26,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859_1); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -37,6 +40,8 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_UTF8); @@ -45,7 +50,11 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_LATIN1, (const char *) src, len); + } if (!IS_HIGHBIT_SET(c)) *dest++ = c; else @@ -58,7 +67,7 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } Datum @@ -67,6 +76,8 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c, c1; @@ -76,7 +87,11 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_UTF8, (const char *) src, len); + } /* fast path for ASCII-subset characters */ if (!IS_HIGHBIT_SET(c)) { @@ -102,11 +117,15 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) len -= 2; } else + { + if (noError) + break; report_untranslatable_char(PG_UTF8, PG_LATIN1, (const char *) src, len); + } } } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c index 578f5df4e7f..317daa2d5ee 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_johab); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ johab_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_JOHAB, PG_UTF8); - LocalToUtf(src, len, dest, - &johab_to_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = LocalToUtf(src, len, dest, + &johab_to_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_johab(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_JOHAB); - UtfToLocal(src, len, dest, - &johab_from_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = UtfToLocal(src, len, dest, + &johab_from_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c index dd9fc2975ad..4c9348aba59 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ sjis_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_UTF8); - LocalToUtf(src, len, dest, - &sjis_to_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = LocalToUtf(src, len, dest, + &sjis_to_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SJIS); - UtfToLocal(src, len, dest, - &sjis_from_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = UtfToLocal(src, len, dest, + &sjis_from_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c index 4bcc886d674..1fffdc5930c 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_shift_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ shift_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &shift_jis_2004_to_unicode_tree, - LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = LocalToUtf(src, len, dest, + &shift_jis_2004_to_unicode_tree, + LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SHIFT_JIS_2004); - UtfToLocal(src, len, dest, - &shift_jis_2004_from_unicode_tree, - ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = UtfToLocal(src, len, dest, + &shift_jis_2004_from_unicode_tree, + ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c index c8e512994a1..d9471dad097 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_uhc); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ uhc_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UHC, PG_UTF8); - LocalToUtf(src, len, dest, - &uhc_to_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = LocalToUtf(src, len, dest, + &uhc_to_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_uhc(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_UHC); - UtfToLocal(src, len, dest, - &uhc_from_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = UtfToLocal(src, len, dest, + &uhc_from_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c index 0c9493dee56..110ba5677d0 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c @@ -48,8 +48,11 @@ PG_FUNCTION_INFO_V1(utf8_to_win); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -81,6 +84,7 @@ win_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -89,12 +93,15 @@ win_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -103,7 +110,7 @@ win_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -113,6 +120,7 @@ utf8_to_win(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -121,12 +129,15 @@ utf8_to_win(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -135,5 +146,5 @@ utf8_to_win(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/mbutils.c b/src/backend/utils/mb/mbutils.c index 2578573b0ab..65753860e35 100644 --- a/src/backend/utils/mb/mbutils.c +++ b/src/backend/utils/mb/mbutils.c @@ -406,12 +406,13 @@ pg_do_encoding_conversion(unsigned char *src, int len, MemoryContextAllocHuge(CurrentMemoryContext, (Size) len * MAX_CONVERSION_GROWTH + 1); - OidFunctionCall5(proc, - Int32GetDatum(src_encoding), - Int32GetDatum(dest_encoding), - CStringGetDatum(src), - CStringGetDatum(result), - Int32GetDatum(len)); + (void) OidFunctionCall6(proc, + Int32GetDatum(src_encoding), + Int32GetDatum(dest_encoding), + CStringGetDatum(src), + CStringGetDatum(result), + Int32GetDatum(len), + BoolGetDatum(false)); /* * If the result is large, it's worth repalloc'ing to release any extra @@ -849,12 +850,13 @@ pg_unicode_to_server(pg_wchar c, unsigned char *s) c_as_utf8[c_as_utf8_len] = '\0'; /* Convert, or throw error if we can't */ - FunctionCall5(Utf8ToServerConvProc, + FunctionCall6(Utf8ToServerConvProc, Int32GetDatum(PG_UTF8), Int32GetDatum(server_encoding), CStringGetDatum(c_as_utf8), CStringGetDatum(s), - Int32GetDatum(c_as_utf8_len)); + Int32GetDatum(c_as_utf8_len), + BoolGetDatum(false)); } diff --git a/src/bin/pg_upgrade/check.c b/src/bin/pg_upgrade/check.c index 43fc297eb69..ee6be95b08d 100644 --- a/src/bin/pg_upgrade/check.c +++ b/src/bin/pg_upgrade/check.c @@ -28,6 +28,7 @@ static void check_for_reg_data_type_usage(ClusterInfo *cluster); static void check_for_jsonb_9_4_usage(ClusterInfo *cluster); static void check_for_pg_role_prefix(ClusterInfo *cluster); static void check_for_new_tablespace_dir(ClusterInfo *new_cluster); +static void check_for_user_defined_encoding_conversions(ClusterInfo *cluster); static char *get_canonical_locale_name(int category, const char *locale); @@ -102,6 +103,15 @@ check_and_dump_old_cluster(bool live_check) check_for_reg_data_type_usage(&old_cluster); check_for_isn_and_int8_passing_mismatch(&old_cluster); + /* + * PG 14 changed the function signature of encoding conversion functions. + * Conversions from older versions cannot be upgraded automatically + * because the user-defined functions used by the encoding conversions + * need to changed to match the new signature. + */ + if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1300) + check_for_user_defined_encoding_conversions(&old_cluster); + /* * Pre-PG 14 allowed user defined postfix operators, which are not * supported anymore. Verify there are none, iff applicable. @@ -1268,6 +1278,91 @@ check_for_pg_role_prefix(ClusterInfo *cluster) check_ok(); } +/* + * Verify that no user-defined encoding conversions exist. + */ +static void +check_for_user_defined_encoding_conversions(ClusterInfo *cluster) +{ + int dbnum; + FILE *script = NULL; + bool found = false; + char output_path[MAXPGPATH]; + + prep_status("Checking for user-defined encoding conversions"); + + snprintf(output_path, sizeof(output_path), + "encoding_conversions.txt"); + + /* Find any user defined encoding conversions */ + for (dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++) + { + PGresult *res; + bool db_used = false; + int ntups; + int rowno; + int i_conoid, + i_conname, + i_nspname; + DbInfo *active_db = &cluster->dbarr.dbs[dbnum]; + PGconn *conn = connectToServer(cluster, active_db->db_name); + + /* + * The query below hardcodes FirstNormalObjectId as 16384 rather than + * interpolating that C #define into the query because, if that + * #define is ever changed, the cutoff we want to use is the value + * used by pre-version 14 servers, not that of some future version. + */ + res = executeQueryOrDie(conn, + "SELECT c.oid as conoid, c.conname, n.nspname " + "FROM pg_catalog.pg_conversion c, " + " pg_catalog.pg_namespace n " + "WHERE c.connamespace = n.oid AND " + " c.oid >= 16384"); + ntups = PQntuples(res); + i_conoid = PQfnumber(res, "conoid"); + i_conname = PQfnumber(res, "conname"); + i_nspname = PQfnumber(res, "nspname"); + for (rowno = 0; rowno < ntups; rowno++) + { + found = true; + if (script == NULL && + (script = fopen_priv(output_path, "w")) == NULL) + pg_fatal("could not open file \"%s\": %s\n", + output_path, strerror(errno)); + if (!db_used) + { + fprintf(script, "In database: %s\n", active_db->db_name); + db_used = true; + } + fprintf(script, " (oid=%s) %s.%s\n", + PQgetvalue(res, rowno, i_conoid), + PQgetvalue(res, rowno, i_nspname), + PQgetvalue(res, rowno, i_conname)); + } + + PQclear(res); + + PQfinish(conn); + } + + if (script) + fclose(script); + + if (found) + { + pg_log(PG_REPORT, "fatal\n"); + pg_fatal("Your installation contains user-defined encoding conversions.\n" + "The conversion function parameters changed in PostgreSQL version 14\n" + "so this cluster cannot currently be upgraded. You can remove the\n" + "encoding conversions in the old cluster and restart the upgrade.\n" + "A list of user-defined encoding conversions is in the file:\n" + " %s\n\n", output_path); + } + else + check_ok(); +} + /* * get_canonical_locale_name diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index f8174061ef3..75b829e8514 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10766,388 +10766,388 @@ # conversion functions { oid => '4302', descr => 'internal conversion function for KOI8R to MULE_INTERNAL', - proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_mic', + proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4303', descr => 'internal conversion function for MULE_INTERNAL to KOI8R', - proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_koi8r', + proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4304', descr => 'internal conversion function for ISO-8859-5 to MULE_INTERNAL', - proname => 'iso_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_mic', + proname => 'iso_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4305', descr => 'internal conversion function for MULE_INTERNAL to ISO-8859-5', - proname => 'mic_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_iso', + proname => 'mic_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4306', descr => 'internal conversion function for WIN1251 to MULE_INTERNAL', - proname => 'win1251_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_mic', + proname => 'win1251_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4307', descr => 'internal conversion function for MULE_INTERNAL to WIN1251', - proname => 'mic_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1251', + proname => 'mic_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4308', descr => 'internal conversion function for WIN866 to MULE_INTERNAL', - proname => 'win866_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_mic', + proname => 'win866_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4309', descr => 'internal conversion function for MULE_INTERNAL to WIN866', - proname => 'mic_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win866', + proname => 'mic_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4310', descr => 'internal conversion function for KOI8R to WIN1251', - proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4311', descr => 'internal conversion function for WIN1251 to KOI8R', - proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4312', descr => 'internal conversion function for KOI8R to WIN866', - proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_win866', + proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4313', descr => 'internal conversion function for WIN866 to KOI8R', - proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_koi8r', + proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4314', descr => 'internal conversion function for WIN866 to WIN1251', - proname => 'win866_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win866_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4315', descr => 'internal conversion function for WIN1251 to WIN866', - proname => 'win1251_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4316', descr => 'internal conversion function for ISO-8859-5 to KOI8R', - proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_koi8r', + proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4317', descr => 'internal conversion function for KOI8R to ISO-8859-5', - proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_iso', + proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4318', descr => 'internal conversion function for ISO-8859-5 to WIN1251', - proname => 'iso_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win1251', + proname => 'iso_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4319', descr => 'internal conversion function for WIN1251 to ISO-8859-5', - proname => 'win1251_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_iso', + proname => 'win1251_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4320', descr => 'internal conversion function for ISO-8859-5 to WIN866', - proname => 'iso_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win866', + proname => 'iso_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4321', descr => 'internal conversion function for WIN866 to ISO-8859-5', - proname => 'win866_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_iso', + proname => 'win866_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4322', descr => 'internal conversion function for EUC_CN to MULE_INTERNAL', - proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_mic', + proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_mic', probin => '$libdir/euc_cn_and_mic' }, { oid => '4323', descr => 'internal conversion function for MULE_INTERNAL to EUC_CN', - proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_cn', + proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_cn', probin => '$libdir/euc_cn_and_mic' }, { oid => '4324', descr => 'internal conversion function for EUC_JP to SJIS', - proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_sjis', + proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4325', descr => 'internal conversion function for SJIS to EUC_JP', - proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_euc_jp', + proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4326', descr => 'internal conversion function for EUC_JP to MULE_INTERNAL', - proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_mic', + proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4327', descr => 'internal conversion function for SJIS to MULE_INTERNAL', - proname => 'sjis_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_mic', + proname => 'sjis_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4328', descr => 'internal conversion function for MULE_INTERNAL to EUC_JP', - proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_jp', + proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4329', descr => 'internal conversion function for MULE_INTERNAL to SJIS', - proname => 'mic_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_sjis', + proname => 'mic_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4330', descr => 'internal conversion function for EUC_KR to MULE_INTERNAL', - proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_mic', + proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_mic', probin => '$libdir/euc_kr_and_mic' }, { oid => '4331', descr => 'internal conversion function for MULE_INTERNAL to EUC_KR', - proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_kr', + proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_kr', probin => '$libdir/euc_kr_and_mic' }, { oid => '4332', descr => 'internal conversion function for EUC_TW to BIG5', - proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_big5', + proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4333', descr => 'internal conversion function for BIG5 to EUC_TW', - proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_euc_tw', + proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4334', descr => 'internal conversion function for EUC_TW to MULE_INTERNAL', - proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_mic', + proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4335', descr => 'internal conversion function for BIG5 to MULE_INTERNAL', - proname => 'big5_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_mic', + proname => 'big5_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4336', descr => 'internal conversion function for MULE_INTERNAL to EUC_TW', - proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_tw', + proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4337', descr => 'internal conversion function for MULE_INTERNAL to BIG5', - proname => 'mic_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_big5', + proname => 'mic_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4338', descr => 'internal conversion function for LATIN2 to MULE_INTERNAL', - proname => 'latin2_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin2_to_mic', + proname => 'latin2_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4339', descr => 'internal conversion function for MULE_INTERNAL to LATIN2', - proname => 'mic_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin2', + proname => 'mic_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4340', descr => 'internal conversion function for WIN1250 to MULE_INTERNAL', - proname => 'win1250_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1250_to_mic', + proname => 'win1250_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4341', descr => 'internal conversion function for MULE_INTERNAL to WIN1250', - proname => 'mic_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1250', + proname => 'mic_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4342', descr => 'internal conversion function for LATIN2 to WIN1250', - proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4343', descr => 'internal conversion function for WIN1250 to LATIN2', - proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4344', descr => 'internal conversion function for LATIN1 to MULE_INTERNAL', - proname => 'latin1_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin1_to_mic', + proname => 'latin1_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin1_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4345', descr => 'internal conversion function for MULE_INTERNAL to LATIN1', - proname => 'mic_to_latin1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin1', + proname => 'mic_to_latin1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin1', probin => '$libdir/latin_and_mic' }, { oid => '4346', descr => 'internal conversion function for LATIN3 to MULE_INTERNAL', - proname => 'latin3_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin3_to_mic', + proname => 'latin3_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin3_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4347', descr => 'internal conversion function for MULE_INTERNAL to LATIN3', - proname => 'mic_to_latin3', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin3', + proname => 'mic_to_latin3', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin3', probin => '$libdir/latin_and_mic' }, { oid => '4348', descr => 'internal conversion function for LATIN4 to MULE_INTERNAL', - proname => 'latin4_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin4_to_mic', + proname => 'latin4_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin4_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4349', descr => 'internal conversion function for MULE_INTERNAL to LATIN4', - proname => 'mic_to_latin4', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin4', + proname => 'mic_to_latin4', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin4', probin => '$libdir/latin_and_mic' }, { oid => '4352', descr => 'internal conversion function for BIG5 to UTF8', - proname => 'big5_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_utf8', + proname => 'big5_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_utf8', probin => '$libdir/utf8_and_big5' }, { oid => '4353', descr => 'internal conversion function for UTF8 to BIG5', - proname => 'utf8_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_big5', + proname => 'utf8_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_big5', probin => '$libdir/utf8_and_big5' }, { oid => '4354', descr => 'internal conversion function for UTF8 to KOI8R', - proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8r', + proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8r', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4355', descr => 'internal conversion function for KOI8R to UTF8', - proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_utf8', + proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4356', descr => 'internal conversion function for UTF8 to KOI8U', - proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8u', + proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8u', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4357', descr => 'internal conversion function for KOI8U to UTF8', - proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8u_to_utf8', + proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8u_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4358', descr => 'internal conversion function for UTF8 to WIN', - proname => 'utf8_to_win', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_win', + proname => 'utf8_to_win', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_win', probin => '$libdir/utf8_and_win' }, { oid => '4359', descr => 'internal conversion function for WIN to UTF8', - proname => 'win_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win_to_utf8', + proname => 'win_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win_to_utf8', probin => '$libdir/utf8_and_win' }, { oid => '4360', descr => 'internal conversion function for EUC_CN to UTF8', - proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_utf8', + proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_utf8', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4361', descr => 'internal conversion function for UTF8 to EUC_CN', - proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_cn', + proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_cn', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4362', descr => 'internal conversion function for EUC_JP to UTF8', - proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_utf8', + proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_utf8', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4363', descr => 'internal conversion function for UTF8 to EUC_JP', - proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_jp', + proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jp', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4364', descr => 'internal conversion function for EUC_KR to UTF8', - proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_utf8', + proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_utf8', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4365', descr => 'internal conversion function for UTF8 to EUC_KR', - proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_kr', + proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_kr', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4366', descr => 'internal conversion function for EUC_TW to UTF8', - proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_utf8', + proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_utf8', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4367', descr => 'internal conversion function for UTF8 to EUC_TW', - proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_tw', + proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_tw', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4368', descr => 'internal conversion function for GB18030 to UTF8', - proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gb18030_to_utf8', + proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gb18030_to_utf8', probin => '$libdir/utf8_and_gb18030' }, { oid => '4369', descr => 'internal conversion function for UTF8 to GB18030', - proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gb18030', + proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gb18030', probin => '$libdir/utf8_and_gb18030' }, { oid => '4370', descr => 'internal conversion function for GBK to UTF8', - proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gbk_to_utf8', + proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gbk_to_utf8', probin => '$libdir/utf8_and_gbk' }, { oid => '4371', descr => 'internal conversion function for UTF8 to GBK', - proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gbk', + proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gbk', probin => '$libdir/utf8_and_gbk' }, { oid => '4372', descr => 'internal conversion function for UTF8 to ISO-8859 2-16', - proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_iso8859', + proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859', probin => '$libdir/utf8_and_iso8859' }, { oid => '4373', descr => 'internal conversion function for ISO-8859 2-16 to UTF8', - proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso8859_to_utf8', + proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_to_utf8', probin => '$libdir/utf8_and_iso8859' }, { oid => '4374', descr => 'internal conversion function for LATIN1 to UTF8', - proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_1_to_utf8', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4375', descr => 'internal conversion function for UTF8 to LATIN1', - proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859_1', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4376', descr => 'internal conversion function for JOHAB to UTF8', - proname => 'johab_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'johab_to_utf8', + proname => 'johab_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'johab_to_utf8', probin => '$libdir/utf8_and_johab' }, { oid => '4377', descr => 'internal conversion function for UTF8 to JOHAB', - proname => 'utf8_to_johab', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_johab', + proname => 'utf8_to_johab', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_johab', probin => '$libdir/utf8_and_johab' }, { oid => '4378', descr => 'internal conversion function for SJIS to UTF8', - proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_utf8', + proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_utf8', probin => '$libdir/utf8_and_sjis' }, { oid => '4379', descr => 'internal conversion function for UTF8 to SJIS', - proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_sjis', + proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_sjis', probin => '$libdir/utf8_and_sjis' }, { oid => '4380', descr => 'internal conversion function for UHC to UTF8', - proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'uhc_to_utf8', + proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'uhc_to_utf8', probin => '$libdir/utf8_and_uhc' }, { oid => '4381', descr => 'internal conversion function for UTF8 to UHC', - proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_uhc', + proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_uhc', probin => '$libdir/utf8_and_uhc' }, { oid => '4382', descr => 'internal conversion function for EUC_JIS_2004 to UTF8', - proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_utf8', probin => '$libdir/utf8_and_euc2004' }, { oid => '4383', descr => 'internal conversion function for UTF8 to EUC_JIS_2004', - proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jis_2004', probin => '$libdir/utf8_and_euc2004' }, { oid => '4384', descr => 'internal conversion function for SHIFT_JIS_2004 to UTF8', - proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_utf8', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4385', descr => 'internal conversion function for UTF8 to SHIFT_JIS_2004', - proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_shift_jis_2004', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4386', descr => 'internal conversion function for EUC_JIS_2004 to SHIFT_JIS_2004', proname => 'euc_jis_2004_to_shift_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_shift_jis_2004', probin => '$libdir/euc2004_sjis2004' }, { oid => '4387', descr => 'internal conversion function for SHIFT_JIS_2004 to EUC_JIS_2004', proname => 'shift_jis_2004_to_euc_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_euc_jis_2004', probin => '$libdir/euc2004_sjis2004' }, diff --git a/src/include/mb/pg_wchar.h b/src/include/mb/pg_wchar.h index 64b22e4b0d4..346a41a1f3d 100644 --- a/src/include/mb/pg_wchar.h +++ b/src/include/mb/pg_wchar.h @@ -627,18 +627,18 @@ extern void pg_unicode_to_server(pg_wchar c, unsigned char *s); extern unsigned short BIG5toCNS(unsigned short big5, unsigned char *lc); extern unsigned short CNStoBIG5(unsigned short cns, unsigned char lc); -extern void UtfToLocal(const unsigned char *utf, int len, - unsigned char *iso, - const pg_mb_radix_tree *map, - const pg_utf_to_local_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); -extern void LocalToUtf(const unsigned char *iso, int len, - unsigned char *utf, - const pg_mb_radix_tree *map, - const pg_local_to_utf_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); +extern int UtfToLocal(const unsigned char *utf, int len, + unsigned char *iso, + const pg_mb_radix_tree *map, + const pg_utf_to_local_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); +extern int LocalToUtf(const unsigned char *iso, int len, + unsigned char *utf, + const pg_mb_radix_tree *map, + const pg_local_to_utf_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); extern bool pg_verifymbstr(const char *mbstr, int len, bool noError); extern bool pg_verify_mbstr(int encoding, const char *mbstr, int len, @@ -656,18 +656,19 @@ extern void report_invalid_encoding(int encoding, const char *mbstr, int len) pg extern void report_untranslatable_char(int src_encoding, int dest_encoding, const char *mbstr, int len) pg_attribute_noreturn(); -extern void local2local(const unsigned char *l, unsigned char *p, int len, - int src_encoding, int dest_encoding, const unsigned char *tab); -extern void latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding); -extern void mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding); -extern void latin2mic_with_table(const unsigned char *l, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); -extern void mic2latin_with_table(const unsigned char *mic, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); +extern int local2local(const unsigned char *l, unsigned char *p, int len, + int src_encoding, int dest_encoding, const unsigned char *tab, + bool noError); +extern int latin2mic(const unsigned char *l, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int mic2latin(const unsigned char *mic, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int latin2mic_with_table(const unsigned char *l, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); +extern int mic2latin_with_table(const unsigned char *mic, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); #ifdef WIN32 extern WCHAR *pgwin32_message_to_UTF16(const char *str, int len, int *utf16len); diff --git a/src/test/regress/expected/opr_sanity.out b/src/test/regress/expected/opr_sanity.out index 254ca06d3dd..23ba60e395f 100644 --- a/src/test/regress/expected/opr_sanity.out +++ b/src/test/regress/expected/opr_sanity.out @@ -1052,13 +1052,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); oid | proname | oid | conname -----+---------+-----+--------- (0 rows) diff --git a/src/test/regress/sql/opr_sanity.sql b/src/test/regress/sql/opr_sanity.sql index bbd3834b634..04691745981 100644 --- a/src/test/regress/sql/opr_sanity.sql +++ b/src/test/regress/sql/opr_sanity.sql @@ -556,13 +556,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); -- Check for conprocs that don't perform the specific conversion that -- pg_conversion alleges they do, by trying to invoke each conversion -- 2.29.2 --------------39E46EF15EBFAA37D53332E5 Content-Type: text/x-patch; charset=UTF-8; name="v3-0003-Add-tests-for-the-new-noError-variants-of-built-i.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="v3-0003-Add-tests-for-the-new-noError-variants-of-built-i.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 34+ messages in thread
* [PATCH v3 2/5] Change conversion function signature. @ 2021-01-28 16:42 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 34+ messages in thread From: Heikki Linnakangas @ 2021-01-28 16:42 UTC (permalink / raw) Add a 'noError' argument, so that we can try to convert a buffer without knowing the character boundaries beforehand. The functions now need to return the number of input bytes successfully converted. This is is a backwards-incompatible change, if you have created a custom encoding conversion with CREATE CONVERSION. This adds a check to pg_upgrade for that, refusing the upgrade if there are any user-defined encoding conversions. --- doc/src/sgml/ref/create_conversion.sgml | 5 +- src/backend/commands/conversioncmds.c | 27 +- src/backend/utils/error/elog.c | 2 + src/backend/utils/mb/conv.c | 112 +++++- .../cyrillic_and_mic/cyrillic_and_mic.c | 127 ++++--- .../euc2004_sjis2004/euc2004_sjis2004.c | 96 ++++- .../euc_cn_and_mic/euc_cn_and_mic.c | 57 ++- .../euc_jp_and_sjis/euc_jp_and_sjis.c | 153 ++++++-- .../euc_kr_and_mic/euc_kr_and_mic.c | 57 ++- .../euc_tw_and_big5/euc_tw_and_big5.c | 165 +++++++-- .../latin2_and_win1250/latin2_and_win1250.c | 49 ++- .../latin_and_mic/latin_and_mic.c | 43 ++- .../utf8_and_big5/utf8_and_big5.c | 37 +- .../utf8_and_cyrillic/utf8_and_cyrillic.c | 67 ++-- .../utf8_and_euc2004/utf8_and_euc2004.c | 37 +- .../utf8_and_euc_cn/utf8_and_euc_cn.c | 37 +- .../utf8_and_euc_jp/utf8_and_euc_jp.c | 37 +- .../utf8_and_euc_kr/utf8_and_euc_kr.c | 37 +- .../utf8_and_euc_tw/utf8_and_euc_tw.c | 37 +- .../utf8_and_gb18030/utf8_and_gb18030.c | 37 +- .../utf8_and_gbk/utf8_and_gbk.c | 37 +- .../utf8_and_iso8859/utf8_and_iso8859.c | 43 ++- .../utf8_and_iso8859_1/utf8_and_iso8859_1.c | 27 +- .../utf8_and_johab/utf8_and_johab.c | 37 +- .../utf8_and_sjis/utf8_and_sjis.c | 37 +- .../utf8_and_sjis2004/utf8_and_sjis2004.c | 37 +- .../utf8_and_uhc/utf8_and_uhc.c | 37 +- .../utf8_and_win/utf8_and_win.c | 43 ++- src/backend/utils/mb/mbutils.c | 18 +- src/bin/pg_upgrade/check.c | 95 +++++ src/include/catalog/pg_proc.dat | 332 +++++++++--------- src/include/mb/pg_wchar.h | 49 +-- src/test/regress/expected/opr_sanity.out | 7 +- src/test/regress/sql/opr_sanity.sql | 7 +- 34 files changed, 1390 insertions(+), 635 deletions(-) diff --git a/doc/src/sgml/ref/create_conversion.sgml b/doc/src/sgml/ref/create_conversion.sgml index e7700fecfc5..f014a676c88 100644 --- a/doc/src/sgml/ref/create_conversion.sgml +++ b/doc/src/sgml/ref/create_conversion.sgml @@ -117,8 +117,9 @@ conv_proc( integer, -- destination encoding ID cstring, -- source string (null terminated C string) internal, -- destination (fill with a null terminated C string) - integer -- source string length -) RETURNS void; + integer, -- source string length + boolean -- if true, don't throw an error if conversion fails +) RETURNS integer; </programlisting></para> </listitem> </varlistentry> diff --git a/src/backend/commands/conversioncmds.c b/src/backend/commands/conversioncmds.c index f7ff321de71..d2041466911 100644 --- a/src/backend/commands/conversioncmds.c +++ b/src/backend/commands/conversioncmds.c @@ -45,8 +45,9 @@ CreateConversionCommand(CreateConversionStmt *stmt) const char *from_encoding_name = stmt->for_encoding_name; const char *to_encoding_name = stmt->to_encoding_name; List *func_name = stmt->func_name; - static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID}; + static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID, BOOLOID}; char result[1]; + Datum funcresult; /* Convert list of names to a name and namespace */ namespaceId = QualifiedNameGetCreationNamespace(stmt->conversion_name, @@ -92,8 +93,8 @@ CreateConversionCommand(CreateConversionStmt *stmt) funcoid = LookupFuncName(func_name, sizeof(funcargs) / sizeof(Oid), funcargs, false); - /* Check it returns VOID, else it's probably the wrong function */ - if (get_func_rettype(funcoid) != VOIDOID) + /* Check it returns int4, else it's probably the wrong function */ + if (get_func_rettype(funcoid) != INT4OID) ereport(ERROR, (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), errmsg("encoding conversion function %s must return type %s", @@ -111,12 +112,20 @@ CreateConversionCommand(CreateConversionStmt *stmt) * string; the conversion function should throw an error if it can't * perform the requested conversion. */ - OidFunctionCall5(funcoid, - Int32GetDatum(from_encoding), - Int32GetDatum(to_encoding), - CStringGetDatum(""), - CStringGetDatum(result), - Int32GetDatum(0)); + funcresult = OidFunctionCall6(funcoid, + Int32GetDatum(from_encoding), + Int32GetDatum(to_encoding), + CStringGetDatum(""), + CStringGetDatum(result), + Int32GetDatum(0), + BoolGetDatum(false)); + + /* The function should return 0 for empty input. Might as well check that, too. */ + if (DatumGetInt32(funcresult) != 0) + ereport(ERROR, + (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), + errmsg("encoding conversion function %s returned incorrect result for empty input", + NameListToString(func_name)))); /* * All seem ok, go ahead (possible failure would be a duplicate conversion diff --git a/src/backend/utils/error/elog.c b/src/backend/utils/error/elog.c index 80c26724612..762f77d533c 100644 --- a/src/backend/utils/error/elog.c +++ b/src/backend/utils/error/elog.c @@ -2280,6 +2280,8 @@ write_console(const char *line, int len) * Conversion on non-win32 platforms is not implemented yet. It requires * non-throw version of pg_do_encoding_conversion(), that converts * unconvertable characters to '?' without errors. + * + * XXX: We have a no-throw version now. It doesn't convert to '?' though. */ #endif diff --git a/src/backend/utils/mb/conv.c b/src/backend/utils/mb/conv.c index a07b54bd3b8..b83358bc7a5 100644 --- a/src/backend/utils/mb/conv.c +++ b/src/backend/utils/mb/conv.c @@ -26,14 +26,16 @@ * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the target charset, or 0 if there is no equivalent code. */ -void +int local2local(const unsigned char *l, unsigned char *p, int len, int src_encoding, int dest_encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -41,7 +43,11 @@ local2local(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(src_encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -50,13 +56,19 @@ local2local(const unsigned char *l, if (c2) *p++ = c2; else + { + if (noError) + break; report_untranslatable_char(src_encoding, dest_encoding, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -67,17 +79,22 @@ local2local(const unsigned char *l, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = l; int c1; while (len > 0) { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (IS_HIGHBIT_SET(c1)) *p++ = lc; *p++ = c1; @@ -85,6 +102,8 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, len--; } *p = '\0'; + + return l - start; } /* @@ -95,17 +114,22 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -118,17 +142,27 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1])) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); + } *p++ = mic[1]; mic += 2; len -= 2; } } *p = '\0'; + + return mic - start; } @@ -144,14 +178,16 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the mule encoding, or 0 if there is no equivalent code. */ -void +int latin2mic_with_table(const unsigned char *l, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -159,7 +195,11 @@ latin2mic_with_table(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -171,13 +211,19 @@ latin2mic_with_table(const unsigned char *l, *p++ = c2; } else + { + if (noError) + break; report_untranslatable_char(encoding, PG_MULE_INTERNAL, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -192,14 +238,16 @@ latin2mic_with_table(const unsigned char *l, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the local charset, or 0 if there is no equivalent code. */ -void +int mic2latin_with_table(const unsigned char *mic, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = mic; unsigned char c1, c2; @@ -207,7 +255,11 @@ mic2latin_with_table(const unsigned char *mic, { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -220,11 +272,17 @@ mic2latin_with_table(const unsigned char *mic, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1]) || (c2 = tab[mic[1] - HIGHBIT]) == 0) { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); break; /* keep compiler quiet */ @@ -235,6 +293,8 @@ mic2latin_with_table(const unsigned char *mic, } } *p = '\0'; + + return mic - start; } /* @@ -425,17 +485,19 @@ pg_mb_radix_conv(const pg_mb_radix_tree *rt, * * See pg_wchar.h for more details about the data structures used here. */ -void +int UtfToLocal(const unsigned char *utf, int len, unsigned char *iso, const pg_mb_radix_tree *map, const pg_utf_to_local_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, bool noError) { uint32 iutf; int l; const pg_utf_to_local_combined *cp; + const unsigned char *start = utf; + const unsigned char *cur = utf; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -449,6 +511,8 @@ UtfToLocal(const unsigned char *utf, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*utf == '\0') break; @@ -584,15 +648,19 @@ UtfToLocal(const unsigned char *utf, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(PG_UTF8, encoding, (const char *) (utf - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(PG_UTF8, (const char *) utf, len); *iso = '\0'; + + return cur - start; } /* @@ -616,18 +684,24 @@ UtfToLocal(const unsigned char *utf, int len, * (if provided) is applied. An error is raised if no match is found. * * See pg_wchar.h for more details about the data structures used here. + * + * Returns the number of input bytes consumed. If noError is true, this can + * be less than 'len'. */ -void +int LocalToUtf(const unsigned char *iso, int len, unsigned char *utf, const pg_mb_radix_tree *map, const pg_local_to_utf_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, + bool noError) { uint32 iiso; int l; const pg_local_to_utf_combined *cp; + const unsigned char *start = iso; + const unsigned char *cur = iso; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -641,6 +715,8 @@ LocalToUtf(const unsigned char *iso, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*iso == '\0') break; @@ -723,13 +799,17 @@ LocalToUtf(const unsigned char *iso, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(encoding, PG_UTF8, (const char *) (iso - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(encoding, (const char *) iso, len); *utf = '\0'; + + return cur - start; } diff --git a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c index 4c5b02654de..368c2deb5e4 100644 --- a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c @@ -44,8 +44,11 @@ PG_FUNCTION_INFO_V1(win866_to_iso); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -306,12 +309,14 @@ koi8r_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -320,12 +325,14 @@ mic_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_KOI8R); - mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -334,12 +341,14 @@ iso_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -348,12 +357,14 @@ mic_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_ISO_8859_5); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -362,12 +373,14 @@ win1251_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -376,12 +389,14 @@ mic_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1251); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -390,12 +405,14 @@ win866_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -404,12 +421,14 @@ mic_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN866); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -418,12 +437,14 @@ koi8r_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN1251); - local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -432,12 +453,14 @@ win1251_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_KOI8R); - local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi); + converted = local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -446,12 +469,14 @@ koi8r_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN866); - local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -460,12 +485,14 @@ win866_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_KOI8R); - local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi); + converted = local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -474,12 +501,14 @@ win866_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_WIN1251); - local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251); + converted = local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -488,12 +517,14 @@ win1251_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_WIN866); - local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866); + converted = local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -502,12 +533,14 @@ iso_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_KOI8R); - local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -516,12 +549,14 @@ koi8r_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_ISO_8859_5); - local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso); + converted = local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -530,12 +565,14 @@ iso_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN1251); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -544,12 +581,14 @@ win1251_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso); + converted = local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -558,12 +597,14 @@ iso_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN866); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -572,10 +613,12 @@ win866_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso); + converted = local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c index 4d7fb116cfd..88529c644cf 100644 --- a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c @@ -19,8 +19,8 @@ PG_MODULE_MAGIC; PG_FUNCTION_INFO_V1(euc_jis_2004_to_shift_jis_2004); PG_FUNCTION_INFO_V1(shift_jis_2004_to_euc_jis_2004); -static void euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len); -static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len); +static int euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError); /* ---------- * conv_proc( @@ -28,8 +28,11 @@ static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -39,12 +42,14 @@ euc_jis_2004_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_SHIFT_JIS_2004); - euc_jis_20042shift_jis_2004(src, dest, len); + converted = euc_jis_20042shift_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -53,20 +58,23 @@ shift_jis_2004_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_EUC_JIS_2004); - shift_jis_20042euc_jis_2004(src, dest, len); + converted = shift_jis_20042euc_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_JIS_2004 -> SHIFT_JIS_2004 */ -static void -euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, ku, ten; @@ -79,8 +87,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -90,8 +102,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) l = pg_encoding_verifymbchar(PG_EUC_JIS_2004, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (c1 == SS2 && l == 2) /* JIS X 0201 kana? */ { @@ -121,8 +137,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) *p++ = (ku + 0x19b) >> 1; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } if (ku % 2) @@ -132,8 +152,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; @@ -149,8 +173,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ku >= 63 && ku <= 94) *p++ = (ku + 0x181) >> 1; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (ku % 2) { @@ -159,20 +187,30 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else - report_invalid_encoding(PG_EUC_JIS_2004, + { + if (noError) + break; + report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } euc += l; len -= l; } *p = '\0'; + + return euc - start; } /* @@ -212,9 +250,10 @@ get_ten(int b, int *ku) * SHIFT_JIS_2004 ---> EUC_JIS_2004 */ -static void -shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len) +static int +shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1; int ku, ten, @@ -230,8 +269,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -241,8 +284,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len l = pg_encoding_verifymbchar(PG_SHIFT_JIS_2004, (const char *) sjis, len); if (l < 0 || l > len) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf && l == 1) { @@ -266,8 +313,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x100; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xe0 && c1 <= 0xef) /* plane 1 62ku-94ku */ @@ -275,9 +326,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x180; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, - (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xf0 && c1 <= 0xf3) /* plane 2 @@ -286,8 +340,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } switch (c1) { case 0xf0: @@ -309,16 +367,24 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 == 0xf4 && kubun == 1) ku = 15; else ku = (c1 << 1) - 0x19a - kubun; } else + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (plane == 2) *p++ = SS3; @@ -330,4 +396,6 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c index e9bb896935f..a8da733803d 100644 --- a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_cn2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_cn(const unsigned char *mic, unsigned char *p, int len); +static int euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_cn_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_cn_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_MULE_INTERNAL); - euc_cn2mic(src, dest, len); + converted = euc_cn2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_CN); - mic2euc_cn(src, dest, len); + converted = mic2euc_cn(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_CN ---> MIC */ -static void -euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; while (len > 0) @@ -76,7 +84,11 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (len < 2 || !IS_HIGHBIT_SET(euc[1])) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = LC_GB2312_80; *p++ = c1; *p++ = euc[1]; @@ -86,21 +98,28 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_CN */ -static void -mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) @@ -109,11 +128,19 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (c1 != LC_GB2312_80) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_CN, (const char *) mic, len); + } if (len < 3 || !IS_HIGHBIT_SET(mic[1]) || !IS_HIGHBIT_SET(mic[2])) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } mic++; *p++ = *mic++; *p++ = *mic++; @@ -122,12 +149,18 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; } } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c index 5059f917a98..cc4817dc4cd 100644 --- a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c @@ -42,17 +42,20 @@ PG_FUNCTION_INFO_V1(mic_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void sjis2mic(const unsigned char *sjis, unsigned char *p, int len); -static void mic2sjis(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_jp(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len); -static void sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len); +static int sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError); +static int mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_jp_to_sjis(PG_FUNCTION_ARGS) @@ -60,12 +63,14 @@ euc_jp_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_SJIS); - euc_jp2sjis(src, dest, len); + converted = euc_jp2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -74,12 +79,14 @@ sjis_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_EUC_JP); - sjis2euc_jp(src, dest, len); + converted = sjis2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -88,12 +95,14 @@ euc_jp_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_MULE_INTERNAL); - euc_jp2mic(src, dest, len); + converted = euc_jp2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -102,12 +111,14 @@ mic_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_JP); - mic2euc_jp(src, dest, len); + converted = mic2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -116,12 +127,14 @@ sjis_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_MULE_INTERNAL); - sjis2mic(src, dest, len); + converted = sjis2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -130,20 +143,23 @@ mic_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_SJIS); - mic2sjis(src, dest, len); + converted = mic2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * SJIS ---> MIC */ -static void -sjis2mic(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -167,7 +183,11 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) * JIS X0208, X0212, user defined extended characters */ if (len < 2 || !ISSJISHEAD(c1) || !ISSJISTAIL(sjis[1])) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } c2 = sjis[1]; k = (c1 << 8) + c2; if (k >= 0xed40 && k < 0xf040) @@ -257,21 +277,28 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; } } *p = '\0'; + + return sjis - start; } /* * MIC ---> SJIS */ -static void -mic2sjis(const unsigned char *mic, unsigned char *p, int len) +static int +mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1, c2, k, @@ -284,8 +311,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -293,8 +324,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) *p++ = mic[1]; else if (c1 == LC_JISX0208) @@ -350,20 +385,27 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_SJIS, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP ---> MIC */ -static void -euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -374,8 +416,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -383,8 +429,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* 1 byte kana? */ *p++ = LC_JISX0201K; @@ -406,14 +456,17 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_JP */ -static void -mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -424,8 +477,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -433,8 +490,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) { *p++ = SS2; @@ -452,20 +513,27 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_JP, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP -> SJIS */ -static void -euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, c2, k; @@ -478,8 +546,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -487,8 +559,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* hankaku kana? */ @@ -551,14 +627,17 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * SJIS ---> EUC_JP */ -static void -sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -573,8 +652,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -582,8 +665,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_SJIS, (const char *) sjis, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf) { /* JIS X0201 (1 byte kana) */ @@ -680,4 +767,6 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c index ac823d6c270..a5b51617e52 100644 --- a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_kr2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_kr(const unsigned char *mic, unsigned char *p, int len); +static int euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_kr_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_kr_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_MULE_INTERNAL); - euc_kr2mic(src, dest, len); + converted = euc_kr2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_KR); - mic2euc_kr(src, dest, len); + converted = mic2euc_kr(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_KR ---> MIC */ -static void -euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -78,8 +86,12 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_KR, (const char *) euc, len); if (l != 2) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = LC_KS5601; *p++ = c1; *p++ = euc[1]; @@ -89,22 +101,29 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_KR */ -static void -mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -115,8 +134,12 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -124,18 +147,28 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_KS5601) { *p++ = mic[1]; *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_KR, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c index 66c242d7f36..ebb4e0acd53 100644 --- a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c @@ -32,17 +32,20 @@ PG_FUNCTION_INFO_V1(mic_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_tw2big5(const unsigned char *euc, unsigned char *p, int len); -static void big52euc_tw(const unsigned char *euc, unsigned char *p, int len); -static void big52mic(const unsigned char *big5, unsigned char *p, int len); -static void mic2big5(const unsigned char *mic, unsigned char *p, int len); -static void euc_tw2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_tw(const unsigned char *mic, unsigned char *p, int len); +static int euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52euc_tw(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError); +static int mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_tw_to_big5(PG_FUNCTION_ARGS) @@ -50,12 +53,14 @@ euc_tw_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_BIG5); - euc_tw2big5(src, dest, len); + converted = euc_tw2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -64,12 +69,14 @@ big5_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_EUC_TW); - big52euc_tw(src, dest, len); + converted = big52euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -78,12 +85,14 @@ euc_tw_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_MULE_INTERNAL); - euc_tw2mic(src, dest, len); + converted = euc_tw2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -92,12 +101,14 @@ mic_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_TW); - mic2euc_tw(src, dest, len); + converted = mic2euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -106,12 +117,14 @@ big5_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_MULE_INTERNAL); - big52mic(src, dest, len); + converted = big52mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -120,21 +133,24 @@ mic_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_BIG5); - mic2big5(src, dest, len); + converted = mic2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_TW ---> Big5 */ -static void -euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; unsigned char c1; unsigned short big5buf, cnsBuf; @@ -149,8 +165,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Verify and decode the next EUC_TW input character */ l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -171,8 +191,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Write it out in Big5 */ big5buf = CNStoBIG5(cnsBuf, lc); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_EUC_TW, PG_BIG5, (const char *) euc, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; @@ -182,22 +206,29 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * Big5 ---> EUC_TW */ -static void -big52euc_tw(const unsigned char *big5, unsigned char *p, int len) +static int +big52euc_tw(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -212,8 +243,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); @@ -237,8 +272,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_EUC_TW, (const char *) big5, len); + } big5 += l; len -= l; @@ -256,14 +295,17 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) } } *p = '\0'; + + return big5 - start; } /* * EUC_TW ---> MIC */ -static void -euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -274,8 +316,12 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -304,22 +350,29 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_TW */ -static void -mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -330,8 +383,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -339,8 +396,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1) { *p++ = mic[1]; @@ -362,20 +423,27 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[3]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_TW, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * Big5 ---> MIC */ -static void -big52mic(const unsigned char *big5, unsigned char *p, int len) +static int +big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -389,8 +457,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } *p++ = c1; big5++; len--; @@ -398,8 +470,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); if (lc != 0) @@ -412,20 +488,27 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_MULE_INTERNAL, (const char *) big5, len); + } big5 += l; len -= l; } *p = '\0'; + + return big5 - start; } /* * MIC ---> Big5 */ -static void -mic2big5(const unsigned char *mic, unsigned char *p, int len) +static int +mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -438,8 +521,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -447,8 +534,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1 || c1 == LC_CNS11643_2 || c1 == LCPRV2_B) { if (c1 == LCPRV2_B) @@ -462,16 +553,26 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } big5buf = CNStoBIG5(cnsBuf, c1); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c index 2e28e6780a5..8610fcb69aa 100644 --- a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c +++ b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(win1250_to_latin2); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -82,12 +85,14 @@ latin2_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -96,12 +101,14 @@ mic_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN2); - mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -110,13 +117,15 @@ win1250_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - win1250_2_iso88592); + converted = latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -125,13 +134,15 @@ mic_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1250); - mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - iso88592_2_win1250); + converted = mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -140,12 +151,15 @@ latin2_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_WIN1250); - local2local(src, dest, len, PG_LATIN2, PG_WIN1250, iso88592_2_win1250); + converted = local2local(src, dest, len, PG_LATIN2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -154,10 +168,13 @@ win1250_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_LATIN2); - local2local(src, dest, len, PG_WIN1250, PG_LATIN2, win1250_2_iso88592); + converted = local2local(src, dest, len, PG_WIN1250, PG_LATIN2, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c index bc651410f21..bff27d1c295 100644 --- a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(mic_to_latin4); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -42,12 +45,14 @@ latin1_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,12 +61,14 @@ mic_to_latin1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN1); - mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -70,12 +77,14 @@ latin3_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN3, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -84,12 +93,14 @@ mic_to_latin3(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN3); - mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,12 +109,14 @@ latin4_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN4, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -112,10 +125,12 @@ mic_to_latin4(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN4); - mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c index d6067cdc24e..3838b15cab9 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ big5_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_UTF8); - LocalToUtf(src, len, dest, - &big5_to_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = LocalToUtf(src, len, dest, + &big5_to_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_BIG5); - UtfToLocal(src, len, dest, - &big5_from_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = UtfToLocal(src, len, dest, + &big5_from_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c index ed90e8e682e..75719fe5f1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c @@ -33,8 +33,11 @@ PG_FUNCTION_INFO_V1(koi8u_to_utf8); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -44,16 +47,19 @@ utf8_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8R); - UtfToLocal(src, len, dest, - &koi8r_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = UtfToLocal(src, len, dest, + &koi8r_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -62,16 +68,19 @@ koi8r_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8r_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = LocalToUtf(src, len, dest, + &koi8r_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -80,16 +89,19 @@ utf8_to_koi8u(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8U); - UtfToLocal(src, len, dest, - &koi8u_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = UtfToLocal(src, len, dest, + &koi8u_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,14 +110,17 @@ koi8u_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8U, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8u_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = LocalToUtf(src, len, dest, + &koi8u_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c index d699affce47..5391001951a 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jis_2004_to_unicode_tree, - LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = LocalToUtf(src, len, dest, + &euc_jis_2004_to_unicode_tree, + LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JIS_2004); - UtfToLocal(src, len, dest, - &euc_jis_2004_from_unicode_tree, - ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = UtfToLocal(src, len, dest, + &euc_jis_2004_from_unicode_tree, + ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c index d7c0ba6a58b..c87d1bf2398 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_cn_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_cn_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = LocalToUtf(src, len, dest, + &euc_cn_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_CN); - UtfToLocal(src, len, dest, - &euc_cn_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = UtfToLocal(src, len, dest, + &euc_cn_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c index 13a3a23e77b..6a55134db21 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jp); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jp_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jp_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = LocalToUtf(src, len, dest, + &euc_jp_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JP); - UtfToLocal(src, len, dest, - &euc_jp_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = UtfToLocal(src, len, dest, + &euc_jp_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c index 1bbb8aaef7b..fe1924e2fec 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_kr_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_kr_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = LocalToUtf(src, len, dest, + &euc_kr_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_KR); - UtfToLocal(src, len, dest, - &euc_kr_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = UtfToLocal(src, len, dest, + &euc_kr_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c index 9830045dccd..68215659b57 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_tw); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_tw_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_tw_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = LocalToUtf(src, len, dest, + &euc_tw_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_TW); - UtfToLocal(src, len, dest, - &euc_tw_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = UtfToLocal(src, len, dest, + &euc_tw_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c index f86ecf27424..e1a59c39a4d 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c @@ -183,8 +183,11 @@ conv_utf8_to_18030(uint32 code) * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -193,16 +196,19 @@ gb18030_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GB18030, PG_UTF8); - LocalToUtf(src, len, dest, - &gb18030_to_unicode_tree, - NULL, 0, - conv_18030_to_utf8, - PG_GB18030); + converted = LocalToUtf(src, len, dest, + &gb18030_to_unicode_tree, + NULL, 0, + conv_18030_to_utf8, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -211,14 +217,17 @@ utf8_to_gb18030(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GB18030); - UtfToLocal(src, len, dest, - &gb18030_from_unicode_tree, - NULL, 0, - conv_utf8_to_18030, - PG_GB18030); + converted = UtfToLocal(src, len, dest, + &gb18030_from_unicode_tree, + NULL, 0, + conv_utf8_to_18030, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c index 2ab8b16c8a8..881386d5347 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_gbk); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ gbk_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GBK, PG_UTF8); - LocalToUtf(src, len, dest, - &gbk_to_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = LocalToUtf(src, len, dest, + &gbk_to_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_gbk(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GBK); - UtfToLocal(src, len, dest, - &gbk_from_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = UtfToLocal(src, len, dest, + &gbk_from_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c index 3e49f67ea2f..d93a521badf 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c @@ -52,8 +52,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -100,6 +103,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -108,12 +112,15 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -122,7 +129,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -132,6 +139,7 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -140,12 +148,15 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -154,5 +165,5 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c index 67e713cca11..8ac93604a1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c @@ -26,8 +26,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859_1); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -37,6 +40,8 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_UTF8); @@ -45,7 +50,11 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_LATIN1, (const char *) src, len); + } if (!IS_HIGHBIT_SET(c)) *dest++ = c; else @@ -58,7 +67,7 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } Datum @@ -67,6 +76,8 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c, c1; @@ -76,7 +87,11 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_UTF8, (const char *) src, len); + } /* fast path for ASCII-subset characters */ if (!IS_HIGHBIT_SET(c)) { @@ -102,11 +117,15 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) len -= 2; } else + { + if (noError) + break; report_untranslatable_char(PG_UTF8, PG_LATIN1, (const char *) src, len); + } } } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c index 578f5df4e7f..317daa2d5ee 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_johab); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ johab_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_JOHAB, PG_UTF8); - LocalToUtf(src, len, dest, - &johab_to_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = LocalToUtf(src, len, dest, + &johab_to_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_johab(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_JOHAB); - UtfToLocal(src, len, dest, - &johab_from_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = UtfToLocal(src, len, dest, + &johab_from_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c index dd9fc2975ad..4c9348aba59 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ sjis_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_UTF8); - LocalToUtf(src, len, dest, - &sjis_to_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = LocalToUtf(src, len, dest, + &sjis_to_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SJIS); - UtfToLocal(src, len, dest, - &sjis_from_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = UtfToLocal(src, len, dest, + &sjis_from_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c index 4bcc886d674..1fffdc5930c 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_shift_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ shift_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &shift_jis_2004_to_unicode_tree, - LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = LocalToUtf(src, len, dest, + &shift_jis_2004_to_unicode_tree, + LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SHIFT_JIS_2004); - UtfToLocal(src, len, dest, - &shift_jis_2004_from_unicode_tree, - ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = UtfToLocal(src, len, dest, + &shift_jis_2004_from_unicode_tree, + ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c index c8e512994a1..d9471dad097 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_uhc); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ uhc_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UHC, PG_UTF8); - LocalToUtf(src, len, dest, - &uhc_to_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = LocalToUtf(src, len, dest, + &uhc_to_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_uhc(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_UHC); - UtfToLocal(src, len, dest, - &uhc_from_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = UtfToLocal(src, len, dest, + &uhc_from_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c index 0c9493dee56..110ba5677d0 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c @@ -48,8 +48,11 @@ PG_FUNCTION_INFO_V1(utf8_to_win); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -81,6 +84,7 @@ win_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -89,12 +93,15 @@ win_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -103,7 +110,7 @@ win_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -113,6 +120,7 @@ utf8_to_win(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -121,12 +129,15 @@ utf8_to_win(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -135,5 +146,5 @@ utf8_to_win(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/mbutils.c b/src/backend/utils/mb/mbutils.c index 2578573b0ab..65753860e35 100644 --- a/src/backend/utils/mb/mbutils.c +++ b/src/backend/utils/mb/mbutils.c @@ -406,12 +406,13 @@ pg_do_encoding_conversion(unsigned char *src, int len, MemoryContextAllocHuge(CurrentMemoryContext, (Size) len * MAX_CONVERSION_GROWTH + 1); - OidFunctionCall5(proc, - Int32GetDatum(src_encoding), - Int32GetDatum(dest_encoding), - CStringGetDatum(src), - CStringGetDatum(result), - Int32GetDatum(len)); + (void) OidFunctionCall6(proc, + Int32GetDatum(src_encoding), + Int32GetDatum(dest_encoding), + CStringGetDatum(src), + CStringGetDatum(result), + Int32GetDatum(len), + BoolGetDatum(false)); /* * If the result is large, it's worth repalloc'ing to release any extra @@ -849,12 +850,13 @@ pg_unicode_to_server(pg_wchar c, unsigned char *s) c_as_utf8[c_as_utf8_len] = '\0'; /* Convert, or throw error if we can't */ - FunctionCall5(Utf8ToServerConvProc, + FunctionCall6(Utf8ToServerConvProc, Int32GetDatum(PG_UTF8), Int32GetDatum(server_encoding), CStringGetDatum(c_as_utf8), CStringGetDatum(s), - Int32GetDatum(c_as_utf8_len)); + Int32GetDatum(c_as_utf8_len), + BoolGetDatum(false)); } diff --git a/src/bin/pg_upgrade/check.c b/src/bin/pg_upgrade/check.c index 43fc297eb69..ee6be95b08d 100644 --- a/src/bin/pg_upgrade/check.c +++ b/src/bin/pg_upgrade/check.c @@ -28,6 +28,7 @@ static void check_for_reg_data_type_usage(ClusterInfo *cluster); static void check_for_jsonb_9_4_usage(ClusterInfo *cluster); static void check_for_pg_role_prefix(ClusterInfo *cluster); static void check_for_new_tablespace_dir(ClusterInfo *new_cluster); +static void check_for_user_defined_encoding_conversions(ClusterInfo *cluster); static char *get_canonical_locale_name(int category, const char *locale); @@ -102,6 +103,15 @@ check_and_dump_old_cluster(bool live_check) check_for_reg_data_type_usage(&old_cluster); check_for_isn_and_int8_passing_mismatch(&old_cluster); + /* + * PG 14 changed the function signature of encoding conversion functions. + * Conversions from older versions cannot be upgraded automatically + * because the user-defined functions used by the encoding conversions + * need to changed to match the new signature. + */ + if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1300) + check_for_user_defined_encoding_conversions(&old_cluster); + /* * Pre-PG 14 allowed user defined postfix operators, which are not * supported anymore. Verify there are none, iff applicable. @@ -1268,6 +1278,91 @@ check_for_pg_role_prefix(ClusterInfo *cluster) check_ok(); } +/* + * Verify that no user-defined encoding conversions exist. + */ +static void +check_for_user_defined_encoding_conversions(ClusterInfo *cluster) +{ + int dbnum; + FILE *script = NULL; + bool found = false; + char output_path[MAXPGPATH]; + + prep_status("Checking for user-defined encoding conversions"); + + snprintf(output_path, sizeof(output_path), + "encoding_conversions.txt"); + + /* Find any user defined encoding conversions */ + for (dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++) + { + PGresult *res; + bool db_used = false; + int ntups; + int rowno; + int i_conoid, + i_conname, + i_nspname; + DbInfo *active_db = &cluster->dbarr.dbs[dbnum]; + PGconn *conn = connectToServer(cluster, active_db->db_name); + + /* + * The query below hardcodes FirstNormalObjectId as 16384 rather than + * interpolating that C #define into the query because, if that + * #define is ever changed, the cutoff we want to use is the value + * used by pre-version 14 servers, not that of some future version. + */ + res = executeQueryOrDie(conn, + "SELECT c.oid as conoid, c.conname, n.nspname " + "FROM pg_catalog.pg_conversion c, " + " pg_catalog.pg_namespace n " + "WHERE c.connamespace = n.oid AND " + " c.oid >= 16384"); + ntups = PQntuples(res); + i_conoid = PQfnumber(res, "conoid"); + i_conname = PQfnumber(res, "conname"); + i_nspname = PQfnumber(res, "nspname"); + for (rowno = 0; rowno < ntups; rowno++) + { + found = true; + if (script == NULL && + (script = fopen_priv(output_path, "w")) == NULL) + pg_fatal("could not open file \"%s\": %s\n", + output_path, strerror(errno)); + if (!db_used) + { + fprintf(script, "In database: %s\n", active_db->db_name); + db_used = true; + } + fprintf(script, " (oid=%s) %s.%s\n", + PQgetvalue(res, rowno, i_conoid), + PQgetvalue(res, rowno, i_nspname), + PQgetvalue(res, rowno, i_conname)); + } + + PQclear(res); + + PQfinish(conn); + } + + if (script) + fclose(script); + + if (found) + { + pg_log(PG_REPORT, "fatal\n"); + pg_fatal("Your installation contains user-defined encoding conversions.\n" + "The conversion function parameters changed in PostgreSQL version 14\n" + "so this cluster cannot currently be upgraded. You can remove the\n" + "encoding conversions in the old cluster and restart the upgrade.\n" + "A list of user-defined encoding conversions is in the file:\n" + " %s\n\n", output_path); + } + else + check_ok(); +} + /* * get_canonical_locale_name diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index f8174061ef3..75b829e8514 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10766,388 +10766,388 @@ # conversion functions { oid => '4302', descr => 'internal conversion function for KOI8R to MULE_INTERNAL', - proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_mic', + proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4303', descr => 'internal conversion function for MULE_INTERNAL to KOI8R', - proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_koi8r', + proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4304', descr => 'internal conversion function for ISO-8859-5 to MULE_INTERNAL', - proname => 'iso_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_mic', + proname => 'iso_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4305', descr => 'internal conversion function for MULE_INTERNAL to ISO-8859-5', - proname => 'mic_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_iso', + proname => 'mic_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4306', descr => 'internal conversion function for WIN1251 to MULE_INTERNAL', - proname => 'win1251_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_mic', + proname => 'win1251_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4307', descr => 'internal conversion function for MULE_INTERNAL to WIN1251', - proname => 'mic_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1251', + proname => 'mic_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4308', descr => 'internal conversion function for WIN866 to MULE_INTERNAL', - proname => 'win866_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_mic', + proname => 'win866_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4309', descr => 'internal conversion function for MULE_INTERNAL to WIN866', - proname => 'mic_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win866', + proname => 'mic_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4310', descr => 'internal conversion function for KOI8R to WIN1251', - proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4311', descr => 'internal conversion function for WIN1251 to KOI8R', - proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4312', descr => 'internal conversion function for KOI8R to WIN866', - proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_win866', + proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4313', descr => 'internal conversion function for WIN866 to KOI8R', - proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_koi8r', + proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4314', descr => 'internal conversion function for WIN866 to WIN1251', - proname => 'win866_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win866_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4315', descr => 'internal conversion function for WIN1251 to WIN866', - proname => 'win1251_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4316', descr => 'internal conversion function for ISO-8859-5 to KOI8R', - proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_koi8r', + proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4317', descr => 'internal conversion function for KOI8R to ISO-8859-5', - proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_iso', + proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4318', descr => 'internal conversion function for ISO-8859-5 to WIN1251', - proname => 'iso_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win1251', + proname => 'iso_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4319', descr => 'internal conversion function for WIN1251 to ISO-8859-5', - proname => 'win1251_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_iso', + proname => 'win1251_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4320', descr => 'internal conversion function for ISO-8859-5 to WIN866', - proname => 'iso_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win866', + proname => 'iso_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4321', descr => 'internal conversion function for WIN866 to ISO-8859-5', - proname => 'win866_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_iso', + proname => 'win866_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4322', descr => 'internal conversion function for EUC_CN to MULE_INTERNAL', - proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_mic', + proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_mic', probin => '$libdir/euc_cn_and_mic' }, { oid => '4323', descr => 'internal conversion function for MULE_INTERNAL to EUC_CN', - proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_cn', + proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_cn', probin => '$libdir/euc_cn_and_mic' }, { oid => '4324', descr => 'internal conversion function for EUC_JP to SJIS', - proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_sjis', + proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4325', descr => 'internal conversion function for SJIS to EUC_JP', - proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_euc_jp', + proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4326', descr => 'internal conversion function for EUC_JP to MULE_INTERNAL', - proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_mic', + proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4327', descr => 'internal conversion function for SJIS to MULE_INTERNAL', - proname => 'sjis_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_mic', + proname => 'sjis_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4328', descr => 'internal conversion function for MULE_INTERNAL to EUC_JP', - proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_jp', + proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4329', descr => 'internal conversion function for MULE_INTERNAL to SJIS', - proname => 'mic_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_sjis', + proname => 'mic_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4330', descr => 'internal conversion function for EUC_KR to MULE_INTERNAL', - proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_mic', + proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_mic', probin => '$libdir/euc_kr_and_mic' }, { oid => '4331', descr => 'internal conversion function for MULE_INTERNAL to EUC_KR', - proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_kr', + proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_kr', probin => '$libdir/euc_kr_and_mic' }, { oid => '4332', descr => 'internal conversion function for EUC_TW to BIG5', - proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_big5', + proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4333', descr => 'internal conversion function for BIG5 to EUC_TW', - proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_euc_tw', + proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4334', descr => 'internal conversion function for EUC_TW to MULE_INTERNAL', - proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_mic', + proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4335', descr => 'internal conversion function for BIG5 to MULE_INTERNAL', - proname => 'big5_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_mic', + proname => 'big5_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4336', descr => 'internal conversion function for MULE_INTERNAL to EUC_TW', - proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_tw', + proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4337', descr => 'internal conversion function for MULE_INTERNAL to BIG5', - proname => 'mic_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_big5', + proname => 'mic_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4338', descr => 'internal conversion function for LATIN2 to MULE_INTERNAL', - proname => 'latin2_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin2_to_mic', + proname => 'latin2_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4339', descr => 'internal conversion function for MULE_INTERNAL to LATIN2', - proname => 'mic_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin2', + proname => 'mic_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4340', descr => 'internal conversion function for WIN1250 to MULE_INTERNAL', - proname => 'win1250_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1250_to_mic', + proname => 'win1250_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4341', descr => 'internal conversion function for MULE_INTERNAL to WIN1250', - proname => 'mic_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1250', + proname => 'mic_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4342', descr => 'internal conversion function for LATIN2 to WIN1250', - proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4343', descr => 'internal conversion function for WIN1250 to LATIN2', - proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4344', descr => 'internal conversion function for LATIN1 to MULE_INTERNAL', - proname => 'latin1_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin1_to_mic', + proname => 'latin1_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin1_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4345', descr => 'internal conversion function for MULE_INTERNAL to LATIN1', - proname => 'mic_to_latin1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin1', + proname => 'mic_to_latin1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin1', probin => '$libdir/latin_and_mic' }, { oid => '4346', descr => 'internal conversion function for LATIN3 to MULE_INTERNAL', - proname => 'latin3_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin3_to_mic', + proname => 'latin3_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin3_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4347', descr => 'internal conversion function for MULE_INTERNAL to LATIN3', - proname => 'mic_to_latin3', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin3', + proname => 'mic_to_latin3', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin3', probin => '$libdir/latin_and_mic' }, { oid => '4348', descr => 'internal conversion function for LATIN4 to MULE_INTERNAL', - proname => 'latin4_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin4_to_mic', + proname => 'latin4_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin4_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4349', descr => 'internal conversion function for MULE_INTERNAL to LATIN4', - proname => 'mic_to_latin4', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin4', + proname => 'mic_to_latin4', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin4', probin => '$libdir/latin_and_mic' }, { oid => '4352', descr => 'internal conversion function for BIG5 to UTF8', - proname => 'big5_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_utf8', + proname => 'big5_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_utf8', probin => '$libdir/utf8_and_big5' }, { oid => '4353', descr => 'internal conversion function for UTF8 to BIG5', - proname => 'utf8_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_big5', + proname => 'utf8_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_big5', probin => '$libdir/utf8_and_big5' }, { oid => '4354', descr => 'internal conversion function for UTF8 to KOI8R', - proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8r', + proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8r', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4355', descr => 'internal conversion function for KOI8R to UTF8', - proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_utf8', + proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4356', descr => 'internal conversion function for UTF8 to KOI8U', - proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8u', + proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8u', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4357', descr => 'internal conversion function for KOI8U to UTF8', - proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8u_to_utf8', + proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8u_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4358', descr => 'internal conversion function for UTF8 to WIN', - proname => 'utf8_to_win', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_win', + proname => 'utf8_to_win', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_win', probin => '$libdir/utf8_and_win' }, { oid => '4359', descr => 'internal conversion function for WIN to UTF8', - proname => 'win_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win_to_utf8', + proname => 'win_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win_to_utf8', probin => '$libdir/utf8_and_win' }, { oid => '4360', descr => 'internal conversion function for EUC_CN to UTF8', - proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_utf8', + proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_utf8', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4361', descr => 'internal conversion function for UTF8 to EUC_CN', - proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_cn', + proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_cn', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4362', descr => 'internal conversion function for EUC_JP to UTF8', - proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_utf8', + proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_utf8', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4363', descr => 'internal conversion function for UTF8 to EUC_JP', - proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_jp', + proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jp', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4364', descr => 'internal conversion function for EUC_KR to UTF8', - proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_utf8', + proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_utf8', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4365', descr => 'internal conversion function for UTF8 to EUC_KR', - proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_kr', + proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_kr', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4366', descr => 'internal conversion function for EUC_TW to UTF8', - proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_utf8', + proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_utf8', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4367', descr => 'internal conversion function for UTF8 to EUC_TW', - proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_tw', + proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_tw', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4368', descr => 'internal conversion function for GB18030 to UTF8', - proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gb18030_to_utf8', + proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gb18030_to_utf8', probin => '$libdir/utf8_and_gb18030' }, { oid => '4369', descr => 'internal conversion function for UTF8 to GB18030', - proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gb18030', + proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gb18030', probin => '$libdir/utf8_and_gb18030' }, { oid => '4370', descr => 'internal conversion function for GBK to UTF8', - proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gbk_to_utf8', + proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gbk_to_utf8', probin => '$libdir/utf8_and_gbk' }, { oid => '4371', descr => 'internal conversion function for UTF8 to GBK', - proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gbk', + proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gbk', probin => '$libdir/utf8_and_gbk' }, { oid => '4372', descr => 'internal conversion function for UTF8 to ISO-8859 2-16', - proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_iso8859', + proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859', probin => '$libdir/utf8_and_iso8859' }, { oid => '4373', descr => 'internal conversion function for ISO-8859 2-16 to UTF8', - proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso8859_to_utf8', + proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_to_utf8', probin => '$libdir/utf8_and_iso8859' }, { oid => '4374', descr => 'internal conversion function for LATIN1 to UTF8', - proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_1_to_utf8', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4375', descr => 'internal conversion function for UTF8 to LATIN1', - proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859_1', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4376', descr => 'internal conversion function for JOHAB to UTF8', - proname => 'johab_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'johab_to_utf8', + proname => 'johab_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'johab_to_utf8', probin => '$libdir/utf8_and_johab' }, { oid => '4377', descr => 'internal conversion function for UTF8 to JOHAB', - proname => 'utf8_to_johab', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_johab', + proname => 'utf8_to_johab', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_johab', probin => '$libdir/utf8_and_johab' }, { oid => '4378', descr => 'internal conversion function for SJIS to UTF8', - proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_utf8', + proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_utf8', probin => '$libdir/utf8_and_sjis' }, { oid => '4379', descr => 'internal conversion function for UTF8 to SJIS', - proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_sjis', + proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_sjis', probin => '$libdir/utf8_and_sjis' }, { oid => '4380', descr => 'internal conversion function for UHC to UTF8', - proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'uhc_to_utf8', + proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'uhc_to_utf8', probin => '$libdir/utf8_and_uhc' }, { oid => '4381', descr => 'internal conversion function for UTF8 to UHC', - proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_uhc', + proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_uhc', probin => '$libdir/utf8_and_uhc' }, { oid => '4382', descr => 'internal conversion function for EUC_JIS_2004 to UTF8', - proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_utf8', probin => '$libdir/utf8_and_euc2004' }, { oid => '4383', descr => 'internal conversion function for UTF8 to EUC_JIS_2004', - proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jis_2004', probin => '$libdir/utf8_and_euc2004' }, { oid => '4384', descr => 'internal conversion function for SHIFT_JIS_2004 to UTF8', - proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_utf8', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4385', descr => 'internal conversion function for UTF8 to SHIFT_JIS_2004', - proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_shift_jis_2004', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4386', descr => 'internal conversion function for EUC_JIS_2004 to SHIFT_JIS_2004', proname => 'euc_jis_2004_to_shift_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_shift_jis_2004', probin => '$libdir/euc2004_sjis2004' }, { oid => '4387', descr => 'internal conversion function for SHIFT_JIS_2004 to EUC_JIS_2004', proname => 'shift_jis_2004_to_euc_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_euc_jis_2004', probin => '$libdir/euc2004_sjis2004' }, diff --git a/src/include/mb/pg_wchar.h b/src/include/mb/pg_wchar.h index 64b22e4b0d4..346a41a1f3d 100644 --- a/src/include/mb/pg_wchar.h +++ b/src/include/mb/pg_wchar.h @@ -627,18 +627,18 @@ extern void pg_unicode_to_server(pg_wchar c, unsigned char *s); extern unsigned short BIG5toCNS(unsigned short big5, unsigned char *lc); extern unsigned short CNStoBIG5(unsigned short cns, unsigned char lc); -extern void UtfToLocal(const unsigned char *utf, int len, - unsigned char *iso, - const pg_mb_radix_tree *map, - const pg_utf_to_local_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); -extern void LocalToUtf(const unsigned char *iso, int len, - unsigned char *utf, - const pg_mb_radix_tree *map, - const pg_local_to_utf_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); +extern int UtfToLocal(const unsigned char *utf, int len, + unsigned char *iso, + const pg_mb_radix_tree *map, + const pg_utf_to_local_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); +extern int LocalToUtf(const unsigned char *iso, int len, + unsigned char *utf, + const pg_mb_radix_tree *map, + const pg_local_to_utf_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); extern bool pg_verifymbstr(const char *mbstr, int len, bool noError); extern bool pg_verify_mbstr(int encoding, const char *mbstr, int len, @@ -656,18 +656,19 @@ extern void report_invalid_encoding(int encoding, const char *mbstr, int len) pg extern void report_untranslatable_char(int src_encoding, int dest_encoding, const char *mbstr, int len) pg_attribute_noreturn(); -extern void local2local(const unsigned char *l, unsigned char *p, int len, - int src_encoding, int dest_encoding, const unsigned char *tab); -extern void latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding); -extern void mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding); -extern void latin2mic_with_table(const unsigned char *l, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); -extern void mic2latin_with_table(const unsigned char *mic, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); +extern int local2local(const unsigned char *l, unsigned char *p, int len, + int src_encoding, int dest_encoding, const unsigned char *tab, + bool noError); +extern int latin2mic(const unsigned char *l, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int mic2latin(const unsigned char *mic, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int latin2mic_with_table(const unsigned char *l, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); +extern int mic2latin_with_table(const unsigned char *mic, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); #ifdef WIN32 extern WCHAR *pgwin32_message_to_UTF16(const char *str, int len, int *utf16len); diff --git a/src/test/regress/expected/opr_sanity.out b/src/test/regress/expected/opr_sanity.out index 254ca06d3dd..23ba60e395f 100644 --- a/src/test/regress/expected/opr_sanity.out +++ b/src/test/regress/expected/opr_sanity.out @@ -1052,13 +1052,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); oid | proname | oid | conname -----+---------+-----+--------- (0 rows) diff --git a/src/test/regress/sql/opr_sanity.sql b/src/test/regress/sql/opr_sanity.sql index bbd3834b634..04691745981 100644 --- a/src/test/regress/sql/opr_sanity.sql +++ b/src/test/regress/sql/opr_sanity.sql @@ -556,13 +556,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); -- Check for conprocs that don't perform the specific conversion that -- pg_conversion alleges they do, by trying to invoke each conversion -- 2.29.2 --------------39E46EF15EBFAA37D53332E5 Content-Type: text/x-patch; charset=UTF-8; name="v3-0003-Add-tests-for-the-new-noError-variants-of-built-i.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="v3-0003-Add-tests-for-the-new-noError-variants-of-built-i.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 34+ messages in thread
* [PATCH v3 2/5] Change conversion function signature. @ 2021-01-28 16:42 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 34+ messages in thread From: Heikki Linnakangas @ 2021-01-28 16:42 UTC (permalink / raw) Add a 'noError' argument, so that we can try to convert a buffer without knowing the character boundaries beforehand. The functions now need to return the number of input bytes successfully converted. This is is a backwards-incompatible change, if you have created a custom encoding conversion with CREATE CONVERSION. This adds a check to pg_upgrade for that, refusing the upgrade if there are any user-defined encoding conversions. --- doc/src/sgml/ref/create_conversion.sgml | 5 +- src/backend/commands/conversioncmds.c | 27 +- src/backend/utils/error/elog.c | 2 + src/backend/utils/mb/conv.c | 112 +++++- .../cyrillic_and_mic/cyrillic_and_mic.c | 127 ++++--- .../euc2004_sjis2004/euc2004_sjis2004.c | 96 ++++- .../euc_cn_and_mic/euc_cn_and_mic.c | 57 ++- .../euc_jp_and_sjis/euc_jp_and_sjis.c | 153 ++++++-- .../euc_kr_and_mic/euc_kr_and_mic.c | 57 ++- .../euc_tw_and_big5/euc_tw_and_big5.c | 165 +++++++-- .../latin2_and_win1250/latin2_and_win1250.c | 49 ++- .../latin_and_mic/latin_and_mic.c | 43 ++- .../utf8_and_big5/utf8_and_big5.c | 37 +- .../utf8_and_cyrillic/utf8_and_cyrillic.c | 67 ++-- .../utf8_and_euc2004/utf8_and_euc2004.c | 37 +- .../utf8_and_euc_cn/utf8_and_euc_cn.c | 37 +- .../utf8_and_euc_jp/utf8_and_euc_jp.c | 37 +- .../utf8_and_euc_kr/utf8_and_euc_kr.c | 37 +- .../utf8_and_euc_tw/utf8_and_euc_tw.c | 37 +- .../utf8_and_gb18030/utf8_and_gb18030.c | 37 +- .../utf8_and_gbk/utf8_and_gbk.c | 37 +- .../utf8_and_iso8859/utf8_and_iso8859.c | 43 ++- .../utf8_and_iso8859_1/utf8_and_iso8859_1.c | 27 +- .../utf8_and_johab/utf8_and_johab.c | 37 +- .../utf8_and_sjis/utf8_and_sjis.c | 37 +- .../utf8_and_sjis2004/utf8_and_sjis2004.c | 37 +- .../utf8_and_uhc/utf8_and_uhc.c | 37 +- .../utf8_and_win/utf8_and_win.c | 43 ++- src/backend/utils/mb/mbutils.c | 18 +- src/bin/pg_upgrade/check.c | 95 +++++ src/include/catalog/pg_proc.dat | 332 +++++++++--------- src/include/mb/pg_wchar.h | 49 +-- src/test/regress/expected/opr_sanity.out | 7 +- src/test/regress/sql/opr_sanity.sql | 7 +- 34 files changed, 1390 insertions(+), 635 deletions(-) diff --git a/doc/src/sgml/ref/create_conversion.sgml b/doc/src/sgml/ref/create_conversion.sgml index e7700fecfc5..f014a676c88 100644 --- a/doc/src/sgml/ref/create_conversion.sgml +++ b/doc/src/sgml/ref/create_conversion.sgml @@ -117,8 +117,9 @@ conv_proc( integer, -- destination encoding ID cstring, -- source string (null terminated C string) internal, -- destination (fill with a null terminated C string) - integer -- source string length -) RETURNS void; + integer, -- source string length + boolean -- if true, don't throw an error if conversion fails +) RETURNS integer; </programlisting></para> </listitem> </varlistentry> diff --git a/src/backend/commands/conversioncmds.c b/src/backend/commands/conversioncmds.c index f7ff321de71..d2041466911 100644 --- a/src/backend/commands/conversioncmds.c +++ b/src/backend/commands/conversioncmds.c @@ -45,8 +45,9 @@ CreateConversionCommand(CreateConversionStmt *stmt) const char *from_encoding_name = stmt->for_encoding_name; const char *to_encoding_name = stmt->to_encoding_name; List *func_name = stmt->func_name; - static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID}; + static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID, BOOLOID}; char result[1]; + Datum funcresult; /* Convert list of names to a name and namespace */ namespaceId = QualifiedNameGetCreationNamespace(stmt->conversion_name, @@ -92,8 +93,8 @@ CreateConversionCommand(CreateConversionStmt *stmt) funcoid = LookupFuncName(func_name, sizeof(funcargs) / sizeof(Oid), funcargs, false); - /* Check it returns VOID, else it's probably the wrong function */ - if (get_func_rettype(funcoid) != VOIDOID) + /* Check it returns int4, else it's probably the wrong function */ + if (get_func_rettype(funcoid) != INT4OID) ereport(ERROR, (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), errmsg("encoding conversion function %s must return type %s", @@ -111,12 +112,20 @@ CreateConversionCommand(CreateConversionStmt *stmt) * string; the conversion function should throw an error if it can't * perform the requested conversion. */ - OidFunctionCall5(funcoid, - Int32GetDatum(from_encoding), - Int32GetDatum(to_encoding), - CStringGetDatum(""), - CStringGetDatum(result), - Int32GetDatum(0)); + funcresult = OidFunctionCall6(funcoid, + Int32GetDatum(from_encoding), + Int32GetDatum(to_encoding), + CStringGetDatum(""), + CStringGetDatum(result), + Int32GetDatum(0), + BoolGetDatum(false)); + + /* The function should return 0 for empty input. Might as well check that, too. */ + if (DatumGetInt32(funcresult) != 0) + ereport(ERROR, + (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), + errmsg("encoding conversion function %s returned incorrect result for empty input", + NameListToString(func_name)))); /* * All seem ok, go ahead (possible failure would be a duplicate conversion diff --git a/src/backend/utils/error/elog.c b/src/backend/utils/error/elog.c index 80c26724612..762f77d533c 100644 --- a/src/backend/utils/error/elog.c +++ b/src/backend/utils/error/elog.c @@ -2280,6 +2280,8 @@ write_console(const char *line, int len) * Conversion on non-win32 platforms is not implemented yet. It requires * non-throw version of pg_do_encoding_conversion(), that converts * unconvertable characters to '?' without errors. + * + * XXX: We have a no-throw version now. It doesn't convert to '?' though. */ #endif diff --git a/src/backend/utils/mb/conv.c b/src/backend/utils/mb/conv.c index a07b54bd3b8..b83358bc7a5 100644 --- a/src/backend/utils/mb/conv.c +++ b/src/backend/utils/mb/conv.c @@ -26,14 +26,16 @@ * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the target charset, or 0 if there is no equivalent code. */ -void +int local2local(const unsigned char *l, unsigned char *p, int len, int src_encoding, int dest_encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -41,7 +43,11 @@ local2local(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(src_encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -50,13 +56,19 @@ local2local(const unsigned char *l, if (c2) *p++ = c2; else + { + if (noError) + break; report_untranslatable_char(src_encoding, dest_encoding, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -67,17 +79,22 @@ local2local(const unsigned char *l, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = l; int c1; while (len > 0) { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (IS_HIGHBIT_SET(c1)) *p++ = lc; *p++ = c1; @@ -85,6 +102,8 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, len--; } *p = '\0'; + + return l - start; } /* @@ -95,17 +114,22 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -118,17 +142,27 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1])) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); + } *p++ = mic[1]; mic += 2; len -= 2; } } *p = '\0'; + + return mic - start; } @@ -144,14 +178,16 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the mule encoding, or 0 if there is no equivalent code. */ -void +int latin2mic_with_table(const unsigned char *l, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -159,7 +195,11 @@ latin2mic_with_table(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -171,13 +211,19 @@ latin2mic_with_table(const unsigned char *l, *p++ = c2; } else + { + if (noError) + break; report_untranslatable_char(encoding, PG_MULE_INTERNAL, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -192,14 +238,16 @@ latin2mic_with_table(const unsigned char *l, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the local charset, or 0 if there is no equivalent code. */ -void +int mic2latin_with_table(const unsigned char *mic, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = mic; unsigned char c1, c2; @@ -207,7 +255,11 @@ mic2latin_with_table(const unsigned char *mic, { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -220,11 +272,17 @@ mic2latin_with_table(const unsigned char *mic, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1]) || (c2 = tab[mic[1] - HIGHBIT]) == 0) { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); break; /* keep compiler quiet */ @@ -235,6 +293,8 @@ mic2latin_with_table(const unsigned char *mic, } } *p = '\0'; + + return mic - start; } /* @@ -425,17 +485,19 @@ pg_mb_radix_conv(const pg_mb_radix_tree *rt, * * See pg_wchar.h for more details about the data structures used here. */ -void +int UtfToLocal(const unsigned char *utf, int len, unsigned char *iso, const pg_mb_radix_tree *map, const pg_utf_to_local_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, bool noError) { uint32 iutf; int l; const pg_utf_to_local_combined *cp; + const unsigned char *start = utf; + const unsigned char *cur = utf; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -449,6 +511,8 @@ UtfToLocal(const unsigned char *utf, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*utf == '\0') break; @@ -584,15 +648,19 @@ UtfToLocal(const unsigned char *utf, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(PG_UTF8, encoding, (const char *) (utf - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(PG_UTF8, (const char *) utf, len); *iso = '\0'; + + return cur - start; } /* @@ -616,18 +684,24 @@ UtfToLocal(const unsigned char *utf, int len, * (if provided) is applied. An error is raised if no match is found. * * See pg_wchar.h for more details about the data structures used here. + * + * Returns the number of input bytes consumed. If noError is true, this can + * be less than 'len'. */ -void +int LocalToUtf(const unsigned char *iso, int len, unsigned char *utf, const pg_mb_radix_tree *map, const pg_local_to_utf_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, + bool noError) { uint32 iiso; int l; const pg_local_to_utf_combined *cp; + const unsigned char *start = iso; + const unsigned char *cur = iso; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -641,6 +715,8 @@ LocalToUtf(const unsigned char *iso, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*iso == '\0') break; @@ -723,13 +799,17 @@ LocalToUtf(const unsigned char *iso, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(encoding, PG_UTF8, (const char *) (iso - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(encoding, (const char *) iso, len); *utf = '\0'; + + return cur - start; } diff --git a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c index 4c5b02654de..368c2deb5e4 100644 --- a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c @@ -44,8 +44,11 @@ PG_FUNCTION_INFO_V1(win866_to_iso); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -306,12 +309,14 @@ koi8r_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -320,12 +325,14 @@ mic_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_KOI8R); - mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -334,12 +341,14 @@ iso_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -348,12 +357,14 @@ mic_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_ISO_8859_5); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -362,12 +373,14 @@ win1251_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -376,12 +389,14 @@ mic_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1251); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -390,12 +405,14 @@ win866_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -404,12 +421,14 @@ mic_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN866); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -418,12 +437,14 @@ koi8r_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN1251); - local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -432,12 +453,14 @@ win1251_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_KOI8R); - local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi); + converted = local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -446,12 +469,14 @@ koi8r_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN866); - local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -460,12 +485,14 @@ win866_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_KOI8R); - local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi); + converted = local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -474,12 +501,14 @@ win866_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_WIN1251); - local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251); + converted = local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -488,12 +517,14 @@ win1251_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_WIN866); - local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866); + converted = local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -502,12 +533,14 @@ iso_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_KOI8R); - local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -516,12 +549,14 @@ koi8r_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_ISO_8859_5); - local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso); + converted = local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -530,12 +565,14 @@ iso_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN1251); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -544,12 +581,14 @@ win1251_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso); + converted = local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -558,12 +597,14 @@ iso_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN866); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -572,10 +613,12 @@ win866_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso); + converted = local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c index 4d7fb116cfd..88529c644cf 100644 --- a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c @@ -19,8 +19,8 @@ PG_MODULE_MAGIC; PG_FUNCTION_INFO_V1(euc_jis_2004_to_shift_jis_2004); PG_FUNCTION_INFO_V1(shift_jis_2004_to_euc_jis_2004); -static void euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len); -static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len); +static int euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError); /* ---------- * conv_proc( @@ -28,8 +28,11 @@ static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -39,12 +42,14 @@ euc_jis_2004_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_SHIFT_JIS_2004); - euc_jis_20042shift_jis_2004(src, dest, len); + converted = euc_jis_20042shift_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -53,20 +58,23 @@ shift_jis_2004_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_EUC_JIS_2004); - shift_jis_20042euc_jis_2004(src, dest, len); + converted = shift_jis_20042euc_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_JIS_2004 -> SHIFT_JIS_2004 */ -static void -euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, ku, ten; @@ -79,8 +87,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -90,8 +102,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) l = pg_encoding_verifymbchar(PG_EUC_JIS_2004, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (c1 == SS2 && l == 2) /* JIS X 0201 kana? */ { @@ -121,8 +137,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) *p++ = (ku + 0x19b) >> 1; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } if (ku % 2) @@ -132,8 +152,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; @@ -149,8 +173,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ku >= 63 && ku <= 94) *p++ = (ku + 0x181) >> 1; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (ku % 2) { @@ -159,20 +187,30 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else - report_invalid_encoding(PG_EUC_JIS_2004, + { + if (noError) + break; + report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } euc += l; len -= l; } *p = '\0'; + + return euc - start; } /* @@ -212,9 +250,10 @@ get_ten(int b, int *ku) * SHIFT_JIS_2004 ---> EUC_JIS_2004 */ -static void -shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len) +static int +shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1; int ku, ten, @@ -230,8 +269,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -241,8 +284,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len l = pg_encoding_verifymbchar(PG_SHIFT_JIS_2004, (const char *) sjis, len); if (l < 0 || l > len) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf && l == 1) { @@ -266,8 +313,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x100; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xe0 && c1 <= 0xef) /* plane 1 62ku-94ku */ @@ -275,9 +326,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x180; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, - (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xf0 && c1 <= 0xf3) /* plane 2 @@ -286,8 +340,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } switch (c1) { case 0xf0: @@ -309,16 +367,24 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 == 0xf4 && kubun == 1) ku = 15; else ku = (c1 << 1) - 0x19a - kubun; } else + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (plane == 2) *p++ = SS3; @@ -330,4 +396,6 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c index e9bb896935f..a8da733803d 100644 --- a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_cn2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_cn(const unsigned char *mic, unsigned char *p, int len); +static int euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_cn_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_cn_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_MULE_INTERNAL); - euc_cn2mic(src, dest, len); + converted = euc_cn2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_CN); - mic2euc_cn(src, dest, len); + converted = mic2euc_cn(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_CN ---> MIC */ -static void -euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; while (len > 0) @@ -76,7 +84,11 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (len < 2 || !IS_HIGHBIT_SET(euc[1])) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = LC_GB2312_80; *p++ = c1; *p++ = euc[1]; @@ -86,21 +98,28 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_CN */ -static void -mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) @@ -109,11 +128,19 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (c1 != LC_GB2312_80) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_CN, (const char *) mic, len); + } if (len < 3 || !IS_HIGHBIT_SET(mic[1]) || !IS_HIGHBIT_SET(mic[2])) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } mic++; *p++ = *mic++; *p++ = *mic++; @@ -122,12 +149,18 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; } } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c index 5059f917a98..cc4817dc4cd 100644 --- a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c @@ -42,17 +42,20 @@ PG_FUNCTION_INFO_V1(mic_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void sjis2mic(const unsigned char *sjis, unsigned char *p, int len); -static void mic2sjis(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_jp(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len); -static void sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len); +static int sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError); +static int mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_jp_to_sjis(PG_FUNCTION_ARGS) @@ -60,12 +63,14 @@ euc_jp_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_SJIS); - euc_jp2sjis(src, dest, len); + converted = euc_jp2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -74,12 +79,14 @@ sjis_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_EUC_JP); - sjis2euc_jp(src, dest, len); + converted = sjis2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -88,12 +95,14 @@ euc_jp_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_MULE_INTERNAL); - euc_jp2mic(src, dest, len); + converted = euc_jp2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -102,12 +111,14 @@ mic_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_JP); - mic2euc_jp(src, dest, len); + converted = mic2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -116,12 +127,14 @@ sjis_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_MULE_INTERNAL); - sjis2mic(src, dest, len); + converted = sjis2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -130,20 +143,23 @@ mic_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_SJIS); - mic2sjis(src, dest, len); + converted = mic2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * SJIS ---> MIC */ -static void -sjis2mic(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -167,7 +183,11 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) * JIS X0208, X0212, user defined extended characters */ if (len < 2 || !ISSJISHEAD(c1) || !ISSJISTAIL(sjis[1])) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } c2 = sjis[1]; k = (c1 << 8) + c2; if (k >= 0xed40 && k < 0xf040) @@ -257,21 +277,28 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; } } *p = '\0'; + + return sjis - start; } /* * MIC ---> SJIS */ -static void -mic2sjis(const unsigned char *mic, unsigned char *p, int len) +static int +mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1, c2, k, @@ -284,8 +311,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -293,8 +324,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) *p++ = mic[1]; else if (c1 == LC_JISX0208) @@ -350,20 +385,27 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_SJIS, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP ---> MIC */ -static void -euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -374,8 +416,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -383,8 +429,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* 1 byte kana? */ *p++ = LC_JISX0201K; @@ -406,14 +456,17 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_JP */ -static void -mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -424,8 +477,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -433,8 +490,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) { *p++ = SS2; @@ -452,20 +513,27 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_JP, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP -> SJIS */ -static void -euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, c2, k; @@ -478,8 +546,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -487,8 +559,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* hankaku kana? */ @@ -551,14 +627,17 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * SJIS ---> EUC_JP */ -static void -sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -573,8 +652,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -582,8 +665,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_SJIS, (const char *) sjis, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf) { /* JIS X0201 (1 byte kana) */ @@ -680,4 +767,6 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c index ac823d6c270..a5b51617e52 100644 --- a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_kr2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_kr(const unsigned char *mic, unsigned char *p, int len); +static int euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_kr_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_kr_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_MULE_INTERNAL); - euc_kr2mic(src, dest, len); + converted = euc_kr2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_KR); - mic2euc_kr(src, dest, len); + converted = mic2euc_kr(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_KR ---> MIC */ -static void -euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -78,8 +86,12 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_KR, (const char *) euc, len); if (l != 2) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = LC_KS5601; *p++ = c1; *p++ = euc[1]; @@ -89,22 +101,29 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_KR */ -static void -mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -115,8 +134,12 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -124,18 +147,28 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_KS5601) { *p++ = mic[1]; *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_KR, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c index 66c242d7f36..ebb4e0acd53 100644 --- a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c @@ -32,17 +32,20 @@ PG_FUNCTION_INFO_V1(mic_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_tw2big5(const unsigned char *euc, unsigned char *p, int len); -static void big52euc_tw(const unsigned char *euc, unsigned char *p, int len); -static void big52mic(const unsigned char *big5, unsigned char *p, int len); -static void mic2big5(const unsigned char *mic, unsigned char *p, int len); -static void euc_tw2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_tw(const unsigned char *mic, unsigned char *p, int len); +static int euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52euc_tw(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError); +static int mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_tw_to_big5(PG_FUNCTION_ARGS) @@ -50,12 +53,14 @@ euc_tw_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_BIG5); - euc_tw2big5(src, dest, len); + converted = euc_tw2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -64,12 +69,14 @@ big5_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_EUC_TW); - big52euc_tw(src, dest, len); + converted = big52euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -78,12 +85,14 @@ euc_tw_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_MULE_INTERNAL); - euc_tw2mic(src, dest, len); + converted = euc_tw2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -92,12 +101,14 @@ mic_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_TW); - mic2euc_tw(src, dest, len); + converted = mic2euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -106,12 +117,14 @@ big5_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_MULE_INTERNAL); - big52mic(src, dest, len); + converted = big52mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -120,21 +133,24 @@ mic_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_BIG5); - mic2big5(src, dest, len); + converted = mic2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_TW ---> Big5 */ -static void -euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; unsigned char c1; unsigned short big5buf, cnsBuf; @@ -149,8 +165,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Verify and decode the next EUC_TW input character */ l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -171,8 +191,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Write it out in Big5 */ big5buf = CNStoBIG5(cnsBuf, lc); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_EUC_TW, PG_BIG5, (const char *) euc, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; @@ -182,22 +206,29 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * Big5 ---> EUC_TW */ -static void -big52euc_tw(const unsigned char *big5, unsigned char *p, int len) +static int +big52euc_tw(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -212,8 +243,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); @@ -237,8 +272,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_EUC_TW, (const char *) big5, len); + } big5 += l; len -= l; @@ -256,14 +295,17 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) } } *p = '\0'; + + return big5 - start; } /* * EUC_TW ---> MIC */ -static void -euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -274,8 +316,12 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -304,22 +350,29 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_TW */ -static void -mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -330,8 +383,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -339,8 +396,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1) { *p++ = mic[1]; @@ -362,20 +423,27 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[3]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_TW, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * Big5 ---> MIC */ -static void -big52mic(const unsigned char *big5, unsigned char *p, int len) +static int +big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -389,8 +457,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } *p++ = c1; big5++; len--; @@ -398,8 +470,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); if (lc != 0) @@ -412,20 +488,27 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_MULE_INTERNAL, (const char *) big5, len); + } big5 += l; len -= l; } *p = '\0'; + + return big5 - start; } /* * MIC ---> Big5 */ -static void -mic2big5(const unsigned char *mic, unsigned char *p, int len) +static int +mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -438,8 +521,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -447,8 +534,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1 || c1 == LC_CNS11643_2 || c1 == LCPRV2_B) { if (c1 == LCPRV2_B) @@ -462,16 +553,26 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } big5buf = CNStoBIG5(cnsBuf, c1); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c index 2e28e6780a5..8610fcb69aa 100644 --- a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c +++ b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(win1250_to_latin2); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -82,12 +85,14 @@ latin2_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -96,12 +101,14 @@ mic_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN2); - mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -110,13 +117,15 @@ win1250_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - win1250_2_iso88592); + converted = latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -125,13 +134,15 @@ mic_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1250); - mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - iso88592_2_win1250); + converted = mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -140,12 +151,15 @@ latin2_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_WIN1250); - local2local(src, dest, len, PG_LATIN2, PG_WIN1250, iso88592_2_win1250); + converted = local2local(src, dest, len, PG_LATIN2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -154,10 +168,13 @@ win1250_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_LATIN2); - local2local(src, dest, len, PG_WIN1250, PG_LATIN2, win1250_2_iso88592); + converted = local2local(src, dest, len, PG_WIN1250, PG_LATIN2, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c index bc651410f21..bff27d1c295 100644 --- a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(mic_to_latin4); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -42,12 +45,14 @@ latin1_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,12 +61,14 @@ mic_to_latin1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN1); - mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -70,12 +77,14 @@ latin3_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN3, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -84,12 +93,14 @@ mic_to_latin3(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN3); - mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,12 +109,14 @@ latin4_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN4, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -112,10 +125,12 @@ mic_to_latin4(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN4); - mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c index d6067cdc24e..3838b15cab9 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ big5_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_UTF8); - LocalToUtf(src, len, dest, - &big5_to_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = LocalToUtf(src, len, dest, + &big5_to_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_BIG5); - UtfToLocal(src, len, dest, - &big5_from_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = UtfToLocal(src, len, dest, + &big5_from_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c index ed90e8e682e..75719fe5f1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c @@ -33,8 +33,11 @@ PG_FUNCTION_INFO_V1(koi8u_to_utf8); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -44,16 +47,19 @@ utf8_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8R); - UtfToLocal(src, len, dest, - &koi8r_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = UtfToLocal(src, len, dest, + &koi8r_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -62,16 +68,19 @@ koi8r_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8r_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = LocalToUtf(src, len, dest, + &koi8r_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -80,16 +89,19 @@ utf8_to_koi8u(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8U); - UtfToLocal(src, len, dest, - &koi8u_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = UtfToLocal(src, len, dest, + &koi8u_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,14 +110,17 @@ koi8u_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8U, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8u_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = LocalToUtf(src, len, dest, + &koi8u_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c index d699affce47..5391001951a 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jis_2004_to_unicode_tree, - LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = LocalToUtf(src, len, dest, + &euc_jis_2004_to_unicode_tree, + LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JIS_2004); - UtfToLocal(src, len, dest, - &euc_jis_2004_from_unicode_tree, - ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = UtfToLocal(src, len, dest, + &euc_jis_2004_from_unicode_tree, + ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c index d7c0ba6a58b..c87d1bf2398 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_cn_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_cn_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = LocalToUtf(src, len, dest, + &euc_cn_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_CN); - UtfToLocal(src, len, dest, - &euc_cn_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = UtfToLocal(src, len, dest, + &euc_cn_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c index 13a3a23e77b..6a55134db21 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jp); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jp_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jp_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = LocalToUtf(src, len, dest, + &euc_jp_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JP); - UtfToLocal(src, len, dest, - &euc_jp_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = UtfToLocal(src, len, dest, + &euc_jp_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c index 1bbb8aaef7b..fe1924e2fec 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_kr_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_kr_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = LocalToUtf(src, len, dest, + &euc_kr_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_KR); - UtfToLocal(src, len, dest, - &euc_kr_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = UtfToLocal(src, len, dest, + &euc_kr_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c index 9830045dccd..68215659b57 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_tw); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_tw_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_tw_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = LocalToUtf(src, len, dest, + &euc_tw_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_TW); - UtfToLocal(src, len, dest, - &euc_tw_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = UtfToLocal(src, len, dest, + &euc_tw_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c index f86ecf27424..e1a59c39a4d 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c @@ -183,8 +183,11 @@ conv_utf8_to_18030(uint32 code) * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -193,16 +196,19 @@ gb18030_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GB18030, PG_UTF8); - LocalToUtf(src, len, dest, - &gb18030_to_unicode_tree, - NULL, 0, - conv_18030_to_utf8, - PG_GB18030); + converted = LocalToUtf(src, len, dest, + &gb18030_to_unicode_tree, + NULL, 0, + conv_18030_to_utf8, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -211,14 +217,17 @@ utf8_to_gb18030(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GB18030); - UtfToLocal(src, len, dest, - &gb18030_from_unicode_tree, - NULL, 0, - conv_utf8_to_18030, - PG_GB18030); + converted = UtfToLocal(src, len, dest, + &gb18030_from_unicode_tree, + NULL, 0, + conv_utf8_to_18030, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c index 2ab8b16c8a8..881386d5347 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_gbk); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ gbk_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GBK, PG_UTF8); - LocalToUtf(src, len, dest, - &gbk_to_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = LocalToUtf(src, len, dest, + &gbk_to_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_gbk(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GBK); - UtfToLocal(src, len, dest, - &gbk_from_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = UtfToLocal(src, len, dest, + &gbk_from_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c index 3e49f67ea2f..d93a521badf 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c @@ -52,8 +52,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -100,6 +103,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -108,12 +112,15 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -122,7 +129,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -132,6 +139,7 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -140,12 +148,15 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -154,5 +165,5 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c index 67e713cca11..8ac93604a1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c @@ -26,8 +26,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859_1); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -37,6 +40,8 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_UTF8); @@ -45,7 +50,11 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_LATIN1, (const char *) src, len); + } if (!IS_HIGHBIT_SET(c)) *dest++ = c; else @@ -58,7 +67,7 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } Datum @@ -67,6 +76,8 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c, c1; @@ -76,7 +87,11 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_UTF8, (const char *) src, len); + } /* fast path for ASCII-subset characters */ if (!IS_HIGHBIT_SET(c)) { @@ -102,11 +117,15 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) len -= 2; } else + { + if (noError) + break; report_untranslatable_char(PG_UTF8, PG_LATIN1, (const char *) src, len); + } } } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c index 578f5df4e7f..317daa2d5ee 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_johab); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ johab_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_JOHAB, PG_UTF8); - LocalToUtf(src, len, dest, - &johab_to_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = LocalToUtf(src, len, dest, + &johab_to_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_johab(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_JOHAB); - UtfToLocal(src, len, dest, - &johab_from_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = UtfToLocal(src, len, dest, + &johab_from_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c index dd9fc2975ad..4c9348aba59 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ sjis_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_UTF8); - LocalToUtf(src, len, dest, - &sjis_to_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = LocalToUtf(src, len, dest, + &sjis_to_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SJIS); - UtfToLocal(src, len, dest, - &sjis_from_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = UtfToLocal(src, len, dest, + &sjis_from_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c index 4bcc886d674..1fffdc5930c 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_shift_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ shift_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &shift_jis_2004_to_unicode_tree, - LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = LocalToUtf(src, len, dest, + &shift_jis_2004_to_unicode_tree, + LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SHIFT_JIS_2004); - UtfToLocal(src, len, dest, - &shift_jis_2004_from_unicode_tree, - ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = UtfToLocal(src, len, dest, + &shift_jis_2004_from_unicode_tree, + ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c index c8e512994a1..d9471dad097 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_uhc); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ uhc_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UHC, PG_UTF8); - LocalToUtf(src, len, dest, - &uhc_to_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = LocalToUtf(src, len, dest, + &uhc_to_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_uhc(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_UHC); - UtfToLocal(src, len, dest, - &uhc_from_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = UtfToLocal(src, len, dest, + &uhc_from_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c index 0c9493dee56..110ba5677d0 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c @@ -48,8 +48,11 @@ PG_FUNCTION_INFO_V1(utf8_to_win); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -81,6 +84,7 @@ win_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -89,12 +93,15 @@ win_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -103,7 +110,7 @@ win_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -113,6 +120,7 @@ utf8_to_win(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -121,12 +129,15 @@ utf8_to_win(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -135,5 +146,5 @@ utf8_to_win(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/mbutils.c b/src/backend/utils/mb/mbutils.c index 2578573b0ab..65753860e35 100644 --- a/src/backend/utils/mb/mbutils.c +++ b/src/backend/utils/mb/mbutils.c @@ -406,12 +406,13 @@ pg_do_encoding_conversion(unsigned char *src, int len, MemoryContextAllocHuge(CurrentMemoryContext, (Size) len * MAX_CONVERSION_GROWTH + 1); - OidFunctionCall5(proc, - Int32GetDatum(src_encoding), - Int32GetDatum(dest_encoding), - CStringGetDatum(src), - CStringGetDatum(result), - Int32GetDatum(len)); + (void) OidFunctionCall6(proc, + Int32GetDatum(src_encoding), + Int32GetDatum(dest_encoding), + CStringGetDatum(src), + CStringGetDatum(result), + Int32GetDatum(len), + BoolGetDatum(false)); /* * If the result is large, it's worth repalloc'ing to release any extra @@ -849,12 +850,13 @@ pg_unicode_to_server(pg_wchar c, unsigned char *s) c_as_utf8[c_as_utf8_len] = '\0'; /* Convert, or throw error if we can't */ - FunctionCall5(Utf8ToServerConvProc, + FunctionCall6(Utf8ToServerConvProc, Int32GetDatum(PG_UTF8), Int32GetDatum(server_encoding), CStringGetDatum(c_as_utf8), CStringGetDatum(s), - Int32GetDatum(c_as_utf8_len)); + Int32GetDatum(c_as_utf8_len), + BoolGetDatum(false)); } diff --git a/src/bin/pg_upgrade/check.c b/src/bin/pg_upgrade/check.c index 43fc297eb69..ee6be95b08d 100644 --- a/src/bin/pg_upgrade/check.c +++ b/src/bin/pg_upgrade/check.c @@ -28,6 +28,7 @@ static void check_for_reg_data_type_usage(ClusterInfo *cluster); static void check_for_jsonb_9_4_usage(ClusterInfo *cluster); static void check_for_pg_role_prefix(ClusterInfo *cluster); static void check_for_new_tablespace_dir(ClusterInfo *new_cluster); +static void check_for_user_defined_encoding_conversions(ClusterInfo *cluster); static char *get_canonical_locale_name(int category, const char *locale); @@ -102,6 +103,15 @@ check_and_dump_old_cluster(bool live_check) check_for_reg_data_type_usage(&old_cluster); check_for_isn_and_int8_passing_mismatch(&old_cluster); + /* + * PG 14 changed the function signature of encoding conversion functions. + * Conversions from older versions cannot be upgraded automatically + * because the user-defined functions used by the encoding conversions + * need to changed to match the new signature. + */ + if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1300) + check_for_user_defined_encoding_conversions(&old_cluster); + /* * Pre-PG 14 allowed user defined postfix operators, which are not * supported anymore. Verify there are none, iff applicable. @@ -1268,6 +1278,91 @@ check_for_pg_role_prefix(ClusterInfo *cluster) check_ok(); } +/* + * Verify that no user-defined encoding conversions exist. + */ +static void +check_for_user_defined_encoding_conversions(ClusterInfo *cluster) +{ + int dbnum; + FILE *script = NULL; + bool found = false; + char output_path[MAXPGPATH]; + + prep_status("Checking for user-defined encoding conversions"); + + snprintf(output_path, sizeof(output_path), + "encoding_conversions.txt"); + + /* Find any user defined encoding conversions */ + for (dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++) + { + PGresult *res; + bool db_used = false; + int ntups; + int rowno; + int i_conoid, + i_conname, + i_nspname; + DbInfo *active_db = &cluster->dbarr.dbs[dbnum]; + PGconn *conn = connectToServer(cluster, active_db->db_name); + + /* + * The query below hardcodes FirstNormalObjectId as 16384 rather than + * interpolating that C #define into the query because, if that + * #define is ever changed, the cutoff we want to use is the value + * used by pre-version 14 servers, not that of some future version. + */ + res = executeQueryOrDie(conn, + "SELECT c.oid as conoid, c.conname, n.nspname " + "FROM pg_catalog.pg_conversion c, " + " pg_catalog.pg_namespace n " + "WHERE c.connamespace = n.oid AND " + " c.oid >= 16384"); + ntups = PQntuples(res); + i_conoid = PQfnumber(res, "conoid"); + i_conname = PQfnumber(res, "conname"); + i_nspname = PQfnumber(res, "nspname"); + for (rowno = 0; rowno < ntups; rowno++) + { + found = true; + if (script == NULL && + (script = fopen_priv(output_path, "w")) == NULL) + pg_fatal("could not open file \"%s\": %s\n", + output_path, strerror(errno)); + if (!db_used) + { + fprintf(script, "In database: %s\n", active_db->db_name); + db_used = true; + } + fprintf(script, " (oid=%s) %s.%s\n", + PQgetvalue(res, rowno, i_conoid), + PQgetvalue(res, rowno, i_nspname), + PQgetvalue(res, rowno, i_conname)); + } + + PQclear(res); + + PQfinish(conn); + } + + if (script) + fclose(script); + + if (found) + { + pg_log(PG_REPORT, "fatal\n"); + pg_fatal("Your installation contains user-defined encoding conversions.\n" + "The conversion function parameters changed in PostgreSQL version 14\n" + "so this cluster cannot currently be upgraded. You can remove the\n" + "encoding conversions in the old cluster and restart the upgrade.\n" + "A list of user-defined encoding conversions is in the file:\n" + " %s\n\n", output_path); + } + else + check_ok(); +} + /* * get_canonical_locale_name diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index f8174061ef3..75b829e8514 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10766,388 +10766,388 @@ # conversion functions { oid => '4302', descr => 'internal conversion function for KOI8R to MULE_INTERNAL', - proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_mic', + proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4303', descr => 'internal conversion function for MULE_INTERNAL to KOI8R', - proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_koi8r', + proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4304', descr => 'internal conversion function for ISO-8859-5 to MULE_INTERNAL', - proname => 'iso_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_mic', + proname => 'iso_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4305', descr => 'internal conversion function for MULE_INTERNAL to ISO-8859-5', - proname => 'mic_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_iso', + proname => 'mic_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4306', descr => 'internal conversion function for WIN1251 to MULE_INTERNAL', - proname => 'win1251_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_mic', + proname => 'win1251_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4307', descr => 'internal conversion function for MULE_INTERNAL to WIN1251', - proname => 'mic_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1251', + proname => 'mic_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4308', descr => 'internal conversion function for WIN866 to MULE_INTERNAL', - proname => 'win866_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_mic', + proname => 'win866_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4309', descr => 'internal conversion function for MULE_INTERNAL to WIN866', - proname => 'mic_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win866', + proname => 'mic_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4310', descr => 'internal conversion function for KOI8R to WIN1251', - proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4311', descr => 'internal conversion function for WIN1251 to KOI8R', - proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4312', descr => 'internal conversion function for KOI8R to WIN866', - proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_win866', + proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4313', descr => 'internal conversion function for WIN866 to KOI8R', - proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_koi8r', + proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4314', descr => 'internal conversion function for WIN866 to WIN1251', - proname => 'win866_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win866_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4315', descr => 'internal conversion function for WIN1251 to WIN866', - proname => 'win1251_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4316', descr => 'internal conversion function for ISO-8859-5 to KOI8R', - proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_koi8r', + proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4317', descr => 'internal conversion function for KOI8R to ISO-8859-5', - proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_iso', + proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4318', descr => 'internal conversion function for ISO-8859-5 to WIN1251', - proname => 'iso_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win1251', + proname => 'iso_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4319', descr => 'internal conversion function for WIN1251 to ISO-8859-5', - proname => 'win1251_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_iso', + proname => 'win1251_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4320', descr => 'internal conversion function for ISO-8859-5 to WIN866', - proname => 'iso_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win866', + proname => 'iso_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4321', descr => 'internal conversion function for WIN866 to ISO-8859-5', - proname => 'win866_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_iso', + proname => 'win866_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4322', descr => 'internal conversion function for EUC_CN to MULE_INTERNAL', - proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_mic', + proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_mic', probin => '$libdir/euc_cn_and_mic' }, { oid => '4323', descr => 'internal conversion function for MULE_INTERNAL to EUC_CN', - proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_cn', + proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_cn', probin => '$libdir/euc_cn_and_mic' }, { oid => '4324', descr => 'internal conversion function for EUC_JP to SJIS', - proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_sjis', + proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4325', descr => 'internal conversion function for SJIS to EUC_JP', - proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_euc_jp', + proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4326', descr => 'internal conversion function for EUC_JP to MULE_INTERNAL', - proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_mic', + proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4327', descr => 'internal conversion function for SJIS to MULE_INTERNAL', - proname => 'sjis_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_mic', + proname => 'sjis_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4328', descr => 'internal conversion function for MULE_INTERNAL to EUC_JP', - proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_jp', + proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4329', descr => 'internal conversion function for MULE_INTERNAL to SJIS', - proname => 'mic_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_sjis', + proname => 'mic_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4330', descr => 'internal conversion function for EUC_KR to MULE_INTERNAL', - proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_mic', + proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_mic', probin => '$libdir/euc_kr_and_mic' }, { oid => '4331', descr => 'internal conversion function for MULE_INTERNAL to EUC_KR', - proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_kr', + proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_kr', probin => '$libdir/euc_kr_and_mic' }, { oid => '4332', descr => 'internal conversion function for EUC_TW to BIG5', - proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_big5', + proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4333', descr => 'internal conversion function for BIG5 to EUC_TW', - proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_euc_tw', + proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4334', descr => 'internal conversion function for EUC_TW to MULE_INTERNAL', - proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_mic', + proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4335', descr => 'internal conversion function for BIG5 to MULE_INTERNAL', - proname => 'big5_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_mic', + proname => 'big5_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4336', descr => 'internal conversion function for MULE_INTERNAL to EUC_TW', - proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_tw', + proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4337', descr => 'internal conversion function for MULE_INTERNAL to BIG5', - proname => 'mic_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_big5', + proname => 'mic_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4338', descr => 'internal conversion function for LATIN2 to MULE_INTERNAL', - proname => 'latin2_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin2_to_mic', + proname => 'latin2_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4339', descr => 'internal conversion function for MULE_INTERNAL to LATIN2', - proname => 'mic_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin2', + proname => 'mic_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4340', descr => 'internal conversion function for WIN1250 to MULE_INTERNAL', - proname => 'win1250_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1250_to_mic', + proname => 'win1250_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4341', descr => 'internal conversion function for MULE_INTERNAL to WIN1250', - proname => 'mic_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1250', + proname => 'mic_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4342', descr => 'internal conversion function for LATIN2 to WIN1250', - proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4343', descr => 'internal conversion function for WIN1250 to LATIN2', - proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4344', descr => 'internal conversion function for LATIN1 to MULE_INTERNAL', - proname => 'latin1_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin1_to_mic', + proname => 'latin1_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin1_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4345', descr => 'internal conversion function for MULE_INTERNAL to LATIN1', - proname => 'mic_to_latin1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin1', + proname => 'mic_to_latin1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin1', probin => '$libdir/latin_and_mic' }, { oid => '4346', descr => 'internal conversion function for LATIN3 to MULE_INTERNAL', - proname => 'latin3_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin3_to_mic', + proname => 'latin3_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin3_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4347', descr => 'internal conversion function for MULE_INTERNAL to LATIN3', - proname => 'mic_to_latin3', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin3', + proname => 'mic_to_latin3', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin3', probin => '$libdir/latin_and_mic' }, { oid => '4348', descr => 'internal conversion function for LATIN4 to MULE_INTERNAL', - proname => 'latin4_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin4_to_mic', + proname => 'latin4_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin4_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4349', descr => 'internal conversion function for MULE_INTERNAL to LATIN4', - proname => 'mic_to_latin4', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin4', + proname => 'mic_to_latin4', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin4', probin => '$libdir/latin_and_mic' }, { oid => '4352', descr => 'internal conversion function for BIG5 to UTF8', - proname => 'big5_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_utf8', + proname => 'big5_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_utf8', probin => '$libdir/utf8_and_big5' }, { oid => '4353', descr => 'internal conversion function for UTF8 to BIG5', - proname => 'utf8_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_big5', + proname => 'utf8_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_big5', probin => '$libdir/utf8_and_big5' }, { oid => '4354', descr => 'internal conversion function for UTF8 to KOI8R', - proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8r', + proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8r', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4355', descr => 'internal conversion function for KOI8R to UTF8', - proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_utf8', + proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4356', descr => 'internal conversion function for UTF8 to KOI8U', - proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8u', + proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8u', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4357', descr => 'internal conversion function for KOI8U to UTF8', - proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8u_to_utf8', + proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8u_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4358', descr => 'internal conversion function for UTF8 to WIN', - proname => 'utf8_to_win', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_win', + proname => 'utf8_to_win', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_win', probin => '$libdir/utf8_and_win' }, { oid => '4359', descr => 'internal conversion function for WIN to UTF8', - proname => 'win_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win_to_utf8', + proname => 'win_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win_to_utf8', probin => '$libdir/utf8_and_win' }, { oid => '4360', descr => 'internal conversion function for EUC_CN to UTF8', - proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_utf8', + proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_utf8', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4361', descr => 'internal conversion function for UTF8 to EUC_CN', - proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_cn', + proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_cn', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4362', descr => 'internal conversion function for EUC_JP to UTF8', - proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_utf8', + proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_utf8', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4363', descr => 'internal conversion function for UTF8 to EUC_JP', - proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_jp', + proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jp', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4364', descr => 'internal conversion function for EUC_KR to UTF8', - proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_utf8', + proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_utf8', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4365', descr => 'internal conversion function for UTF8 to EUC_KR', - proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_kr', + proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_kr', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4366', descr => 'internal conversion function for EUC_TW to UTF8', - proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_utf8', + proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_utf8', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4367', descr => 'internal conversion function for UTF8 to EUC_TW', - proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_tw', + proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_tw', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4368', descr => 'internal conversion function for GB18030 to UTF8', - proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gb18030_to_utf8', + proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gb18030_to_utf8', probin => '$libdir/utf8_and_gb18030' }, { oid => '4369', descr => 'internal conversion function for UTF8 to GB18030', - proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gb18030', + proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gb18030', probin => '$libdir/utf8_and_gb18030' }, { oid => '4370', descr => 'internal conversion function for GBK to UTF8', - proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gbk_to_utf8', + proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gbk_to_utf8', probin => '$libdir/utf8_and_gbk' }, { oid => '4371', descr => 'internal conversion function for UTF8 to GBK', - proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gbk', + proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gbk', probin => '$libdir/utf8_and_gbk' }, { oid => '4372', descr => 'internal conversion function for UTF8 to ISO-8859 2-16', - proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_iso8859', + proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859', probin => '$libdir/utf8_and_iso8859' }, { oid => '4373', descr => 'internal conversion function for ISO-8859 2-16 to UTF8', - proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso8859_to_utf8', + proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_to_utf8', probin => '$libdir/utf8_and_iso8859' }, { oid => '4374', descr => 'internal conversion function for LATIN1 to UTF8', - proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_1_to_utf8', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4375', descr => 'internal conversion function for UTF8 to LATIN1', - proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859_1', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4376', descr => 'internal conversion function for JOHAB to UTF8', - proname => 'johab_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'johab_to_utf8', + proname => 'johab_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'johab_to_utf8', probin => '$libdir/utf8_and_johab' }, { oid => '4377', descr => 'internal conversion function for UTF8 to JOHAB', - proname => 'utf8_to_johab', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_johab', + proname => 'utf8_to_johab', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_johab', probin => '$libdir/utf8_and_johab' }, { oid => '4378', descr => 'internal conversion function for SJIS to UTF8', - proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_utf8', + proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_utf8', probin => '$libdir/utf8_and_sjis' }, { oid => '4379', descr => 'internal conversion function for UTF8 to SJIS', - proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_sjis', + proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_sjis', probin => '$libdir/utf8_and_sjis' }, { oid => '4380', descr => 'internal conversion function for UHC to UTF8', - proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'uhc_to_utf8', + proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'uhc_to_utf8', probin => '$libdir/utf8_and_uhc' }, { oid => '4381', descr => 'internal conversion function for UTF8 to UHC', - proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_uhc', + proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_uhc', probin => '$libdir/utf8_and_uhc' }, { oid => '4382', descr => 'internal conversion function for EUC_JIS_2004 to UTF8', - proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_utf8', probin => '$libdir/utf8_and_euc2004' }, { oid => '4383', descr => 'internal conversion function for UTF8 to EUC_JIS_2004', - proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jis_2004', probin => '$libdir/utf8_and_euc2004' }, { oid => '4384', descr => 'internal conversion function for SHIFT_JIS_2004 to UTF8', - proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_utf8', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4385', descr => 'internal conversion function for UTF8 to SHIFT_JIS_2004', - proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_shift_jis_2004', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4386', descr => 'internal conversion function for EUC_JIS_2004 to SHIFT_JIS_2004', proname => 'euc_jis_2004_to_shift_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_shift_jis_2004', probin => '$libdir/euc2004_sjis2004' }, { oid => '4387', descr => 'internal conversion function for SHIFT_JIS_2004 to EUC_JIS_2004', proname => 'shift_jis_2004_to_euc_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_euc_jis_2004', probin => '$libdir/euc2004_sjis2004' }, diff --git a/src/include/mb/pg_wchar.h b/src/include/mb/pg_wchar.h index 64b22e4b0d4..346a41a1f3d 100644 --- a/src/include/mb/pg_wchar.h +++ b/src/include/mb/pg_wchar.h @@ -627,18 +627,18 @@ extern void pg_unicode_to_server(pg_wchar c, unsigned char *s); extern unsigned short BIG5toCNS(unsigned short big5, unsigned char *lc); extern unsigned short CNStoBIG5(unsigned short cns, unsigned char lc); -extern void UtfToLocal(const unsigned char *utf, int len, - unsigned char *iso, - const pg_mb_radix_tree *map, - const pg_utf_to_local_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); -extern void LocalToUtf(const unsigned char *iso, int len, - unsigned char *utf, - const pg_mb_radix_tree *map, - const pg_local_to_utf_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); +extern int UtfToLocal(const unsigned char *utf, int len, + unsigned char *iso, + const pg_mb_radix_tree *map, + const pg_utf_to_local_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); +extern int LocalToUtf(const unsigned char *iso, int len, + unsigned char *utf, + const pg_mb_radix_tree *map, + const pg_local_to_utf_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); extern bool pg_verifymbstr(const char *mbstr, int len, bool noError); extern bool pg_verify_mbstr(int encoding, const char *mbstr, int len, @@ -656,18 +656,19 @@ extern void report_invalid_encoding(int encoding, const char *mbstr, int len) pg extern void report_untranslatable_char(int src_encoding, int dest_encoding, const char *mbstr, int len) pg_attribute_noreturn(); -extern void local2local(const unsigned char *l, unsigned char *p, int len, - int src_encoding, int dest_encoding, const unsigned char *tab); -extern void latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding); -extern void mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding); -extern void latin2mic_with_table(const unsigned char *l, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); -extern void mic2latin_with_table(const unsigned char *mic, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); +extern int local2local(const unsigned char *l, unsigned char *p, int len, + int src_encoding, int dest_encoding, const unsigned char *tab, + bool noError); +extern int latin2mic(const unsigned char *l, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int mic2latin(const unsigned char *mic, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int latin2mic_with_table(const unsigned char *l, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); +extern int mic2latin_with_table(const unsigned char *mic, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); #ifdef WIN32 extern WCHAR *pgwin32_message_to_UTF16(const char *str, int len, int *utf16len); diff --git a/src/test/regress/expected/opr_sanity.out b/src/test/regress/expected/opr_sanity.out index 254ca06d3dd..23ba60e395f 100644 --- a/src/test/regress/expected/opr_sanity.out +++ b/src/test/regress/expected/opr_sanity.out @@ -1052,13 +1052,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); oid | proname | oid | conname -----+---------+-----+--------- (0 rows) diff --git a/src/test/regress/sql/opr_sanity.sql b/src/test/regress/sql/opr_sanity.sql index bbd3834b634..04691745981 100644 --- a/src/test/regress/sql/opr_sanity.sql +++ b/src/test/regress/sql/opr_sanity.sql @@ -556,13 +556,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); -- Check for conprocs that don't perform the specific conversion that -- pg_conversion alleges they do, by trying to invoke each conversion -- 2.29.2 --------------39E46EF15EBFAA37D53332E5 Content-Type: text/x-patch; charset=UTF-8; name="v3-0003-Add-tests-for-the-new-noError-variants-of-built-i.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="v3-0003-Add-tests-for-the-new-noError-variants-of-built-i.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 34+ messages in thread
* [PATCH v3 2/5] Change conversion function signature. @ 2021-01-28 16:42 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 34+ messages in thread From: Heikki Linnakangas @ 2021-01-28 16:42 UTC (permalink / raw) Add a 'noError' argument, so that we can try to convert a buffer without knowing the character boundaries beforehand. The functions now need to return the number of input bytes successfully converted. This is is a backwards-incompatible change, if you have created a custom encoding conversion with CREATE CONVERSION. This adds a check to pg_upgrade for that, refusing the upgrade if there are any user-defined encoding conversions. --- doc/src/sgml/ref/create_conversion.sgml | 5 +- src/backend/commands/conversioncmds.c | 27 +- src/backend/utils/error/elog.c | 2 + src/backend/utils/mb/conv.c | 112 +++++- .../cyrillic_and_mic/cyrillic_and_mic.c | 127 ++++--- .../euc2004_sjis2004/euc2004_sjis2004.c | 96 ++++- .../euc_cn_and_mic/euc_cn_and_mic.c | 57 ++- .../euc_jp_and_sjis/euc_jp_and_sjis.c | 153 ++++++-- .../euc_kr_and_mic/euc_kr_and_mic.c | 57 ++- .../euc_tw_and_big5/euc_tw_and_big5.c | 165 +++++++-- .../latin2_and_win1250/latin2_and_win1250.c | 49 ++- .../latin_and_mic/latin_and_mic.c | 43 ++- .../utf8_and_big5/utf8_and_big5.c | 37 +- .../utf8_and_cyrillic/utf8_and_cyrillic.c | 67 ++-- .../utf8_and_euc2004/utf8_and_euc2004.c | 37 +- .../utf8_and_euc_cn/utf8_and_euc_cn.c | 37 +- .../utf8_and_euc_jp/utf8_and_euc_jp.c | 37 +- .../utf8_and_euc_kr/utf8_and_euc_kr.c | 37 +- .../utf8_and_euc_tw/utf8_and_euc_tw.c | 37 +- .../utf8_and_gb18030/utf8_and_gb18030.c | 37 +- .../utf8_and_gbk/utf8_and_gbk.c | 37 +- .../utf8_and_iso8859/utf8_and_iso8859.c | 43 ++- .../utf8_and_iso8859_1/utf8_and_iso8859_1.c | 27 +- .../utf8_and_johab/utf8_and_johab.c | 37 +- .../utf8_and_sjis/utf8_and_sjis.c | 37 +- .../utf8_and_sjis2004/utf8_and_sjis2004.c | 37 +- .../utf8_and_uhc/utf8_and_uhc.c | 37 +- .../utf8_and_win/utf8_and_win.c | 43 ++- src/backend/utils/mb/mbutils.c | 18 +- src/bin/pg_upgrade/check.c | 95 +++++ src/include/catalog/pg_proc.dat | 332 +++++++++--------- src/include/mb/pg_wchar.h | 49 +-- src/test/regress/expected/opr_sanity.out | 7 +- src/test/regress/sql/opr_sanity.sql | 7 +- 34 files changed, 1390 insertions(+), 635 deletions(-) diff --git a/doc/src/sgml/ref/create_conversion.sgml b/doc/src/sgml/ref/create_conversion.sgml index e7700fecfc5..f014a676c88 100644 --- a/doc/src/sgml/ref/create_conversion.sgml +++ b/doc/src/sgml/ref/create_conversion.sgml @@ -117,8 +117,9 @@ conv_proc( integer, -- destination encoding ID cstring, -- source string (null terminated C string) internal, -- destination (fill with a null terminated C string) - integer -- source string length -) RETURNS void; + integer, -- source string length + boolean -- if true, don't throw an error if conversion fails +) RETURNS integer; </programlisting></para> </listitem> </varlistentry> diff --git a/src/backend/commands/conversioncmds.c b/src/backend/commands/conversioncmds.c index f7ff321de71..d2041466911 100644 --- a/src/backend/commands/conversioncmds.c +++ b/src/backend/commands/conversioncmds.c @@ -45,8 +45,9 @@ CreateConversionCommand(CreateConversionStmt *stmt) const char *from_encoding_name = stmt->for_encoding_name; const char *to_encoding_name = stmt->to_encoding_name; List *func_name = stmt->func_name; - static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID}; + static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID, BOOLOID}; char result[1]; + Datum funcresult; /* Convert list of names to a name and namespace */ namespaceId = QualifiedNameGetCreationNamespace(stmt->conversion_name, @@ -92,8 +93,8 @@ CreateConversionCommand(CreateConversionStmt *stmt) funcoid = LookupFuncName(func_name, sizeof(funcargs) / sizeof(Oid), funcargs, false); - /* Check it returns VOID, else it's probably the wrong function */ - if (get_func_rettype(funcoid) != VOIDOID) + /* Check it returns int4, else it's probably the wrong function */ + if (get_func_rettype(funcoid) != INT4OID) ereport(ERROR, (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), errmsg("encoding conversion function %s must return type %s", @@ -111,12 +112,20 @@ CreateConversionCommand(CreateConversionStmt *stmt) * string; the conversion function should throw an error if it can't * perform the requested conversion. */ - OidFunctionCall5(funcoid, - Int32GetDatum(from_encoding), - Int32GetDatum(to_encoding), - CStringGetDatum(""), - CStringGetDatum(result), - Int32GetDatum(0)); + funcresult = OidFunctionCall6(funcoid, + Int32GetDatum(from_encoding), + Int32GetDatum(to_encoding), + CStringGetDatum(""), + CStringGetDatum(result), + Int32GetDatum(0), + BoolGetDatum(false)); + + /* The function should return 0 for empty input. Might as well check that, too. */ + if (DatumGetInt32(funcresult) != 0) + ereport(ERROR, + (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), + errmsg("encoding conversion function %s returned incorrect result for empty input", + NameListToString(func_name)))); /* * All seem ok, go ahead (possible failure would be a duplicate conversion diff --git a/src/backend/utils/error/elog.c b/src/backend/utils/error/elog.c index 80c26724612..762f77d533c 100644 --- a/src/backend/utils/error/elog.c +++ b/src/backend/utils/error/elog.c @@ -2280,6 +2280,8 @@ write_console(const char *line, int len) * Conversion on non-win32 platforms is not implemented yet. It requires * non-throw version of pg_do_encoding_conversion(), that converts * unconvertable characters to '?' without errors. + * + * XXX: We have a no-throw version now. It doesn't convert to '?' though. */ #endif diff --git a/src/backend/utils/mb/conv.c b/src/backend/utils/mb/conv.c index a07b54bd3b8..b83358bc7a5 100644 --- a/src/backend/utils/mb/conv.c +++ b/src/backend/utils/mb/conv.c @@ -26,14 +26,16 @@ * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the target charset, or 0 if there is no equivalent code. */ -void +int local2local(const unsigned char *l, unsigned char *p, int len, int src_encoding, int dest_encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -41,7 +43,11 @@ local2local(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(src_encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -50,13 +56,19 @@ local2local(const unsigned char *l, if (c2) *p++ = c2; else + { + if (noError) + break; report_untranslatable_char(src_encoding, dest_encoding, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -67,17 +79,22 @@ local2local(const unsigned char *l, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = l; int c1; while (len > 0) { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (IS_HIGHBIT_SET(c1)) *p++ = lc; *p++ = c1; @@ -85,6 +102,8 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, len--; } *p = '\0'; + + return l - start; } /* @@ -95,17 +114,22 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -118,17 +142,27 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1])) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); + } *p++ = mic[1]; mic += 2; len -= 2; } } *p = '\0'; + + return mic - start; } @@ -144,14 +178,16 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the mule encoding, or 0 if there is no equivalent code. */ -void +int latin2mic_with_table(const unsigned char *l, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -159,7 +195,11 @@ latin2mic_with_table(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -171,13 +211,19 @@ latin2mic_with_table(const unsigned char *l, *p++ = c2; } else + { + if (noError) + break; report_untranslatable_char(encoding, PG_MULE_INTERNAL, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -192,14 +238,16 @@ latin2mic_with_table(const unsigned char *l, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the local charset, or 0 if there is no equivalent code. */ -void +int mic2latin_with_table(const unsigned char *mic, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = mic; unsigned char c1, c2; @@ -207,7 +255,11 @@ mic2latin_with_table(const unsigned char *mic, { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -220,11 +272,17 @@ mic2latin_with_table(const unsigned char *mic, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1]) || (c2 = tab[mic[1] - HIGHBIT]) == 0) { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); break; /* keep compiler quiet */ @@ -235,6 +293,8 @@ mic2latin_with_table(const unsigned char *mic, } } *p = '\0'; + + return mic - start; } /* @@ -425,17 +485,19 @@ pg_mb_radix_conv(const pg_mb_radix_tree *rt, * * See pg_wchar.h for more details about the data structures used here. */ -void +int UtfToLocal(const unsigned char *utf, int len, unsigned char *iso, const pg_mb_radix_tree *map, const pg_utf_to_local_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, bool noError) { uint32 iutf; int l; const pg_utf_to_local_combined *cp; + const unsigned char *start = utf; + const unsigned char *cur = utf; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -449,6 +511,8 @@ UtfToLocal(const unsigned char *utf, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*utf == '\0') break; @@ -584,15 +648,19 @@ UtfToLocal(const unsigned char *utf, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(PG_UTF8, encoding, (const char *) (utf - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(PG_UTF8, (const char *) utf, len); *iso = '\0'; + + return cur - start; } /* @@ -616,18 +684,24 @@ UtfToLocal(const unsigned char *utf, int len, * (if provided) is applied. An error is raised if no match is found. * * See pg_wchar.h for more details about the data structures used here. + * + * Returns the number of input bytes consumed. If noError is true, this can + * be less than 'len'. */ -void +int LocalToUtf(const unsigned char *iso, int len, unsigned char *utf, const pg_mb_radix_tree *map, const pg_local_to_utf_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, + bool noError) { uint32 iiso; int l; const pg_local_to_utf_combined *cp; + const unsigned char *start = iso; + const unsigned char *cur = iso; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -641,6 +715,8 @@ LocalToUtf(const unsigned char *iso, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*iso == '\0') break; @@ -723,13 +799,17 @@ LocalToUtf(const unsigned char *iso, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(encoding, PG_UTF8, (const char *) (iso - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(encoding, (const char *) iso, len); *utf = '\0'; + + return cur - start; } diff --git a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c index 4c5b02654de..368c2deb5e4 100644 --- a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c @@ -44,8 +44,11 @@ PG_FUNCTION_INFO_V1(win866_to_iso); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -306,12 +309,14 @@ koi8r_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -320,12 +325,14 @@ mic_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_KOI8R); - mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -334,12 +341,14 @@ iso_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -348,12 +357,14 @@ mic_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_ISO_8859_5); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -362,12 +373,14 @@ win1251_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -376,12 +389,14 @@ mic_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1251); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -390,12 +405,14 @@ win866_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -404,12 +421,14 @@ mic_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN866); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -418,12 +437,14 @@ koi8r_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN1251); - local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -432,12 +453,14 @@ win1251_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_KOI8R); - local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi); + converted = local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -446,12 +469,14 @@ koi8r_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN866); - local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -460,12 +485,14 @@ win866_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_KOI8R); - local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi); + converted = local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -474,12 +501,14 @@ win866_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_WIN1251); - local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251); + converted = local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -488,12 +517,14 @@ win1251_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_WIN866); - local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866); + converted = local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -502,12 +533,14 @@ iso_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_KOI8R); - local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -516,12 +549,14 @@ koi8r_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_ISO_8859_5); - local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso); + converted = local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -530,12 +565,14 @@ iso_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN1251); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -544,12 +581,14 @@ win1251_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso); + converted = local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -558,12 +597,14 @@ iso_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN866); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -572,10 +613,12 @@ win866_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso); + converted = local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c index 4d7fb116cfd..88529c644cf 100644 --- a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c @@ -19,8 +19,8 @@ PG_MODULE_MAGIC; PG_FUNCTION_INFO_V1(euc_jis_2004_to_shift_jis_2004); PG_FUNCTION_INFO_V1(shift_jis_2004_to_euc_jis_2004); -static void euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len); -static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len); +static int euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError); /* ---------- * conv_proc( @@ -28,8 +28,11 @@ static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -39,12 +42,14 @@ euc_jis_2004_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_SHIFT_JIS_2004); - euc_jis_20042shift_jis_2004(src, dest, len); + converted = euc_jis_20042shift_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -53,20 +58,23 @@ shift_jis_2004_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_EUC_JIS_2004); - shift_jis_20042euc_jis_2004(src, dest, len); + converted = shift_jis_20042euc_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_JIS_2004 -> SHIFT_JIS_2004 */ -static void -euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, ku, ten; @@ -79,8 +87,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -90,8 +102,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) l = pg_encoding_verifymbchar(PG_EUC_JIS_2004, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (c1 == SS2 && l == 2) /* JIS X 0201 kana? */ { @@ -121,8 +137,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) *p++ = (ku + 0x19b) >> 1; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } if (ku % 2) @@ -132,8 +152,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; @@ -149,8 +173,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ku >= 63 && ku <= 94) *p++ = (ku + 0x181) >> 1; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (ku % 2) { @@ -159,20 +187,30 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else - report_invalid_encoding(PG_EUC_JIS_2004, + { + if (noError) + break; + report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } euc += l; len -= l; } *p = '\0'; + + return euc - start; } /* @@ -212,9 +250,10 @@ get_ten(int b, int *ku) * SHIFT_JIS_2004 ---> EUC_JIS_2004 */ -static void -shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len) +static int +shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1; int ku, ten, @@ -230,8 +269,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -241,8 +284,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len l = pg_encoding_verifymbchar(PG_SHIFT_JIS_2004, (const char *) sjis, len); if (l < 0 || l > len) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf && l == 1) { @@ -266,8 +313,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x100; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xe0 && c1 <= 0xef) /* plane 1 62ku-94ku */ @@ -275,9 +326,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x180; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, - (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xf0 && c1 <= 0xf3) /* plane 2 @@ -286,8 +340,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } switch (c1) { case 0xf0: @@ -309,16 +367,24 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 == 0xf4 && kubun == 1) ku = 15; else ku = (c1 << 1) - 0x19a - kubun; } else + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (plane == 2) *p++ = SS3; @@ -330,4 +396,6 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c index e9bb896935f..a8da733803d 100644 --- a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_cn2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_cn(const unsigned char *mic, unsigned char *p, int len); +static int euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_cn_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_cn_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_MULE_INTERNAL); - euc_cn2mic(src, dest, len); + converted = euc_cn2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_CN); - mic2euc_cn(src, dest, len); + converted = mic2euc_cn(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_CN ---> MIC */ -static void -euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; while (len > 0) @@ -76,7 +84,11 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (len < 2 || !IS_HIGHBIT_SET(euc[1])) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = LC_GB2312_80; *p++ = c1; *p++ = euc[1]; @@ -86,21 +98,28 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_CN */ -static void -mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) @@ -109,11 +128,19 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (c1 != LC_GB2312_80) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_CN, (const char *) mic, len); + } if (len < 3 || !IS_HIGHBIT_SET(mic[1]) || !IS_HIGHBIT_SET(mic[2])) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } mic++; *p++ = *mic++; *p++ = *mic++; @@ -122,12 +149,18 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; } } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c index 5059f917a98..cc4817dc4cd 100644 --- a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c @@ -42,17 +42,20 @@ PG_FUNCTION_INFO_V1(mic_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void sjis2mic(const unsigned char *sjis, unsigned char *p, int len); -static void mic2sjis(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_jp(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len); -static void sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len); +static int sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError); +static int mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_jp_to_sjis(PG_FUNCTION_ARGS) @@ -60,12 +63,14 @@ euc_jp_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_SJIS); - euc_jp2sjis(src, dest, len); + converted = euc_jp2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -74,12 +79,14 @@ sjis_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_EUC_JP); - sjis2euc_jp(src, dest, len); + converted = sjis2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -88,12 +95,14 @@ euc_jp_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_MULE_INTERNAL); - euc_jp2mic(src, dest, len); + converted = euc_jp2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -102,12 +111,14 @@ mic_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_JP); - mic2euc_jp(src, dest, len); + converted = mic2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -116,12 +127,14 @@ sjis_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_MULE_INTERNAL); - sjis2mic(src, dest, len); + converted = sjis2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -130,20 +143,23 @@ mic_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_SJIS); - mic2sjis(src, dest, len); + converted = mic2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * SJIS ---> MIC */ -static void -sjis2mic(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -167,7 +183,11 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) * JIS X0208, X0212, user defined extended characters */ if (len < 2 || !ISSJISHEAD(c1) || !ISSJISTAIL(sjis[1])) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } c2 = sjis[1]; k = (c1 << 8) + c2; if (k >= 0xed40 && k < 0xf040) @@ -257,21 +277,28 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; } } *p = '\0'; + + return sjis - start; } /* * MIC ---> SJIS */ -static void -mic2sjis(const unsigned char *mic, unsigned char *p, int len) +static int +mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1, c2, k, @@ -284,8 +311,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -293,8 +324,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) *p++ = mic[1]; else if (c1 == LC_JISX0208) @@ -350,20 +385,27 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_SJIS, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP ---> MIC */ -static void -euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -374,8 +416,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -383,8 +429,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* 1 byte kana? */ *p++ = LC_JISX0201K; @@ -406,14 +456,17 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_JP */ -static void -mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -424,8 +477,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -433,8 +490,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) { *p++ = SS2; @@ -452,20 +513,27 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_JP, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP -> SJIS */ -static void -euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, c2, k; @@ -478,8 +546,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -487,8 +559,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* hankaku kana? */ @@ -551,14 +627,17 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * SJIS ---> EUC_JP */ -static void -sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -573,8 +652,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -582,8 +665,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_SJIS, (const char *) sjis, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf) { /* JIS X0201 (1 byte kana) */ @@ -680,4 +767,6 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c index ac823d6c270..a5b51617e52 100644 --- a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_kr2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_kr(const unsigned char *mic, unsigned char *p, int len); +static int euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_kr_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_kr_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_MULE_INTERNAL); - euc_kr2mic(src, dest, len); + converted = euc_kr2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_KR); - mic2euc_kr(src, dest, len); + converted = mic2euc_kr(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_KR ---> MIC */ -static void -euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -78,8 +86,12 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_KR, (const char *) euc, len); if (l != 2) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = LC_KS5601; *p++ = c1; *p++ = euc[1]; @@ -89,22 +101,29 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_KR */ -static void -mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -115,8 +134,12 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -124,18 +147,28 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_KS5601) { *p++ = mic[1]; *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_KR, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c index 66c242d7f36..ebb4e0acd53 100644 --- a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c @@ -32,17 +32,20 @@ PG_FUNCTION_INFO_V1(mic_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_tw2big5(const unsigned char *euc, unsigned char *p, int len); -static void big52euc_tw(const unsigned char *euc, unsigned char *p, int len); -static void big52mic(const unsigned char *big5, unsigned char *p, int len); -static void mic2big5(const unsigned char *mic, unsigned char *p, int len); -static void euc_tw2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_tw(const unsigned char *mic, unsigned char *p, int len); +static int euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52euc_tw(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError); +static int mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_tw_to_big5(PG_FUNCTION_ARGS) @@ -50,12 +53,14 @@ euc_tw_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_BIG5); - euc_tw2big5(src, dest, len); + converted = euc_tw2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -64,12 +69,14 @@ big5_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_EUC_TW); - big52euc_tw(src, dest, len); + converted = big52euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -78,12 +85,14 @@ euc_tw_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_MULE_INTERNAL); - euc_tw2mic(src, dest, len); + converted = euc_tw2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -92,12 +101,14 @@ mic_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_TW); - mic2euc_tw(src, dest, len); + converted = mic2euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -106,12 +117,14 @@ big5_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_MULE_INTERNAL); - big52mic(src, dest, len); + converted = big52mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -120,21 +133,24 @@ mic_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_BIG5); - mic2big5(src, dest, len); + converted = mic2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_TW ---> Big5 */ -static void -euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; unsigned char c1; unsigned short big5buf, cnsBuf; @@ -149,8 +165,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Verify and decode the next EUC_TW input character */ l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -171,8 +191,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Write it out in Big5 */ big5buf = CNStoBIG5(cnsBuf, lc); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_EUC_TW, PG_BIG5, (const char *) euc, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; @@ -182,22 +206,29 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * Big5 ---> EUC_TW */ -static void -big52euc_tw(const unsigned char *big5, unsigned char *p, int len) +static int +big52euc_tw(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -212,8 +243,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); @@ -237,8 +272,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_EUC_TW, (const char *) big5, len); + } big5 += l; len -= l; @@ -256,14 +295,17 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) } } *p = '\0'; + + return big5 - start; } /* * EUC_TW ---> MIC */ -static void -euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -274,8 +316,12 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -304,22 +350,29 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_TW */ -static void -mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -330,8 +383,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -339,8 +396,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1) { *p++ = mic[1]; @@ -362,20 +423,27 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[3]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_TW, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * Big5 ---> MIC */ -static void -big52mic(const unsigned char *big5, unsigned char *p, int len) +static int +big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -389,8 +457,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } *p++ = c1; big5++; len--; @@ -398,8 +470,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); if (lc != 0) @@ -412,20 +488,27 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_MULE_INTERNAL, (const char *) big5, len); + } big5 += l; len -= l; } *p = '\0'; + + return big5 - start; } /* * MIC ---> Big5 */ -static void -mic2big5(const unsigned char *mic, unsigned char *p, int len) +static int +mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -438,8 +521,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -447,8 +534,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1 || c1 == LC_CNS11643_2 || c1 == LCPRV2_B) { if (c1 == LCPRV2_B) @@ -462,16 +553,26 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } big5buf = CNStoBIG5(cnsBuf, c1); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c index 2e28e6780a5..8610fcb69aa 100644 --- a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c +++ b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(win1250_to_latin2); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -82,12 +85,14 @@ latin2_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -96,12 +101,14 @@ mic_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN2); - mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -110,13 +117,15 @@ win1250_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - win1250_2_iso88592); + converted = latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -125,13 +134,15 @@ mic_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1250); - mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - iso88592_2_win1250); + converted = mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -140,12 +151,15 @@ latin2_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_WIN1250); - local2local(src, dest, len, PG_LATIN2, PG_WIN1250, iso88592_2_win1250); + converted = local2local(src, dest, len, PG_LATIN2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -154,10 +168,13 @@ win1250_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_LATIN2); - local2local(src, dest, len, PG_WIN1250, PG_LATIN2, win1250_2_iso88592); + converted = local2local(src, dest, len, PG_WIN1250, PG_LATIN2, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c index bc651410f21..bff27d1c295 100644 --- a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(mic_to_latin4); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -42,12 +45,14 @@ latin1_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,12 +61,14 @@ mic_to_latin1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN1); - mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -70,12 +77,14 @@ latin3_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN3, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -84,12 +93,14 @@ mic_to_latin3(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN3); - mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,12 +109,14 @@ latin4_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN4, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -112,10 +125,12 @@ mic_to_latin4(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN4); - mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c index d6067cdc24e..3838b15cab9 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ big5_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_UTF8); - LocalToUtf(src, len, dest, - &big5_to_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = LocalToUtf(src, len, dest, + &big5_to_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_BIG5); - UtfToLocal(src, len, dest, - &big5_from_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = UtfToLocal(src, len, dest, + &big5_from_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c index ed90e8e682e..75719fe5f1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c @@ -33,8 +33,11 @@ PG_FUNCTION_INFO_V1(koi8u_to_utf8); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -44,16 +47,19 @@ utf8_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8R); - UtfToLocal(src, len, dest, - &koi8r_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = UtfToLocal(src, len, dest, + &koi8r_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -62,16 +68,19 @@ koi8r_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8r_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = LocalToUtf(src, len, dest, + &koi8r_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -80,16 +89,19 @@ utf8_to_koi8u(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8U); - UtfToLocal(src, len, dest, - &koi8u_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = UtfToLocal(src, len, dest, + &koi8u_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,14 +110,17 @@ koi8u_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8U, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8u_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = LocalToUtf(src, len, dest, + &koi8u_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c index d699affce47..5391001951a 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jis_2004_to_unicode_tree, - LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = LocalToUtf(src, len, dest, + &euc_jis_2004_to_unicode_tree, + LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JIS_2004); - UtfToLocal(src, len, dest, - &euc_jis_2004_from_unicode_tree, - ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = UtfToLocal(src, len, dest, + &euc_jis_2004_from_unicode_tree, + ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c index d7c0ba6a58b..c87d1bf2398 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_cn_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_cn_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = LocalToUtf(src, len, dest, + &euc_cn_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_CN); - UtfToLocal(src, len, dest, - &euc_cn_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = UtfToLocal(src, len, dest, + &euc_cn_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c index 13a3a23e77b..6a55134db21 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jp); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jp_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jp_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = LocalToUtf(src, len, dest, + &euc_jp_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JP); - UtfToLocal(src, len, dest, - &euc_jp_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = UtfToLocal(src, len, dest, + &euc_jp_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c index 1bbb8aaef7b..fe1924e2fec 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_kr_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_kr_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = LocalToUtf(src, len, dest, + &euc_kr_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_KR); - UtfToLocal(src, len, dest, - &euc_kr_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = UtfToLocal(src, len, dest, + &euc_kr_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c index 9830045dccd..68215659b57 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_tw); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_tw_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_tw_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = LocalToUtf(src, len, dest, + &euc_tw_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_TW); - UtfToLocal(src, len, dest, - &euc_tw_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = UtfToLocal(src, len, dest, + &euc_tw_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c index f86ecf27424..e1a59c39a4d 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c @@ -183,8 +183,11 @@ conv_utf8_to_18030(uint32 code) * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -193,16 +196,19 @@ gb18030_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GB18030, PG_UTF8); - LocalToUtf(src, len, dest, - &gb18030_to_unicode_tree, - NULL, 0, - conv_18030_to_utf8, - PG_GB18030); + converted = LocalToUtf(src, len, dest, + &gb18030_to_unicode_tree, + NULL, 0, + conv_18030_to_utf8, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -211,14 +217,17 @@ utf8_to_gb18030(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GB18030); - UtfToLocal(src, len, dest, - &gb18030_from_unicode_tree, - NULL, 0, - conv_utf8_to_18030, - PG_GB18030); + converted = UtfToLocal(src, len, dest, + &gb18030_from_unicode_tree, + NULL, 0, + conv_utf8_to_18030, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c index 2ab8b16c8a8..881386d5347 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_gbk); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ gbk_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GBK, PG_UTF8); - LocalToUtf(src, len, dest, - &gbk_to_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = LocalToUtf(src, len, dest, + &gbk_to_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_gbk(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GBK); - UtfToLocal(src, len, dest, - &gbk_from_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = UtfToLocal(src, len, dest, + &gbk_from_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c index 3e49f67ea2f..d93a521badf 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c @@ -52,8 +52,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -100,6 +103,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -108,12 +112,15 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -122,7 +129,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -132,6 +139,7 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -140,12 +148,15 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -154,5 +165,5 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c index 67e713cca11..8ac93604a1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c @@ -26,8 +26,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859_1); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -37,6 +40,8 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_UTF8); @@ -45,7 +50,11 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_LATIN1, (const char *) src, len); + } if (!IS_HIGHBIT_SET(c)) *dest++ = c; else @@ -58,7 +67,7 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } Datum @@ -67,6 +76,8 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c, c1; @@ -76,7 +87,11 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_UTF8, (const char *) src, len); + } /* fast path for ASCII-subset characters */ if (!IS_HIGHBIT_SET(c)) { @@ -102,11 +117,15 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) len -= 2; } else + { + if (noError) + break; report_untranslatable_char(PG_UTF8, PG_LATIN1, (const char *) src, len); + } } } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c index 578f5df4e7f..317daa2d5ee 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_johab); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ johab_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_JOHAB, PG_UTF8); - LocalToUtf(src, len, dest, - &johab_to_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = LocalToUtf(src, len, dest, + &johab_to_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_johab(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_JOHAB); - UtfToLocal(src, len, dest, - &johab_from_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = UtfToLocal(src, len, dest, + &johab_from_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c index dd9fc2975ad..4c9348aba59 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ sjis_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_UTF8); - LocalToUtf(src, len, dest, - &sjis_to_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = LocalToUtf(src, len, dest, + &sjis_to_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SJIS); - UtfToLocal(src, len, dest, - &sjis_from_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = UtfToLocal(src, len, dest, + &sjis_from_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c index 4bcc886d674..1fffdc5930c 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_shift_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ shift_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &shift_jis_2004_to_unicode_tree, - LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = LocalToUtf(src, len, dest, + &shift_jis_2004_to_unicode_tree, + LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SHIFT_JIS_2004); - UtfToLocal(src, len, dest, - &shift_jis_2004_from_unicode_tree, - ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = UtfToLocal(src, len, dest, + &shift_jis_2004_from_unicode_tree, + ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c index c8e512994a1..d9471dad097 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_uhc); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ uhc_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UHC, PG_UTF8); - LocalToUtf(src, len, dest, - &uhc_to_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = LocalToUtf(src, len, dest, + &uhc_to_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_uhc(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_UHC); - UtfToLocal(src, len, dest, - &uhc_from_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = UtfToLocal(src, len, dest, + &uhc_from_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c index 0c9493dee56..110ba5677d0 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c @@ -48,8 +48,11 @@ PG_FUNCTION_INFO_V1(utf8_to_win); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -81,6 +84,7 @@ win_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -89,12 +93,15 @@ win_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -103,7 +110,7 @@ win_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -113,6 +120,7 @@ utf8_to_win(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -121,12 +129,15 @@ utf8_to_win(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -135,5 +146,5 @@ utf8_to_win(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/mbutils.c b/src/backend/utils/mb/mbutils.c index 2578573b0ab..65753860e35 100644 --- a/src/backend/utils/mb/mbutils.c +++ b/src/backend/utils/mb/mbutils.c @@ -406,12 +406,13 @@ pg_do_encoding_conversion(unsigned char *src, int len, MemoryContextAllocHuge(CurrentMemoryContext, (Size) len * MAX_CONVERSION_GROWTH + 1); - OidFunctionCall5(proc, - Int32GetDatum(src_encoding), - Int32GetDatum(dest_encoding), - CStringGetDatum(src), - CStringGetDatum(result), - Int32GetDatum(len)); + (void) OidFunctionCall6(proc, + Int32GetDatum(src_encoding), + Int32GetDatum(dest_encoding), + CStringGetDatum(src), + CStringGetDatum(result), + Int32GetDatum(len), + BoolGetDatum(false)); /* * If the result is large, it's worth repalloc'ing to release any extra @@ -849,12 +850,13 @@ pg_unicode_to_server(pg_wchar c, unsigned char *s) c_as_utf8[c_as_utf8_len] = '\0'; /* Convert, or throw error if we can't */ - FunctionCall5(Utf8ToServerConvProc, + FunctionCall6(Utf8ToServerConvProc, Int32GetDatum(PG_UTF8), Int32GetDatum(server_encoding), CStringGetDatum(c_as_utf8), CStringGetDatum(s), - Int32GetDatum(c_as_utf8_len)); + Int32GetDatum(c_as_utf8_len), + BoolGetDatum(false)); } diff --git a/src/bin/pg_upgrade/check.c b/src/bin/pg_upgrade/check.c index 43fc297eb69..ee6be95b08d 100644 --- a/src/bin/pg_upgrade/check.c +++ b/src/bin/pg_upgrade/check.c @@ -28,6 +28,7 @@ static void check_for_reg_data_type_usage(ClusterInfo *cluster); static void check_for_jsonb_9_4_usage(ClusterInfo *cluster); static void check_for_pg_role_prefix(ClusterInfo *cluster); static void check_for_new_tablespace_dir(ClusterInfo *new_cluster); +static void check_for_user_defined_encoding_conversions(ClusterInfo *cluster); static char *get_canonical_locale_name(int category, const char *locale); @@ -102,6 +103,15 @@ check_and_dump_old_cluster(bool live_check) check_for_reg_data_type_usage(&old_cluster); check_for_isn_and_int8_passing_mismatch(&old_cluster); + /* + * PG 14 changed the function signature of encoding conversion functions. + * Conversions from older versions cannot be upgraded automatically + * because the user-defined functions used by the encoding conversions + * need to changed to match the new signature. + */ + if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1300) + check_for_user_defined_encoding_conversions(&old_cluster); + /* * Pre-PG 14 allowed user defined postfix operators, which are not * supported anymore. Verify there are none, iff applicable. @@ -1268,6 +1278,91 @@ check_for_pg_role_prefix(ClusterInfo *cluster) check_ok(); } +/* + * Verify that no user-defined encoding conversions exist. + */ +static void +check_for_user_defined_encoding_conversions(ClusterInfo *cluster) +{ + int dbnum; + FILE *script = NULL; + bool found = false; + char output_path[MAXPGPATH]; + + prep_status("Checking for user-defined encoding conversions"); + + snprintf(output_path, sizeof(output_path), + "encoding_conversions.txt"); + + /* Find any user defined encoding conversions */ + for (dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++) + { + PGresult *res; + bool db_used = false; + int ntups; + int rowno; + int i_conoid, + i_conname, + i_nspname; + DbInfo *active_db = &cluster->dbarr.dbs[dbnum]; + PGconn *conn = connectToServer(cluster, active_db->db_name); + + /* + * The query below hardcodes FirstNormalObjectId as 16384 rather than + * interpolating that C #define into the query because, if that + * #define is ever changed, the cutoff we want to use is the value + * used by pre-version 14 servers, not that of some future version. + */ + res = executeQueryOrDie(conn, + "SELECT c.oid as conoid, c.conname, n.nspname " + "FROM pg_catalog.pg_conversion c, " + " pg_catalog.pg_namespace n " + "WHERE c.connamespace = n.oid AND " + " c.oid >= 16384"); + ntups = PQntuples(res); + i_conoid = PQfnumber(res, "conoid"); + i_conname = PQfnumber(res, "conname"); + i_nspname = PQfnumber(res, "nspname"); + for (rowno = 0; rowno < ntups; rowno++) + { + found = true; + if (script == NULL && + (script = fopen_priv(output_path, "w")) == NULL) + pg_fatal("could not open file \"%s\": %s\n", + output_path, strerror(errno)); + if (!db_used) + { + fprintf(script, "In database: %s\n", active_db->db_name); + db_used = true; + } + fprintf(script, " (oid=%s) %s.%s\n", + PQgetvalue(res, rowno, i_conoid), + PQgetvalue(res, rowno, i_nspname), + PQgetvalue(res, rowno, i_conname)); + } + + PQclear(res); + + PQfinish(conn); + } + + if (script) + fclose(script); + + if (found) + { + pg_log(PG_REPORT, "fatal\n"); + pg_fatal("Your installation contains user-defined encoding conversions.\n" + "The conversion function parameters changed in PostgreSQL version 14\n" + "so this cluster cannot currently be upgraded. You can remove the\n" + "encoding conversions in the old cluster and restart the upgrade.\n" + "A list of user-defined encoding conversions is in the file:\n" + " %s\n\n", output_path); + } + else + check_ok(); +} + /* * get_canonical_locale_name diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index f8174061ef3..75b829e8514 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10766,388 +10766,388 @@ # conversion functions { oid => '4302', descr => 'internal conversion function for KOI8R to MULE_INTERNAL', - proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_mic', + proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4303', descr => 'internal conversion function for MULE_INTERNAL to KOI8R', - proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_koi8r', + proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4304', descr => 'internal conversion function for ISO-8859-5 to MULE_INTERNAL', - proname => 'iso_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_mic', + proname => 'iso_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4305', descr => 'internal conversion function for MULE_INTERNAL to ISO-8859-5', - proname => 'mic_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_iso', + proname => 'mic_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4306', descr => 'internal conversion function for WIN1251 to MULE_INTERNAL', - proname => 'win1251_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_mic', + proname => 'win1251_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4307', descr => 'internal conversion function for MULE_INTERNAL to WIN1251', - proname => 'mic_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1251', + proname => 'mic_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4308', descr => 'internal conversion function for WIN866 to MULE_INTERNAL', - proname => 'win866_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_mic', + proname => 'win866_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4309', descr => 'internal conversion function for MULE_INTERNAL to WIN866', - proname => 'mic_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win866', + proname => 'mic_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4310', descr => 'internal conversion function for KOI8R to WIN1251', - proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4311', descr => 'internal conversion function for WIN1251 to KOI8R', - proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4312', descr => 'internal conversion function for KOI8R to WIN866', - proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_win866', + proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4313', descr => 'internal conversion function for WIN866 to KOI8R', - proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_koi8r', + proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4314', descr => 'internal conversion function for WIN866 to WIN1251', - proname => 'win866_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win866_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4315', descr => 'internal conversion function for WIN1251 to WIN866', - proname => 'win1251_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4316', descr => 'internal conversion function for ISO-8859-5 to KOI8R', - proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_koi8r', + proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4317', descr => 'internal conversion function for KOI8R to ISO-8859-5', - proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_iso', + proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4318', descr => 'internal conversion function for ISO-8859-5 to WIN1251', - proname => 'iso_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win1251', + proname => 'iso_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4319', descr => 'internal conversion function for WIN1251 to ISO-8859-5', - proname => 'win1251_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_iso', + proname => 'win1251_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4320', descr => 'internal conversion function for ISO-8859-5 to WIN866', - proname => 'iso_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win866', + proname => 'iso_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4321', descr => 'internal conversion function for WIN866 to ISO-8859-5', - proname => 'win866_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_iso', + proname => 'win866_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4322', descr => 'internal conversion function for EUC_CN to MULE_INTERNAL', - proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_mic', + proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_mic', probin => '$libdir/euc_cn_and_mic' }, { oid => '4323', descr => 'internal conversion function for MULE_INTERNAL to EUC_CN', - proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_cn', + proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_cn', probin => '$libdir/euc_cn_and_mic' }, { oid => '4324', descr => 'internal conversion function for EUC_JP to SJIS', - proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_sjis', + proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4325', descr => 'internal conversion function for SJIS to EUC_JP', - proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_euc_jp', + proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4326', descr => 'internal conversion function for EUC_JP to MULE_INTERNAL', - proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_mic', + proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4327', descr => 'internal conversion function for SJIS to MULE_INTERNAL', - proname => 'sjis_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_mic', + proname => 'sjis_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4328', descr => 'internal conversion function for MULE_INTERNAL to EUC_JP', - proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_jp', + proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4329', descr => 'internal conversion function for MULE_INTERNAL to SJIS', - proname => 'mic_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_sjis', + proname => 'mic_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4330', descr => 'internal conversion function for EUC_KR to MULE_INTERNAL', - proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_mic', + proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_mic', probin => '$libdir/euc_kr_and_mic' }, { oid => '4331', descr => 'internal conversion function for MULE_INTERNAL to EUC_KR', - proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_kr', + proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_kr', probin => '$libdir/euc_kr_and_mic' }, { oid => '4332', descr => 'internal conversion function for EUC_TW to BIG5', - proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_big5', + proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4333', descr => 'internal conversion function for BIG5 to EUC_TW', - proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_euc_tw', + proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4334', descr => 'internal conversion function for EUC_TW to MULE_INTERNAL', - proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_mic', + proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4335', descr => 'internal conversion function for BIG5 to MULE_INTERNAL', - proname => 'big5_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_mic', + proname => 'big5_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4336', descr => 'internal conversion function for MULE_INTERNAL to EUC_TW', - proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_tw', + proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4337', descr => 'internal conversion function for MULE_INTERNAL to BIG5', - proname => 'mic_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_big5', + proname => 'mic_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4338', descr => 'internal conversion function for LATIN2 to MULE_INTERNAL', - proname => 'latin2_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin2_to_mic', + proname => 'latin2_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4339', descr => 'internal conversion function for MULE_INTERNAL to LATIN2', - proname => 'mic_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin2', + proname => 'mic_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4340', descr => 'internal conversion function for WIN1250 to MULE_INTERNAL', - proname => 'win1250_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1250_to_mic', + proname => 'win1250_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4341', descr => 'internal conversion function for MULE_INTERNAL to WIN1250', - proname => 'mic_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1250', + proname => 'mic_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4342', descr => 'internal conversion function for LATIN2 to WIN1250', - proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4343', descr => 'internal conversion function for WIN1250 to LATIN2', - proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4344', descr => 'internal conversion function for LATIN1 to MULE_INTERNAL', - proname => 'latin1_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin1_to_mic', + proname => 'latin1_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin1_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4345', descr => 'internal conversion function for MULE_INTERNAL to LATIN1', - proname => 'mic_to_latin1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin1', + proname => 'mic_to_latin1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin1', probin => '$libdir/latin_and_mic' }, { oid => '4346', descr => 'internal conversion function for LATIN3 to MULE_INTERNAL', - proname => 'latin3_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin3_to_mic', + proname => 'latin3_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin3_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4347', descr => 'internal conversion function for MULE_INTERNAL to LATIN3', - proname => 'mic_to_latin3', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin3', + proname => 'mic_to_latin3', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin3', probin => '$libdir/latin_and_mic' }, { oid => '4348', descr => 'internal conversion function for LATIN4 to MULE_INTERNAL', - proname => 'latin4_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin4_to_mic', + proname => 'latin4_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin4_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4349', descr => 'internal conversion function for MULE_INTERNAL to LATIN4', - proname => 'mic_to_latin4', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin4', + proname => 'mic_to_latin4', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin4', probin => '$libdir/latin_and_mic' }, { oid => '4352', descr => 'internal conversion function for BIG5 to UTF8', - proname => 'big5_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_utf8', + proname => 'big5_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_utf8', probin => '$libdir/utf8_and_big5' }, { oid => '4353', descr => 'internal conversion function for UTF8 to BIG5', - proname => 'utf8_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_big5', + proname => 'utf8_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_big5', probin => '$libdir/utf8_and_big5' }, { oid => '4354', descr => 'internal conversion function for UTF8 to KOI8R', - proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8r', + proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8r', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4355', descr => 'internal conversion function for KOI8R to UTF8', - proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_utf8', + proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4356', descr => 'internal conversion function for UTF8 to KOI8U', - proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8u', + proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8u', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4357', descr => 'internal conversion function for KOI8U to UTF8', - proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8u_to_utf8', + proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8u_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4358', descr => 'internal conversion function for UTF8 to WIN', - proname => 'utf8_to_win', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_win', + proname => 'utf8_to_win', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_win', probin => '$libdir/utf8_and_win' }, { oid => '4359', descr => 'internal conversion function for WIN to UTF8', - proname => 'win_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win_to_utf8', + proname => 'win_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win_to_utf8', probin => '$libdir/utf8_and_win' }, { oid => '4360', descr => 'internal conversion function for EUC_CN to UTF8', - proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_utf8', + proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_utf8', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4361', descr => 'internal conversion function for UTF8 to EUC_CN', - proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_cn', + proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_cn', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4362', descr => 'internal conversion function for EUC_JP to UTF8', - proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_utf8', + proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_utf8', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4363', descr => 'internal conversion function for UTF8 to EUC_JP', - proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_jp', + proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jp', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4364', descr => 'internal conversion function for EUC_KR to UTF8', - proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_utf8', + proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_utf8', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4365', descr => 'internal conversion function for UTF8 to EUC_KR', - proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_kr', + proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_kr', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4366', descr => 'internal conversion function for EUC_TW to UTF8', - proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_utf8', + proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_utf8', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4367', descr => 'internal conversion function for UTF8 to EUC_TW', - proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_tw', + proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_tw', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4368', descr => 'internal conversion function for GB18030 to UTF8', - proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gb18030_to_utf8', + proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gb18030_to_utf8', probin => '$libdir/utf8_and_gb18030' }, { oid => '4369', descr => 'internal conversion function for UTF8 to GB18030', - proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gb18030', + proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gb18030', probin => '$libdir/utf8_and_gb18030' }, { oid => '4370', descr => 'internal conversion function for GBK to UTF8', - proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gbk_to_utf8', + proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gbk_to_utf8', probin => '$libdir/utf8_and_gbk' }, { oid => '4371', descr => 'internal conversion function for UTF8 to GBK', - proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gbk', + proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gbk', probin => '$libdir/utf8_and_gbk' }, { oid => '4372', descr => 'internal conversion function for UTF8 to ISO-8859 2-16', - proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_iso8859', + proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859', probin => '$libdir/utf8_and_iso8859' }, { oid => '4373', descr => 'internal conversion function for ISO-8859 2-16 to UTF8', - proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso8859_to_utf8', + proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_to_utf8', probin => '$libdir/utf8_and_iso8859' }, { oid => '4374', descr => 'internal conversion function for LATIN1 to UTF8', - proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_1_to_utf8', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4375', descr => 'internal conversion function for UTF8 to LATIN1', - proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859_1', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4376', descr => 'internal conversion function for JOHAB to UTF8', - proname => 'johab_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'johab_to_utf8', + proname => 'johab_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'johab_to_utf8', probin => '$libdir/utf8_and_johab' }, { oid => '4377', descr => 'internal conversion function for UTF8 to JOHAB', - proname => 'utf8_to_johab', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_johab', + proname => 'utf8_to_johab', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_johab', probin => '$libdir/utf8_and_johab' }, { oid => '4378', descr => 'internal conversion function for SJIS to UTF8', - proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_utf8', + proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_utf8', probin => '$libdir/utf8_and_sjis' }, { oid => '4379', descr => 'internal conversion function for UTF8 to SJIS', - proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_sjis', + proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_sjis', probin => '$libdir/utf8_and_sjis' }, { oid => '4380', descr => 'internal conversion function for UHC to UTF8', - proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'uhc_to_utf8', + proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'uhc_to_utf8', probin => '$libdir/utf8_and_uhc' }, { oid => '4381', descr => 'internal conversion function for UTF8 to UHC', - proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_uhc', + proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_uhc', probin => '$libdir/utf8_and_uhc' }, { oid => '4382', descr => 'internal conversion function for EUC_JIS_2004 to UTF8', - proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_utf8', probin => '$libdir/utf8_and_euc2004' }, { oid => '4383', descr => 'internal conversion function for UTF8 to EUC_JIS_2004', - proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jis_2004', probin => '$libdir/utf8_and_euc2004' }, { oid => '4384', descr => 'internal conversion function for SHIFT_JIS_2004 to UTF8', - proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_utf8', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4385', descr => 'internal conversion function for UTF8 to SHIFT_JIS_2004', - proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_shift_jis_2004', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4386', descr => 'internal conversion function for EUC_JIS_2004 to SHIFT_JIS_2004', proname => 'euc_jis_2004_to_shift_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_shift_jis_2004', probin => '$libdir/euc2004_sjis2004' }, { oid => '4387', descr => 'internal conversion function for SHIFT_JIS_2004 to EUC_JIS_2004', proname => 'shift_jis_2004_to_euc_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_euc_jis_2004', probin => '$libdir/euc2004_sjis2004' }, diff --git a/src/include/mb/pg_wchar.h b/src/include/mb/pg_wchar.h index 64b22e4b0d4..346a41a1f3d 100644 --- a/src/include/mb/pg_wchar.h +++ b/src/include/mb/pg_wchar.h @@ -627,18 +627,18 @@ extern void pg_unicode_to_server(pg_wchar c, unsigned char *s); extern unsigned short BIG5toCNS(unsigned short big5, unsigned char *lc); extern unsigned short CNStoBIG5(unsigned short cns, unsigned char lc); -extern void UtfToLocal(const unsigned char *utf, int len, - unsigned char *iso, - const pg_mb_radix_tree *map, - const pg_utf_to_local_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); -extern void LocalToUtf(const unsigned char *iso, int len, - unsigned char *utf, - const pg_mb_radix_tree *map, - const pg_local_to_utf_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); +extern int UtfToLocal(const unsigned char *utf, int len, + unsigned char *iso, + const pg_mb_radix_tree *map, + const pg_utf_to_local_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); +extern int LocalToUtf(const unsigned char *iso, int len, + unsigned char *utf, + const pg_mb_radix_tree *map, + const pg_local_to_utf_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); extern bool pg_verifymbstr(const char *mbstr, int len, bool noError); extern bool pg_verify_mbstr(int encoding, const char *mbstr, int len, @@ -656,18 +656,19 @@ extern void report_invalid_encoding(int encoding, const char *mbstr, int len) pg extern void report_untranslatable_char(int src_encoding, int dest_encoding, const char *mbstr, int len) pg_attribute_noreturn(); -extern void local2local(const unsigned char *l, unsigned char *p, int len, - int src_encoding, int dest_encoding, const unsigned char *tab); -extern void latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding); -extern void mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding); -extern void latin2mic_with_table(const unsigned char *l, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); -extern void mic2latin_with_table(const unsigned char *mic, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); +extern int local2local(const unsigned char *l, unsigned char *p, int len, + int src_encoding, int dest_encoding, const unsigned char *tab, + bool noError); +extern int latin2mic(const unsigned char *l, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int mic2latin(const unsigned char *mic, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int latin2mic_with_table(const unsigned char *l, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); +extern int mic2latin_with_table(const unsigned char *mic, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); #ifdef WIN32 extern WCHAR *pgwin32_message_to_UTF16(const char *str, int len, int *utf16len); diff --git a/src/test/regress/expected/opr_sanity.out b/src/test/regress/expected/opr_sanity.out index 254ca06d3dd..23ba60e395f 100644 --- a/src/test/regress/expected/opr_sanity.out +++ b/src/test/regress/expected/opr_sanity.out @@ -1052,13 +1052,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); oid | proname | oid | conname -----+---------+-----+--------- (0 rows) diff --git a/src/test/regress/sql/opr_sanity.sql b/src/test/regress/sql/opr_sanity.sql index bbd3834b634..04691745981 100644 --- a/src/test/regress/sql/opr_sanity.sql +++ b/src/test/regress/sql/opr_sanity.sql @@ -556,13 +556,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); -- Check for conprocs that don't perform the specific conversion that -- pg_conversion alleges they do, by trying to invoke each conversion -- 2.29.2 --------------39E46EF15EBFAA37D53332E5 Content-Type: text/x-patch; charset=UTF-8; name="v3-0003-Add-tests-for-the-new-noError-variants-of-built-i.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="v3-0003-Add-tests-for-the-new-noError-variants-of-built-i.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 34+ messages in thread
* [PATCH v3 2/5] Change conversion function signature. @ 2021-01-28 16:42 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 34+ messages in thread From: Heikki Linnakangas @ 2021-01-28 16:42 UTC (permalink / raw) Add a 'noError' argument, so that we can try to convert a buffer without knowing the character boundaries beforehand. The functions now need to return the number of input bytes successfully converted. This is is a backwards-incompatible change, if you have created a custom encoding conversion with CREATE CONVERSION. This adds a check to pg_upgrade for that, refusing the upgrade if there are any user-defined encoding conversions. --- doc/src/sgml/ref/create_conversion.sgml | 5 +- src/backend/commands/conversioncmds.c | 27 +- src/backend/utils/error/elog.c | 2 + src/backend/utils/mb/conv.c | 112 +++++- .../cyrillic_and_mic/cyrillic_and_mic.c | 127 ++++--- .../euc2004_sjis2004/euc2004_sjis2004.c | 96 ++++- .../euc_cn_and_mic/euc_cn_and_mic.c | 57 ++- .../euc_jp_and_sjis/euc_jp_and_sjis.c | 153 ++++++-- .../euc_kr_and_mic/euc_kr_and_mic.c | 57 ++- .../euc_tw_and_big5/euc_tw_and_big5.c | 165 +++++++-- .../latin2_and_win1250/latin2_and_win1250.c | 49 ++- .../latin_and_mic/latin_and_mic.c | 43 ++- .../utf8_and_big5/utf8_and_big5.c | 37 +- .../utf8_and_cyrillic/utf8_and_cyrillic.c | 67 ++-- .../utf8_and_euc2004/utf8_and_euc2004.c | 37 +- .../utf8_and_euc_cn/utf8_and_euc_cn.c | 37 +- .../utf8_and_euc_jp/utf8_and_euc_jp.c | 37 +- .../utf8_and_euc_kr/utf8_and_euc_kr.c | 37 +- .../utf8_and_euc_tw/utf8_and_euc_tw.c | 37 +- .../utf8_and_gb18030/utf8_and_gb18030.c | 37 +- .../utf8_and_gbk/utf8_and_gbk.c | 37 +- .../utf8_and_iso8859/utf8_and_iso8859.c | 43 ++- .../utf8_and_iso8859_1/utf8_and_iso8859_1.c | 27 +- .../utf8_and_johab/utf8_and_johab.c | 37 +- .../utf8_and_sjis/utf8_and_sjis.c | 37 +- .../utf8_and_sjis2004/utf8_and_sjis2004.c | 37 +- .../utf8_and_uhc/utf8_and_uhc.c | 37 +- .../utf8_and_win/utf8_and_win.c | 43 ++- src/backend/utils/mb/mbutils.c | 18 +- src/bin/pg_upgrade/check.c | 95 +++++ src/include/catalog/pg_proc.dat | 332 +++++++++--------- src/include/mb/pg_wchar.h | 49 +-- src/test/regress/expected/opr_sanity.out | 7 +- src/test/regress/sql/opr_sanity.sql | 7 +- 34 files changed, 1390 insertions(+), 635 deletions(-) diff --git a/doc/src/sgml/ref/create_conversion.sgml b/doc/src/sgml/ref/create_conversion.sgml index e7700fecfc5..f014a676c88 100644 --- a/doc/src/sgml/ref/create_conversion.sgml +++ b/doc/src/sgml/ref/create_conversion.sgml @@ -117,8 +117,9 @@ conv_proc( integer, -- destination encoding ID cstring, -- source string (null terminated C string) internal, -- destination (fill with a null terminated C string) - integer -- source string length -) RETURNS void; + integer, -- source string length + boolean -- if true, don't throw an error if conversion fails +) RETURNS integer; </programlisting></para> </listitem> </varlistentry> diff --git a/src/backend/commands/conversioncmds.c b/src/backend/commands/conversioncmds.c index f7ff321de71..d2041466911 100644 --- a/src/backend/commands/conversioncmds.c +++ b/src/backend/commands/conversioncmds.c @@ -45,8 +45,9 @@ CreateConversionCommand(CreateConversionStmt *stmt) const char *from_encoding_name = stmt->for_encoding_name; const char *to_encoding_name = stmt->to_encoding_name; List *func_name = stmt->func_name; - static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID}; + static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID, BOOLOID}; char result[1]; + Datum funcresult; /* Convert list of names to a name and namespace */ namespaceId = QualifiedNameGetCreationNamespace(stmt->conversion_name, @@ -92,8 +93,8 @@ CreateConversionCommand(CreateConversionStmt *stmt) funcoid = LookupFuncName(func_name, sizeof(funcargs) / sizeof(Oid), funcargs, false); - /* Check it returns VOID, else it's probably the wrong function */ - if (get_func_rettype(funcoid) != VOIDOID) + /* Check it returns int4, else it's probably the wrong function */ + if (get_func_rettype(funcoid) != INT4OID) ereport(ERROR, (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), errmsg("encoding conversion function %s must return type %s", @@ -111,12 +112,20 @@ CreateConversionCommand(CreateConversionStmt *stmt) * string; the conversion function should throw an error if it can't * perform the requested conversion. */ - OidFunctionCall5(funcoid, - Int32GetDatum(from_encoding), - Int32GetDatum(to_encoding), - CStringGetDatum(""), - CStringGetDatum(result), - Int32GetDatum(0)); + funcresult = OidFunctionCall6(funcoid, + Int32GetDatum(from_encoding), + Int32GetDatum(to_encoding), + CStringGetDatum(""), + CStringGetDatum(result), + Int32GetDatum(0), + BoolGetDatum(false)); + + /* The function should return 0 for empty input. Might as well check that, too. */ + if (DatumGetInt32(funcresult) != 0) + ereport(ERROR, + (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), + errmsg("encoding conversion function %s returned incorrect result for empty input", + NameListToString(func_name)))); /* * All seem ok, go ahead (possible failure would be a duplicate conversion diff --git a/src/backend/utils/error/elog.c b/src/backend/utils/error/elog.c index 80c26724612..762f77d533c 100644 --- a/src/backend/utils/error/elog.c +++ b/src/backend/utils/error/elog.c @@ -2280,6 +2280,8 @@ write_console(const char *line, int len) * Conversion on non-win32 platforms is not implemented yet. It requires * non-throw version of pg_do_encoding_conversion(), that converts * unconvertable characters to '?' without errors. + * + * XXX: We have a no-throw version now. It doesn't convert to '?' though. */ #endif diff --git a/src/backend/utils/mb/conv.c b/src/backend/utils/mb/conv.c index a07b54bd3b8..b83358bc7a5 100644 --- a/src/backend/utils/mb/conv.c +++ b/src/backend/utils/mb/conv.c @@ -26,14 +26,16 @@ * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the target charset, or 0 if there is no equivalent code. */ -void +int local2local(const unsigned char *l, unsigned char *p, int len, int src_encoding, int dest_encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -41,7 +43,11 @@ local2local(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(src_encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -50,13 +56,19 @@ local2local(const unsigned char *l, if (c2) *p++ = c2; else + { + if (noError) + break; report_untranslatable_char(src_encoding, dest_encoding, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -67,17 +79,22 @@ local2local(const unsigned char *l, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = l; int c1; while (len > 0) { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (IS_HIGHBIT_SET(c1)) *p++ = lc; *p++ = c1; @@ -85,6 +102,8 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, len--; } *p = '\0'; + + return l - start; } /* @@ -95,17 +114,22 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -118,17 +142,27 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1])) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); + } *p++ = mic[1]; mic += 2; len -= 2; } } *p = '\0'; + + return mic - start; } @@ -144,14 +178,16 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the mule encoding, or 0 if there is no equivalent code. */ -void +int latin2mic_with_table(const unsigned char *l, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -159,7 +195,11 @@ latin2mic_with_table(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -171,13 +211,19 @@ latin2mic_with_table(const unsigned char *l, *p++ = c2; } else + { + if (noError) + break; report_untranslatable_char(encoding, PG_MULE_INTERNAL, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -192,14 +238,16 @@ latin2mic_with_table(const unsigned char *l, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the local charset, or 0 if there is no equivalent code. */ -void +int mic2latin_with_table(const unsigned char *mic, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = mic; unsigned char c1, c2; @@ -207,7 +255,11 @@ mic2latin_with_table(const unsigned char *mic, { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -220,11 +272,17 @@ mic2latin_with_table(const unsigned char *mic, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1]) || (c2 = tab[mic[1] - HIGHBIT]) == 0) { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); break; /* keep compiler quiet */ @@ -235,6 +293,8 @@ mic2latin_with_table(const unsigned char *mic, } } *p = '\0'; + + return mic - start; } /* @@ -425,17 +485,19 @@ pg_mb_radix_conv(const pg_mb_radix_tree *rt, * * See pg_wchar.h for more details about the data structures used here. */ -void +int UtfToLocal(const unsigned char *utf, int len, unsigned char *iso, const pg_mb_radix_tree *map, const pg_utf_to_local_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, bool noError) { uint32 iutf; int l; const pg_utf_to_local_combined *cp; + const unsigned char *start = utf; + const unsigned char *cur = utf; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -449,6 +511,8 @@ UtfToLocal(const unsigned char *utf, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*utf == '\0') break; @@ -584,15 +648,19 @@ UtfToLocal(const unsigned char *utf, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(PG_UTF8, encoding, (const char *) (utf - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(PG_UTF8, (const char *) utf, len); *iso = '\0'; + + return cur - start; } /* @@ -616,18 +684,24 @@ UtfToLocal(const unsigned char *utf, int len, * (if provided) is applied. An error is raised if no match is found. * * See pg_wchar.h for more details about the data structures used here. + * + * Returns the number of input bytes consumed. If noError is true, this can + * be less than 'len'. */ -void +int LocalToUtf(const unsigned char *iso, int len, unsigned char *utf, const pg_mb_radix_tree *map, const pg_local_to_utf_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, + bool noError) { uint32 iiso; int l; const pg_local_to_utf_combined *cp; + const unsigned char *start = iso; + const unsigned char *cur = iso; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -641,6 +715,8 @@ LocalToUtf(const unsigned char *iso, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*iso == '\0') break; @@ -723,13 +799,17 @@ LocalToUtf(const unsigned char *iso, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(encoding, PG_UTF8, (const char *) (iso - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(encoding, (const char *) iso, len); *utf = '\0'; + + return cur - start; } diff --git a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c index 4c5b02654de..368c2deb5e4 100644 --- a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c @@ -44,8 +44,11 @@ PG_FUNCTION_INFO_V1(win866_to_iso); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -306,12 +309,14 @@ koi8r_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -320,12 +325,14 @@ mic_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_KOI8R); - mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -334,12 +341,14 @@ iso_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -348,12 +357,14 @@ mic_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_ISO_8859_5); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -362,12 +373,14 @@ win1251_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -376,12 +389,14 @@ mic_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1251); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -390,12 +405,14 @@ win866_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -404,12 +421,14 @@ mic_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN866); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -418,12 +437,14 @@ koi8r_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN1251); - local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -432,12 +453,14 @@ win1251_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_KOI8R); - local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi); + converted = local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -446,12 +469,14 @@ koi8r_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN866); - local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -460,12 +485,14 @@ win866_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_KOI8R); - local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi); + converted = local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -474,12 +501,14 @@ win866_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_WIN1251); - local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251); + converted = local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -488,12 +517,14 @@ win1251_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_WIN866); - local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866); + converted = local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -502,12 +533,14 @@ iso_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_KOI8R); - local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -516,12 +549,14 @@ koi8r_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_ISO_8859_5); - local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso); + converted = local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -530,12 +565,14 @@ iso_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN1251); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -544,12 +581,14 @@ win1251_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso); + converted = local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -558,12 +597,14 @@ iso_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN866); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -572,10 +613,12 @@ win866_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso); + converted = local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c index 4d7fb116cfd..88529c644cf 100644 --- a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c @@ -19,8 +19,8 @@ PG_MODULE_MAGIC; PG_FUNCTION_INFO_V1(euc_jis_2004_to_shift_jis_2004); PG_FUNCTION_INFO_V1(shift_jis_2004_to_euc_jis_2004); -static void euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len); -static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len); +static int euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError); /* ---------- * conv_proc( @@ -28,8 +28,11 @@ static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -39,12 +42,14 @@ euc_jis_2004_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_SHIFT_JIS_2004); - euc_jis_20042shift_jis_2004(src, dest, len); + converted = euc_jis_20042shift_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -53,20 +58,23 @@ shift_jis_2004_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_EUC_JIS_2004); - shift_jis_20042euc_jis_2004(src, dest, len); + converted = shift_jis_20042euc_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_JIS_2004 -> SHIFT_JIS_2004 */ -static void -euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, ku, ten; @@ -79,8 +87,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -90,8 +102,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) l = pg_encoding_verifymbchar(PG_EUC_JIS_2004, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (c1 == SS2 && l == 2) /* JIS X 0201 kana? */ { @@ -121,8 +137,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) *p++ = (ku + 0x19b) >> 1; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } if (ku % 2) @@ -132,8 +152,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; @@ -149,8 +173,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ku >= 63 && ku <= 94) *p++ = (ku + 0x181) >> 1; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (ku % 2) { @@ -159,20 +187,30 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else - report_invalid_encoding(PG_EUC_JIS_2004, + { + if (noError) + break; + report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } euc += l; len -= l; } *p = '\0'; + + return euc - start; } /* @@ -212,9 +250,10 @@ get_ten(int b, int *ku) * SHIFT_JIS_2004 ---> EUC_JIS_2004 */ -static void -shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len) +static int +shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1; int ku, ten, @@ -230,8 +269,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -241,8 +284,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len l = pg_encoding_verifymbchar(PG_SHIFT_JIS_2004, (const char *) sjis, len); if (l < 0 || l > len) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf && l == 1) { @@ -266,8 +313,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x100; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xe0 && c1 <= 0xef) /* plane 1 62ku-94ku */ @@ -275,9 +326,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x180; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, - (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xf0 && c1 <= 0xf3) /* plane 2 @@ -286,8 +340,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } switch (c1) { case 0xf0: @@ -309,16 +367,24 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 == 0xf4 && kubun == 1) ku = 15; else ku = (c1 << 1) - 0x19a - kubun; } else + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (plane == 2) *p++ = SS3; @@ -330,4 +396,6 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c index e9bb896935f..a8da733803d 100644 --- a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_cn2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_cn(const unsigned char *mic, unsigned char *p, int len); +static int euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_cn_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_cn_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_MULE_INTERNAL); - euc_cn2mic(src, dest, len); + converted = euc_cn2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_CN); - mic2euc_cn(src, dest, len); + converted = mic2euc_cn(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_CN ---> MIC */ -static void -euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; while (len > 0) @@ -76,7 +84,11 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (len < 2 || !IS_HIGHBIT_SET(euc[1])) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = LC_GB2312_80; *p++ = c1; *p++ = euc[1]; @@ -86,21 +98,28 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_CN */ -static void -mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) @@ -109,11 +128,19 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (c1 != LC_GB2312_80) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_CN, (const char *) mic, len); + } if (len < 3 || !IS_HIGHBIT_SET(mic[1]) || !IS_HIGHBIT_SET(mic[2])) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } mic++; *p++ = *mic++; *p++ = *mic++; @@ -122,12 +149,18 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; } } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c index 5059f917a98..cc4817dc4cd 100644 --- a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c @@ -42,17 +42,20 @@ PG_FUNCTION_INFO_V1(mic_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void sjis2mic(const unsigned char *sjis, unsigned char *p, int len); -static void mic2sjis(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_jp(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len); -static void sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len); +static int sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError); +static int mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_jp_to_sjis(PG_FUNCTION_ARGS) @@ -60,12 +63,14 @@ euc_jp_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_SJIS); - euc_jp2sjis(src, dest, len); + converted = euc_jp2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -74,12 +79,14 @@ sjis_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_EUC_JP); - sjis2euc_jp(src, dest, len); + converted = sjis2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -88,12 +95,14 @@ euc_jp_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_MULE_INTERNAL); - euc_jp2mic(src, dest, len); + converted = euc_jp2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -102,12 +111,14 @@ mic_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_JP); - mic2euc_jp(src, dest, len); + converted = mic2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -116,12 +127,14 @@ sjis_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_MULE_INTERNAL); - sjis2mic(src, dest, len); + converted = sjis2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -130,20 +143,23 @@ mic_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_SJIS); - mic2sjis(src, dest, len); + converted = mic2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * SJIS ---> MIC */ -static void -sjis2mic(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -167,7 +183,11 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) * JIS X0208, X0212, user defined extended characters */ if (len < 2 || !ISSJISHEAD(c1) || !ISSJISTAIL(sjis[1])) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } c2 = sjis[1]; k = (c1 << 8) + c2; if (k >= 0xed40 && k < 0xf040) @@ -257,21 +277,28 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; } } *p = '\0'; + + return sjis - start; } /* * MIC ---> SJIS */ -static void -mic2sjis(const unsigned char *mic, unsigned char *p, int len) +static int +mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1, c2, k, @@ -284,8 +311,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -293,8 +324,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) *p++ = mic[1]; else if (c1 == LC_JISX0208) @@ -350,20 +385,27 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_SJIS, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP ---> MIC */ -static void -euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -374,8 +416,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -383,8 +429,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* 1 byte kana? */ *p++ = LC_JISX0201K; @@ -406,14 +456,17 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_JP */ -static void -mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -424,8 +477,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -433,8 +490,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) { *p++ = SS2; @@ -452,20 +513,27 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_JP, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP -> SJIS */ -static void -euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, c2, k; @@ -478,8 +546,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -487,8 +559,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* hankaku kana? */ @@ -551,14 +627,17 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * SJIS ---> EUC_JP */ -static void -sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -573,8 +652,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -582,8 +665,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_SJIS, (const char *) sjis, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf) { /* JIS X0201 (1 byte kana) */ @@ -680,4 +767,6 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c index ac823d6c270..a5b51617e52 100644 --- a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_kr2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_kr(const unsigned char *mic, unsigned char *p, int len); +static int euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_kr_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_kr_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_MULE_INTERNAL); - euc_kr2mic(src, dest, len); + converted = euc_kr2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_KR); - mic2euc_kr(src, dest, len); + converted = mic2euc_kr(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_KR ---> MIC */ -static void -euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -78,8 +86,12 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_KR, (const char *) euc, len); if (l != 2) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = LC_KS5601; *p++ = c1; *p++ = euc[1]; @@ -89,22 +101,29 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_KR */ -static void -mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -115,8 +134,12 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -124,18 +147,28 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_KS5601) { *p++ = mic[1]; *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_KR, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c index 66c242d7f36..ebb4e0acd53 100644 --- a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c @@ -32,17 +32,20 @@ PG_FUNCTION_INFO_V1(mic_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_tw2big5(const unsigned char *euc, unsigned char *p, int len); -static void big52euc_tw(const unsigned char *euc, unsigned char *p, int len); -static void big52mic(const unsigned char *big5, unsigned char *p, int len); -static void mic2big5(const unsigned char *mic, unsigned char *p, int len); -static void euc_tw2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_tw(const unsigned char *mic, unsigned char *p, int len); +static int euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52euc_tw(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError); +static int mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_tw_to_big5(PG_FUNCTION_ARGS) @@ -50,12 +53,14 @@ euc_tw_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_BIG5); - euc_tw2big5(src, dest, len); + converted = euc_tw2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -64,12 +69,14 @@ big5_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_EUC_TW); - big52euc_tw(src, dest, len); + converted = big52euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -78,12 +85,14 @@ euc_tw_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_MULE_INTERNAL); - euc_tw2mic(src, dest, len); + converted = euc_tw2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -92,12 +101,14 @@ mic_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_TW); - mic2euc_tw(src, dest, len); + converted = mic2euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -106,12 +117,14 @@ big5_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_MULE_INTERNAL); - big52mic(src, dest, len); + converted = big52mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -120,21 +133,24 @@ mic_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_BIG5); - mic2big5(src, dest, len); + converted = mic2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_TW ---> Big5 */ -static void -euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; unsigned char c1; unsigned short big5buf, cnsBuf; @@ -149,8 +165,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Verify and decode the next EUC_TW input character */ l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -171,8 +191,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Write it out in Big5 */ big5buf = CNStoBIG5(cnsBuf, lc); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_EUC_TW, PG_BIG5, (const char *) euc, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; @@ -182,22 +206,29 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * Big5 ---> EUC_TW */ -static void -big52euc_tw(const unsigned char *big5, unsigned char *p, int len) +static int +big52euc_tw(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -212,8 +243,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); @@ -237,8 +272,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_EUC_TW, (const char *) big5, len); + } big5 += l; len -= l; @@ -256,14 +295,17 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) } } *p = '\0'; + + return big5 - start; } /* * EUC_TW ---> MIC */ -static void -euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -274,8 +316,12 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -304,22 +350,29 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_TW */ -static void -mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -330,8 +383,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -339,8 +396,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1) { *p++ = mic[1]; @@ -362,20 +423,27 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[3]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_TW, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * Big5 ---> MIC */ -static void -big52mic(const unsigned char *big5, unsigned char *p, int len) +static int +big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -389,8 +457,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } *p++ = c1; big5++; len--; @@ -398,8 +470,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); if (lc != 0) @@ -412,20 +488,27 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_MULE_INTERNAL, (const char *) big5, len); + } big5 += l; len -= l; } *p = '\0'; + + return big5 - start; } /* * MIC ---> Big5 */ -static void -mic2big5(const unsigned char *mic, unsigned char *p, int len) +static int +mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -438,8 +521,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -447,8 +534,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1 || c1 == LC_CNS11643_2 || c1 == LCPRV2_B) { if (c1 == LCPRV2_B) @@ -462,16 +553,26 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } big5buf = CNStoBIG5(cnsBuf, c1); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c index 2e28e6780a5..8610fcb69aa 100644 --- a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c +++ b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(win1250_to_latin2); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -82,12 +85,14 @@ latin2_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -96,12 +101,14 @@ mic_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN2); - mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -110,13 +117,15 @@ win1250_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - win1250_2_iso88592); + converted = latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -125,13 +134,15 @@ mic_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1250); - mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - iso88592_2_win1250); + converted = mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -140,12 +151,15 @@ latin2_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_WIN1250); - local2local(src, dest, len, PG_LATIN2, PG_WIN1250, iso88592_2_win1250); + converted = local2local(src, dest, len, PG_LATIN2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -154,10 +168,13 @@ win1250_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_LATIN2); - local2local(src, dest, len, PG_WIN1250, PG_LATIN2, win1250_2_iso88592); + converted = local2local(src, dest, len, PG_WIN1250, PG_LATIN2, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c index bc651410f21..bff27d1c295 100644 --- a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(mic_to_latin4); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -42,12 +45,14 @@ latin1_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,12 +61,14 @@ mic_to_latin1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN1); - mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -70,12 +77,14 @@ latin3_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN3, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -84,12 +93,14 @@ mic_to_latin3(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN3); - mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,12 +109,14 @@ latin4_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN4, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -112,10 +125,12 @@ mic_to_latin4(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN4); - mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c index d6067cdc24e..3838b15cab9 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ big5_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_UTF8); - LocalToUtf(src, len, dest, - &big5_to_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = LocalToUtf(src, len, dest, + &big5_to_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_BIG5); - UtfToLocal(src, len, dest, - &big5_from_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = UtfToLocal(src, len, dest, + &big5_from_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c index ed90e8e682e..75719fe5f1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c @@ -33,8 +33,11 @@ PG_FUNCTION_INFO_V1(koi8u_to_utf8); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -44,16 +47,19 @@ utf8_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8R); - UtfToLocal(src, len, dest, - &koi8r_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = UtfToLocal(src, len, dest, + &koi8r_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -62,16 +68,19 @@ koi8r_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8r_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = LocalToUtf(src, len, dest, + &koi8r_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -80,16 +89,19 @@ utf8_to_koi8u(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8U); - UtfToLocal(src, len, dest, - &koi8u_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = UtfToLocal(src, len, dest, + &koi8u_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,14 +110,17 @@ koi8u_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8U, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8u_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = LocalToUtf(src, len, dest, + &koi8u_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c index d699affce47..5391001951a 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jis_2004_to_unicode_tree, - LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = LocalToUtf(src, len, dest, + &euc_jis_2004_to_unicode_tree, + LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JIS_2004); - UtfToLocal(src, len, dest, - &euc_jis_2004_from_unicode_tree, - ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = UtfToLocal(src, len, dest, + &euc_jis_2004_from_unicode_tree, + ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c index d7c0ba6a58b..c87d1bf2398 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_cn_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_cn_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = LocalToUtf(src, len, dest, + &euc_cn_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_CN); - UtfToLocal(src, len, dest, - &euc_cn_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = UtfToLocal(src, len, dest, + &euc_cn_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c index 13a3a23e77b..6a55134db21 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jp); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jp_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jp_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = LocalToUtf(src, len, dest, + &euc_jp_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JP); - UtfToLocal(src, len, dest, - &euc_jp_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = UtfToLocal(src, len, dest, + &euc_jp_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c index 1bbb8aaef7b..fe1924e2fec 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_kr_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_kr_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = LocalToUtf(src, len, dest, + &euc_kr_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_KR); - UtfToLocal(src, len, dest, - &euc_kr_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = UtfToLocal(src, len, dest, + &euc_kr_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c index 9830045dccd..68215659b57 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_tw); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_tw_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_tw_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = LocalToUtf(src, len, dest, + &euc_tw_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_TW); - UtfToLocal(src, len, dest, - &euc_tw_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = UtfToLocal(src, len, dest, + &euc_tw_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c index f86ecf27424..e1a59c39a4d 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c @@ -183,8 +183,11 @@ conv_utf8_to_18030(uint32 code) * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -193,16 +196,19 @@ gb18030_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GB18030, PG_UTF8); - LocalToUtf(src, len, dest, - &gb18030_to_unicode_tree, - NULL, 0, - conv_18030_to_utf8, - PG_GB18030); + converted = LocalToUtf(src, len, dest, + &gb18030_to_unicode_tree, + NULL, 0, + conv_18030_to_utf8, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -211,14 +217,17 @@ utf8_to_gb18030(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GB18030); - UtfToLocal(src, len, dest, - &gb18030_from_unicode_tree, - NULL, 0, - conv_utf8_to_18030, - PG_GB18030); + converted = UtfToLocal(src, len, dest, + &gb18030_from_unicode_tree, + NULL, 0, + conv_utf8_to_18030, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c index 2ab8b16c8a8..881386d5347 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_gbk); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ gbk_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GBK, PG_UTF8); - LocalToUtf(src, len, dest, - &gbk_to_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = LocalToUtf(src, len, dest, + &gbk_to_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_gbk(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GBK); - UtfToLocal(src, len, dest, - &gbk_from_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = UtfToLocal(src, len, dest, + &gbk_from_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c index 3e49f67ea2f..d93a521badf 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c @@ -52,8 +52,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -100,6 +103,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -108,12 +112,15 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -122,7 +129,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -132,6 +139,7 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -140,12 +148,15 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -154,5 +165,5 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c index 67e713cca11..8ac93604a1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c @@ -26,8 +26,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859_1); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -37,6 +40,8 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_UTF8); @@ -45,7 +50,11 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_LATIN1, (const char *) src, len); + } if (!IS_HIGHBIT_SET(c)) *dest++ = c; else @@ -58,7 +67,7 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } Datum @@ -67,6 +76,8 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c, c1; @@ -76,7 +87,11 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_UTF8, (const char *) src, len); + } /* fast path for ASCII-subset characters */ if (!IS_HIGHBIT_SET(c)) { @@ -102,11 +117,15 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) len -= 2; } else + { + if (noError) + break; report_untranslatable_char(PG_UTF8, PG_LATIN1, (const char *) src, len); + } } } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c index 578f5df4e7f..317daa2d5ee 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_johab); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ johab_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_JOHAB, PG_UTF8); - LocalToUtf(src, len, dest, - &johab_to_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = LocalToUtf(src, len, dest, + &johab_to_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_johab(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_JOHAB); - UtfToLocal(src, len, dest, - &johab_from_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = UtfToLocal(src, len, dest, + &johab_from_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c index dd9fc2975ad..4c9348aba59 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ sjis_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_UTF8); - LocalToUtf(src, len, dest, - &sjis_to_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = LocalToUtf(src, len, dest, + &sjis_to_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SJIS); - UtfToLocal(src, len, dest, - &sjis_from_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = UtfToLocal(src, len, dest, + &sjis_from_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c index 4bcc886d674..1fffdc5930c 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_shift_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ shift_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &shift_jis_2004_to_unicode_tree, - LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = LocalToUtf(src, len, dest, + &shift_jis_2004_to_unicode_tree, + LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SHIFT_JIS_2004); - UtfToLocal(src, len, dest, - &shift_jis_2004_from_unicode_tree, - ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = UtfToLocal(src, len, dest, + &shift_jis_2004_from_unicode_tree, + ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c index c8e512994a1..d9471dad097 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_uhc); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ uhc_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UHC, PG_UTF8); - LocalToUtf(src, len, dest, - &uhc_to_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = LocalToUtf(src, len, dest, + &uhc_to_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_uhc(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_UHC); - UtfToLocal(src, len, dest, - &uhc_from_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = UtfToLocal(src, len, dest, + &uhc_from_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c index 0c9493dee56..110ba5677d0 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c @@ -48,8 +48,11 @@ PG_FUNCTION_INFO_V1(utf8_to_win); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -81,6 +84,7 @@ win_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -89,12 +93,15 @@ win_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -103,7 +110,7 @@ win_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -113,6 +120,7 @@ utf8_to_win(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -121,12 +129,15 @@ utf8_to_win(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -135,5 +146,5 @@ utf8_to_win(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/mbutils.c b/src/backend/utils/mb/mbutils.c index 2578573b0ab..65753860e35 100644 --- a/src/backend/utils/mb/mbutils.c +++ b/src/backend/utils/mb/mbutils.c @@ -406,12 +406,13 @@ pg_do_encoding_conversion(unsigned char *src, int len, MemoryContextAllocHuge(CurrentMemoryContext, (Size) len * MAX_CONVERSION_GROWTH + 1); - OidFunctionCall5(proc, - Int32GetDatum(src_encoding), - Int32GetDatum(dest_encoding), - CStringGetDatum(src), - CStringGetDatum(result), - Int32GetDatum(len)); + (void) OidFunctionCall6(proc, + Int32GetDatum(src_encoding), + Int32GetDatum(dest_encoding), + CStringGetDatum(src), + CStringGetDatum(result), + Int32GetDatum(len), + BoolGetDatum(false)); /* * If the result is large, it's worth repalloc'ing to release any extra @@ -849,12 +850,13 @@ pg_unicode_to_server(pg_wchar c, unsigned char *s) c_as_utf8[c_as_utf8_len] = '\0'; /* Convert, or throw error if we can't */ - FunctionCall5(Utf8ToServerConvProc, + FunctionCall6(Utf8ToServerConvProc, Int32GetDatum(PG_UTF8), Int32GetDatum(server_encoding), CStringGetDatum(c_as_utf8), CStringGetDatum(s), - Int32GetDatum(c_as_utf8_len)); + Int32GetDatum(c_as_utf8_len), + BoolGetDatum(false)); } diff --git a/src/bin/pg_upgrade/check.c b/src/bin/pg_upgrade/check.c index 43fc297eb69..ee6be95b08d 100644 --- a/src/bin/pg_upgrade/check.c +++ b/src/bin/pg_upgrade/check.c @@ -28,6 +28,7 @@ static void check_for_reg_data_type_usage(ClusterInfo *cluster); static void check_for_jsonb_9_4_usage(ClusterInfo *cluster); static void check_for_pg_role_prefix(ClusterInfo *cluster); static void check_for_new_tablespace_dir(ClusterInfo *new_cluster); +static void check_for_user_defined_encoding_conversions(ClusterInfo *cluster); static char *get_canonical_locale_name(int category, const char *locale); @@ -102,6 +103,15 @@ check_and_dump_old_cluster(bool live_check) check_for_reg_data_type_usage(&old_cluster); check_for_isn_and_int8_passing_mismatch(&old_cluster); + /* + * PG 14 changed the function signature of encoding conversion functions. + * Conversions from older versions cannot be upgraded automatically + * because the user-defined functions used by the encoding conversions + * need to changed to match the new signature. + */ + if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1300) + check_for_user_defined_encoding_conversions(&old_cluster); + /* * Pre-PG 14 allowed user defined postfix operators, which are not * supported anymore. Verify there are none, iff applicable. @@ -1268,6 +1278,91 @@ check_for_pg_role_prefix(ClusterInfo *cluster) check_ok(); } +/* + * Verify that no user-defined encoding conversions exist. + */ +static void +check_for_user_defined_encoding_conversions(ClusterInfo *cluster) +{ + int dbnum; + FILE *script = NULL; + bool found = false; + char output_path[MAXPGPATH]; + + prep_status("Checking for user-defined encoding conversions"); + + snprintf(output_path, sizeof(output_path), + "encoding_conversions.txt"); + + /* Find any user defined encoding conversions */ + for (dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++) + { + PGresult *res; + bool db_used = false; + int ntups; + int rowno; + int i_conoid, + i_conname, + i_nspname; + DbInfo *active_db = &cluster->dbarr.dbs[dbnum]; + PGconn *conn = connectToServer(cluster, active_db->db_name); + + /* + * The query below hardcodes FirstNormalObjectId as 16384 rather than + * interpolating that C #define into the query because, if that + * #define is ever changed, the cutoff we want to use is the value + * used by pre-version 14 servers, not that of some future version. + */ + res = executeQueryOrDie(conn, + "SELECT c.oid as conoid, c.conname, n.nspname " + "FROM pg_catalog.pg_conversion c, " + " pg_catalog.pg_namespace n " + "WHERE c.connamespace = n.oid AND " + " c.oid >= 16384"); + ntups = PQntuples(res); + i_conoid = PQfnumber(res, "conoid"); + i_conname = PQfnumber(res, "conname"); + i_nspname = PQfnumber(res, "nspname"); + for (rowno = 0; rowno < ntups; rowno++) + { + found = true; + if (script == NULL && + (script = fopen_priv(output_path, "w")) == NULL) + pg_fatal("could not open file \"%s\": %s\n", + output_path, strerror(errno)); + if (!db_used) + { + fprintf(script, "In database: %s\n", active_db->db_name); + db_used = true; + } + fprintf(script, " (oid=%s) %s.%s\n", + PQgetvalue(res, rowno, i_conoid), + PQgetvalue(res, rowno, i_nspname), + PQgetvalue(res, rowno, i_conname)); + } + + PQclear(res); + + PQfinish(conn); + } + + if (script) + fclose(script); + + if (found) + { + pg_log(PG_REPORT, "fatal\n"); + pg_fatal("Your installation contains user-defined encoding conversions.\n" + "The conversion function parameters changed in PostgreSQL version 14\n" + "so this cluster cannot currently be upgraded. You can remove the\n" + "encoding conversions in the old cluster and restart the upgrade.\n" + "A list of user-defined encoding conversions is in the file:\n" + " %s\n\n", output_path); + } + else + check_ok(); +} + /* * get_canonical_locale_name diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index f8174061ef3..75b829e8514 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10766,388 +10766,388 @@ # conversion functions { oid => '4302', descr => 'internal conversion function for KOI8R to MULE_INTERNAL', - proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_mic', + proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4303', descr => 'internal conversion function for MULE_INTERNAL to KOI8R', - proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_koi8r', + proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4304', descr => 'internal conversion function for ISO-8859-5 to MULE_INTERNAL', - proname => 'iso_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_mic', + proname => 'iso_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4305', descr => 'internal conversion function for MULE_INTERNAL to ISO-8859-5', - proname => 'mic_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_iso', + proname => 'mic_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4306', descr => 'internal conversion function for WIN1251 to MULE_INTERNAL', - proname => 'win1251_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_mic', + proname => 'win1251_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4307', descr => 'internal conversion function for MULE_INTERNAL to WIN1251', - proname => 'mic_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1251', + proname => 'mic_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4308', descr => 'internal conversion function for WIN866 to MULE_INTERNAL', - proname => 'win866_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_mic', + proname => 'win866_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4309', descr => 'internal conversion function for MULE_INTERNAL to WIN866', - proname => 'mic_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win866', + proname => 'mic_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4310', descr => 'internal conversion function for KOI8R to WIN1251', - proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4311', descr => 'internal conversion function for WIN1251 to KOI8R', - proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4312', descr => 'internal conversion function for KOI8R to WIN866', - proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_win866', + proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4313', descr => 'internal conversion function for WIN866 to KOI8R', - proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_koi8r', + proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4314', descr => 'internal conversion function for WIN866 to WIN1251', - proname => 'win866_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win866_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4315', descr => 'internal conversion function for WIN1251 to WIN866', - proname => 'win1251_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4316', descr => 'internal conversion function for ISO-8859-5 to KOI8R', - proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_koi8r', + proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4317', descr => 'internal conversion function for KOI8R to ISO-8859-5', - proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_iso', + proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4318', descr => 'internal conversion function for ISO-8859-5 to WIN1251', - proname => 'iso_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win1251', + proname => 'iso_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4319', descr => 'internal conversion function for WIN1251 to ISO-8859-5', - proname => 'win1251_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_iso', + proname => 'win1251_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4320', descr => 'internal conversion function for ISO-8859-5 to WIN866', - proname => 'iso_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win866', + proname => 'iso_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4321', descr => 'internal conversion function for WIN866 to ISO-8859-5', - proname => 'win866_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_iso', + proname => 'win866_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4322', descr => 'internal conversion function for EUC_CN to MULE_INTERNAL', - proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_mic', + proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_mic', probin => '$libdir/euc_cn_and_mic' }, { oid => '4323', descr => 'internal conversion function for MULE_INTERNAL to EUC_CN', - proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_cn', + proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_cn', probin => '$libdir/euc_cn_and_mic' }, { oid => '4324', descr => 'internal conversion function for EUC_JP to SJIS', - proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_sjis', + proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4325', descr => 'internal conversion function for SJIS to EUC_JP', - proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_euc_jp', + proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4326', descr => 'internal conversion function for EUC_JP to MULE_INTERNAL', - proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_mic', + proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4327', descr => 'internal conversion function for SJIS to MULE_INTERNAL', - proname => 'sjis_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_mic', + proname => 'sjis_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4328', descr => 'internal conversion function for MULE_INTERNAL to EUC_JP', - proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_jp', + proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4329', descr => 'internal conversion function for MULE_INTERNAL to SJIS', - proname => 'mic_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_sjis', + proname => 'mic_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4330', descr => 'internal conversion function for EUC_KR to MULE_INTERNAL', - proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_mic', + proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_mic', probin => '$libdir/euc_kr_and_mic' }, { oid => '4331', descr => 'internal conversion function for MULE_INTERNAL to EUC_KR', - proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_kr', + proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_kr', probin => '$libdir/euc_kr_and_mic' }, { oid => '4332', descr => 'internal conversion function for EUC_TW to BIG5', - proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_big5', + proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4333', descr => 'internal conversion function for BIG5 to EUC_TW', - proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_euc_tw', + proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4334', descr => 'internal conversion function for EUC_TW to MULE_INTERNAL', - proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_mic', + proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4335', descr => 'internal conversion function for BIG5 to MULE_INTERNAL', - proname => 'big5_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_mic', + proname => 'big5_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4336', descr => 'internal conversion function for MULE_INTERNAL to EUC_TW', - proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_tw', + proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4337', descr => 'internal conversion function for MULE_INTERNAL to BIG5', - proname => 'mic_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_big5', + proname => 'mic_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4338', descr => 'internal conversion function for LATIN2 to MULE_INTERNAL', - proname => 'latin2_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin2_to_mic', + proname => 'latin2_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4339', descr => 'internal conversion function for MULE_INTERNAL to LATIN2', - proname => 'mic_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin2', + proname => 'mic_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4340', descr => 'internal conversion function for WIN1250 to MULE_INTERNAL', - proname => 'win1250_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1250_to_mic', + proname => 'win1250_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4341', descr => 'internal conversion function for MULE_INTERNAL to WIN1250', - proname => 'mic_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1250', + proname => 'mic_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4342', descr => 'internal conversion function for LATIN2 to WIN1250', - proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4343', descr => 'internal conversion function for WIN1250 to LATIN2', - proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4344', descr => 'internal conversion function for LATIN1 to MULE_INTERNAL', - proname => 'latin1_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin1_to_mic', + proname => 'latin1_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin1_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4345', descr => 'internal conversion function for MULE_INTERNAL to LATIN1', - proname => 'mic_to_latin1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin1', + proname => 'mic_to_latin1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin1', probin => '$libdir/latin_and_mic' }, { oid => '4346', descr => 'internal conversion function for LATIN3 to MULE_INTERNAL', - proname => 'latin3_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin3_to_mic', + proname => 'latin3_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin3_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4347', descr => 'internal conversion function for MULE_INTERNAL to LATIN3', - proname => 'mic_to_latin3', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin3', + proname => 'mic_to_latin3', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin3', probin => '$libdir/latin_and_mic' }, { oid => '4348', descr => 'internal conversion function for LATIN4 to MULE_INTERNAL', - proname => 'latin4_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin4_to_mic', + proname => 'latin4_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin4_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4349', descr => 'internal conversion function for MULE_INTERNAL to LATIN4', - proname => 'mic_to_latin4', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin4', + proname => 'mic_to_latin4', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin4', probin => '$libdir/latin_and_mic' }, { oid => '4352', descr => 'internal conversion function for BIG5 to UTF8', - proname => 'big5_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_utf8', + proname => 'big5_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_utf8', probin => '$libdir/utf8_and_big5' }, { oid => '4353', descr => 'internal conversion function for UTF8 to BIG5', - proname => 'utf8_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_big5', + proname => 'utf8_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_big5', probin => '$libdir/utf8_and_big5' }, { oid => '4354', descr => 'internal conversion function for UTF8 to KOI8R', - proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8r', + proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8r', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4355', descr => 'internal conversion function for KOI8R to UTF8', - proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_utf8', + proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4356', descr => 'internal conversion function for UTF8 to KOI8U', - proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8u', + proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8u', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4357', descr => 'internal conversion function for KOI8U to UTF8', - proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8u_to_utf8', + proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8u_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4358', descr => 'internal conversion function for UTF8 to WIN', - proname => 'utf8_to_win', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_win', + proname => 'utf8_to_win', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_win', probin => '$libdir/utf8_and_win' }, { oid => '4359', descr => 'internal conversion function for WIN to UTF8', - proname => 'win_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win_to_utf8', + proname => 'win_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win_to_utf8', probin => '$libdir/utf8_and_win' }, { oid => '4360', descr => 'internal conversion function for EUC_CN to UTF8', - proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_utf8', + proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_utf8', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4361', descr => 'internal conversion function for UTF8 to EUC_CN', - proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_cn', + proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_cn', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4362', descr => 'internal conversion function for EUC_JP to UTF8', - proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_utf8', + proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_utf8', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4363', descr => 'internal conversion function for UTF8 to EUC_JP', - proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_jp', + proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jp', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4364', descr => 'internal conversion function for EUC_KR to UTF8', - proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_utf8', + proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_utf8', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4365', descr => 'internal conversion function for UTF8 to EUC_KR', - proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_kr', + proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_kr', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4366', descr => 'internal conversion function for EUC_TW to UTF8', - proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_utf8', + proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_utf8', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4367', descr => 'internal conversion function for UTF8 to EUC_TW', - proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_tw', + proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_tw', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4368', descr => 'internal conversion function for GB18030 to UTF8', - proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gb18030_to_utf8', + proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gb18030_to_utf8', probin => '$libdir/utf8_and_gb18030' }, { oid => '4369', descr => 'internal conversion function for UTF8 to GB18030', - proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gb18030', + proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gb18030', probin => '$libdir/utf8_and_gb18030' }, { oid => '4370', descr => 'internal conversion function for GBK to UTF8', - proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gbk_to_utf8', + proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gbk_to_utf8', probin => '$libdir/utf8_and_gbk' }, { oid => '4371', descr => 'internal conversion function for UTF8 to GBK', - proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gbk', + proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gbk', probin => '$libdir/utf8_and_gbk' }, { oid => '4372', descr => 'internal conversion function for UTF8 to ISO-8859 2-16', - proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_iso8859', + proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859', probin => '$libdir/utf8_and_iso8859' }, { oid => '4373', descr => 'internal conversion function for ISO-8859 2-16 to UTF8', - proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso8859_to_utf8', + proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_to_utf8', probin => '$libdir/utf8_and_iso8859' }, { oid => '4374', descr => 'internal conversion function for LATIN1 to UTF8', - proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_1_to_utf8', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4375', descr => 'internal conversion function for UTF8 to LATIN1', - proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859_1', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4376', descr => 'internal conversion function for JOHAB to UTF8', - proname => 'johab_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'johab_to_utf8', + proname => 'johab_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'johab_to_utf8', probin => '$libdir/utf8_and_johab' }, { oid => '4377', descr => 'internal conversion function for UTF8 to JOHAB', - proname => 'utf8_to_johab', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_johab', + proname => 'utf8_to_johab', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_johab', probin => '$libdir/utf8_and_johab' }, { oid => '4378', descr => 'internal conversion function for SJIS to UTF8', - proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_utf8', + proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_utf8', probin => '$libdir/utf8_and_sjis' }, { oid => '4379', descr => 'internal conversion function for UTF8 to SJIS', - proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_sjis', + proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_sjis', probin => '$libdir/utf8_and_sjis' }, { oid => '4380', descr => 'internal conversion function for UHC to UTF8', - proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'uhc_to_utf8', + proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'uhc_to_utf8', probin => '$libdir/utf8_and_uhc' }, { oid => '4381', descr => 'internal conversion function for UTF8 to UHC', - proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_uhc', + proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_uhc', probin => '$libdir/utf8_and_uhc' }, { oid => '4382', descr => 'internal conversion function for EUC_JIS_2004 to UTF8', - proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_utf8', probin => '$libdir/utf8_and_euc2004' }, { oid => '4383', descr => 'internal conversion function for UTF8 to EUC_JIS_2004', - proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jis_2004', probin => '$libdir/utf8_and_euc2004' }, { oid => '4384', descr => 'internal conversion function for SHIFT_JIS_2004 to UTF8', - proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_utf8', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4385', descr => 'internal conversion function for UTF8 to SHIFT_JIS_2004', - proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_shift_jis_2004', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4386', descr => 'internal conversion function for EUC_JIS_2004 to SHIFT_JIS_2004', proname => 'euc_jis_2004_to_shift_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_shift_jis_2004', probin => '$libdir/euc2004_sjis2004' }, { oid => '4387', descr => 'internal conversion function for SHIFT_JIS_2004 to EUC_JIS_2004', proname => 'shift_jis_2004_to_euc_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_euc_jis_2004', probin => '$libdir/euc2004_sjis2004' }, diff --git a/src/include/mb/pg_wchar.h b/src/include/mb/pg_wchar.h index 64b22e4b0d4..346a41a1f3d 100644 --- a/src/include/mb/pg_wchar.h +++ b/src/include/mb/pg_wchar.h @@ -627,18 +627,18 @@ extern void pg_unicode_to_server(pg_wchar c, unsigned char *s); extern unsigned short BIG5toCNS(unsigned short big5, unsigned char *lc); extern unsigned short CNStoBIG5(unsigned short cns, unsigned char lc); -extern void UtfToLocal(const unsigned char *utf, int len, - unsigned char *iso, - const pg_mb_radix_tree *map, - const pg_utf_to_local_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); -extern void LocalToUtf(const unsigned char *iso, int len, - unsigned char *utf, - const pg_mb_radix_tree *map, - const pg_local_to_utf_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); +extern int UtfToLocal(const unsigned char *utf, int len, + unsigned char *iso, + const pg_mb_radix_tree *map, + const pg_utf_to_local_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); +extern int LocalToUtf(const unsigned char *iso, int len, + unsigned char *utf, + const pg_mb_radix_tree *map, + const pg_local_to_utf_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); extern bool pg_verifymbstr(const char *mbstr, int len, bool noError); extern bool pg_verify_mbstr(int encoding, const char *mbstr, int len, @@ -656,18 +656,19 @@ extern void report_invalid_encoding(int encoding, const char *mbstr, int len) pg extern void report_untranslatable_char(int src_encoding, int dest_encoding, const char *mbstr, int len) pg_attribute_noreturn(); -extern void local2local(const unsigned char *l, unsigned char *p, int len, - int src_encoding, int dest_encoding, const unsigned char *tab); -extern void latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding); -extern void mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding); -extern void latin2mic_with_table(const unsigned char *l, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); -extern void mic2latin_with_table(const unsigned char *mic, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); +extern int local2local(const unsigned char *l, unsigned char *p, int len, + int src_encoding, int dest_encoding, const unsigned char *tab, + bool noError); +extern int latin2mic(const unsigned char *l, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int mic2latin(const unsigned char *mic, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int latin2mic_with_table(const unsigned char *l, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); +extern int mic2latin_with_table(const unsigned char *mic, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); #ifdef WIN32 extern WCHAR *pgwin32_message_to_UTF16(const char *str, int len, int *utf16len); diff --git a/src/test/regress/expected/opr_sanity.out b/src/test/regress/expected/opr_sanity.out index 254ca06d3dd..23ba60e395f 100644 --- a/src/test/regress/expected/opr_sanity.out +++ b/src/test/regress/expected/opr_sanity.out @@ -1052,13 +1052,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); oid | proname | oid | conname -----+---------+-----+--------- (0 rows) diff --git a/src/test/regress/sql/opr_sanity.sql b/src/test/regress/sql/opr_sanity.sql index bbd3834b634..04691745981 100644 --- a/src/test/regress/sql/opr_sanity.sql +++ b/src/test/regress/sql/opr_sanity.sql @@ -556,13 +556,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); -- Check for conprocs that don't perform the specific conversion that -- pg_conversion alleges they do, by trying to invoke each conversion -- 2.29.2 --------------39E46EF15EBFAA37D53332E5 Content-Type: text/x-patch; charset=UTF-8; name="v3-0003-Add-tests-for-the-new-noError-variants-of-built-i.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="v3-0003-Add-tests-for-the-new-noError-variants-of-built-i.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 34+ messages in thread
* [PATCH v3 2/5] Change conversion function signature. @ 2021-01-28 16:42 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 34+ messages in thread From: Heikki Linnakangas @ 2021-01-28 16:42 UTC (permalink / raw) Add a 'noError' argument, so that we can try to convert a buffer without knowing the character boundaries beforehand. The functions now need to return the number of input bytes successfully converted. This is is a backwards-incompatible change, if you have created a custom encoding conversion with CREATE CONVERSION. This adds a check to pg_upgrade for that, refusing the upgrade if there are any user-defined encoding conversions. --- doc/src/sgml/ref/create_conversion.sgml | 5 +- src/backend/commands/conversioncmds.c | 27 +- src/backend/utils/error/elog.c | 2 + src/backend/utils/mb/conv.c | 112 +++++- .../cyrillic_and_mic/cyrillic_and_mic.c | 127 ++++--- .../euc2004_sjis2004/euc2004_sjis2004.c | 96 ++++- .../euc_cn_and_mic/euc_cn_and_mic.c | 57 ++- .../euc_jp_and_sjis/euc_jp_and_sjis.c | 153 ++++++-- .../euc_kr_and_mic/euc_kr_and_mic.c | 57 ++- .../euc_tw_and_big5/euc_tw_and_big5.c | 165 +++++++-- .../latin2_and_win1250/latin2_and_win1250.c | 49 ++- .../latin_and_mic/latin_and_mic.c | 43 ++- .../utf8_and_big5/utf8_and_big5.c | 37 +- .../utf8_and_cyrillic/utf8_and_cyrillic.c | 67 ++-- .../utf8_and_euc2004/utf8_and_euc2004.c | 37 +- .../utf8_and_euc_cn/utf8_and_euc_cn.c | 37 +- .../utf8_and_euc_jp/utf8_and_euc_jp.c | 37 +- .../utf8_and_euc_kr/utf8_and_euc_kr.c | 37 +- .../utf8_and_euc_tw/utf8_and_euc_tw.c | 37 +- .../utf8_and_gb18030/utf8_and_gb18030.c | 37 +- .../utf8_and_gbk/utf8_and_gbk.c | 37 +- .../utf8_and_iso8859/utf8_and_iso8859.c | 43 ++- .../utf8_and_iso8859_1/utf8_and_iso8859_1.c | 27 +- .../utf8_and_johab/utf8_and_johab.c | 37 +- .../utf8_and_sjis/utf8_and_sjis.c | 37 +- .../utf8_and_sjis2004/utf8_and_sjis2004.c | 37 +- .../utf8_and_uhc/utf8_and_uhc.c | 37 +- .../utf8_and_win/utf8_and_win.c | 43 ++- src/backend/utils/mb/mbutils.c | 18 +- src/bin/pg_upgrade/check.c | 95 +++++ src/include/catalog/pg_proc.dat | 332 +++++++++--------- src/include/mb/pg_wchar.h | 49 +-- src/test/regress/expected/opr_sanity.out | 7 +- src/test/regress/sql/opr_sanity.sql | 7 +- 34 files changed, 1390 insertions(+), 635 deletions(-) diff --git a/doc/src/sgml/ref/create_conversion.sgml b/doc/src/sgml/ref/create_conversion.sgml index e7700fecfc5..f014a676c88 100644 --- a/doc/src/sgml/ref/create_conversion.sgml +++ b/doc/src/sgml/ref/create_conversion.sgml @@ -117,8 +117,9 @@ conv_proc( integer, -- destination encoding ID cstring, -- source string (null terminated C string) internal, -- destination (fill with a null terminated C string) - integer -- source string length -) RETURNS void; + integer, -- source string length + boolean -- if true, don't throw an error if conversion fails +) RETURNS integer; </programlisting></para> </listitem> </varlistentry> diff --git a/src/backend/commands/conversioncmds.c b/src/backend/commands/conversioncmds.c index f7ff321de71..d2041466911 100644 --- a/src/backend/commands/conversioncmds.c +++ b/src/backend/commands/conversioncmds.c @@ -45,8 +45,9 @@ CreateConversionCommand(CreateConversionStmt *stmt) const char *from_encoding_name = stmt->for_encoding_name; const char *to_encoding_name = stmt->to_encoding_name; List *func_name = stmt->func_name; - static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID}; + static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID, BOOLOID}; char result[1]; + Datum funcresult; /* Convert list of names to a name and namespace */ namespaceId = QualifiedNameGetCreationNamespace(stmt->conversion_name, @@ -92,8 +93,8 @@ CreateConversionCommand(CreateConversionStmt *stmt) funcoid = LookupFuncName(func_name, sizeof(funcargs) / sizeof(Oid), funcargs, false); - /* Check it returns VOID, else it's probably the wrong function */ - if (get_func_rettype(funcoid) != VOIDOID) + /* Check it returns int4, else it's probably the wrong function */ + if (get_func_rettype(funcoid) != INT4OID) ereport(ERROR, (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), errmsg("encoding conversion function %s must return type %s", @@ -111,12 +112,20 @@ CreateConversionCommand(CreateConversionStmt *stmt) * string; the conversion function should throw an error if it can't * perform the requested conversion. */ - OidFunctionCall5(funcoid, - Int32GetDatum(from_encoding), - Int32GetDatum(to_encoding), - CStringGetDatum(""), - CStringGetDatum(result), - Int32GetDatum(0)); + funcresult = OidFunctionCall6(funcoid, + Int32GetDatum(from_encoding), + Int32GetDatum(to_encoding), + CStringGetDatum(""), + CStringGetDatum(result), + Int32GetDatum(0), + BoolGetDatum(false)); + + /* The function should return 0 for empty input. Might as well check that, too. */ + if (DatumGetInt32(funcresult) != 0) + ereport(ERROR, + (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), + errmsg("encoding conversion function %s returned incorrect result for empty input", + NameListToString(func_name)))); /* * All seem ok, go ahead (possible failure would be a duplicate conversion diff --git a/src/backend/utils/error/elog.c b/src/backend/utils/error/elog.c index 80c26724612..762f77d533c 100644 --- a/src/backend/utils/error/elog.c +++ b/src/backend/utils/error/elog.c @@ -2280,6 +2280,8 @@ write_console(const char *line, int len) * Conversion on non-win32 platforms is not implemented yet. It requires * non-throw version of pg_do_encoding_conversion(), that converts * unconvertable characters to '?' without errors. + * + * XXX: We have a no-throw version now. It doesn't convert to '?' though. */ #endif diff --git a/src/backend/utils/mb/conv.c b/src/backend/utils/mb/conv.c index a07b54bd3b8..b83358bc7a5 100644 --- a/src/backend/utils/mb/conv.c +++ b/src/backend/utils/mb/conv.c @@ -26,14 +26,16 @@ * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the target charset, or 0 if there is no equivalent code. */ -void +int local2local(const unsigned char *l, unsigned char *p, int len, int src_encoding, int dest_encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -41,7 +43,11 @@ local2local(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(src_encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -50,13 +56,19 @@ local2local(const unsigned char *l, if (c2) *p++ = c2; else + { + if (noError) + break; report_untranslatable_char(src_encoding, dest_encoding, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -67,17 +79,22 @@ local2local(const unsigned char *l, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = l; int c1; while (len > 0) { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (IS_HIGHBIT_SET(c1)) *p++ = lc; *p++ = c1; @@ -85,6 +102,8 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, len--; } *p = '\0'; + + return l - start; } /* @@ -95,17 +114,22 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -118,17 +142,27 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1])) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); + } *p++ = mic[1]; mic += 2; len -= 2; } } *p = '\0'; + + return mic - start; } @@ -144,14 +178,16 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the mule encoding, or 0 if there is no equivalent code. */ -void +int latin2mic_with_table(const unsigned char *l, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -159,7 +195,11 @@ latin2mic_with_table(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -171,13 +211,19 @@ latin2mic_with_table(const unsigned char *l, *p++ = c2; } else + { + if (noError) + break; report_untranslatable_char(encoding, PG_MULE_INTERNAL, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -192,14 +238,16 @@ latin2mic_with_table(const unsigned char *l, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the local charset, or 0 if there is no equivalent code. */ -void +int mic2latin_with_table(const unsigned char *mic, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = mic; unsigned char c1, c2; @@ -207,7 +255,11 @@ mic2latin_with_table(const unsigned char *mic, { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -220,11 +272,17 @@ mic2latin_with_table(const unsigned char *mic, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1]) || (c2 = tab[mic[1] - HIGHBIT]) == 0) { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); break; /* keep compiler quiet */ @@ -235,6 +293,8 @@ mic2latin_with_table(const unsigned char *mic, } } *p = '\0'; + + return mic - start; } /* @@ -425,17 +485,19 @@ pg_mb_radix_conv(const pg_mb_radix_tree *rt, * * See pg_wchar.h for more details about the data structures used here. */ -void +int UtfToLocal(const unsigned char *utf, int len, unsigned char *iso, const pg_mb_radix_tree *map, const pg_utf_to_local_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, bool noError) { uint32 iutf; int l; const pg_utf_to_local_combined *cp; + const unsigned char *start = utf; + const unsigned char *cur = utf; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -449,6 +511,8 @@ UtfToLocal(const unsigned char *utf, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*utf == '\0') break; @@ -584,15 +648,19 @@ UtfToLocal(const unsigned char *utf, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(PG_UTF8, encoding, (const char *) (utf - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(PG_UTF8, (const char *) utf, len); *iso = '\0'; + + return cur - start; } /* @@ -616,18 +684,24 @@ UtfToLocal(const unsigned char *utf, int len, * (if provided) is applied. An error is raised if no match is found. * * See pg_wchar.h for more details about the data structures used here. + * + * Returns the number of input bytes consumed. If noError is true, this can + * be less than 'len'. */ -void +int LocalToUtf(const unsigned char *iso, int len, unsigned char *utf, const pg_mb_radix_tree *map, const pg_local_to_utf_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, + bool noError) { uint32 iiso; int l; const pg_local_to_utf_combined *cp; + const unsigned char *start = iso; + const unsigned char *cur = iso; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -641,6 +715,8 @@ LocalToUtf(const unsigned char *iso, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*iso == '\0') break; @@ -723,13 +799,17 @@ LocalToUtf(const unsigned char *iso, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(encoding, PG_UTF8, (const char *) (iso - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(encoding, (const char *) iso, len); *utf = '\0'; + + return cur - start; } diff --git a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c index 4c5b02654de..368c2deb5e4 100644 --- a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c @@ -44,8 +44,11 @@ PG_FUNCTION_INFO_V1(win866_to_iso); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -306,12 +309,14 @@ koi8r_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -320,12 +325,14 @@ mic_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_KOI8R); - mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -334,12 +341,14 @@ iso_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -348,12 +357,14 @@ mic_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_ISO_8859_5); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -362,12 +373,14 @@ win1251_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -376,12 +389,14 @@ mic_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1251); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -390,12 +405,14 @@ win866_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -404,12 +421,14 @@ mic_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN866); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -418,12 +437,14 @@ koi8r_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN1251); - local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -432,12 +453,14 @@ win1251_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_KOI8R); - local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi); + converted = local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -446,12 +469,14 @@ koi8r_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN866); - local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -460,12 +485,14 @@ win866_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_KOI8R); - local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi); + converted = local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -474,12 +501,14 @@ win866_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_WIN1251); - local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251); + converted = local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -488,12 +517,14 @@ win1251_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_WIN866); - local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866); + converted = local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -502,12 +533,14 @@ iso_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_KOI8R); - local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -516,12 +549,14 @@ koi8r_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_ISO_8859_5); - local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso); + converted = local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -530,12 +565,14 @@ iso_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN1251); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -544,12 +581,14 @@ win1251_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso); + converted = local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -558,12 +597,14 @@ iso_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN866); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -572,10 +613,12 @@ win866_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso); + converted = local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c index 4d7fb116cfd..88529c644cf 100644 --- a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c @@ -19,8 +19,8 @@ PG_MODULE_MAGIC; PG_FUNCTION_INFO_V1(euc_jis_2004_to_shift_jis_2004); PG_FUNCTION_INFO_V1(shift_jis_2004_to_euc_jis_2004); -static void euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len); -static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len); +static int euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError); /* ---------- * conv_proc( @@ -28,8 +28,11 @@ static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -39,12 +42,14 @@ euc_jis_2004_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_SHIFT_JIS_2004); - euc_jis_20042shift_jis_2004(src, dest, len); + converted = euc_jis_20042shift_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -53,20 +58,23 @@ shift_jis_2004_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_EUC_JIS_2004); - shift_jis_20042euc_jis_2004(src, dest, len); + converted = shift_jis_20042euc_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_JIS_2004 -> SHIFT_JIS_2004 */ -static void -euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, ku, ten; @@ -79,8 +87,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -90,8 +102,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) l = pg_encoding_verifymbchar(PG_EUC_JIS_2004, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (c1 == SS2 && l == 2) /* JIS X 0201 kana? */ { @@ -121,8 +137,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) *p++ = (ku + 0x19b) >> 1; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } if (ku % 2) @@ -132,8 +152,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; @@ -149,8 +173,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ku >= 63 && ku <= 94) *p++ = (ku + 0x181) >> 1; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (ku % 2) { @@ -159,20 +187,30 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else - report_invalid_encoding(PG_EUC_JIS_2004, + { + if (noError) + break; + report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } euc += l; len -= l; } *p = '\0'; + + return euc - start; } /* @@ -212,9 +250,10 @@ get_ten(int b, int *ku) * SHIFT_JIS_2004 ---> EUC_JIS_2004 */ -static void -shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len) +static int +shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1; int ku, ten, @@ -230,8 +269,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -241,8 +284,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len l = pg_encoding_verifymbchar(PG_SHIFT_JIS_2004, (const char *) sjis, len); if (l < 0 || l > len) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf && l == 1) { @@ -266,8 +313,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x100; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xe0 && c1 <= 0xef) /* plane 1 62ku-94ku */ @@ -275,9 +326,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x180; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, - (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xf0 && c1 <= 0xf3) /* plane 2 @@ -286,8 +340,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } switch (c1) { case 0xf0: @@ -309,16 +367,24 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 == 0xf4 && kubun == 1) ku = 15; else ku = (c1 << 1) - 0x19a - kubun; } else + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (plane == 2) *p++ = SS3; @@ -330,4 +396,6 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c index e9bb896935f..a8da733803d 100644 --- a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_cn2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_cn(const unsigned char *mic, unsigned char *p, int len); +static int euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_cn_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_cn_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_MULE_INTERNAL); - euc_cn2mic(src, dest, len); + converted = euc_cn2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_CN); - mic2euc_cn(src, dest, len); + converted = mic2euc_cn(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_CN ---> MIC */ -static void -euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; while (len > 0) @@ -76,7 +84,11 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (len < 2 || !IS_HIGHBIT_SET(euc[1])) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = LC_GB2312_80; *p++ = c1; *p++ = euc[1]; @@ -86,21 +98,28 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_CN */ -static void -mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) @@ -109,11 +128,19 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (c1 != LC_GB2312_80) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_CN, (const char *) mic, len); + } if (len < 3 || !IS_HIGHBIT_SET(mic[1]) || !IS_HIGHBIT_SET(mic[2])) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } mic++; *p++ = *mic++; *p++ = *mic++; @@ -122,12 +149,18 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; } } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c index 5059f917a98..cc4817dc4cd 100644 --- a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c @@ -42,17 +42,20 @@ PG_FUNCTION_INFO_V1(mic_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void sjis2mic(const unsigned char *sjis, unsigned char *p, int len); -static void mic2sjis(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_jp(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len); -static void sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len); +static int sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError); +static int mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_jp_to_sjis(PG_FUNCTION_ARGS) @@ -60,12 +63,14 @@ euc_jp_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_SJIS); - euc_jp2sjis(src, dest, len); + converted = euc_jp2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -74,12 +79,14 @@ sjis_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_EUC_JP); - sjis2euc_jp(src, dest, len); + converted = sjis2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -88,12 +95,14 @@ euc_jp_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_MULE_INTERNAL); - euc_jp2mic(src, dest, len); + converted = euc_jp2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -102,12 +111,14 @@ mic_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_JP); - mic2euc_jp(src, dest, len); + converted = mic2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -116,12 +127,14 @@ sjis_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_MULE_INTERNAL); - sjis2mic(src, dest, len); + converted = sjis2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -130,20 +143,23 @@ mic_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_SJIS); - mic2sjis(src, dest, len); + converted = mic2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * SJIS ---> MIC */ -static void -sjis2mic(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -167,7 +183,11 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) * JIS X0208, X0212, user defined extended characters */ if (len < 2 || !ISSJISHEAD(c1) || !ISSJISTAIL(sjis[1])) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } c2 = sjis[1]; k = (c1 << 8) + c2; if (k >= 0xed40 && k < 0xf040) @@ -257,21 +277,28 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; } } *p = '\0'; + + return sjis - start; } /* * MIC ---> SJIS */ -static void -mic2sjis(const unsigned char *mic, unsigned char *p, int len) +static int +mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1, c2, k, @@ -284,8 +311,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -293,8 +324,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) *p++ = mic[1]; else if (c1 == LC_JISX0208) @@ -350,20 +385,27 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_SJIS, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP ---> MIC */ -static void -euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -374,8 +416,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -383,8 +429,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* 1 byte kana? */ *p++ = LC_JISX0201K; @@ -406,14 +456,17 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_JP */ -static void -mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -424,8 +477,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -433,8 +490,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) { *p++ = SS2; @@ -452,20 +513,27 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_JP, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP -> SJIS */ -static void -euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, c2, k; @@ -478,8 +546,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -487,8 +559,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* hankaku kana? */ @@ -551,14 +627,17 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * SJIS ---> EUC_JP */ -static void -sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -573,8 +652,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -582,8 +665,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_SJIS, (const char *) sjis, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf) { /* JIS X0201 (1 byte kana) */ @@ -680,4 +767,6 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c index ac823d6c270..a5b51617e52 100644 --- a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_kr2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_kr(const unsigned char *mic, unsigned char *p, int len); +static int euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_kr_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_kr_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_MULE_INTERNAL); - euc_kr2mic(src, dest, len); + converted = euc_kr2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_KR); - mic2euc_kr(src, dest, len); + converted = mic2euc_kr(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_KR ---> MIC */ -static void -euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -78,8 +86,12 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_KR, (const char *) euc, len); if (l != 2) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = LC_KS5601; *p++ = c1; *p++ = euc[1]; @@ -89,22 +101,29 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_KR */ -static void -mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -115,8 +134,12 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -124,18 +147,28 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_KS5601) { *p++ = mic[1]; *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_KR, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c index 66c242d7f36..ebb4e0acd53 100644 --- a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c @@ -32,17 +32,20 @@ PG_FUNCTION_INFO_V1(mic_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_tw2big5(const unsigned char *euc, unsigned char *p, int len); -static void big52euc_tw(const unsigned char *euc, unsigned char *p, int len); -static void big52mic(const unsigned char *big5, unsigned char *p, int len); -static void mic2big5(const unsigned char *mic, unsigned char *p, int len); -static void euc_tw2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_tw(const unsigned char *mic, unsigned char *p, int len); +static int euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52euc_tw(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError); +static int mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_tw_to_big5(PG_FUNCTION_ARGS) @@ -50,12 +53,14 @@ euc_tw_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_BIG5); - euc_tw2big5(src, dest, len); + converted = euc_tw2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -64,12 +69,14 @@ big5_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_EUC_TW); - big52euc_tw(src, dest, len); + converted = big52euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -78,12 +85,14 @@ euc_tw_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_MULE_INTERNAL); - euc_tw2mic(src, dest, len); + converted = euc_tw2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -92,12 +101,14 @@ mic_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_TW); - mic2euc_tw(src, dest, len); + converted = mic2euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -106,12 +117,14 @@ big5_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_MULE_INTERNAL); - big52mic(src, dest, len); + converted = big52mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -120,21 +133,24 @@ mic_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_BIG5); - mic2big5(src, dest, len); + converted = mic2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_TW ---> Big5 */ -static void -euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; unsigned char c1; unsigned short big5buf, cnsBuf; @@ -149,8 +165,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Verify and decode the next EUC_TW input character */ l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -171,8 +191,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Write it out in Big5 */ big5buf = CNStoBIG5(cnsBuf, lc); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_EUC_TW, PG_BIG5, (const char *) euc, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; @@ -182,22 +206,29 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * Big5 ---> EUC_TW */ -static void -big52euc_tw(const unsigned char *big5, unsigned char *p, int len) +static int +big52euc_tw(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -212,8 +243,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); @@ -237,8 +272,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_EUC_TW, (const char *) big5, len); + } big5 += l; len -= l; @@ -256,14 +295,17 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) } } *p = '\0'; + + return big5 - start; } /* * EUC_TW ---> MIC */ -static void -euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -274,8 +316,12 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -304,22 +350,29 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_TW */ -static void -mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -330,8 +383,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -339,8 +396,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1) { *p++ = mic[1]; @@ -362,20 +423,27 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[3]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_TW, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * Big5 ---> MIC */ -static void -big52mic(const unsigned char *big5, unsigned char *p, int len) +static int +big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -389,8 +457,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } *p++ = c1; big5++; len--; @@ -398,8 +470,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); if (lc != 0) @@ -412,20 +488,27 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_MULE_INTERNAL, (const char *) big5, len); + } big5 += l; len -= l; } *p = '\0'; + + return big5 - start; } /* * MIC ---> Big5 */ -static void -mic2big5(const unsigned char *mic, unsigned char *p, int len) +static int +mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -438,8 +521,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -447,8 +534,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1 || c1 == LC_CNS11643_2 || c1 == LCPRV2_B) { if (c1 == LCPRV2_B) @@ -462,16 +553,26 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } big5buf = CNStoBIG5(cnsBuf, c1); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c index 2e28e6780a5..8610fcb69aa 100644 --- a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c +++ b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(win1250_to_latin2); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -82,12 +85,14 @@ latin2_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -96,12 +101,14 @@ mic_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN2); - mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -110,13 +117,15 @@ win1250_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - win1250_2_iso88592); + converted = latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -125,13 +134,15 @@ mic_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1250); - mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - iso88592_2_win1250); + converted = mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -140,12 +151,15 @@ latin2_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_WIN1250); - local2local(src, dest, len, PG_LATIN2, PG_WIN1250, iso88592_2_win1250); + converted = local2local(src, dest, len, PG_LATIN2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -154,10 +168,13 @@ win1250_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_LATIN2); - local2local(src, dest, len, PG_WIN1250, PG_LATIN2, win1250_2_iso88592); + converted = local2local(src, dest, len, PG_WIN1250, PG_LATIN2, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c index bc651410f21..bff27d1c295 100644 --- a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(mic_to_latin4); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -42,12 +45,14 @@ latin1_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,12 +61,14 @@ mic_to_latin1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN1); - mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -70,12 +77,14 @@ latin3_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN3, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -84,12 +93,14 @@ mic_to_latin3(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN3); - mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,12 +109,14 @@ latin4_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN4, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -112,10 +125,12 @@ mic_to_latin4(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN4); - mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c index d6067cdc24e..3838b15cab9 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ big5_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_UTF8); - LocalToUtf(src, len, dest, - &big5_to_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = LocalToUtf(src, len, dest, + &big5_to_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_BIG5); - UtfToLocal(src, len, dest, - &big5_from_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = UtfToLocal(src, len, dest, + &big5_from_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c index ed90e8e682e..75719fe5f1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c @@ -33,8 +33,11 @@ PG_FUNCTION_INFO_V1(koi8u_to_utf8); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -44,16 +47,19 @@ utf8_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8R); - UtfToLocal(src, len, dest, - &koi8r_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = UtfToLocal(src, len, dest, + &koi8r_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -62,16 +68,19 @@ koi8r_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8r_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = LocalToUtf(src, len, dest, + &koi8r_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -80,16 +89,19 @@ utf8_to_koi8u(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8U); - UtfToLocal(src, len, dest, - &koi8u_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = UtfToLocal(src, len, dest, + &koi8u_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,14 +110,17 @@ koi8u_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8U, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8u_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = LocalToUtf(src, len, dest, + &koi8u_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c index d699affce47..5391001951a 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jis_2004_to_unicode_tree, - LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = LocalToUtf(src, len, dest, + &euc_jis_2004_to_unicode_tree, + LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JIS_2004); - UtfToLocal(src, len, dest, - &euc_jis_2004_from_unicode_tree, - ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = UtfToLocal(src, len, dest, + &euc_jis_2004_from_unicode_tree, + ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c index d7c0ba6a58b..c87d1bf2398 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_cn_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_cn_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = LocalToUtf(src, len, dest, + &euc_cn_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_CN); - UtfToLocal(src, len, dest, - &euc_cn_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = UtfToLocal(src, len, dest, + &euc_cn_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c index 13a3a23e77b..6a55134db21 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jp); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jp_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jp_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = LocalToUtf(src, len, dest, + &euc_jp_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JP); - UtfToLocal(src, len, dest, - &euc_jp_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = UtfToLocal(src, len, dest, + &euc_jp_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c index 1bbb8aaef7b..fe1924e2fec 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_kr_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_kr_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = LocalToUtf(src, len, dest, + &euc_kr_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_KR); - UtfToLocal(src, len, dest, - &euc_kr_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = UtfToLocal(src, len, dest, + &euc_kr_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c index 9830045dccd..68215659b57 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_tw); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_tw_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_tw_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = LocalToUtf(src, len, dest, + &euc_tw_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_TW); - UtfToLocal(src, len, dest, - &euc_tw_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = UtfToLocal(src, len, dest, + &euc_tw_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c index f86ecf27424..e1a59c39a4d 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c @@ -183,8 +183,11 @@ conv_utf8_to_18030(uint32 code) * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -193,16 +196,19 @@ gb18030_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GB18030, PG_UTF8); - LocalToUtf(src, len, dest, - &gb18030_to_unicode_tree, - NULL, 0, - conv_18030_to_utf8, - PG_GB18030); + converted = LocalToUtf(src, len, dest, + &gb18030_to_unicode_tree, + NULL, 0, + conv_18030_to_utf8, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -211,14 +217,17 @@ utf8_to_gb18030(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GB18030); - UtfToLocal(src, len, dest, - &gb18030_from_unicode_tree, - NULL, 0, - conv_utf8_to_18030, - PG_GB18030); + converted = UtfToLocal(src, len, dest, + &gb18030_from_unicode_tree, + NULL, 0, + conv_utf8_to_18030, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c index 2ab8b16c8a8..881386d5347 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_gbk); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ gbk_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GBK, PG_UTF8); - LocalToUtf(src, len, dest, - &gbk_to_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = LocalToUtf(src, len, dest, + &gbk_to_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_gbk(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GBK); - UtfToLocal(src, len, dest, - &gbk_from_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = UtfToLocal(src, len, dest, + &gbk_from_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c index 3e49f67ea2f..d93a521badf 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c @@ -52,8 +52,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -100,6 +103,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -108,12 +112,15 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -122,7 +129,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -132,6 +139,7 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -140,12 +148,15 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -154,5 +165,5 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c index 67e713cca11..8ac93604a1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c @@ -26,8 +26,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859_1); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -37,6 +40,8 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_UTF8); @@ -45,7 +50,11 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_LATIN1, (const char *) src, len); + } if (!IS_HIGHBIT_SET(c)) *dest++ = c; else @@ -58,7 +67,7 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } Datum @@ -67,6 +76,8 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c, c1; @@ -76,7 +87,11 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_UTF8, (const char *) src, len); + } /* fast path for ASCII-subset characters */ if (!IS_HIGHBIT_SET(c)) { @@ -102,11 +117,15 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) len -= 2; } else + { + if (noError) + break; report_untranslatable_char(PG_UTF8, PG_LATIN1, (const char *) src, len); + } } } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c index 578f5df4e7f..317daa2d5ee 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_johab); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ johab_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_JOHAB, PG_UTF8); - LocalToUtf(src, len, dest, - &johab_to_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = LocalToUtf(src, len, dest, + &johab_to_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_johab(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_JOHAB); - UtfToLocal(src, len, dest, - &johab_from_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = UtfToLocal(src, len, dest, + &johab_from_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c index dd9fc2975ad..4c9348aba59 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ sjis_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_UTF8); - LocalToUtf(src, len, dest, - &sjis_to_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = LocalToUtf(src, len, dest, + &sjis_to_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SJIS); - UtfToLocal(src, len, dest, - &sjis_from_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = UtfToLocal(src, len, dest, + &sjis_from_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c index 4bcc886d674..1fffdc5930c 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_shift_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ shift_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &shift_jis_2004_to_unicode_tree, - LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = LocalToUtf(src, len, dest, + &shift_jis_2004_to_unicode_tree, + LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SHIFT_JIS_2004); - UtfToLocal(src, len, dest, - &shift_jis_2004_from_unicode_tree, - ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = UtfToLocal(src, len, dest, + &shift_jis_2004_from_unicode_tree, + ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c index c8e512994a1..d9471dad097 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_uhc); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ uhc_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UHC, PG_UTF8); - LocalToUtf(src, len, dest, - &uhc_to_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = LocalToUtf(src, len, dest, + &uhc_to_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_uhc(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_UHC); - UtfToLocal(src, len, dest, - &uhc_from_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = UtfToLocal(src, len, dest, + &uhc_from_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c index 0c9493dee56..110ba5677d0 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c @@ -48,8 +48,11 @@ PG_FUNCTION_INFO_V1(utf8_to_win); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -81,6 +84,7 @@ win_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -89,12 +93,15 @@ win_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -103,7 +110,7 @@ win_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -113,6 +120,7 @@ utf8_to_win(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -121,12 +129,15 @@ utf8_to_win(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -135,5 +146,5 @@ utf8_to_win(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/mbutils.c b/src/backend/utils/mb/mbutils.c index 2578573b0ab..65753860e35 100644 --- a/src/backend/utils/mb/mbutils.c +++ b/src/backend/utils/mb/mbutils.c @@ -406,12 +406,13 @@ pg_do_encoding_conversion(unsigned char *src, int len, MemoryContextAllocHuge(CurrentMemoryContext, (Size) len * MAX_CONVERSION_GROWTH + 1); - OidFunctionCall5(proc, - Int32GetDatum(src_encoding), - Int32GetDatum(dest_encoding), - CStringGetDatum(src), - CStringGetDatum(result), - Int32GetDatum(len)); + (void) OidFunctionCall6(proc, + Int32GetDatum(src_encoding), + Int32GetDatum(dest_encoding), + CStringGetDatum(src), + CStringGetDatum(result), + Int32GetDatum(len), + BoolGetDatum(false)); /* * If the result is large, it's worth repalloc'ing to release any extra @@ -849,12 +850,13 @@ pg_unicode_to_server(pg_wchar c, unsigned char *s) c_as_utf8[c_as_utf8_len] = '\0'; /* Convert, or throw error if we can't */ - FunctionCall5(Utf8ToServerConvProc, + FunctionCall6(Utf8ToServerConvProc, Int32GetDatum(PG_UTF8), Int32GetDatum(server_encoding), CStringGetDatum(c_as_utf8), CStringGetDatum(s), - Int32GetDatum(c_as_utf8_len)); + Int32GetDatum(c_as_utf8_len), + BoolGetDatum(false)); } diff --git a/src/bin/pg_upgrade/check.c b/src/bin/pg_upgrade/check.c index 43fc297eb69..ee6be95b08d 100644 --- a/src/bin/pg_upgrade/check.c +++ b/src/bin/pg_upgrade/check.c @@ -28,6 +28,7 @@ static void check_for_reg_data_type_usage(ClusterInfo *cluster); static void check_for_jsonb_9_4_usage(ClusterInfo *cluster); static void check_for_pg_role_prefix(ClusterInfo *cluster); static void check_for_new_tablespace_dir(ClusterInfo *new_cluster); +static void check_for_user_defined_encoding_conversions(ClusterInfo *cluster); static char *get_canonical_locale_name(int category, const char *locale); @@ -102,6 +103,15 @@ check_and_dump_old_cluster(bool live_check) check_for_reg_data_type_usage(&old_cluster); check_for_isn_and_int8_passing_mismatch(&old_cluster); + /* + * PG 14 changed the function signature of encoding conversion functions. + * Conversions from older versions cannot be upgraded automatically + * because the user-defined functions used by the encoding conversions + * need to changed to match the new signature. + */ + if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1300) + check_for_user_defined_encoding_conversions(&old_cluster); + /* * Pre-PG 14 allowed user defined postfix operators, which are not * supported anymore. Verify there are none, iff applicable. @@ -1268,6 +1278,91 @@ check_for_pg_role_prefix(ClusterInfo *cluster) check_ok(); } +/* + * Verify that no user-defined encoding conversions exist. + */ +static void +check_for_user_defined_encoding_conversions(ClusterInfo *cluster) +{ + int dbnum; + FILE *script = NULL; + bool found = false; + char output_path[MAXPGPATH]; + + prep_status("Checking for user-defined encoding conversions"); + + snprintf(output_path, sizeof(output_path), + "encoding_conversions.txt"); + + /* Find any user defined encoding conversions */ + for (dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++) + { + PGresult *res; + bool db_used = false; + int ntups; + int rowno; + int i_conoid, + i_conname, + i_nspname; + DbInfo *active_db = &cluster->dbarr.dbs[dbnum]; + PGconn *conn = connectToServer(cluster, active_db->db_name); + + /* + * The query below hardcodes FirstNormalObjectId as 16384 rather than + * interpolating that C #define into the query because, if that + * #define is ever changed, the cutoff we want to use is the value + * used by pre-version 14 servers, not that of some future version. + */ + res = executeQueryOrDie(conn, + "SELECT c.oid as conoid, c.conname, n.nspname " + "FROM pg_catalog.pg_conversion c, " + " pg_catalog.pg_namespace n " + "WHERE c.connamespace = n.oid AND " + " c.oid >= 16384"); + ntups = PQntuples(res); + i_conoid = PQfnumber(res, "conoid"); + i_conname = PQfnumber(res, "conname"); + i_nspname = PQfnumber(res, "nspname"); + for (rowno = 0; rowno < ntups; rowno++) + { + found = true; + if (script == NULL && + (script = fopen_priv(output_path, "w")) == NULL) + pg_fatal("could not open file \"%s\": %s\n", + output_path, strerror(errno)); + if (!db_used) + { + fprintf(script, "In database: %s\n", active_db->db_name); + db_used = true; + } + fprintf(script, " (oid=%s) %s.%s\n", + PQgetvalue(res, rowno, i_conoid), + PQgetvalue(res, rowno, i_nspname), + PQgetvalue(res, rowno, i_conname)); + } + + PQclear(res); + + PQfinish(conn); + } + + if (script) + fclose(script); + + if (found) + { + pg_log(PG_REPORT, "fatal\n"); + pg_fatal("Your installation contains user-defined encoding conversions.\n" + "The conversion function parameters changed in PostgreSQL version 14\n" + "so this cluster cannot currently be upgraded. You can remove the\n" + "encoding conversions in the old cluster and restart the upgrade.\n" + "A list of user-defined encoding conversions is in the file:\n" + " %s\n\n", output_path); + } + else + check_ok(); +} + /* * get_canonical_locale_name diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index f8174061ef3..75b829e8514 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10766,388 +10766,388 @@ # conversion functions { oid => '4302', descr => 'internal conversion function for KOI8R to MULE_INTERNAL', - proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_mic', + proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4303', descr => 'internal conversion function for MULE_INTERNAL to KOI8R', - proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_koi8r', + proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4304', descr => 'internal conversion function for ISO-8859-5 to MULE_INTERNAL', - proname => 'iso_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_mic', + proname => 'iso_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4305', descr => 'internal conversion function for MULE_INTERNAL to ISO-8859-5', - proname => 'mic_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_iso', + proname => 'mic_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4306', descr => 'internal conversion function for WIN1251 to MULE_INTERNAL', - proname => 'win1251_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_mic', + proname => 'win1251_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4307', descr => 'internal conversion function for MULE_INTERNAL to WIN1251', - proname => 'mic_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1251', + proname => 'mic_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4308', descr => 'internal conversion function for WIN866 to MULE_INTERNAL', - proname => 'win866_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_mic', + proname => 'win866_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4309', descr => 'internal conversion function for MULE_INTERNAL to WIN866', - proname => 'mic_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win866', + proname => 'mic_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4310', descr => 'internal conversion function for KOI8R to WIN1251', - proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4311', descr => 'internal conversion function for WIN1251 to KOI8R', - proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4312', descr => 'internal conversion function for KOI8R to WIN866', - proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_win866', + proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4313', descr => 'internal conversion function for WIN866 to KOI8R', - proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_koi8r', + proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4314', descr => 'internal conversion function for WIN866 to WIN1251', - proname => 'win866_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win866_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4315', descr => 'internal conversion function for WIN1251 to WIN866', - proname => 'win1251_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4316', descr => 'internal conversion function for ISO-8859-5 to KOI8R', - proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_koi8r', + proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4317', descr => 'internal conversion function for KOI8R to ISO-8859-5', - proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_iso', + proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4318', descr => 'internal conversion function for ISO-8859-5 to WIN1251', - proname => 'iso_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win1251', + proname => 'iso_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4319', descr => 'internal conversion function for WIN1251 to ISO-8859-5', - proname => 'win1251_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_iso', + proname => 'win1251_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4320', descr => 'internal conversion function for ISO-8859-5 to WIN866', - proname => 'iso_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win866', + proname => 'iso_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4321', descr => 'internal conversion function for WIN866 to ISO-8859-5', - proname => 'win866_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_iso', + proname => 'win866_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4322', descr => 'internal conversion function for EUC_CN to MULE_INTERNAL', - proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_mic', + proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_mic', probin => '$libdir/euc_cn_and_mic' }, { oid => '4323', descr => 'internal conversion function for MULE_INTERNAL to EUC_CN', - proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_cn', + proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_cn', probin => '$libdir/euc_cn_and_mic' }, { oid => '4324', descr => 'internal conversion function for EUC_JP to SJIS', - proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_sjis', + proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4325', descr => 'internal conversion function for SJIS to EUC_JP', - proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_euc_jp', + proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4326', descr => 'internal conversion function for EUC_JP to MULE_INTERNAL', - proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_mic', + proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4327', descr => 'internal conversion function for SJIS to MULE_INTERNAL', - proname => 'sjis_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_mic', + proname => 'sjis_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4328', descr => 'internal conversion function for MULE_INTERNAL to EUC_JP', - proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_jp', + proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4329', descr => 'internal conversion function for MULE_INTERNAL to SJIS', - proname => 'mic_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_sjis', + proname => 'mic_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4330', descr => 'internal conversion function for EUC_KR to MULE_INTERNAL', - proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_mic', + proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_mic', probin => '$libdir/euc_kr_and_mic' }, { oid => '4331', descr => 'internal conversion function for MULE_INTERNAL to EUC_KR', - proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_kr', + proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_kr', probin => '$libdir/euc_kr_and_mic' }, { oid => '4332', descr => 'internal conversion function for EUC_TW to BIG5', - proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_big5', + proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4333', descr => 'internal conversion function for BIG5 to EUC_TW', - proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_euc_tw', + proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4334', descr => 'internal conversion function for EUC_TW to MULE_INTERNAL', - proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_mic', + proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4335', descr => 'internal conversion function for BIG5 to MULE_INTERNAL', - proname => 'big5_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_mic', + proname => 'big5_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4336', descr => 'internal conversion function for MULE_INTERNAL to EUC_TW', - proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_tw', + proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4337', descr => 'internal conversion function for MULE_INTERNAL to BIG5', - proname => 'mic_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_big5', + proname => 'mic_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4338', descr => 'internal conversion function for LATIN2 to MULE_INTERNAL', - proname => 'latin2_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin2_to_mic', + proname => 'latin2_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4339', descr => 'internal conversion function for MULE_INTERNAL to LATIN2', - proname => 'mic_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin2', + proname => 'mic_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4340', descr => 'internal conversion function for WIN1250 to MULE_INTERNAL', - proname => 'win1250_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1250_to_mic', + proname => 'win1250_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4341', descr => 'internal conversion function for MULE_INTERNAL to WIN1250', - proname => 'mic_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1250', + proname => 'mic_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4342', descr => 'internal conversion function for LATIN2 to WIN1250', - proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4343', descr => 'internal conversion function for WIN1250 to LATIN2', - proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4344', descr => 'internal conversion function for LATIN1 to MULE_INTERNAL', - proname => 'latin1_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin1_to_mic', + proname => 'latin1_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin1_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4345', descr => 'internal conversion function for MULE_INTERNAL to LATIN1', - proname => 'mic_to_latin1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin1', + proname => 'mic_to_latin1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin1', probin => '$libdir/latin_and_mic' }, { oid => '4346', descr => 'internal conversion function for LATIN3 to MULE_INTERNAL', - proname => 'latin3_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin3_to_mic', + proname => 'latin3_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin3_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4347', descr => 'internal conversion function for MULE_INTERNAL to LATIN3', - proname => 'mic_to_latin3', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin3', + proname => 'mic_to_latin3', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin3', probin => '$libdir/latin_and_mic' }, { oid => '4348', descr => 'internal conversion function for LATIN4 to MULE_INTERNAL', - proname => 'latin4_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin4_to_mic', + proname => 'latin4_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin4_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4349', descr => 'internal conversion function for MULE_INTERNAL to LATIN4', - proname => 'mic_to_latin4', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin4', + proname => 'mic_to_latin4', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin4', probin => '$libdir/latin_and_mic' }, { oid => '4352', descr => 'internal conversion function for BIG5 to UTF8', - proname => 'big5_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_utf8', + proname => 'big5_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_utf8', probin => '$libdir/utf8_and_big5' }, { oid => '4353', descr => 'internal conversion function for UTF8 to BIG5', - proname => 'utf8_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_big5', + proname => 'utf8_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_big5', probin => '$libdir/utf8_and_big5' }, { oid => '4354', descr => 'internal conversion function for UTF8 to KOI8R', - proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8r', + proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8r', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4355', descr => 'internal conversion function for KOI8R to UTF8', - proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_utf8', + proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4356', descr => 'internal conversion function for UTF8 to KOI8U', - proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8u', + proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8u', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4357', descr => 'internal conversion function for KOI8U to UTF8', - proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8u_to_utf8', + proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8u_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4358', descr => 'internal conversion function for UTF8 to WIN', - proname => 'utf8_to_win', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_win', + proname => 'utf8_to_win', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_win', probin => '$libdir/utf8_and_win' }, { oid => '4359', descr => 'internal conversion function for WIN to UTF8', - proname => 'win_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win_to_utf8', + proname => 'win_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win_to_utf8', probin => '$libdir/utf8_and_win' }, { oid => '4360', descr => 'internal conversion function for EUC_CN to UTF8', - proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_utf8', + proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_utf8', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4361', descr => 'internal conversion function for UTF8 to EUC_CN', - proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_cn', + proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_cn', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4362', descr => 'internal conversion function for EUC_JP to UTF8', - proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_utf8', + proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_utf8', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4363', descr => 'internal conversion function for UTF8 to EUC_JP', - proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_jp', + proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jp', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4364', descr => 'internal conversion function for EUC_KR to UTF8', - proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_utf8', + proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_utf8', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4365', descr => 'internal conversion function for UTF8 to EUC_KR', - proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_kr', + proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_kr', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4366', descr => 'internal conversion function for EUC_TW to UTF8', - proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_utf8', + proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_utf8', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4367', descr => 'internal conversion function for UTF8 to EUC_TW', - proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_tw', + proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_tw', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4368', descr => 'internal conversion function for GB18030 to UTF8', - proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gb18030_to_utf8', + proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gb18030_to_utf8', probin => '$libdir/utf8_and_gb18030' }, { oid => '4369', descr => 'internal conversion function for UTF8 to GB18030', - proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gb18030', + proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gb18030', probin => '$libdir/utf8_and_gb18030' }, { oid => '4370', descr => 'internal conversion function for GBK to UTF8', - proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gbk_to_utf8', + proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gbk_to_utf8', probin => '$libdir/utf8_and_gbk' }, { oid => '4371', descr => 'internal conversion function for UTF8 to GBK', - proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gbk', + proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gbk', probin => '$libdir/utf8_and_gbk' }, { oid => '4372', descr => 'internal conversion function for UTF8 to ISO-8859 2-16', - proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_iso8859', + proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859', probin => '$libdir/utf8_and_iso8859' }, { oid => '4373', descr => 'internal conversion function for ISO-8859 2-16 to UTF8', - proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso8859_to_utf8', + proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_to_utf8', probin => '$libdir/utf8_and_iso8859' }, { oid => '4374', descr => 'internal conversion function for LATIN1 to UTF8', - proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_1_to_utf8', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4375', descr => 'internal conversion function for UTF8 to LATIN1', - proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859_1', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4376', descr => 'internal conversion function for JOHAB to UTF8', - proname => 'johab_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'johab_to_utf8', + proname => 'johab_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'johab_to_utf8', probin => '$libdir/utf8_and_johab' }, { oid => '4377', descr => 'internal conversion function for UTF8 to JOHAB', - proname => 'utf8_to_johab', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_johab', + proname => 'utf8_to_johab', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_johab', probin => '$libdir/utf8_and_johab' }, { oid => '4378', descr => 'internal conversion function for SJIS to UTF8', - proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_utf8', + proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_utf8', probin => '$libdir/utf8_and_sjis' }, { oid => '4379', descr => 'internal conversion function for UTF8 to SJIS', - proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_sjis', + proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_sjis', probin => '$libdir/utf8_and_sjis' }, { oid => '4380', descr => 'internal conversion function for UHC to UTF8', - proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'uhc_to_utf8', + proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'uhc_to_utf8', probin => '$libdir/utf8_and_uhc' }, { oid => '4381', descr => 'internal conversion function for UTF8 to UHC', - proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_uhc', + proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_uhc', probin => '$libdir/utf8_and_uhc' }, { oid => '4382', descr => 'internal conversion function for EUC_JIS_2004 to UTF8', - proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_utf8', probin => '$libdir/utf8_and_euc2004' }, { oid => '4383', descr => 'internal conversion function for UTF8 to EUC_JIS_2004', - proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jis_2004', probin => '$libdir/utf8_and_euc2004' }, { oid => '4384', descr => 'internal conversion function for SHIFT_JIS_2004 to UTF8', - proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_utf8', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4385', descr => 'internal conversion function for UTF8 to SHIFT_JIS_2004', - proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_shift_jis_2004', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4386', descr => 'internal conversion function for EUC_JIS_2004 to SHIFT_JIS_2004', proname => 'euc_jis_2004_to_shift_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_shift_jis_2004', probin => '$libdir/euc2004_sjis2004' }, { oid => '4387', descr => 'internal conversion function for SHIFT_JIS_2004 to EUC_JIS_2004', proname => 'shift_jis_2004_to_euc_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_euc_jis_2004', probin => '$libdir/euc2004_sjis2004' }, diff --git a/src/include/mb/pg_wchar.h b/src/include/mb/pg_wchar.h index 64b22e4b0d4..346a41a1f3d 100644 --- a/src/include/mb/pg_wchar.h +++ b/src/include/mb/pg_wchar.h @@ -627,18 +627,18 @@ extern void pg_unicode_to_server(pg_wchar c, unsigned char *s); extern unsigned short BIG5toCNS(unsigned short big5, unsigned char *lc); extern unsigned short CNStoBIG5(unsigned short cns, unsigned char lc); -extern void UtfToLocal(const unsigned char *utf, int len, - unsigned char *iso, - const pg_mb_radix_tree *map, - const pg_utf_to_local_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); -extern void LocalToUtf(const unsigned char *iso, int len, - unsigned char *utf, - const pg_mb_radix_tree *map, - const pg_local_to_utf_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); +extern int UtfToLocal(const unsigned char *utf, int len, + unsigned char *iso, + const pg_mb_radix_tree *map, + const pg_utf_to_local_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); +extern int LocalToUtf(const unsigned char *iso, int len, + unsigned char *utf, + const pg_mb_radix_tree *map, + const pg_local_to_utf_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); extern bool pg_verifymbstr(const char *mbstr, int len, bool noError); extern bool pg_verify_mbstr(int encoding, const char *mbstr, int len, @@ -656,18 +656,19 @@ extern void report_invalid_encoding(int encoding, const char *mbstr, int len) pg extern void report_untranslatable_char(int src_encoding, int dest_encoding, const char *mbstr, int len) pg_attribute_noreturn(); -extern void local2local(const unsigned char *l, unsigned char *p, int len, - int src_encoding, int dest_encoding, const unsigned char *tab); -extern void latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding); -extern void mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding); -extern void latin2mic_with_table(const unsigned char *l, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); -extern void mic2latin_with_table(const unsigned char *mic, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); +extern int local2local(const unsigned char *l, unsigned char *p, int len, + int src_encoding, int dest_encoding, const unsigned char *tab, + bool noError); +extern int latin2mic(const unsigned char *l, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int mic2latin(const unsigned char *mic, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int latin2mic_with_table(const unsigned char *l, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); +extern int mic2latin_with_table(const unsigned char *mic, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); #ifdef WIN32 extern WCHAR *pgwin32_message_to_UTF16(const char *str, int len, int *utf16len); diff --git a/src/test/regress/expected/opr_sanity.out b/src/test/regress/expected/opr_sanity.out index 254ca06d3dd..23ba60e395f 100644 --- a/src/test/regress/expected/opr_sanity.out +++ b/src/test/regress/expected/opr_sanity.out @@ -1052,13 +1052,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); oid | proname | oid | conname -----+---------+-----+--------- (0 rows) diff --git a/src/test/regress/sql/opr_sanity.sql b/src/test/regress/sql/opr_sanity.sql index bbd3834b634..04691745981 100644 --- a/src/test/regress/sql/opr_sanity.sql +++ b/src/test/regress/sql/opr_sanity.sql @@ -556,13 +556,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); -- Check for conprocs that don't perform the specific conversion that -- pg_conversion alleges they do, by trying to invoke each conversion -- 2.29.2 --------------39E46EF15EBFAA37D53332E5 Content-Type: text/x-patch; charset=UTF-8; name="v3-0003-Add-tests-for-the-new-noError-variants-of-built-i.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="v3-0003-Add-tests-for-the-new-noError-variants-of-built-i.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 34+ messages in thread
* [PATCH v3 2/5] Change conversion function signature. @ 2021-01-28 16:42 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 34+ messages in thread From: Heikki Linnakangas @ 2021-01-28 16:42 UTC (permalink / raw) Add a 'noError' argument, so that we can try to convert a buffer without knowing the character boundaries beforehand. The functions now need to return the number of input bytes successfully converted. This is is a backwards-incompatible change, if you have created a custom encoding conversion with CREATE CONVERSION. This adds a check to pg_upgrade for that, refusing the upgrade if there are any user-defined encoding conversions. --- doc/src/sgml/ref/create_conversion.sgml | 5 +- src/backend/commands/conversioncmds.c | 27 +- src/backend/utils/error/elog.c | 2 + src/backend/utils/mb/conv.c | 112 +++++- .../cyrillic_and_mic/cyrillic_and_mic.c | 127 ++++--- .../euc2004_sjis2004/euc2004_sjis2004.c | 96 ++++- .../euc_cn_and_mic/euc_cn_and_mic.c | 57 ++- .../euc_jp_and_sjis/euc_jp_and_sjis.c | 153 ++++++-- .../euc_kr_and_mic/euc_kr_and_mic.c | 57 ++- .../euc_tw_and_big5/euc_tw_and_big5.c | 165 +++++++-- .../latin2_and_win1250/latin2_and_win1250.c | 49 ++- .../latin_and_mic/latin_and_mic.c | 43 ++- .../utf8_and_big5/utf8_and_big5.c | 37 +- .../utf8_and_cyrillic/utf8_and_cyrillic.c | 67 ++-- .../utf8_and_euc2004/utf8_and_euc2004.c | 37 +- .../utf8_and_euc_cn/utf8_and_euc_cn.c | 37 +- .../utf8_and_euc_jp/utf8_and_euc_jp.c | 37 +- .../utf8_and_euc_kr/utf8_and_euc_kr.c | 37 +- .../utf8_and_euc_tw/utf8_and_euc_tw.c | 37 +- .../utf8_and_gb18030/utf8_and_gb18030.c | 37 +- .../utf8_and_gbk/utf8_and_gbk.c | 37 +- .../utf8_and_iso8859/utf8_and_iso8859.c | 43 ++- .../utf8_and_iso8859_1/utf8_and_iso8859_1.c | 27 +- .../utf8_and_johab/utf8_and_johab.c | 37 +- .../utf8_and_sjis/utf8_and_sjis.c | 37 +- .../utf8_and_sjis2004/utf8_and_sjis2004.c | 37 +- .../utf8_and_uhc/utf8_and_uhc.c | 37 +- .../utf8_and_win/utf8_and_win.c | 43 ++- src/backend/utils/mb/mbutils.c | 18 +- src/bin/pg_upgrade/check.c | 95 +++++ src/include/catalog/pg_proc.dat | 332 +++++++++--------- src/include/mb/pg_wchar.h | 49 +-- src/test/regress/expected/opr_sanity.out | 7 +- src/test/regress/sql/opr_sanity.sql | 7 +- 34 files changed, 1390 insertions(+), 635 deletions(-) diff --git a/doc/src/sgml/ref/create_conversion.sgml b/doc/src/sgml/ref/create_conversion.sgml index e7700fecfc5..f014a676c88 100644 --- a/doc/src/sgml/ref/create_conversion.sgml +++ b/doc/src/sgml/ref/create_conversion.sgml @@ -117,8 +117,9 @@ conv_proc( integer, -- destination encoding ID cstring, -- source string (null terminated C string) internal, -- destination (fill with a null terminated C string) - integer -- source string length -) RETURNS void; + integer, -- source string length + boolean -- if true, don't throw an error if conversion fails +) RETURNS integer; </programlisting></para> </listitem> </varlistentry> diff --git a/src/backend/commands/conversioncmds.c b/src/backend/commands/conversioncmds.c index f7ff321de71..d2041466911 100644 --- a/src/backend/commands/conversioncmds.c +++ b/src/backend/commands/conversioncmds.c @@ -45,8 +45,9 @@ CreateConversionCommand(CreateConversionStmt *stmt) const char *from_encoding_name = stmt->for_encoding_name; const char *to_encoding_name = stmt->to_encoding_name; List *func_name = stmt->func_name; - static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID}; + static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID, BOOLOID}; char result[1]; + Datum funcresult; /* Convert list of names to a name and namespace */ namespaceId = QualifiedNameGetCreationNamespace(stmt->conversion_name, @@ -92,8 +93,8 @@ CreateConversionCommand(CreateConversionStmt *stmt) funcoid = LookupFuncName(func_name, sizeof(funcargs) / sizeof(Oid), funcargs, false); - /* Check it returns VOID, else it's probably the wrong function */ - if (get_func_rettype(funcoid) != VOIDOID) + /* Check it returns int4, else it's probably the wrong function */ + if (get_func_rettype(funcoid) != INT4OID) ereport(ERROR, (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), errmsg("encoding conversion function %s must return type %s", @@ -111,12 +112,20 @@ CreateConversionCommand(CreateConversionStmt *stmt) * string; the conversion function should throw an error if it can't * perform the requested conversion. */ - OidFunctionCall5(funcoid, - Int32GetDatum(from_encoding), - Int32GetDatum(to_encoding), - CStringGetDatum(""), - CStringGetDatum(result), - Int32GetDatum(0)); + funcresult = OidFunctionCall6(funcoid, + Int32GetDatum(from_encoding), + Int32GetDatum(to_encoding), + CStringGetDatum(""), + CStringGetDatum(result), + Int32GetDatum(0), + BoolGetDatum(false)); + + /* The function should return 0 for empty input. Might as well check that, too. */ + if (DatumGetInt32(funcresult) != 0) + ereport(ERROR, + (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), + errmsg("encoding conversion function %s returned incorrect result for empty input", + NameListToString(func_name)))); /* * All seem ok, go ahead (possible failure would be a duplicate conversion diff --git a/src/backend/utils/error/elog.c b/src/backend/utils/error/elog.c index 80c26724612..762f77d533c 100644 --- a/src/backend/utils/error/elog.c +++ b/src/backend/utils/error/elog.c @@ -2280,6 +2280,8 @@ write_console(const char *line, int len) * Conversion on non-win32 platforms is not implemented yet. It requires * non-throw version of pg_do_encoding_conversion(), that converts * unconvertable characters to '?' without errors. + * + * XXX: We have a no-throw version now. It doesn't convert to '?' though. */ #endif diff --git a/src/backend/utils/mb/conv.c b/src/backend/utils/mb/conv.c index a07b54bd3b8..b83358bc7a5 100644 --- a/src/backend/utils/mb/conv.c +++ b/src/backend/utils/mb/conv.c @@ -26,14 +26,16 @@ * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the target charset, or 0 if there is no equivalent code. */ -void +int local2local(const unsigned char *l, unsigned char *p, int len, int src_encoding, int dest_encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -41,7 +43,11 @@ local2local(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(src_encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -50,13 +56,19 @@ local2local(const unsigned char *l, if (c2) *p++ = c2; else + { + if (noError) + break; report_untranslatable_char(src_encoding, dest_encoding, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -67,17 +79,22 @@ local2local(const unsigned char *l, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = l; int c1; while (len > 0) { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (IS_HIGHBIT_SET(c1)) *p++ = lc; *p++ = c1; @@ -85,6 +102,8 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, len--; } *p = '\0'; + + return l - start; } /* @@ -95,17 +114,22 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -118,17 +142,27 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1])) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); + } *p++ = mic[1]; mic += 2; len -= 2; } } *p = '\0'; + + return mic - start; } @@ -144,14 +178,16 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the mule encoding, or 0 if there is no equivalent code. */ -void +int latin2mic_with_table(const unsigned char *l, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -159,7 +195,11 @@ latin2mic_with_table(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -171,13 +211,19 @@ latin2mic_with_table(const unsigned char *l, *p++ = c2; } else + { + if (noError) + break; report_untranslatable_char(encoding, PG_MULE_INTERNAL, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -192,14 +238,16 @@ latin2mic_with_table(const unsigned char *l, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the local charset, or 0 if there is no equivalent code. */ -void +int mic2latin_with_table(const unsigned char *mic, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = mic; unsigned char c1, c2; @@ -207,7 +255,11 @@ mic2latin_with_table(const unsigned char *mic, { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -220,11 +272,17 @@ mic2latin_with_table(const unsigned char *mic, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1]) || (c2 = tab[mic[1] - HIGHBIT]) == 0) { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); break; /* keep compiler quiet */ @@ -235,6 +293,8 @@ mic2latin_with_table(const unsigned char *mic, } } *p = '\0'; + + return mic - start; } /* @@ -425,17 +485,19 @@ pg_mb_radix_conv(const pg_mb_radix_tree *rt, * * See pg_wchar.h for more details about the data structures used here. */ -void +int UtfToLocal(const unsigned char *utf, int len, unsigned char *iso, const pg_mb_radix_tree *map, const pg_utf_to_local_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, bool noError) { uint32 iutf; int l; const pg_utf_to_local_combined *cp; + const unsigned char *start = utf; + const unsigned char *cur = utf; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -449,6 +511,8 @@ UtfToLocal(const unsigned char *utf, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*utf == '\0') break; @@ -584,15 +648,19 @@ UtfToLocal(const unsigned char *utf, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(PG_UTF8, encoding, (const char *) (utf - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(PG_UTF8, (const char *) utf, len); *iso = '\0'; + + return cur - start; } /* @@ -616,18 +684,24 @@ UtfToLocal(const unsigned char *utf, int len, * (if provided) is applied. An error is raised if no match is found. * * See pg_wchar.h for more details about the data structures used here. + * + * Returns the number of input bytes consumed. If noError is true, this can + * be less than 'len'. */ -void +int LocalToUtf(const unsigned char *iso, int len, unsigned char *utf, const pg_mb_radix_tree *map, const pg_local_to_utf_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, + bool noError) { uint32 iiso; int l; const pg_local_to_utf_combined *cp; + const unsigned char *start = iso; + const unsigned char *cur = iso; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -641,6 +715,8 @@ LocalToUtf(const unsigned char *iso, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*iso == '\0') break; @@ -723,13 +799,17 @@ LocalToUtf(const unsigned char *iso, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(encoding, PG_UTF8, (const char *) (iso - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(encoding, (const char *) iso, len); *utf = '\0'; + + return cur - start; } diff --git a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c index 4c5b02654de..368c2deb5e4 100644 --- a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c @@ -44,8 +44,11 @@ PG_FUNCTION_INFO_V1(win866_to_iso); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -306,12 +309,14 @@ koi8r_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -320,12 +325,14 @@ mic_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_KOI8R); - mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -334,12 +341,14 @@ iso_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -348,12 +357,14 @@ mic_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_ISO_8859_5); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -362,12 +373,14 @@ win1251_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -376,12 +389,14 @@ mic_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1251); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -390,12 +405,14 @@ win866_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -404,12 +421,14 @@ mic_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN866); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -418,12 +437,14 @@ koi8r_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN1251); - local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -432,12 +453,14 @@ win1251_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_KOI8R); - local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi); + converted = local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -446,12 +469,14 @@ koi8r_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN866); - local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -460,12 +485,14 @@ win866_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_KOI8R); - local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi); + converted = local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -474,12 +501,14 @@ win866_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_WIN1251); - local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251); + converted = local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -488,12 +517,14 @@ win1251_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_WIN866); - local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866); + converted = local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -502,12 +533,14 @@ iso_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_KOI8R); - local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -516,12 +549,14 @@ koi8r_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_ISO_8859_5); - local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso); + converted = local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -530,12 +565,14 @@ iso_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN1251); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -544,12 +581,14 @@ win1251_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso); + converted = local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -558,12 +597,14 @@ iso_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN866); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -572,10 +613,12 @@ win866_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso); + converted = local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c index 4d7fb116cfd..88529c644cf 100644 --- a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c @@ -19,8 +19,8 @@ PG_MODULE_MAGIC; PG_FUNCTION_INFO_V1(euc_jis_2004_to_shift_jis_2004); PG_FUNCTION_INFO_V1(shift_jis_2004_to_euc_jis_2004); -static void euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len); -static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len); +static int euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError); /* ---------- * conv_proc( @@ -28,8 +28,11 @@ static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -39,12 +42,14 @@ euc_jis_2004_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_SHIFT_JIS_2004); - euc_jis_20042shift_jis_2004(src, dest, len); + converted = euc_jis_20042shift_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -53,20 +58,23 @@ shift_jis_2004_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_EUC_JIS_2004); - shift_jis_20042euc_jis_2004(src, dest, len); + converted = shift_jis_20042euc_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_JIS_2004 -> SHIFT_JIS_2004 */ -static void -euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, ku, ten; @@ -79,8 +87,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -90,8 +102,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) l = pg_encoding_verifymbchar(PG_EUC_JIS_2004, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (c1 == SS2 && l == 2) /* JIS X 0201 kana? */ { @@ -121,8 +137,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) *p++ = (ku + 0x19b) >> 1; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } if (ku % 2) @@ -132,8 +152,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; @@ -149,8 +173,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ku >= 63 && ku <= 94) *p++ = (ku + 0x181) >> 1; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (ku % 2) { @@ -159,20 +187,30 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else - report_invalid_encoding(PG_EUC_JIS_2004, + { + if (noError) + break; + report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } euc += l; len -= l; } *p = '\0'; + + return euc - start; } /* @@ -212,9 +250,10 @@ get_ten(int b, int *ku) * SHIFT_JIS_2004 ---> EUC_JIS_2004 */ -static void -shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len) +static int +shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1; int ku, ten, @@ -230,8 +269,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -241,8 +284,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len l = pg_encoding_verifymbchar(PG_SHIFT_JIS_2004, (const char *) sjis, len); if (l < 0 || l > len) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf && l == 1) { @@ -266,8 +313,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x100; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xe0 && c1 <= 0xef) /* plane 1 62ku-94ku */ @@ -275,9 +326,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x180; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, - (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xf0 && c1 <= 0xf3) /* plane 2 @@ -286,8 +340,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } switch (c1) { case 0xf0: @@ -309,16 +367,24 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 == 0xf4 && kubun == 1) ku = 15; else ku = (c1 << 1) - 0x19a - kubun; } else + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (plane == 2) *p++ = SS3; @@ -330,4 +396,6 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c index e9bb896935f..a8da733803d 100644 --- a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_cn2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_cn(const unsigned char *mic, unsigned char *p, int len); +static int euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_cn_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_cn_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_MULE_INTERNAL); - euc_cn2mic(src, dest, len); + converted = euc_cn2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_CN); - mic2euc_cn(src, dest, len); + converted = mic2euc_cn(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_CN ---> MIC */ -static void -euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; while (len > 0) @@ -76,7 +84,11 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (len < 2 || !IS_HIGHBIT_SET(euc[1])) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = LC_GB2312_80; *p++ = c1; *p++ = euc[1]; @@ -86,21 +98,28 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_CN */ -static void -mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) @@ -109,11 +128,19 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (c1 != LC_GB2312_80) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_CN, (const char *) mic, len); + } if (len < 3 || !IS_HIGHBIT_SET(mic[1]) || !IS_HIGHBIT_SET(mic[2])) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } mic++; *p++ = *mic++; *p++ = *mic++; @@ -122,12 +149,18 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; } } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c index 5059f917a98..cc4817dc4cd 100644 --- a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c @@ -42,17 +42,20 @@ PG_FUNCTION_INFO_V1(mic_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void sjis2mic(const unsigned char *sjis, unsigned char *p, int len); -static void mic2sjis(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_jp(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len); -static void sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len); +static int sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError); +static int mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_jp_to_sjis(PG_FUNCTION_ARGS) @@ -60,12 +63,14 @@ euc_jp_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_SJIS); - euc_jp2sjis(src, dest, len); + converted = euc_jp2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -74,12 +79,14 @@ sjis_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_EUC_JP); - sjis2euc_jp(src, dest, len); + converted = sjis2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -88,12 +95,14 @@ euc_jp_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_MULE_INTERNAL); - euc_jp2mic(src, dest, len); + converted = euc_jp2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -102,12 +111,14 @@ mic_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_JP); - mic2euc_jp(src, dest, len); + converted = mic2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -116,12 +127,14 @@ sjis_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_MULE_INTERNAL); - sjis2mic(src, dest, len); + converted = sjis2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -130,20 +143,23 @@ mic_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_SJIS); - mic2sjis(src, dest, len); + converted = mic2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * SJIS ---> MIC */ -static void -sjis2mic(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -167,7 +183,11 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) * JIS X0208, X0212, user defined extended characters */ if (len < 2 || !ISSJISHEAD(c1) || !ISSJISTAIL(sjis[1])) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } c2 = sjis[1]; k = (c1 << 8) + c2; if (k >= 0xed40 && k < 0xf040) @@ -257,21 +277,28 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; } } *p = '\0'; + + return sjis - start; } /* * MIC ---> SJIS */ -static void -mic2sjis(const unsigned char *mic, unsigned char *p, int len) +static int +mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1, c2, k, @@ -284,8 +311,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -293,8 +324,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) *p++ = mic[1]; else if (c1 == LC_JISX0208) @@ -350,20 +385,27 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_SJIS, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP ---> MIC */ -static void -euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -374,8 +416,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -383,8 +429,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* 1 byte kana? */ *p++ = LC_JISX0201K; @@ -406,14 +456,17 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_JP */ -static void -mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -424,8 +477,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -433,8 +490,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) { *p++ = SS2; @@ -452,20 +513,27 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_JP, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP -> SJIS */ -static void -euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, c2, k; @@ -478,8 +546,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -487,8 +559,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* hankaku kana? */ @@ -551,14 +627,17 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * SJIS ---> EUC_JP */ -static void -sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -573,8 +652,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -582,8 +665,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_SJIS, (const char *) sjis, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf) { /* JIS X0201 (1 byte kana) */ @@ -680,4 +767,6 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c index ac823d6c270..a5b51617e52 100644 --- a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_kr2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_kr(const unsigned char *mic, unsigned char *p, int len); +static int euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_kr_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_kr_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_MULE_INTERNAL); - euc_kr2mic(src, dest, len); + converted = euc_kr2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_KR); - mic2euc_kr(src, dest, len); + converted = mic2euc_kr(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_KR ---> MIC */ -static void -euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -78,8 +86,12 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_KR, (const char *) euc, len); if (l != 2) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = LC_KS5601; *p++ = c1; *p++ = euc[1]; @@ -89,22 +101,29 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_KR */ -static void -mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -115,8 +134,12 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -124,18 +147,28 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_KS5601) { *p++ = mic[1]; *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_KR, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c index 66c242d7f36..ebb4e0acd53 100644 --- a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c @@ -32,17 +32,20 @@ PG_FUNCTION_INFO_V1(mic_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_tw2big5(const unsigned char *euc, unsigned char *p, int len); -static void big52euc_tw(const unsigned char *euc, unsigned char *p, int len); -static void big52mic(const unsigned char *big5, unsigned char *p, int len); -static void mic2big5(const unsigned char *mic, unsigned char *p, int len); -static void euc_tw2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_tw(const unsigned char *mic, unsigned char *p, int len); +static int euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52euc_tw(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError); +static int mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_tw_to_big5(PG_FUNCTION_ARGS) @@ -50,12 +53,14 @@ euc_tw_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_BIG5); - euc_tw2big5(src, dest, len); + converted = euc_tw2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -64,12 +69,14 @@ big5_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_EUC_TW); - big52euc_tw(src, dest, len); + converted = big52euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -78,12 +85,14 @@ euc_tw_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_MULE_INTERNAL); - euc_tw2mic(src, dest, len); + converted = euc_tw2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -92,12 +101,14 @@ mic_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_TW); - mic2euc_tw(src, dest, len); + converted = mic2euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -106,12 +117,14 @@ big5_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_MULE_INTERNAL); - big52mic(src, dest, len); + converted = big52mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -120,21 +133,24 @@ mic_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_BIG5); - mic2big5(src, dest, len); + converted = mic2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_TW ---> Big5 */ -static void -euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; unsigned char c1; unsigned short big5buf, cnsBuf; @@ -149,8 +165,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Verify and decode the next EUC_TW input character */ l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -171,8 +191,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Write it out in Big5 */ big5buf = CNStoBIG5(cnsBuf, lc); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_EUC_TW, PG_BIG5, (const char *) euc, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; @@ -182,22 +206,29 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * Big5 ---> EUC_TW */ -static void -big52euc_tw(const unsigned char *big5, unsigned char *p, int len) +static int +big52euc_tw(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -212,8 +243,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); @@ -237,8 +272,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_EUC_TW, (const char *) big5, len); + } big5 += l; len -= l; @@ -256,14 +295,17 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) } } *p = '\0'; + + return big5 - start; } /* * EUC_TW ---> MIC */ -static void -euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -274,8 +316,12 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -304,22 +350,29 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_TW */ -static void -mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -330,8 +383,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -339,8 +396,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1) { *p++ = mic[1]; @@ -362,20 +423,27 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[3]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_TW, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * Big5 ---> MIC */ -static void -big52mic(const unsigned char *big5, unsigned char *p, int len) +static int +big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -389,8 +457,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } *p++ = c1; big5++; len--; @@ -398,8 +470,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); if (lc != 0) @@ -412,20 +488,27 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_MULE_INTERNAL, (const char *) big5, len); + } big5 += l; len -= l; } *p = '\0'; + + return big5 - start; } /* * MIC ---> Big5 */ -static void -mic2big5(const unsigned char *mic, unsigned char *p, int len) +static int +mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -438,8 +521,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -447,8 +534,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1 || c1 == LC_CNS11643_2 || c1 == LCPRV2_B) { if (c1 == LCPRV2_B) @@ -462,16 +553,26 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } big5buf = CNStoBIG5(cnsBuf, c1); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c index 2e28e6780a5..8610fcb69aa 100644 --- a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c +++ b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(win1250_to_latin2); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -82,12 +85,14 @@ latin2_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -96,12 +101,14 @@ mic_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN2); - mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -110,13 +117,15 @@ win1250_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - win1250_2_iso88592); + converted = latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -125,13 +134,15 @@ mic_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1250); - mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - iso88592_2_win1250); + converted = mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -140,12 +151,15 @@ latin2_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_WIN1250); - local2local(src, dest, len, PG_LATIN2, PG_WIN1250, iso88592_2_win1250); + converted = local2local(src, dest, len, PG_LATIN2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -154,10 +168,13 @@ win1250_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_LATIN2); - local2local(src, dest, len, PG_WIN1250, PG_LATIN2, win1250_2_iso88592); + converted = local2local(src, dest, len, PG_WIN1250, PG_LATIN2, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c index bc651410f21..bff27d1c295 100644 --- a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(mic_to_latin4); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -42,12 +45,14 @@ latin1_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,12 +61,14 @@ mic_to_latin1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN1); - mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -70,12 +77,14 @@ latin3_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN3, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -84,12 +93,14 @@ mic_to_latin3(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN3); - mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,12 +109,14 @@ latin4_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN4, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -112,10 +125,12 @@ mic_to_latin4(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN4); - mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c index d6067cdc24e..3838b15cab9 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ big5_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_UTF8); - LocalToUtf(src, len, dest, - &big5_to_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = LocalToUtf(src, len, dest, + &big5_to_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_BIG5); - UtfToLocal(src, len, dest, - &big5_from_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = UtfToLocal(src, len, dest, + &big5_from_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c index ed90e8e682e..75719fe5f1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c @@ -33,8 +33,11 @@ PG_FUNCTION_INFO_V1(koi8u_to_utf8); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -44,16 +47,19 @@ utf8_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8R); - UtfToLocal(src, len, dest, - &koi8r_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = UtfToLocal(src, len, dest, + &koi8r_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -62,16 +68,19 @@ koi8r_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8r_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = LocalToUtf(src, len, dest, + &koi8r_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -80,16 +89,19 @@ utf8_to_koi8u(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8U); - UtfToLocal(src, len, dest, - &koi8u_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = UtfToLocal(src, len, dest, + &koi8u_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,14 +110,17 @@ koi8u_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8U, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8u_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = LocalToUtf(src, len, dest, + &koi8u_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c index d699affce47..5391001951a 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jis_2004_to_unicode_tree, - LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = LocalToUtf(src, len, dest, + &euc_jis_2004_to_unicode_tree, + LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JIS_2004); - UtfToLocal(src, len, dest, - &euc_jis_2004_from_unicode_tree, - ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = UtfToLocal(src, len, dest, + &euc_jis_2004_from_unicode_tree, + ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c index d7c0ba6a58b..c87d1bf2398 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_cn_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_cn_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = LocalToUtf(src, len, dest, + &euc_cn_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_CN); - UtfToLocal(src, len, dest, - &euc_cn_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = UtfToLocal(src, len, dest, + &euc_cn_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c index 13a3a23e77b..6a55134db21 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jp); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jp_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jp_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = LocalToUtf(src, len, dest, + &euc_jp_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JP); - UtfToLocal(src, len, dest, - &euc_jp_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = UtfToLocal(src, len, dest, + &euc_jp_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c index 1bbb8aaef7b..fe1924e2fec 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_kr_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_kr_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = LocalToUtf(src, len, dest, + &euc_kr_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_KR); - UtfToLocal(src, len, dest, - &euc_kr_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = UtfToLocal(src, len, dest, + &euc_kr_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c index 9830045dccd..68215659b57 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_tw); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_tw_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_tw_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = LocalToUtf(src, len, dest, + &euc_tw_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_TW); - UtfToLocal(src, len, dest, - &euc_tw_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = UtfToLocal(src, len, dest, + &euc_tw_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c index f86ecf27424..e1a59c39a4d 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c @@ -183,8 +183,11 @@ conv_utf8_to_18030(uint32 code) * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -193,16 +196,19 @@ gb18030_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GB18030, PG_UTF8); - LocalToUtf(src, len, dest, - &gb18030_to_unicode_tree, - NULL, 0, - conv_18030_to_utf8, - PG_GB18030); + converted = LocalToUtf(src, len, dest, + &gb18030_to_unicode_tree, + NULL, 0, + conv_18030_to_utf8, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -211,14 +217,17 @@ utf8_to_gb18030(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GB18030); - UtfToLocal(src, len, dest, - &gb18030_from_unicode_tree, - NULL, 0, - conv_utf8_to_18030, - PG_GB18030); + converted = UtfToLocal(src, len, dest, + &gb18030_from_unicode_tree, + NULL, 0, + conv_utf8_to_18030, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c index 2ab8b16c8a8..881386d5347 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_gbk); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ gbk_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GBK, PG_UTF8); - LocalToUtf(src, len, dest, - &gbk_to_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = LocalToUtf(src, len, dest, + &gbk_to_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_gbk(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GBK); - UtfToLocal(src, len, dest, - &gbk_from_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = UtfToLocal(src, len, dest, + &gbk_from_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c index 3e49f67ea2f..d93a521badf 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c @@ -52,8 +52,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -100,6 +103,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -108,12 +112,15 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -122,7 +129,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -132,6 +139,7 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -140,12 +148,15 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -154,5 +165,5 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c index 67e713cca11..8ac93604a1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c @@ -26,8 +26,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859_1); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -37,6 +40,8 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_UTF8); @@ -45,7 +50,11 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_LATIN1, (const char *) src, len); + } if (!IS_HIGHBIT_SET(c)) *dest++ = c; else @@ -58,7 +67,7 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } Datum @@ -67,6 +76,8 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c, c1; @@ -76,7 +87,11 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_UTF8, (const char *) src, len); + } /* fast path for ASCII-subset characters */ if (!IS_HIGHBIT_SET(c)) { @@ -102,11 +117,15 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) len -= 2; } else + { + if (noError) + break; report_untranslatable_char(PG_UTF8, PG_LATIN1, (const char *) src, len); + } } } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c index 578f5df4e7f..317daa2d5ee 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_johab); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ johab_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_JOHAB, PG_UTF8); - LocalToUtf(src, len, dest, - &johab_to_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = LocalToUtf(src, len, dest, + &johab_to_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_johab(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_JOHAB); - UtfToLocal(src, len, dest, - &johab_from_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = UtfToLocal(src, len, dest, + &johab_from_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c index dd9fc2975ad..4c9348aba59 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ sjis_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_UTF8); - LocalToUtf(src, len, dest, - &sjis_to_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = LocalToUtf(src, len, dest, + &sjis_to_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SJIS); - UtfToLocal(src, len, dest, - &sjis_from_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = UtfToLocal(src, len, dest, + &sjis_from_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c index 4bcc886d674..1fffdc5930c 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_shift_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ shift_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &shift_jis_2004_to_unicode_tree, - LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = LocalToUtf(src, len, dest, + &shift_jis_2004_to_unicode_tree, + LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SHIFT_JIS_2004); - UtfToLocal(src, len, dest, - &shift_jis_2004_from_unicode_tree, - ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = UtfToLocal(src, len, dest, + &shift_jis_2004_from_unicode_tree, + ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c index c8e512994a1..d9471dad097 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_uhc); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ uhc_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UHC, PG_UTF8); - LocalToUtf(src, len, dest, - &uhc_to_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = LocalToUtf(src, len, dest, + &uhc_to_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_uhc(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_UHC); - UtfToLocal(src, len, dest, - &uhc_from_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = UtfToLocal(src, len, dest, + &uhc_from_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c index 0c9493dee56..110ba5677d0 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c @@ -48,8 +48,11 @@ PG_FUNCTION_INFO_V1(utf8_to_win); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -81,6 +84,7 @@ win_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -89,12 +93,15 @@ win_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -103,7 +110,7 @@ win_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -113,6 +120,7 @@ utf8_to_win(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -121,12 +129,15 @@ utf8_to_win(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -135,5 +146,5 @@ utf8_to_win(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/mbutils.c b/src/backend/utils/mb/mbutils.c index 2578573b0ab..65753860e35 100644 --- a/src/backend/utils/mb/mbutils.c +++ b/src/backend/utils/mb/mbutils.c @@ -406,12 +406,13 @@ pg_do_encoding_conversion(unsigned char *src, int len, MemoryContextAllocHuge(CurrentMemoryContext, (Size) len * MAX_CONVERSION_GROWTH + 1); - OidFunctionCall5(proc, - Int32GetDatum(src_encoding), - Int32GetDatum(dest_encoding), - CStringGetDatum(src), - CStringGetDatum(result), - Int32GetDatum(len)); + (void) OidFunctionCall6(proc, + Int32GetDatum(src_encoding), + Int32GetDatum(dest_encoding), + CStringGetDatum(src), + CStringGetDatum(result), + Int32GetDatum(len), + BoolGetDatum(false)); /* * If the result is large, it's worth repalloc'ing to release any extra @@ -849,12 +850,13 @@ pg_unicode_to_server(pg_wchar c, unsigned char *s) c_as_utf8[c_as_utf8_len] = '\0'; /* Convert, or throw error if we can't */ - FunctionCall5(Utf8ToServerConvProc, + FunctionCall6(Utf8ToServerConvProc, Int32GetDatum(PG_UTF8), Int32GetDatum(server_encoding), CStringGetDatum(c_as_utf8), CStringGetDatum(s), - Int32GetDatum(c_as_utf8_len)); + Int32GetDatum(c_as_utf8_len), + BoolGetDatum(false)); } diff --git a/src/bin/pg_upgrade/check.c b/src/bin/pg_upgrade/check.c index 43fc297eb69..ee6be95b08d 100644 --- a/src/bin/pg_upgrade/check.c +++ b/src/bin/pg_upgrade/check.c @@ -28,6 +28,7 @@ static void check_for_reg_data_type_usage(ClusterInfo *cluster); static void check_for_jsonb_9_4_usage(ClusterInfo *cluster); static void check_for_pg_role_prefix(ClusterInfo *cluster); static void check_for_new_tablespace_dir(ClusterInfo *new_cluster); +static void check_for_user_defined_encoding_conversions(ClusterInfo *cluster); static char *get_canonical_locale_name(int category, const char *locale); @@ -102,6 +103,15 @@ check_and_dump_old_cluster(bool live_check) check_for_reg_data_type_usage(&old_cluster); check_for_isn_and_int8_passing_mismatch(&old_cluster); + /* + * PG 14 changed the function signature of encoding conversion functions. + * Conversions from older versions cannot be upgraded automatically + * because the user-defined functions used by the encoding conversions + * need to changed to match the new signature. + */ + if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1300) + check_for_user_defined_encoding_conversions(&old_cluster); + /* * Pre-PG 14 allowed user defined postfix operators, which are not * supported anymore. Verify there are none, iff applicable. @@ -1268,6 +1278,91 @@ check_for_pg_role_prefix(ClusterInfo *cluster) check_ok(); } +/* + * Verify that no user-defined encoding conversions exist. + */ +static void +check_for_user_defined_encoding_conversions(ClusterInfo *cluster) +{ + int dbnum; + FILE *script = NULL; + bool found = false; + char output_path[MAXPGPATH]; + + prep_status("Checking for user-defined encoding conversions"); + + snprintf(output_path, sizeof(output_path), + "encoding_conversions.txt"); + + /* Find any user defined encoding conversions */ + for (dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++) + { + PGresult *res; + bool db_used = false; + int ntups; + int rowno; + int i_conoid, + i_conname, + i_nspname; + DbInfo *active_db = &cluster->dbarr.dbs[dbnum]; + PGconn *conn = connectToServer(cluster, active_db->db_name); + + /* + * The query below hardcodes FirstNormalObjectId as 16384 rather than + * interpolating that C #define into the query because, if that + * #define is ever changed, the cutoff we want to use is the value + * used by pre-version 14 servers, not that of some future version. + */ + res = executeQueryOrDie(conn, + "SELECT c.oid as conoid, c.conname, n.nspname " + "FROM pg_catalog.pg_conversion c, " + " pg_catalog.pg_namespace n " + "WHERE c.connamespace = n.oid AND " + " c.oid >= 16384"); + ntups = PQntuples(res); + i_conoid = PQfnumber(res, "conoid"); + i_conname = PQfnumber(res, "conname"); + i_nspname = PQfnumber(res, "nspname"); + for (rowno = 0; rowno < ntups; rowno++) + { + found = true; + if (script == NULL && + (script = fopen_priv(output_path, "w")) == NULL) + pg_fatal("could not open file \"%s\": %s\n", + output_path, strerror(errno)); + if (!db_used) + { + fprintf(script, "In database: %s\n", active_db->db_name); + db_used = true; + } + fprintf(script, " (oid=%s) %s.%s\n", + PQgetvalue(res, rowno, i_conoid), + PQgetvalue(res, rowno, i_nspname), + PQgetvalue(res, rowno, i_conname)); + } + + PQclear(res); + + PQfinish(conn); + } + + if (script) + fclose(script); + + if (found) + { + pg_log(PG_REPORT, "fatal\n"); + pg_fatal("Your installation contains user-defined encoding conversions.\n" + "The conversion function parameters changed in PostgreSQL version 14\n" + "so this cluster cannot currently be upgraded. You can remove the\n" + "encoding conversions in the old cluster and restart the upgrade.\n" + "A list of user-defined encoding conversions is in the file:\n" + " %s\n\n", output_path); + } + else + check_ok(); +} + /* * get_canonical_locale_name diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index f8174061ef3..75b829e8514 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10766,388 +10766,388 @@ # conversion functions { oid => '4302', descr => 'internal conversion function for KOI8R to MULE_INTERNAL', - proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_mic', + proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4303', descr => 'internal conversion function for MULE_INTERNAL to KOI8R', - proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_koi8r', + proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4304', descr => 'internal conversion function for ISO-8859-5 to MULE_INTERNAL', - proname => 'iso_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_mic', + proname => 'iso_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4305', descr => 'internal conversion function for MULE_INTERNAL to ISO-8859-5', - proname => 'mic_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_iso', + proname => 'mic_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4306', descr => 'internal conversion function for WIN1251 to MULE_INTERNAL', - proname => 'win1251_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_mic', + proname => 'win1251_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4307', descr => 'internal conversion function for MULE_INTERNAL to WIN1251', - proname => 'mic_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1251', + proname => 'mic_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4308', descr => 'internal conversion function for WIN866 to MULE_INTERNAL', - proname => 'win866_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_mic', + proname => 'win866_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4309', descr => 'internal conversion function for MULE_INTERNAL to WIN866', - proname => 'mic_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win866', + proname => 'mic_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4310', descr => 'internal conversion function for KOI8R to WIN1251', - proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4311', descr => 'internal conversion function for WIN1251 to KOI8R', - proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4312', descr => 'internal conversion function for KOI8R to WIN866', - proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_win866', + proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4313', descr => 'internal conversion function for WIN866 to KOI8R', - proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_koi8r', + proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4314', descr => 'internal conversion function for WIN866 to WIN1251', - proname => 'win866_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win866_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4315', descr => 'internal conversion function for WIN1251 to WIN866', - proname => 'win1251_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4316', descr => 'internal conversion function for ISO-8859-5 to KOI8R', - proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_koi8r', + proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4317', descr => 'internal conversion function for KOI8R to ISO-8859-5', - proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_iso', + proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4318', descr => 'internal conversion function for ISO-8859-5 to WIN1251', - proname => 'iso_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win1251', + proname => 'iso_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4319', descr => 'internal conversion function for WIN1251 to ISO-8859-5', - proname => 'win1251_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_iso', + proname => 'win1251_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4320', descr => 'internal conversion function for ISO-8859-5 to WIN866', - proname => 'iso_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win866', + proname => 'iso_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4321', descr => 'internal conversion function for WIN866 to ISO-8859-5', - proname => 'win866_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_iso', + proname => 'win866_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4322', descr => 'internal conversion function for EUC_CN to MULE_INTERNAL', - proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_mic', + proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_mic', probin => '$libdir/euc_cn_and_mic' }, { oid => '4323', descr => 'internal conversion function for MULE_INTERNAL to EUC_CN', - proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_cn', + proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_cn', probin => '$libdir/euc_cn_and_mic' }, { oid => '4324', descr => 'internal conversion function for EUC_JP to SJIS', - proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_sjis', + proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4325', descr => 'internal conversion function for SJIS to EUC_JP', - proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_euc_jp', + proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4326', descr => 'internal conversion function for EUC_JP to MULE_INTERNAL', - proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_mic', + proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4327', descr => 'internal conversion function for SJIS to MULE_INTERNAL', - proname => 'sjis_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_mic', + proname => 'sjis_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4328', descr => 'internal conversion function for MULE_INTERNAL to EUC_JP', - proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_jp', + proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4329', descr => 'internal conversion function for MULE_INTERNAL to SJIS', - proname => 'mic_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_sjis', + proname => 'mic_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4330', descr => 'internal conversion function for EUC_KR to MULE_INTERNAL', - proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_mic', + proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_mic', probin => '$libdir/euc_kr_and_mic' }, { oid => '4331', descr => 'internal conversion function for MULE_INTERNAL to EUC_KR', - proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_kr', + proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_kr', probin => '$libdir/euc_kr_and_mic' }, { oid => '4332', descr => 'internal conversion function for EUC_TW to BIG5', - proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_big5', + proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4333', descr => 'internal conversion function for BIG5 to EUC_TW', - proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_euc_tw', + proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4334', descr => 'internal conversion function for EUC_TW to MULE_INTERNAL', - proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_mic', + proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4335', descr => 'internal conversion function for BIG5 to MULE_INTERNAL', - proname => 'big5_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_mic', + proname => 'big5_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4336', descr => 'internal conversion function for MULE_INTERNAL to EUC_TW', - proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_tw', + proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4337', descr => 'internal conversion function for MULE_INTERNAL to BIG5', - proname => 'mic_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_big5', + proname => 'mic_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4338', descr => 'internal conversion function for LATIN2 to MULE_INTERNAL', - proname => 'latin2_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin2_to_mic', + proname => 'latin2_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4339', descr => 'internal conversion function for MULE_INTERNAL to LATIN2', - proname => 'mic_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin2', + proname => 'mic_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4340', descr => 'internal conversion function for WIN1250 to MULE_INTERNAL', - proname => 'win1250_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1250_to_mic', + proname => 'win1250_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4341', descr => 'internal conversion function for MULE_INTERNAL to WIN1250', - proname => 'mic_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1250', + proname => 'mic_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4342', descr => 'internal conversion function for LATIN2 to WIN1250', - proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4343', descr => 'internal conversion function for WIN1250 to LATIN2', - proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4344', descr => 'internal conversion function for LATIN1 to MULE_INTERNAL', - proname => 'latin1_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin1_to_mic', + proname => 'latin1_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin1_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4345', descr => 'internal conversion function for MULE_INTERNAL to LATIN1', - proname => 'mic_to_latin1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin1', + proname => 'mic_to_latin1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin1', probin => '$libdir/latin_and_mic' }, { oid => '4346', descr => 'internal conversion function for LATIN3 to MULE_INTERNAL', - proname => 'latin3_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin3_to_mic', + proname => 'latin3_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin3_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4347', descr => 'internal conversion function for MULE_INTERNAL to LATIN3', - proname => 'mic_to_latin3', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin3', + proname => 'mic_to_latin3', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin3', probin => '$libdir/latin_and_mic' }, { oid => '4348', descr => 'internal conversion function for LATIN4 to MULE_INTERNAL', - proname => 'latin4_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin4_to_mic', + proname => 'latin4_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin4_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4349', descr => 'internal conversion function for MULE_INTERNAL to LATIN4', - proname => 'mic_to_latin4', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin4', + proname => 'mic_to_latin4', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin4', probin => '$libdir/latin_and_mic' }, { oid => '4352', descr => 'internal conversion function for BIG5 to UTF8', - proname => 'big5_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_utf8', + proname => 'big5_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_utf8', probin => '$libdir/utf8_and_big5' }, { oid => '4353', descr => 'internal conversion function for UTF8 to BIG5', - proname => 'utf8_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_big5', + proname => 'utf8_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_big5', probin => '$libdir/utf8_and_big5' }, { oid => '4354', descr => 'internal conversion function for UTF8 to KOI8R', - proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8r', + proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8r', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4355', descr => 'internal conversion function for KOI8R to UTF8', - proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_utf8', + proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4356', descr => 'internal conversion function for UTF8 to KOI8U', - proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8u', + proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8u', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4357', descr => 'internal conversion function for KOI8U to UTF8', - proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8u_to_utf8', + proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8u_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4358', descr => 'internal conversion function for UTF8 to WIN', - proname => 'utf8_to_win', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_win', + proname => 'utf8_to_win', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_win', probin => '$libdir/utf8_and_win' }, { oid => '4359', descr => 'internal conversion function for WIN to UTF8', - proname => 'win_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win_to_utf8', + proname => 'win_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win_to_utf8', probin => '$libdir/utf8_and_win' }, { oid => '4360', descr => 'internal conversion function for EUC_CN to UTF8', - proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_utf8', + proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_utf8', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4361', descr => 'internal conversion function for UTF8 to EUC_CN', - proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_cn', + proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_cn', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4362', descr => 'internal conversion function for EUC_JP to UTF8', - proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_utf8', + proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_utf8', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4363', descr => 'internal conversion function for UTF8 to EUC_JP', - proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_jp', + proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jp', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4364', descr => 'internal conversion function for EUC_KR to UTF8', - proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_utf8', + proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_utf8', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4365', descr => 'internal conversion function for UTF8 to EUC_KR', - proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_kr', + proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_kr', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4366', descr => 'internal conversion function for EUC_TW to UTF8', - proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_utf8', + proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_utf8', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4367', descr => 'internal conversion function for UTF8 to EUC_TW', - proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_tw', + proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_tw', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4368', descr => 'internal conversion function for GB18030 to UTF8', - proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gb18030_to_utf8', + proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gb18030_to_utf8', probin => '$libdir/utf8_and_gb18030' }, { oid => '4369', descr => 'internal conversion function for UTF8 to GB18030', - proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gb18030', + proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gb18030', probin => '$libdir/utf8_and_gb18030' }, { oid => '4370', descr => 'internal conversion function for GBK to UTF8', - proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gbk_to_utf8', + proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gbk_to_utf8', probin => '$libdir/utf8_and_gbk' }, { oid => '4371', descr => 'internal conversion function for UTF8 to GBK', - proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gbk', + proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gbk', probin => '$libdir/utf8_and_gbk' }, { oid => '4372', descr => 'internal conversion function for UTF8 to ISO-8859 2-16', - proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_iso8859', + proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859', probin => '$libdir/utf8_and_iso8859' }, { oid => '4373', descr => 'internal conversion function for ISO-8859 2-16 to UTF8', - proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso8859_to_utf8', + proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_to_utf8', probin => '$libdir/utf8_and_iso8859' }, { oid => '4374', descr => 'internal conversion function for LATIN1 to UTF8', - proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_1_to_utf8', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4375', descr => 'internal conversion function for UTF8 to LATIN1', - proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859_1', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4376', descr => 'internal conversion function for JOHAB to UTF8', - proname => 'johab_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'johab_to_utf8', + proname => 'johab_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'johab_to_utf8', probin => '$libdir/utf8_and_johab' }, { oid => '4377', descr => 'internal conversion function for UTF8 to JOHAB', - proname => 'utf8_to_johab', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_johab', + proname => 'utf8_to_johab', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_johab', probin => '$libdir/utf8_and_johab' }, { oid => '4378', descr => 'internal conversion function for SJIS to UTF8', - proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_utf8', + proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_utf8', probin => '$libdir/utf8_and_sjis' }, { oid => '4379', descr => 'internal conversion function for UTF8 to SJIS', - proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_sjis', + proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_sjis', probin => '$libdir/utf8_and_sjis' }, { oid => '4380', descr => 'internal conversion function for UHC to UTF8', - proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'uhc_to_utf8', + proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'uhc_to_utf8', probin => '$libdir/utf8_and_uhc' }, { oid => '4381', descr => 'internal conversion function for UTF8 to UHC', - proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_uhc', + proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_uhc', probin => '$libdir/utf8_and_uhc' }, { oid => '4382', descr => 'internal conversion function for EUC_JIS_2004 to UTF8', - proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_utf8', probin => '$libdir/utf8_and_euc2004' }, { oid => '4383', descr => 'internal conversion function for UTF8 to EUC_JIS_2004', - proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jis_2004', probin => '$libdir/utf8_and_euc2004' }, { oid => '4384', descr => 'internal conversion function for SHIFT_JIS_2004 to UTF8', - proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_utf8', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4385', descr => 'internal conversion function for UTF8 to SHIFT_JIS_2004', - proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_shift_jis_2004', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4386', descr => 'internal conversion function for EUC_JIS_2004 to SHIFT_JIS_2004', proname => 'euc_jis_2004_to_shift_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_shift_jis_2004', probin => '$libdir/euc2004_sjis2004' }, { oid => '4387', descr => 'internal conversion function for SHIFT_JIS_2004 to EUC_JIS_2004', proname => 'shift_jis_2004_to_euc_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_euc_jis_2004', probin => '$libdir/euc2004_sjis2004' }, diff --git a/src/include/mb/pg_wchar.h b/src/include/mb/pg_wchar.h index 64b22e4b0d4..346a41a1f3d 100644 --- a/src/include/mb/pg_wchar.h +++ b/src/include/mb/pg_wchar.h @@ -627,18 +627,18 @@ extern void pg_unicode_to_server(pg_wchar c, unsigned char *s); extern unsigned short BIG5toCNS(unsigned short big5, unsigned char *lc); extern unsigned short CNStoBIG5(unsigned short cns, unsigned char lc); -extern void UtfToLocal(const unsigned char *utf, int len, - unsigned char *iso, - const pg_mb_radix_tree *map, - const pg_utf_to_local_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); -extern void LocalToUtf(const unsigned char *iso, int len, - unsigned char *utf, - const pg_mb_radix_tree *map, - const pg_local_to_utf_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); +extern int UtfToLocal(const unsigned char *utf, int len, + unsigned char *iso, + const pg_mb_radix_tree *map, + const pg_utf_to_local_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); +extern int LocalToUtf(const unsigned char *iso, int len, + unsigned char *utf, + const pg_mb_radix_tree *map, + const pg_local_to_utf_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); extern bool pg_verifymbstr(const char *mbstr, int len, bool noError); extern bool pg_verify_mbstr(int encoding, const char *mbstr, int len, @@ -656,18 +656,19 @@ extern void report_invalid_encoding(int encoding, const char *mbstr, int len) pg extern void report_untranslatable_char(int src_encoding, int dest_encoding, const char *mbstr, int len) pg_attribute_noreturn(); -extern void local2local(const unsigned char *l, unsigned char *p, int len, - int src_encoding, int dest_encoding, const unsigned char *tab); -extern void latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding); -extern void mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding); -extern void latin2mic_with_table(const unsigned char *l, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); -extern void mic2latin_with_table(const unsigned char *mic, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); +extern int local2local(const unsigned char *l, unsigned char *p, int len, + int src_encoding, int dest_encoding, const unsigned char *tab, + bool noError); +extern int latin2mic(const unsigned char *l, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int mic2latin(const unsigned char *mic, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int latin2mic_with_table(const unsigned char *l, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); +extern int mic2latin_with_table(const unsigned char *mic, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); #ifdef WIN32 extern WCHAR *pgwin32_message_to_UTF16(const char *str, int len, int *utf16len); diff --git a/src/test/regress/expected/opr_sanity.out b/src/test/regress/expected/opr_sanity.out index 254ca06d3dd..23ba60e395f 100644 --- a/src/test/regress/expected/opr_sanity.out +++ b/src/test/regress/expected/opr_sanity.out @@ -1052,13 +1052,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); oid | proname | oid | conname -----+---------+-----+--------- (0 rows) diff --git a/src/test/regress/sql/opr_sanity.sql b/src/test/regress/sql/opr_sanity.sql index bbd3834b634..04691745981 100644 --- a/src/test/regress/sql/opr_sanity.sql +++ b/src/test/regress/sql/opr_sanity.sql @@ -556,13 +556,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); -- Check for conprocs that don't perform the specific conversion that -- pg_conversion alleges they do, by trying to invoke each conversion -- 2.29.2 --------------39E46EF15EBFAA37D53332E5 Content-Type: text/x-patch; charset=UTF-8; name="v3-0003-Add-tests-for-the-new-noError-variants-of-built-i.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="v3-0003-Add-tests-for-the-new-noError-variants-of-built-i.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 34+ messages in thread
* [PATCH v3 2/5] Change conversion function signature. @ 2021-01-28 16:42 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 34+ messages in thread From: Heikki Linnakangas @ 2021-01-28 16:42 UTC (permalink / raw) Add a 'noError' argument, so that we can try to convert a buffer without knowing the character boundaries beforehand. The functions now need to return the number of input bytes successfully converted. This is is a backwards-incompatible change, if you have created a custom encoding conversion with CREATE CONVERSION. This adds a check to pg_upgrade for that, refusing the upgrade if there are any user-defined encoding conversions. --- doc/src/sgml/ref/create_conversion.sgml | 5 +- src/backend/commands/conversioncmds.c | 27 +- src/backend/utils/error/elog.c | 2 + src/backend/utils/mb/conv.c | 112 +++++- .../cyrillic_and_mic/cyrillic_and_mic.c | 127 ++++--- .../euc2004_sjis2004/euc2004_sjis2004.c | 96 ++++- .../euc_cn_and_mic/euc_cn_and_mic.c | 57 ++- .../euc_jp_and_sjis/euc_jp_and_sjis.c | 153 ++++++-- .../euc_kr_and_mic/euc_kr_and_mic.c | 57 ++- .../euc_tw_and_big5/euc_tw_and_big5.c | 165 +++++++-- .../latin2_and_win1250/latin2_and_win1250.c | 49 ++- .../latin_and_mic/latin_and_mic.c | 43 ++- .../utf8_and_big5/utf8_and_big5.c | 37 +- .../utf8_and_cyrillic/utf8_and_cyrillic.c | 67 ++-- .../utf8_and_euc2004/utf8_and_euc2004.c | 37 +- .../utf8_and_euc_cn/utf8_and_euc_cn.c | 37 +- .../utf8_and_euc_jp/utf8_and_euc_jp.c | 37 +- .../utf8_and_euc_kr/utf8_and_euc_kr.c | 37 +- .../utf8_and_euc_tw/utf8_and_euc_tw.c | 37 +- .../utf8_and_gb18030/utf8_and_gb18030.c | 37 +- .../utf8_and_gbk/utf8_and_gbk.c | 37 +- .../utf8_and_iso8859/utf8_and_iso8859.c | 43 ++- .../utf8_and_iso8859_1/utf8_and_iso8859_1.c | 27 +- .../utf8_and_johab/utf8_and_johab.c | 37 +- .../utf8_and_sjis/utf8_and_sjis.c | 37 +- .../utf8_and_sjis2004/utf8_and_sjis2004.c | 37 +- .../utf8_and_uhc/utf8_and_uhc.c | 37 +- .../utf8_and_win/utf8_and_win.c | 43 ++- src/backend/utils/mb/mbutils.c | 18 +- src/bin/pg_upgrade/check.c | 95 +++++ src/include/catalog/pg_proc.dat | 332 +++++++++--------- src/include/mb/pg_wchar.h | 49 +-- src/test/regress/expected/opr_sanity.out | 7 +- src/test/regress/sql/opr_sanity.sql | 7 +- 34 files changed, 1390 insertions(+), 635 deletions(-) diff --git a/doc/src/sgml/ref/create_conversion.sgml b/doc/src/sgml/ref/create_conversion.sgml index e7700fecfc5..f014a676c88 100644 --- a/doc/src/sgml/ref/create_conversion.sgml +++ b/doc/src/sgml/ref/create_conversion.sgml @@ -117,8 +117,9 @@ conv_proc( integer, -- destination encoding ID cstring, -- source string (null terminated C string) internal, -- destination (fill with a null terminated C string) - integer -- source string length -) RETURNS void; + integer, -- source string length + boolean -- if true, don't throw an error if conversion fails +) RETURNS integer; </programlisting></para> </listitem> </varlistentry> diff --git a/src/backend/commands/conversioncmds.c b/src/backend/commands/conversioncmds.c index f7ff321de71..d2041466911 100644 --- a/src/backend/commands/conversioncmds.c +++ b/src/backend/commands/conversioncmds.c @@ -45,8 +45,9 @@ CreateConversionCommand(CreateConversionStmt *stmt) const char *from_encoding_name = stmt->for_encoding_name; const char *to_encoding_name = stmt->to_encoding_name; List *func_name = stmt->func_name; - static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID}; + static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID, BOOLOID}; char result[1]; + Datum funcresult; /* Convert list of names to a name and namespace */ namespaceId = QualifiedNameGetCreationNamespace(stmt->conversion_name, @@ -92,8 +93,8 @@ CreateConversionCommand(CreateConversionStmt *stmt) funcoid = LookupFuncName(func_name, sizeof(funcargs) / sizeof(Oid), funcargs, false); - /* Check it returns VOID, else it's probably the wrong function */ - if (get_func_rettype(funcoid) != VOIDOID) + /* Check it returns int4, else it's probably the wrong function */ + if (get_func_rettype(funcoid) != INT4OID) ereport(ERROR, (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), errmsg("encoding conversion function %s must return type %s", @@ -111,12 +112,20 @@ CreateConversionCommand(CreateConversionStmt *stmt) * string; the conversion function should throw an error if it can't * perform the requested conversion. */ - OidFunctionCall5(funcoid, - Int32GetDatum(from_encoding), - Int32GetDatum(to_encoding), - CStringGetDatum(""), - CStringGetDatum(result), - Int32GetDatum(0)); + funcresult = OidFunctionCall6(funcoid, + Int32GetDatum(from_encoding), + Int32GetDatum(to_encoding), + CStringGetDatum(""), + CStringGetDatum(result), + Int32GetDatum(0), + BoolGetDatum(false)); + + /* The function should return 0 for empty input. Might as well check that, too. */ + if (DatumGetInt32(funcresult) != 0) + ereport(ERROR, + (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), + errmsg("encoding conversion function %s returned incorrect result for empty input", + NameListToString(func_name)))); /* * All seem ok, go ahead (possible failure would be a duplicate conversion diff --git a/src/backend/utils/error/elog.c b/src/backend/utils/error/elog.c index 80c26724612..762f77d533c 100644 --- a/src/backend/utils/error/elog.c +++ b/src/backend/utils/error/elog.c @@ -2280,6 +2280,8 @@ write_console(const char *line, int len) * Conversion on non-win32 platforms is not implemented yet. It requires * non-throw version of pg_do_encoding_conversion(), that converts * unconvertable characters to '?' without errors. + * + * XXX: We have a no-throw version now. It doesn't convert to '?' though. */ #endif diff --git a/src/backend/utils/mb/conv.c b/src/backend/utils/mb/conv.c index a07b54bd3b8..b83358bc7a5 100644 --- a/src/backend/utils/mb/conv.c +++ b/src/backend/utils/mb/conv.c @@ -26,14 +26,16 @@ * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the target charset, or 0 if there is no equivalent code. */ -void +int local2local(const unsigned char *l, unsigned char *p, int len, int src_encoding, int dest_encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -41,7 +43,11 @@ local2local(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(src_encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -50,13 +56,19 @@ local2local(const unsigned char *l, if (c2) *p++ = c2; else + { + if (noError) + break; report_untranslatable_char(src_encoding, dest_encoding, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -67,17 +79,22 @@ local2local(const unsigned char *l, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = l; int c1; while (len > 0) { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (IS_HIGHBIT_SET(c1)) *p++ = lc; *p++ = c1; @@ -85,6 +102,8 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, len--; } *p = '\0'; + + return l - start; } /* @@ -95,17 +114,22 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -118,17 +142,27 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1])) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); + } *p++ = mic[1]; mic += 2; len -= 2; } } *p = '\0'; + + return mic - start; } @@ -144,14 +178,16 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the mule encoding, or 0 if there is no equivalent code. */ -void +int latin2mic_with_table(const unsigned char *l, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -159,7 +195,11 @@ latin2mic_with_table(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -171,13 +211,19 @@ latin2mic_with_table(const unsigned char *l, *p++ = c2; } else + { + if (noError) + break; report_untranslatable_char(encoding, PG_MULE_INTERNAL, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -192,14 +238,16 @@ latin2mic_with_table(const unsigned char *l, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the local charset, or 0 if there is no equivalent code. */ -void +int mic2latin_with_table(const unsigned char *mic, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = mic; unsigned char c1, c2; @@ -207,7 +255,11 @@ mic2latin_with_table(const unsigned char *mic, { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -220,11 +272,17 @@ mic2latin_with_table(const unsigned char *mic, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1]) || (c2 = tab[mic[1] - HIGHBIT]) == 0) { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); break; /* keep compiler quiet */ @@ -235,6 +293,8 @@ mic2latin_with_table(const unsigned char *mic, } } *p = '\0'; + + return mic - start; } /* @@ -425,17 +485,19 @@ pg_mb_radix_conv(const pg_mb_radix_tree *rt, * * See pg_wchar.h for more details about the data structures used here. */ -void +int UtfToLocal(const unsigned char *utf, int len, unsigned char *iso, const pg_mb_radix_tree *map, const pg_utf_to_local_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, bool noError) { uint32 iutf; int l; const pg_utf_to_local_combined *cp; + const unsigned char *start = utf; + const unsigned char *cur = utf; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -449,6 +511,8 @@ UtfToLocal(const unsigned char *utf, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*utf == '\0') break; @@ -584,15 +648,19 @@ UtfToLocal(const unsigned char *utf, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(PG_UTF8, encoding, (const char *) (utf - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(PG_UTF8, (const char *) utf, len); *iso = '\0'; + + return cur - start; } /* @@ -616,18 +684,24 @@ UtfToLocal(const unsigned char *utf, int len, * (if provided) is applied. An error is raised if no match is found. * * See pg_wchar.h for more details about the data structures used here. + * + * Returns the number of input bytes consumed. If noError is true, this can + * be less than 'len'. */ -void +int LocalToUtf(const unsigned char *iso, int len, unsigned char *utf, const pg_mb_radix_tree *map, const pg_local_to_utf_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, + bool noError) { uint32 iiso; int l; const pg_local_to_utf_combined *cp; + const unsigned char *start = iso; + const unsigned char *cur = iso; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -641,6 +715,8 @@ LocalToUtf(const unsigned char *iso, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*iso == '\0') break; @@ -723,13 +799,17 @@ LocalToUtf(const unsigned char *iso, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(encoding, PG_UTF8, (const char *) (iso - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(encoding, (const char *) iso, len); *utf = '\0'; + + return cur - start; } diff --git a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c index 4c5b02654de..368c2deb5e4 100644 --- a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c @@ -44,8 +44,11 @@ PG_FUNCTION_INFO_V1(win866_to_iso); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -306,12 +309,14 @@ koi8r_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -320,12 +325,14 @@ mic_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_KOI8R); - mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -334,12 +341,14 @@ iso_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -348,12 +357,14 @@ mic_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_ISO_8859_5); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -362,12 +373,14 @@ win1251_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -376,12 +389,14 @@ mic_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1251); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -390,12 +405,14 @@ win866_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -404,12 +421,14 @@ mic_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN866); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -418,12 +437,14 @@ koi8r_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN1251); - local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -432,12 +453,14 @@ win1251_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_KOI8R); - local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi); + converted = local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -446,12 +469,14 @@ koi8r_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN866); - local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -460,12 +485,14 @@ win866_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_KOI8R); - local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi); + converted = local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -474,12 +501,14 @@ win866_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_WIN1251); - local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251); + converted = local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -488,12 +517,14 @@ win1251_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_WIN866); - local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866); + converted = local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -502,12 +533,14 @@ iso_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_KOI8R); - local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -516,12 +549,14 @@ koi8r_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_ISO_8859_5); - local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso); + converted = local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -530,12 +565,14 @@ iso_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN1251); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -544,12 +581,14 @@ win1251_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso); + converted = local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -558,12 +597,14 @@ iso_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN866); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -572,10 +613,12 @@ win866_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso); + converted = local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c index 4d7fb116cfd..88529c644cf 100644 --- a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c @@ -19,8 +19,8 @@ PG_MODULE_MAGIC; PG_FUNCTION_INFO_V1(euc_jis_2004_to_shift_jis_2004); PG_FUNCTION_INFO_V1(shift_jis_2004_to_euc_jis_2004); -static void euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len); -static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len); +static int euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError); /* ---------- * conv_proc( @@ -28,8 +28,11 @@ static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -39,12 +42,14 @@ euc_jis_2004_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_SHIFT_JIS_2004); - euc_jis_20042shift_jis_2004(src, dest, len); + converted = euc_jis_20042shift_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -53,20 +58,23 @@ shift_jis_2004_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_EUC_JIS_2004); - shift_jis_20042euc_jis_2004(src, dest, len); + converted = shift_jis_20042euc_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_JIS_2004 -> SHIFT_JIS_2004 */ -static void -euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, ku, ten; @@ -79,8 +87,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -90,8 +102,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) l = pg_encoding_verifymbchar(PG_EUC_JIS_2004, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (c1 == SS2 && l == 2) /* JIS X 0201 kana? */ { @@ -121,8 +137,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) *p++ = (ku + 0x19b) >> 1; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } if (ku % 2) @@ -132,8 +152,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; @@ -149,8 +173,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ku >= 63 && ku <= 94) *p++ = (ku + 0x181) >> 1; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (ku % 2) { @@ -159,20 +187,30 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else - report_invalid_encoding(PG_EUC_JIS_2004, + { + if (noError) + break; + report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } euc += l; len -= l; } *p = '\0'; + + return euc - start; } /* @@ -212,9 +250,10 @@ get_ten(int b, int *ku) * SHIFT_JIS_2004 ---> EUC_JIS_2004 */ -static void -shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len) +static int +shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1; int ku, ten, @@ -230,8 +269,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -241,8 +284,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len l = pg_encoding_verifymbchar(PG_SHIFT_JIS_2004, (const char *) sjis, len); if (l < 0 || l > len) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf && l == 1) { @@ -266,8 +313,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x100; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xe0 && c1 <= 0xef) /* plane 1 62ku-94ku */ @@ -275,9 +326,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x180; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, - (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xf0 && c1 <= 0xf3) /* plane 2 @@ -286,8 +340,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } switch (c1) { case 0xf0: @@ -309,16 +367,24 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 == 0xf4 && kubun == 1) ku = 15; else ku = (c1 << 1) - 0x19a - kubun; } else + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (plane == 2) *p++ = SS3; @@ -330,4 +396,6 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c index e9bb896935f..a8da733803d 100644 --- a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_cn2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_cn(const unsigned char *mic, unsigned char *p, int len); +static int euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_cn_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_cn_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_MULE_INTERNAL); - euc_cn2mic(src, dest, len); + converted = euc_cn2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_CN); - mic2euc_cn(src, dest, len); + converted = mic2euc_cn(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_CN ---> MIC */ -static void -euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; while (len > 0) @@ -76,7 +84,11 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (len < 2 || !IS_HIGHBIT_SET(euc[1])) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = LC_GB2312_80; *p++ = c1; *p++ = euc[1]; @@ -86,21 +98,28 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_CN */ -static void -mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) @@ -109,11 +128,19 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (c1 != LC_GB2312_80) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_CN, (const char *) mic, len); + } if (len < 3 || !IS_HIGHBIT_SET(mic[1]) || !IS_HIGHBIT_SET(mic[2])) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } mic++; *p++ = *mic++; *p++ = *mic++; @@ -122,12 +149,18 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; } } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c index 5059f917a98..cc4817dc4cd 100644 --- a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c @@ -42,17 +42,20 @@ PG_FUNCTION_INFO_V1(mic_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void sjis2mic(const unsigned char *sjis, unsigned char *p, int len); -static void mic2sjis(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_jp(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len); -static void sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len); +static int sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError); +static int mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_jp_to_sjis(PG_FUNCTION_ARGS) @@ -60,12 +63,14 @@ euc_jp_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_SJIS); - euc_jp2sjis(src, dest, len); + converted = euc_jp2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -74,12 +79,14 @@ sjis_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_EUC_JP); - sjis2euc_jp(src, dest, len); + converted = sjis2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -88,12 +95,14 @@ euc_jp_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_MULE_INTERNAL); - euc_jp2mic(src, dest, len); + converted = euc_jp2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -102,12 +111,14 @@ mic_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_JP); - mic2euc_jp(src, dest, len); + converted = mic2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -116,12 +127,14 @@ sjis_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_MULE_INTERNAL); - sjis2mic(src, dest, len); + converted = sjis2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -130,20 +143,23 @@ mic_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_SJIS); - mic2sjis(src, dest, len); + converted = mic2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * SJIS ---> MIC */ -static void -sjis2mic(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -167,7 +183,11 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) * JIS X0208, X0212, user defined extended characters */ if (len < 2 || !ISSJISHEAD(c1) || !ISSJISTAIL(sjis[1])) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } c2 = sjis[1]; k = (c1 << 8) + c2; if (k >= 0xed40 && k < 0xf040) @@ -257,21 +277,28 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; } } *p = '\0'; + + return sjis - start; } /* * MIC ---> SJIS */ -static void -mic2sjis(const unsigned char *mic, unsigned char *p, int len) +static int +mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1, c2, k, @@ -284,8 +311,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -293,8 +324,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) *p++ = mic[1]; else if (c1 == LC_JISX0208) @@ -350,20 +385,27 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_SJIS, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP ---> MIC */ -static void -euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -374,8 +416,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -383,8 +429,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* 1 byte kana? */ *p++ = LC_JISX0201K; @@ -406,14 +456,17 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_JP */ -static void -mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -424,8 +477,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -433,8 +490,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) { *p++ = SS2; @@ -452,20 +513,27 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_JP, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP -> SJIS */ -static void -euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, c2, k; @@ -478,8 +546,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -487,8 +559,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* hankaku kana? */ @@ -551,14 +627,17 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * SJIS ---> EUC_JP */ -static void -sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -573,8 +652,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -582,8 +665,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_SJIS, (const char *) sjis, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf) { /* JIS X0201 (1 byte kana) */ @@ -680,4 +767,6 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c index ac823d6c270..a5b51617e52 100644 --- a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_kr2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_kr(const unsigned char *mic, unsigned char *p, int len); +static int euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_kr_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_kr_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_MULE_INTERNAL); - euc_kr2mic(src, dest, len); + converted = euc_kr2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_KR); - mic2euc_kr(src, dest, len); + converted = mic2euc_kr(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_KR ---> MIC */ -static void -euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -78,8 +86,12 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_KR, (const char *) euc, len); if (l != 2) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = LC_KS5601; *p++ = c1; *p++ = euc[1]; @@ -89,22 +101,29 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_KR */ -static void -mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -115,8 +134,12 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -124,18 +147,28 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_KS5601) { *p++ = mic[1]; *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_KR, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c index 66c242d7f36..ebb4e0acd53 100644 --- a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c @@ -32,17 +32,20 @@ PG_FUNCTION_INFO_V1(mic_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_tw2big5(const unsigned char *euc, unsigned char *p, int len); -static void big52euc_tw(const unsigned char *euc, unsigned char *p, int len); -static void big52mic(const unsigned char *big5, unsigned char *p, int len); -static void mic2big5(const unsigned char *mic, unsigned char *p, int len); -static void euc_tw2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_tw(const unsigned char *mic, unsigned char *p, int len); +static int euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52euc_tw(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError); +static int mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_tw_to_big5(PG_FUNCTION_ARGS) @@ -50,12 +53,14 @@ euc_tw_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_BIG5); - euc_tw2big5(src, dest, len); + converted = euc_tw2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -64,12 +69,14 @@ big5_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_EUC_TW); - big52euc_tw(src, dest, len); + converted = big52euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -78,12 +85,14 @@ euc_tw_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_MULE_INTERNAL); - euc_tw2mic(src, dest, len); + converted = euc_tw2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -92,12 +101,14 @@ mic_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_TW); - mic2euc_tw(src, dest, len); + converted = mic2euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -106,12 +117,14 @@ big5_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_MULE_INTERNAL); - big52mic(src, dest, len); + converted = big52mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -120,21 +133,24 @@ mic_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_BIG5); - mic2big5(src, dest, len); + converted = mic2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_TW ---> Big5 */ -static void -euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; unsigned char c1; unsigned short big5buf, cnsBuf; @@ -149,8 +165,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Verify and decode the next EUC_TW input character */ l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -171,8 +191,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Write it out in Big5 */ big5buf = CNStoBIG5(cnsBuf, lc); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_EUC_TW, PG_BIG5, (const char *) euc, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; @@ -182,22 +206,29 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * Big5 ---> EUC_TW */ -static void -big52euc_tw(const unsigned char *big5, unsigned char *p, int len) +static int +big52euc_tw(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -212,8 +243,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); @@ -237,8 +272,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_EUC_TW, (const char *) big5, len); + } big5 += l; len -= l; @@ -256,14 +295,17 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) } } *p = '\0'; + + return big5 - start; } /* * EUC_TW ---> MIC */ -static void -euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -274,8 +316,12 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -304,22 +350,29 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_TW */ -static void -mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -330,8 +383,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -339,8 +396,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1) { *p++ = mic[1]; @@ -362,20 +423,27 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[3]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_TW, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * Big5 ---> MIC */ -static void -big52mic(const unsigned char *big5, unsigned char *p, int len) +static int +big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -389,8 +457,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } *p++ = c1; big5++; len--; @@ -398,8 +470,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); if (lc != 0) @@ -412,20 +488,27 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_MULE_INTERNAL, (const char *) big5, len); + } big5 += l; len -= l; } *p = '\0'; + + return big5 - start; } /* * MIC ---> Big5 */ -static void -mic2big5(const unsigned char *mic, unsigned char *p, int len) +static int +mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -438,8 +521,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -447,8 +534,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1 || c1 == LC_CNS11643_2 || c1 == LCPRV2_B) { if (c1 == LCPRV2_B) @@ -462,16 +553,26 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } big5buf = CNStoBIG5(cnsBuf, c1); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c index 2e28e6780a5..8610fcb69aa 100644 --- a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c +++ b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(win1250_to_latin2); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -82,12 +85,14 @@ latin2_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -96,12 +101,14 @@ mic_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN2); - mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -110,13 +117,15 @@ win1250_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - win1250_2_iso88592); + converted = latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -125,13 +134,15 @@ mic_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1250); - mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - iso88592_2_win1250); + converted = mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -140,12 +151,15 @@ latin2_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_WIN1250); - local2local(src, dest, len, PG_LATIN2, PG_WIN1250, iso88592_2_win1250); + converted = local2local(src, dest, len, PG_LATIN2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -154,10 +168,13 @@ win1250_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_LATIN2); - local2local(src, dest, len, PG_WIN1250, PG_LATIN2, win1250_2_iso88592); + converted = local2local(src, dest, len, PG_WIN1250, PG_LATIN2, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c index bc651410f21..bff27d1c295 100644 --- a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(mic_to_latin4); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -42,12 +45,14 @@ latin1_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,12 +61,14 @@ mic_to_latin1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN1); - mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -70,12 +77,14 @@ latin3_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN3, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -84,12 +93,14 @@ mic_to_latin3(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN3); - mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,12 +109,14 @@ latin4_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN4, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -112,10 +125,12 @@ mic_to_latin4(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN4); - mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c index d6067cdc24e..3838b15cab9 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ big5_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_UTF8); - LocalToUtf(src, len, dest, - &big5_to_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = LocalToUtf(src, len, dest, + &big5_to_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_BIG5); - UtfToLocal(src, len, dest, - &big5_from_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = UtfToLocal(src, len, dest, + &big5_from_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c index ed90e8e682e..75719fe5f1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c @@ -33,8 +33,11 @@ PG_FUNCTION_INFO_V1(koi8u_to_utf8); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -44,16 +47,19 @@ utf8_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8R); - UtfToLocal(src, len, dest, - &koi8r_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = UtfToLocal(src, len, dest, + &koi8r_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -62,16 +68,19 @@ koi8r_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8r_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = LocalToUtf(src, len, dest, + &koi8r_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -80,16 +89,19 @@ utf8_to_koi8u(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8U); - UtfToLocal(src, len, dest, - &koi8u_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = UtfToLocal(src, len, dest, + &koi8u_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,14 +110,17 @@ koi8u_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8U, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8u_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = LocalToUtf(src, len, dest, + &koi8u_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c index d699affce47..5391001951a 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jis_2004_to_unicode_tree, - LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = LocalToUtf(src, len, dest, + &euc_jis_2004_to_unicode_tree, + LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JIS_2004); - UtfToLocal(src, len, dest, - &euc_jis_2004_from_unicode_tree, - ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = UtfToLocal(src, len, dest, + &euc_jis_2004_from_unicode_tree, + ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c index d7c0ba6a58b..c87d1bf2398 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_cn_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_cn_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = LocalToUtf(src, len, dest, + &euc_cn_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_CN); - UtfToLocal(src, len, dest, - &euc_cn_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = UtfToLocal(src, len, dest, + &euc_cn_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c index 13a3a23e77b..6a55134db21 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jp); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jp_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jp_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = LocalToUtf(src, len, dest, + &euc_jp_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JP); - UtfToLocal(src, len, dest, - &euc_jp_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = UtfToLocal(src, len, dest, + &euc_jp_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c index 1bbb8aaef7b..fe1924e2fec 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_kr_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_kr_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = LocalToUtf(src, len, dest, + &euc_kr_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_KR); - UtfToLocal(src, len, dest, - &euc_kr_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = UtfToLocal(src, len, dest, + &euc_kr_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c index 9830045dccd..68215659b57 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_tw); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_tw_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_tw_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = LocalToUtf(src, len, dest, + &euc_tw_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_TW); - UtfToLocal(src, len, dest, - &euc_tw_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = UtfToLocal(src, len, dest, + &euc_tw_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c index f86ecf27424..e1a59c39a4d 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c @@ -183,8 +183,11 @@ conv_utf8_to_18030(uint32 code) * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -193,16 +196,19 @@ gb18030_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GB18030, PG_UTF8); - LocalToUtf(src, len, dest, - &gb18030_to_unicode_tree, - NULL, 0, - conv_18030_to_utf8, - PG_GB18030); + converted = LocalToUtf(src, len, dest, + &gb18030_to_unicode_tree, + NULL, 0, + conv_18030_to_utf8, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -211,14 +217,17 @@ utf8_to_gb18030(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GB18030); - UtfToLocal(src, len, dest, - &gb18030_from_unicode_tree, - NULL, 0, - conv_utf8_to_18030, - PG_GB18030); + converted = UtfToLocal(src, len, dest, + &gb18030_from_unicode_tree, + NULL, 0, + conv_utf8_to_18030, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c index 2ab8b16c8a8..881386d5347 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_gbk); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ gbk_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GBK, PG_UTF8); - LocalToUtf(src, len, dest, - &gbk_to_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = LocalToUtf(src, len, dest, + &gbk_to_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_gbk(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GBK); - UtfToLocal(src, len, dest, - &gbk_from_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = UtfToLocal(src, len, dest, + &gbk_from_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c index 3e49f67ea2f..d93a521badf 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c @@ -52,8 +52,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -100,6 +103,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -108,12 +112,15 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -122,7 +129,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -132,6 +139,7 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -140,12 +148,15 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -154,5 +165,5 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c index 67e713cca11..8ac93604a1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c @@ -26,8 +26,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859_1); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -37,6 +40,8 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_UTF8); @@ -45,7 +50,11 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_LATIN1, (const char *) src, len); + } if (!IS_HIGHBIT_SET(c)) *dest++ = c; else @@ -58,7 +67,7 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } Datum @@ -67,6 +76,8 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c, c1; @@ -76,7 +87,11 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_UTF8, (const char *) src, len); + } /* fast path for ASCII-subset characters */ if (!IS_HIGHBIT_SET(c)) { @@ -102,11 +117,15 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) len -= 2; } else + { + if (noError) + break; report_untranslatable_char(PG_UTF8, PG_LATIN1, (const char *) src, len); + } } } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c index 578f5df4e7f..317daa2d5ee 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_johab); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ johab_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_JOHAB, PG_UTF8); - LocalToUtf(src, len, dest, - &johab_to_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = LocalToUtf(src, len, dest, + &johab_to_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_johab(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_JOHAB); - UtfToLocal(src, len, dest, - &johab_from_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = UtfToLocal(src, len, dest, + &johab_from_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c index dd9fc2975ad..4c9348aba59 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ sjis_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_UTF8); - LocalToUtf(src, len, dest, - &sjis_to_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = LocalToUtf(src, len, dest, + &sjis_to_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SJIS); - UtfToLocal(src, len, dest, - &sjis_from_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = UtfToLocal(src, len, dest, + &sjis_from_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c index 4bcc886d674..1fffdc5930c 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_shift_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ shift_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &shift_jis_2004_to_unicode_tree, - LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = LocalToUtf(src, len, dest, + &shift_jis_2004_to_unicode_tree, + LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SHIFT_JIS_2004); - UtfToLocal(src, len, dest, - &shift_jis_2004_from_unicode_tree, - ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = UtfToLocal(src, len, dest, + &shift_jis_2004_from_unicode_tree, + ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c index c8e512994a1..d9471dad097 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_uhc); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ uhc_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UHC, PG_UTF8); - LocalToUtf(src, len, dest, - &uhc_to_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = LocalToUtf(src, len, dest, + &uhc_to_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_uhc(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_UHC); - UtfToLocal(src, len, dest, - &uhc_from_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = UtfToLocal(src, len, dest, + &uhc_from_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c index 0c9493dee56..110ba5677d0 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c @@ -48,8 +48,11 @@ PG_FUNCTION_INFO_V1(utf8_to_win); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -81,6 +84,7 @@ win_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -89,12 +93,15 @@ win_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -103,7 +110,7 @@ win_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -113,6 +120,7 @@ utf8_to_win(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -121,12 +129,15 @@ utf8_to_win(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -135,5 +146,5 @@ utf8_to_win(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/mbutils.c b/src/backend/utils/mb/mbutils.c index 2578573b0ab..65753860e35 100644 --- a/src/backend/utils/mb/mbutils.c +++ b/src/backend/utils/mb/mbutils.c @@ -406,12 +406,13 @@ pg_do_encoding_conversion(unsigned char *src, int len, MemoryContextAllocHuge(CurrentMemoryContext, (Size) len * MAX_CONVERSION_GROWTH + 1); - OidFunctionCall5(proc, - Int32GetDatum(src_encoding), - Int32GetDatum(dest_encoding), - CStringGetDatum(src), - CStringGetDatum(result), - Int32GetDatum(len)); + (void) OidFunctionCall6(proc, + Int32GetDatum(src_encoding), + Int32GetDatum(dest_encoding), + CStringGetDatum(src), + CStringGetDatum(result), + Int32GetDatum(len), + BoolGetDatum(false)); /* * If the result is large, it's worth repalloc'ing to release any extra @@ -849,12 +850,13 @@ pg_unicode_to_server(pg_wchar c, unsigned char *s) c_as_utf8[c_as_utf8_len] = '\0'; /* Convert, or throw error if we can't */ - FunctionCall5(Utf8ToServerConvProc, + FunctionCall6(Utf8ToServerConvProc, Int32GetDatum(PG_UTF8), Int32GetDatum(server_encoding), CStringGetDatum(c_as_utf8), CStringGetDatum(s), - Int32GetDatum(c_as_utf8_len)); + Int32GetDatum(c_as_utf8_len), + BoolGetDatum(false)); } diff --git a/src/bin/pg_upgrade/check.c b/src/bin/pg_upgrade/check.c index 43fc297eb69..ee6be95b08d 100644 --- a/src/bin/pg_upgrade/check.c +++ b/src/bin/pg_upgrade/check.c @@ -28,6 +28,7 @@ static void check_for_reg_data_type_usage(ClusterInfo *cluster); static void check_for_jsonb_9_4_usage(ClusterInfo *cluster); static void check_for_pg_role_prefix(ClusterInfo *cluster); static void check_for_new_tablespace_dir(ClusterInfo *new_cluster); +static void check_for_user_defined_encoding_conversions(ClusterInfo *cluster); static char *get_canonical_locale_name(int category, const char *locale); @@ -102,6 +103,15 @@ check_and_dump_old_cluster(bool live_check) check_for_reg_data_type_usage(&old_cluster); check_for_isn_and_int8_passing_mismatch(&old_cluster); + /* + * PG 14 changed the function signature of encoding conversion functions. + * Conversions from older versions cannot be upgraded automatically + * because the user-defined functions used by the encoding conversions + * need to changed to match the new signature. + */ + if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1300) + check_for_user_defined_encoding_conversions(&old_cluster); + /* * Pre-PG 14 allowed user defined postfix operators, which are not * supported anymore. Verify there are none, iff applicable. @@ -1268,6 +1278,91 @@ check_for_pg_role_prefix(ClusterInfo *cluster) check_ok(); } +/* + * Verify that no user-defined encoding conversions exist. + */ +static void +check_for_user_defined_encoding_conversions(ClusterInfo *cluster) +{ + int dbnum; + FILE *script = NULL; + bool found = false; + char output_path[MAXPGPATH]; + + prep_status("Checking for user-defined encoding conversions"); + + snprintf(output_path, sizeof(output_path), + "encoding_conversions.txt"); + + /* Find any user defined encoding conversions */ + for (dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++) + { + PGresult *res; + bool db_used = false; + int ntups; + int rowno; + int i_conoid, + i_conname, + i_nspname; + DbInfo *active_db = &cluster->dbarr.dbs[dbnum]; + PGconn *conn = connectToServer(cluster, active_db->db_name); + + /* + * The query below hardcodes FirstNormalObjectId as 16384 rather than + * interpolating that C #define into the query because, if that + * #define is ever changed, the cutoff we want to use is the value + * used by pre-version 14 servers, not that of some future version. + */ + res = executeQueryOrDie(conn, + "SELECT c.oid as conoid, c.conname, n.nspname " + "FROM pg_catalog.pg_conversion c, " + " pg_catalog.pg_namespace n " + "WHERE c.connamespace = n.oid AND " + " c.oid >= 16384"); + ntups = PQntuples(res); + i_conoid = PQfnumber(res, "conoid"); + i_conname = PQfnumber(res, "conname"); + i_nspname = PQfnumber(res, "nspname"); + for (rowno = 0; rowno < ntups; rowno++) + { + found = true; + if (script == NULL && + (script = fopen_priv(output_path, "w")) == NULL) + pg_fatal("could not open file \"%s\": %s\n", + output_path, strerror(errno)); + if (!db_used) + { + fprintf(script, "In database: %s\n", active_db->db_name); + db_used = true; + } + fprintf(script, " (oid=%s) %s.%s\n", + PQgetvalue(res, rowno, i_conoid), + PQgetvalue(res, rowno, i_nspname), + PQgetvalue(res, rowno, i_conname)); + } + + PQclear(res); + + PQfinish(conn); + } + + if (script) + fclose(script); + + if (found) + { + pg_log(PG_REPORT, "fatal\n"); + pg_fatal("Your installation contains user-defined encoding conversions.\n" + "The conversion function parameters changed in PostgreSQL version 14\n" + "so this cluster cannot currently be upgraded. You can remove the\n" + "encoding conversions in the old cluster and restart the upgrade.\n" + "A list of user-defined encoding conversions is in the file:\n" + " %s\n\n", output_path); + } + else + check_ok(); +} + /* * get_canonical_locale_name diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index f8174061ef3..75b829e8514 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10766,388 +10766,388 @@ # conversion functions { oid => '4302', descr => 'internal conversion function for KOI8R to MULE_INTERNAL', - proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_mic', + proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4303', descr => 'internal conversion function for MULE_INTERNAL to KOI8R', - proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_koi8r', + proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4304', descr => 'internal conversion function for ISO-8859-5 to MULE_INTERNAL', - proname => 'iso_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_mic', + proname => 'iso_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4305', descr => 'internal conversion function for MULE_INTERNAL to ISO-8859-5', - proname => 'mic_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_iso', + proname => 'mic_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4306', descr => 'internal conversion function for WIN1251 to MULE_INTERNAL', - proname => 'win1251_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_mic', + proname => 'win1251_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4307', descr => 'internal conversion function for MULE_INTERNAL to WIN1251', - proname => 'mic_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1251', + proname => 'mic_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4308', descr => 'internal conversion function for WIN866 to MULE_INTERNAL', - proname => 'win866_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_mic', + proname => 'win866_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4309', descr => 'internal conversion function for MULE_INTERNAL to WIN866', - proname => 'mic_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win866', + proname => 'mic_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4310', descr => 'internal conversion function for KOI8R to WIN1251', - proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4311', descr => 'internal conversion function for WIN1251 to KOI8R', - proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4312', descr => 'internal conversion function for KOI8R to WIN866', - proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_win866', + proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4313', descr => 'internal conversion function for WIN866 to KOI8R', - proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_koi8r', + proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4314', descr => 'internal conversion function for WIN866 to WIN1251', - proname => 'win866_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win866_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4315', descr => 'internal conversion function for WIN1251 to WIN866', - proname => 'win1251_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4316', descr => 'internal conversion function for ISO-8859-5 to KOI8R', - proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_koi8r', + proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4317', descr => 'internal conversion function for KOI8R to ISO-8859-5', - proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_iso', + proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4318', descr => 'internal conversion function for ISO-8859-5 to WIN1251', - proname => 'iso_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win1251', + proname => 'iso_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4319', descr => 'internal conversion function for WIN1251 to ISO-8859-5', - proname => 'win1251_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_iso', + proname => 'win1251_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4320', descr => 'internal conversion function for ISO-8859-5 to WIN866', - proname => 'iso_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win866', + proname => 'iso_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4321', descr => 'internal conversion function for WIN866 to ISO-8859-5', - proname => 'win866_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_iso', + proname => 'win866_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4322', descr => 'internal conversion function for EUC_CN to MULE_INTERNAL', - proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_mic', + proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_mic', probin => '$libdir/euc_cn_and_mic' }, { oid => '4323', descr => 'internal conversion function for MULE_INTERNAL to EUC_CN', - proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_cn', + proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_cn', probin => '$libdir/euc_cn_and_mic' }, { oid => '4324', descr => 'internal conversion function for EUC_JP to SJIS', - proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_sjis', + proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4325', descr => 'internal conversion function for SJIS to EUC_JP', - proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_euc_jp', + proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4326', descr => 'internal conversion function for EUC_JP to MULE_INTERNAL', - proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_mic', + proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4327', descr => 'internal conversion function for SJIS to MULE_INTERNAL', - proname => 'sjis_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_mic', + proname => 'sjis_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4328', descr => 'internal conversion function for MULE_INTERNAL to EUC_JP', - proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_jp', + proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4329', descr => 'internal conversion function for MULE_INTERNAL to SJIS', - proname => 'mic_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_sjis', + proname => 'mic_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4330', descr => 'internal conversion function for EUC_KR to MULE_INTERNAL', - proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_mic', + proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_mic', probin => '$libdir/euc_kr_and_mic' }, { oid => '4331', descr => 'internal conversion function for MULE_INTERNAL to EUC_KR', - proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_kr', + proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_kr', probin => '$libdir/euc_kr_and_mic' }, { oid => '4332', descr => 'internal conversion function for EUC_TW to BIG5', - proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_big5', + proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4333', descr => 'internal conversion function for BIG5 to EUC_TW', - proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_euc_tw', + proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4334', descr => 'internal conversion function for EUC_TW to MULE_INTERNAL', - proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_mic', + proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4335', descr => 'internal conversion function for BIG5 to MULE_INTERNAL', - proname => 'big5_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_mic', + proname => 'big5_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4336', descr => 'internal conversion function for MULE_INTERNAL to EUC_TW', - proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_tw', + proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4337', descr => 'internal conversion function for MULE_INTERNAL to BIG5', - proname => 'mic_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_big5', + proname => 'mic_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4338', descr => 'internal conversion function for LATIN2 to MULE_INTERNAL', - proname => 'latin2_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin2_to_mic', + proname => 'latin2_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4339', descr => 'internal conversion function for MULE_INTERNAL to LATIN2', - proname => 'mic_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin2', + proname => 'mic_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4340', descr => 'internal conversion function for WIN1250 to MULE_INTERNAL', - proname => 'win1250_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1250_to_mic', + proname => 'win1250_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4341', descr => 'internal conversion function for MULE_INTERNAL to WIN1250', - proname => 'mic_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1250', + proname => 'mic_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4342', descr => 'internal conversion function for LATIN2 to WIN1250', - proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4343', descr => 'internal conversion function for WIN1250 to LATIN2', - proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4344', descr => 'internal conversion function for LATIN1 to MULE_INTERNAL', - proname => 'latin1_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin1_to_mic', + proname => 'latin1_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin1_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4345', descr => 'internal conversion function for MULE_INTERNAL to LATIN1', - proname => 'mic_to_latin1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin1', + proname => 'mic_to_latin1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin1', probin => '$libdir/latin_and_mic' }, { oid => '4346', descr => 'internal conversion function for LATIN3 to MULE_INTERNAL', - proname => 'latin3_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin3_to_mic', + proname => 'latin3_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin3_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4347', descr => 'internal conversion function for MULE_INTERNAL to LATIN3', - proname => 'mic_to_latin3', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin3', + proname => 'mic_to_latin3', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin3', probin => '$libdir/latin_and_mic' }, { oid => '4348', descr => 'internal conversion function for LATIN4 to MULE_INTERNAL', - proname => 'latin4_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin4_to_mic', + proname => 'latin4_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin4_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4349', descr => 'internal conversion function for MULE_INTERNAL to LATIN4', - proname => 'mic_to_latin4', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin4', + proname => 'mic_to_latin4', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin4', probin => '$libdir/latin_and_mic' }, { oid => '4352', descr => 'internal conversion function for BIG5 to UTF8', - proname => 'big5_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_utf8', + proname => 'big5_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_utf8', probin => '$libdir/utf8_and_big5' }, { oid => '4353', descr => 'internal conversion function for UTF8 to BIG5', - proname => 'utf8_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_big5', + proname => 'utf8_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_big5', probin => '$libdir/utf8_and_big5' }, { oid => '4354', descr => 'internal conversion function for UTF8 to KOI8R', - proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8r', + proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8r', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4355', descr => 'internal conversion function for KOI8R to UTF8', - proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_utf8', + proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4356', descr => 'internal conversion function for UTF8 to KOI8U', - proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8u', + proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8u', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4357', descr => 'internal conversion function for KOI8U to UTF8', - proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8u_to_utf8', + proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8u_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4358', descr => 'internal conversion function for UTF8 to WIN', - proname => 'utf8_to_win', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_win', + proname => 'utf8_to_win', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_win', probin => '$libdir/utf8_and_win' }, { oid => '4359', descr => 'internal conversion function for WIN to UTF8', - proname => 'win_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win_to_utf8', + proname => 'win_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win_to_utf8', probin => '$libdir/utf8_and_win' }, { oid => '4360', descr => 'internal conversion function for EUC_CN to UTF8', - proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_utf8', + proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_utf8', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4361', descr => 'internal conversion function for UTF8 to EUC_CN', - proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_cn', + proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_cn', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4362', descr => 'internal conversion function for EUC_JP to UTF8', - proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_utf8', + proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_utf8', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4363', descr => 'internal conversion function for UTF8 to EUC_JP', - proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_jp', + proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jp', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4364', descr => 'internal conversion function for EUC_KR to UTF8', - proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_utf8', + proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_utf8', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4365', descr => 'internal conversion function for UTF8 to EUC_KR', - proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_kr', + proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_kr', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4366', descr => 'internal conversion function for EUC_TW to UTF8', - proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_utf8', + proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_utf8', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4367', descr => 'internal conversion function for UTF8 to EUC_TW', - proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_tw', + proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_tw', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4368', descr => 'internal conversion function for GB18030 to UTF8', - proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gb18030_to_utf8', + proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gb18030_to_utf8', probin => '$libdir/utf8_and_gb18030' }, { oid => '4369', descr => 'internal conversion function for UTF8 to GB18030', - proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gb18030', + proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gb18030', probin => '$libdir/utf8_and_gb18030' }, { oid => '4370', descr => 'internal conversion function for GBK to UTF8', - proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gbk_to_utf8', + proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gbk_to_utf8', probin => '$libdir/utf8_and_gbk' }, { oid => '4371', descr => 'internal conversion function for UTF8 to GBK', - proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gbk', + proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gbk', probin => '$libdir/utf8_and_gbk' }, { oid => '4372', descr => 'internal conversion function for UTF8 to ISO-8859 2-16', - proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_iso8859', + proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859', probin => '$libdir/utf8_and_iso8859' }, { oid => '4373', descr => 'internal conversion function for ISO-8859 2-16 to UTF8', - proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso8859_to_utf8', + proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_to_utf8', probin => '$libdir/utf8_and_iso8859' }, { oid => '4374', descr => 'internal conversion function for LATIN1 to UTF8', - proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_1_to_utf8', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4375', descr => 'internal conversion function for UTF8 to LATIN1', - proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859_1', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4376', descr => 'internal conversion function for JOHAB to UTF8', - proname => 'johab_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'johab_to_utf8', + proname => 'johab_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'johab_to_utf8', probin => '$libdir/utf8_and_johab' }, { oid => '4377', descr => 'internal conversion function for UTF8 to JOHAB', - proname => 'utf8_to_johab', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_johab', + proname => 'utf8_to_johab', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_johab', probin => '$libdir/utf8_and_johab' }, { oid => '4378', descr => 'internal conversion function for SJIS to UTF8', - proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_utf8', + proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_utf8', probin => '$libdir/utf8_and_sjis' }, { oid => '4379', descr => 'internal conversion function for UTF8 to SJIS', - proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_sjis', + proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_sjis', probin => '$libdir/utf8_and_sjis' }, { oid => '4380', descr => 'internal conversion function for UHC to UTF8', - proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'uhc_to_utf8', + proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'uhc_to_utf8', probin => '$libdir/utf8_and_uhc' }, { oid => '4381', descr => 'internal conversion function for UTF8 to UHC', - proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_uhc', + proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_uhc', probin => '$libdir/utf8_and_uhc' }, { oid => '4382', descr => 'internal conversion function for EUC_JIS_2004 to UTF8', - proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_utf8', probin => '$libdir/utf8_and_euc2004' }, { oid => '4383', descr => 'internal conversion function for UTF8 to EUC_JIS_2004', - proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jis_2004', probin => '$libdir/utf8_and_euc2004' }, { oid => '4384', descr => 'internal conversion function for SHIFT_JIS_2004 to UTF8', - proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_utf8', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4385', descr => 'internal conversion function for UTF8 to SHIFT_JIS_2004', - proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_shift_jis_2004', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4386', descr => 'internal conversion function for EUC_JIS_2004 to SHIFT_JIS_2004', proname => 'euc_jis_2004_to_shift_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_shift_jis_2004', probin => '$libdir/euc2004_sjis2004' }, { oid => '4387', descr => 'internal conversion function for SHIFT_JIS_2004 to EUC_JIS_2004', proname => 'shift_jis_2004_to_euc_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_euc_jis_2004', probin => '$libdir/euc2004_sjis2004' }, diff --git a/src/include/mb/pg_wchar.h b/src/include/mb/pg_wchar.h index 64b22e4b0d4..346a41a1f3d 100644 --- a/src/include/mb/pg_wchar.h +++ b/src/include/mb/pg_wchar.h @@ -627,18 +627,18 @@ extern void pg_unicode_to_server(pg_wchar c, unsigned char *s); extern unsigned short BIG5toCNS(unsigned short big5, unsigned char *lc); extern unsigned short CNStoBIG5(unsigned short cns, unsigned char lc); -extern void UtfToLocal(const unsigned char *utf, int len, - unsigned char *iso, - const pg_mb_radix_tree *map, - const pg_utf_to_local_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); -extern void LocalToUtf(const unsigned char *iso, int len, - unsigned char *utf, - const pg_mb_radix_tree *map, - const pg_local_to_utf_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); +extern int UtfToLocal(const unsigned char *utf, int len, + unsigned char *iso, + const pg_mb_radix_tree *map, + const pg_utf_to_local_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); +extern int LocalToUtf(const unsigned char *iso, int len, + unsigned char *utf, + const pg_mb_radix_tree *map, + const pg_local_to_utf_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); extern bool pg_verifymbstr(const char *mbstr, int len, bool noError); extern bool pg_verify_mbstr(int encoding, const char *mbstr, int len, @@ -656,18 +656,19 @@ extern void report_invalid_encoding(int encoding, const char *mbstr, int len) pg extern void report_untranslatable_char(int src_encoding, int dest_encoding, const char *mbstr, int len) pg_attribute_noreturn(); -extern void local2local(const unsigned char *l, unsigned char *p, int len, - int src_encoding, int dest_encoding, const unsigned char *tab); -extern void latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding); -extern void mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding); -extern void latin2mic_with_table(const unsigned char *l, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); -extern void mic2latin_with_table(const unsigned char *mic, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); +extern int local2local(const unsigned char *l, unsigned char *p, int len, + int src_encoding, int dest_encoding, const unsigned char *tab, + bool noError); +extern int latin2mic(const unsigned char *l, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int mic2latin(const unsigned char *mic, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int latin2mic_with_table(const unsigned char *l, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); +extern int mic2latin_with_table(const unsigned char *mic, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); #ifdef WIN32 extern WCHAR *pgwin32_message_to_UTF16(const char *str, int len, int *utf16len); diff --git a/src/test/regress/expected/opr_sanity.out b/src/test/regress/expected/opr_sanity.out index 254ca06d3dd..23ba60e395f 100644 --- a/src/test/regress/expected/opr_sanity.out +++ b/src/test/regress/expected/opr_sanity.out @@ -1052,13 +1052,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); oid | proname | oid | conname -----+---------+-----+--------- (0 rows) diff --git a/src/test/regress/sql/opr_sanity.sql b/src/test/regress/sql/opr_sanity.sql index bbd3834b634..04691745981 100644 --- a/src/test/regress/sql/opr_sanity.sql +++ b/src/test/regress/sql/opr_sanity.sql @@ -556,13 +556,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); -- Check for conprocs that don't perform the specific conversion that -- pg_conversion alleges they do, by trying to invoke each conversion -- 2.29.2 --------------39E46EF15EBFAA37D53332E5 Content-Type: text/x-patch; charset=UTF-8; name="v3-0003-Add-tests-for-the-new-noError-variants-of-built-i.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="v3-0003-Add-tests-for-the-new-noError-variants-of-built-i.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 34+ messages in thread
* [PATCH v3 2/5] Change conversion function signature. @ 2021-01-28 16:42 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 34+ messages in thread From: Heikki Linnakangas @ 2021-01-28 16:42 UTC (permalink / raw) Add a 'noError' argument, so that we can try to convert a buffer without knowing the character boundaries beforehand. The functions now need to return the number of input bytes successfully converted. This is is a backwards-incompatible change, if you have created a custom encoding conversion with CREATE CONVERSION. This adds a check to pg_upgrade for that, refusing the upgrade if there are any user-defined encoding conversions. --- doc/src/sgml/ref/create_conversion.sgml | 5 +- src/backend/commands/conversioncmds.c | 27 +- src/backend/utils/error/elog.c | 2 + src/backend/utils/mb/conv.c | 112 +++++- .../cyrillic_and_mic/cyrillic_and_mic.c | 127 ++++--- .../euc2004_sjis2004/euc2004_sjis2004.c | 96 ++++- .../euc_cn_and_mic/euc_cn_and_mic.c | 57 ++- .../euc_jp_and_sjis/euc_jp_and_sjis.c | 153 ++++++-- .../euc_kr_and_mic/euc_kr_and_mic.c | 57 ++- .../euc_tw_and_big5/euc_tw_and_big5.c | 165 +++++++-- .../latin2_and_win1250/latin2_and_win1250.c | 49 ++- .../latin_and_mic/latin_and_mic.c | 43 ++- .../utf8_and_big5/utf8_and_big5.c | 37 +- .../utf8_and_cyrillic/utf8_and_cyrillic.c | 67 ++-- .../utf8_and_euc2004/utf8_and_euc2004.c | 37 +- .../utf8_and_euc_cn/utf8_and_euc_cn.c | 37 +- .../utf8_and_euc_jp/utf8_and_euc_jp.c | 37 +- .../utf8_and_euc_kr/utf8_and_euc_kr.c | 37 +- .../utf8_and_euc_tw/utf8_and_euc_tw.c | 37 +- .../utf8_and_gb18030/utf8_and_gb18030.c | 37 +- .../utf8_and_gbk/utf8_and_gbk.c | 37 +- .../utf8_and_iso8859/utf8_and_iso8859.c | 43 ++- .../utf8_and_iso8859_1/utf8_and_iso8859_1.c | 27 +- .../utf8_and_johab/utf8_and_johab.c | 37 +- .../utf8_and_sjis/utf8_and_sjis.c | 37 +- .../utf8_and_sjis2004/utf8_and_sjis2004.c | 37 +- .../utf8_and_uhc/utf8_and_uhc.c | 37 +- .../utf8_and_win/utf8_and_win.c | 43 ++- src/backend/utils/mb/mbutils.c | 18 +- src/bin/pg_upgrade/check.c | 95 +++++ src/include/catalog/pg_proc.dat | 332 +++++++++--------- src/include/mb/pg_wchar.h | 49 +-- src/test/regress/expected/opr_sanity.out | 7 +- src/test/regress/sql/opr_sanity.sql | 7 +- 34 files changed, 1390 insertions(+), 635 deletions(-) diff --git a/doc/src/sgml/ref/create_conversion.sgml b/doc/src/sgml/ref/create_conversion.sgml index e7700fecfc5..f014a676c88 100644 --- a/doc/src/sgml/ref/create_conversion.sgml +++ b/doc/src/sgml/ref/create_conversion.sgml @@ -117,8 +117,9 @@ conv_proc( integer, -- destination encoding ID cstring, -- source string (null terminated C string) internal, -- destination (fill with a null terminated C string) - integer -- source string length -) RETURNS void; + integer, -- source string length + boolean -- if true, don't throw an error if conversion fails +) RETURNS integer; </programlisting></para> </listitem> </varlistentry> diff --git a/src/backend/commands/conversioncmds.c b/src/backend/commands/conversioncmds.c index f7ff321de71..d2041466911 100644 --- a/src/backend/commands/conversioncmds.c +++ b/src/backend/commands/conversioncmds.c @@ -45,8 +45,9 @@ CreateConversionCommand(CreateConversionStmt *stmt) const char *from_encoding_name = stmt->for_encoding_name; const char *to_encoding_name = stmt->to_encoding_name; List *func_name = stmt->func_name; - static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID}; + static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID, BOOLOID}; char result[1]; + Datum funcresult; /* Convert list of names to a name and namespace */ namespaceId = QualifiedNameGetCreationNamespace(stmt->conversion_name, @@ -92,8 +93,8 @@ CreateConversionCommand(CreateConversionStmt *stmt) funcoid = LookupFuncName(func_name, sizeof(funcargs) / sizeof(Oid), funcargs, false); - /* Check it returns VOID, else it's probably the wrong function */ - if (get_func_rettype(funcoid) != VOIDOID) + /* Check it returns int4, else it's probably the wrong function */ + if (get_func_rettype(funcoid) != INT4OID) ereport(ERROR, (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), errmsg("encoding conversion function %s must return type %s", @@ -111,12 +112,20 @@ CreateConversionCommand(CreateConversionStmt *stmt) * string; the conversion function should throw an error if it can't * perform the requested conversion. */ - OidFunctionCall5(funcoid, - Int32GetDatum(from_encoding), - Int32GetDatum(to_encoding), - CStringGetDatum(""), - CStringGetDatum(result), - Int32GetDatum(0)); + funcresult = OidFunctionCall6(funcoid, + Int32GetDatum(from_encoding), + Int32GetDatum(to_encoding), + CStringGetDatum(""), + CStringGetDatum(result), + Int32GetDatum(0), + BoolGetDatum(false)); + + /* The function should return 0 for empty input. Might as well check that, too. */ + if (DatumGetInt32(funcresult) != 0) + ereport(ERROR, + (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), + errmsg("encoding conversion function %s returned incorrect result for empty input", + NameListToString(func_name)))); /* * All seem ok, go ahead (possible failure would be a duplicate conversion diff --git a/src/backend/utils/error/elog.c b/src/backend/utils/error/elog.c index 80c26724612..762f77d533c 100644 --- a/src/backend/utils/error/elog.c +++ b/src/backend/utils/error/elog.c @@ -2280,6 +2280,8 @@ write_console(const char *line, int len) * Conversion on non-win32 platforms is not implemented yet. It requires * non-throw version of pg_do_encoding_conversion(), that converts * unconvertable characters to '?' without errors. + * + * XXX: We have a no-throw version now. It doesn't convert to '?' though. */ #endif diff --git a/src/backend/utils/mb/conv.c b/src/backend/utils/mb/conv.c index a07b54bd3b8..b83358bc7a5 100644 --- a/src/backend/utils/mb/conv.c +++ b/src/backend/utils/mb/conv.c @@ -26,14 +26,16 @@ * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the target charset, or 0 if there is no equivalent code. */ -void +int local2local(const unsigned char *l, unsigned char *p, int len, int src_encoding, int dest_encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -41,7 +43,11 @@ local2local(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(src_encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -50,13 +56,19 @@ local2local(const unsigned char *l, if (c2) *p++ = c2; else + { + if (noError) + break; report_untranslatable_char(src_encoding, dest_encoding, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -67,17 +79,22 @@ local2local(const unsigned char *l, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = l; int c1; while (len > 0) { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (IS_HIGHBIT_SET(c1)) *p++ = lc; *p++ = c1; @@ -85,6 +102,8 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, len--; } *p = '\0'; + + return l - start; } /* @@ -95,17 +114,22 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -118,17 +142,27 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1])) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); + } *p++ = mic[1]; mic += 2; len -= 2; } } *p = '\0'; + + return mic - start; } @@ -144,14 +178,16 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the mule encoding, or 0 if there is no equivalent code. */ -void +int latin2mic_with_table(const unsigned char *l, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -159,7 +195,11 @@ latin2mic_with_table(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -171,13 +211,19 @@ latin2mic_with_table(const unsigned char *l, *p++ = c2; } else + { + if (noError) + break; report_untranslatable_char(encoding, PG_MULE_INTERNAL, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -192,14 +238,16 @@ latin2mic_with_table(const unsigned char *l, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the local charset, or 0 if there is no equivalent code. */ -void +int mic2latin_with_table(const unsigned char *mic, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = mic; unsigned char c1, c2; @@ -207,7 +255,11 @@ mic2latin_with_table(const unsigned char *mic, { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -220,11 +272,17 @@ mic2latin_with_table(const unsigned char *mic, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1]) || (c2 = tab[mic[1] - HIGHBIT]) == 0) { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); break; /* keep compiler quiet */ @@ -235,6 +293,8 @@ mic2latin_with_table(const unsigned char *mic, } } *p = '\0'; + + return mic - start; } /* @@ -425,17 +485,19 @@ pg_mb_radix_conv(const pg_mb_radix_tree *rt, * * See pg_wchar.h for more details about the data structures used here. */ -void +int UtfToLocal(const unsigned char *utf, int len, unsigned char *iso, const pg_mb_radix_tree *map, const pg_utf_to_local_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, bool noError) { uint32 iutf; int l; const pg_utf_to_local_combined *cp; + const unsigned char *start = utf; + const unsigned char *cur = utf; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -449,6 +511,8 @@ UtfToLocal(const unsigned char *utf, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*utf == '\0') break; @@ -584,15 +648,19 @@ UtfToLocal(const unsigned char *utf, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(PG_UTF8, encoding, (const char *) (utf - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(PG_UTF8, (const char *) utf, len); *iso = '\0'; + + return cur - start; } /* @@ -616,18 +684,24 @@ UtfToLocal(const unsigned char *utf, int len, * (if provided) is applied. An error is raised if no match is found. * * See pg_wchar.h for more details about the data structures used here. + * + * Returns the number of input bytes consumed. If noError is true, this can + * be less than 'len'. */ -void +int LocalToUtf(const unsigned char *iso, int len, unsigned char *utf, const pg_mb_radix_tree *map, const pg_local_to_utf_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, + bool noError) { uint32 iiso; int l; const pg_local_to_utf_combined *cp; + const unsigned char *start = iso; + const unsigned char *cur = iso; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -641,6 +715,8 @@ LocalToUtf(const unsigned char *iso, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*iso == '\0') break; @@ -723,13 +799,17 @@ LocalToUtf(const unsigned char *iso, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(encoding, PG_UTF8, (const char *) (iso - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(encoding, (const char *) iso, len); *utf = '\0'; + + return cur - start; } diff --git a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c index 4c5b02654de..368c2deb5e4 100644 --- a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c @@ -44,8 +44,11 @@ PG_FUNCTION_INFO_V1(win866_to_iso); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -306,12 +309,14 @@ koi8r_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -320,12 +325,14 @@ mic_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_KOI8R); - mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -334,12 +341,14 @@ iso_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -348,12 +357,14 @@ mic_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_ISO_8859_5); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -362,12 +373,14 @@ win1251_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -376,12 +389,14 @@ mic_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1251); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -390,12 +405,14 @@ win866_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -404,12 +421,14 @@ mic_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN866); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -418,12 +437,14 @@ koi8r_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN1251); - local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -432,12 +453,14 @@ win1251_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_KOI8R); - local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi); + converted = local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -446,12 +469,14 @@ koi8r_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN866); - local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -460,12 +485,14 @@ win866_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_KOI8R); - local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi); + converted = local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -474,12 +501,14 @@ win866_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_WIN1251); - local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251); + converted = local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -488,12 +517,14 @@ win1251_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_WIN866); - local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866); + converted = local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -502,12 +533,14 @@ iso_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_KOI8R); - local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -516,12 +549,14 @@ koi8r_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_ISO_8859_5); - local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso); + converted = local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -530,12 +565,14 @@ iso_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN1251); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -544,12 +581,14 @@ win1251_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso); + converted = local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -558,12 +597,14 @@ iso_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN866); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -572,10 +613,12 @@ win866_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso); + converted = local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c index 4d7fb116cfd..88529c644cf 100644 --- a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c @@ -19,8 +19,8 @@ PG_MODULE_MAGIC; PG_FUNCTION_INFO_V1(euc_jis_2004_to_shift_jis_2004); PG_FUNCTION_INFO_V1(shift_jis_2004_to_euc_jis_2004); -static void euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len); -static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len); +static int euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError); /* ---------- * conv_proc( @@ -28,8 +28,11 @@ static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -39,12 +42,14 @@ euc_jis_2004_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_SHIFT_JIS_2004); - euc_jis_20042shift_jis_2004(src, dest, len); + converted = euc_jis_20042shift_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -53,20 +58,23 @@ shift_jis_2004_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_EUC_JIS_2004); - shift_jis_20042euc_jis_2004(src, dest, len); + converted = shift_jis_20042euc_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_JIS_2004 -> SHIFT_JIS_2004 */ -static void -euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, ku, ten; @@ -79,8 +87,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -90,8 +102,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) l = pg_encoding_verifymbchar(PG_EUC_JIS_2004, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (c1 == SS2 && l == 2) /* JIS X 0201 kana? */ { @@ -121,8 +137,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) *p++ = (ku + 0x19b) >> 1; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } if (ku % 2) @@ -132,8 +152,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; @@ -149,8 +173,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ku >= 63 && ku <= 94) *p++ = (ku + 0x181) >> 1; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (ku % 2) { @@ -159,20 +187,30 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else - report_invalid_encoding(PG_EUC_JIS_2004, + { + if (noError) + break; + report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } euc += l; len -= l; } *p = '\0'; + + return euc - start; } /* @@ -212,9 +250,10 @@ get_ten(int b, int *ku) * SHIFT_JIS_2004 ---> EUC_JIS_2004 */ -static void -shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len) +static int +shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1; int ku, ten, @@ -230,8 +269,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -241,8 +284,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len l = pg_encoding_verifymbchar(PG_SHIFT_JIS_2004, (const char *) sjis, len); if (l < 0 || l > len) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf && l == 1) { @@ -266,8 +313,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x100; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xe0 && c1 <= 0xef) /* plane 1 62ku-94ku */ @@ -275,9 +326,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x180; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, - (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xf0 && c1 <= 0xf3) /* plane 2 @@ -286,8 +340,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } switch (c1) { case 0xf0: @@ -309,16 +367,24 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 == 0xf4 && kubun == 1) ku = 15; else ku = (c1 << 1) - 0x19a - kubun; } else + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (plane == 2) *p++ = SS3; @@ -330,4 +396,6 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c index e9bb896935f..a8da733803d 100644 --- a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_cn2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_cn(const unsigned char *mic, unsigned char *p, int len); +static int euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_cn_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_cn_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_MULE_INTERNAL); - euc_cn2mic(src, dest, len); + converted = euc_cn2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_CN); - mic2euc_cn(src, dest, len); + converted = mic2euc_cn(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_CN ---> MIC */ -static void -euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; while (len > 0) @@ -76,7 +84,11 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (len < 2 || !IS_HIGHBIT_SET(euc[1])) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = LC_GB2312_80; *p++ = c1; *p++ = euc[1]; @@ -86,21 +98,28 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_CN */ -static void -mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) @@ -109,11 +128,19 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (c1 != LC_GB2312_80) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_CN, (const char *) mic, len); + } if (len < 3 || !IS_HIGHBIT_SET(mic[1]) || !IS_HIGHBIT_SET(mic[2])) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } mic++; *p++ = *mic++; *p++ = *mic++; @@ -122,12 +149,18 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; } } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c index 5059f917a98..cc4817dc4cd 100644 --- a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c @@ -42,17 +42,20 @@ PG_FUNCTION_INFO_V1(mic_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void sjis2mic(const unsigned char *sjis, unsigned char *p, int len); -static void mic2sjis(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_jp(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len); -static void sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len); +static int sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError); +static int mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_jp_to_sjis(PG_FUNCTION_ARGS) @@ -60,12 +63,14 @@ euc_jp_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_SJIS); - euc_jp2sjis(src, dest, len); + converted = euc_jp2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -74,12 +79,14 @@ sjis_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_EUC_JP); - sjis2euc_jp(src, dest, len); + converted = sjis2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -88,12 +95,14 @@ euc_jp_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_MULE_INTERNAL); - euc_jp2mic(src, dest, len); + converted = euc_jp2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -102,12 +111,14 @@ mic_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_JP); - mic2euc_jp(src, dest, len); + converted = mic2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -116,12 +127,14 @@ sjis_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_MULE_INTERNAL); - sjis2mic(src, dest, len); + converted = sjis2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -130,20 +143,23 @@ mic_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_SJIS); - mic2sjis(src, dest, len); + converted = mic2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * SJIS ---> MIC */ -static void -sjis2mic(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -167,7 +183,11 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) * JIS X0208, X0212, user defined extended characters */ if (len < 2 || !ISSJISHEAD(c1) || !ISSJISTAIL(sjis[1])) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } c2 = sjis[1]; k = (c1 << 8) + c2; if (k >= 0xed40 && k < 0xf040) @@ -257,21 +277,28 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; } } *p = '\0'; + + return sjis - start; } /* * MIC ---> SJIS */ -static void -mic2sjis(const unsigned char *mic, unsigned char *p, int len) +static int +mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1, c2, k, @@ -284,8 +311,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -293,8 +324,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) *p++ = mic[1]; else if (c1 == LC_JISX0208) @@ -350,20 +385,27 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_SJIS, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP ---> MIC */ -static void -euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -374,8 +416,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -383,8 +429,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* 1 byte kana? */ *p++ = LC_JISX0201K; @@ -406,14 +456,17 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_JP */ -static void -mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -424,8 +477,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -433,8 +490,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) { *p++ = SS2; @@ -452,20 +513,27 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_JP, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP -> SJIS */ -static void -euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, c2, k; @@ -478,8 +546,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -487,8 +559,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* hankaku kana? */ @@ -551,14 +627,17 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * SJIS ---> EUC_JP */ -static void -sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -573,8 +652,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -582,8 +665,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_SJIS, (const char *) sjis, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf) { /* JIS X0201 (1 byte kana) */ @@ -680,4 +767,6 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c index ac823d6c270..a5b51617e52 100644 --- a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_kr2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_kr(const unsigned char *mic, unsigned char *p, int len); +static int euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_kr_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_kr_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_MULE_INTERNAL); - euc_kr2mic(src, dest, len); + converted = euc_kr2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_KR); - mic2euc_kr(src, dest, len); + converted = mic2euc_kr(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_KR ---> MIC */ -static void -euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -78,8 +86,12 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_KR, (const char *) euc, len); if (l != 2) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = LC_KS5601; *p++ = c1; *p++ = euc[1]; @@ -89,22 +101,29 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_KR */ -static void -mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -115,8 +134,12 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -124,18 +147,28 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_KS5601) { *p++ = mic[1]; *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_KR, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c index 66c242d7f36..ebb4e0acd53 100644 --- a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c @@ -32,17 +32,20 @@ PG_FUNCTION_INFO_V1(mic_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_tw2big5(const unsigned char *euc, unsigned char *p, int len); -static void big52euc_tw(const unsigned char *euc, unsigned char *p, int len); -static void big52mic(const unsigned char *big5, unsigned char *p, int len); -static void mic2big5(const unsigned char *mic, unsigned char *p, int len); -static void euc_tw2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_tw(const unsigned char *mic, unsigned char *p, int len); +static int euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52euc_tw(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError); +static int mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_tw_to_big5(PG_FUNCTION_ARGS) @@ -50,12 +53,14 @@ euc_tw_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_BIG5); - euc_tw2big5(src, dest, len); + converted = euc_tw2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -64,12 +69,14 @@ big5_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_EUC_TW); - big52euc_tw(src, dest, len); + converted = big52euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -78,12 +85,14 @@ euc_tw_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_MULE_INTERNAL); - euc_tw2mic(src, dest, len); + converted = euc_tw2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -92,12 +101,14 @@ mic_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_TW); - mic2euc_tw(src, dest, len); + converted = mic2euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -106,12 +117,14 @@ big5_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_MULE_INTERNAL); - big52mic(src, dest, len); + converted = big52mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -120,21 +133,24 @@ mic_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_BIG5); - mic2big5(src, dest, len); + converted = mic2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_TW ---> Big5 */ -static void -euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; unsigned char c1; unsigned short big5buf, cnsBuf; @@ -149,8 +165,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Verify and decode the next EUC_TW input character */ l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -171,8 +191,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Write it out in Big5 */ big5buf = CNStoBIG5(cnsBuf, lc); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_EUC_TW, PG_BIG5, (const char *) euc, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; @@ -182,22 +206,29 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * Big5 ---> EUC_TW */ -static void -big52euc_tw(const unsigned char *big5, unsigned char *p, int len) +static int +big52euc_tw(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -212,8 +243,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); @@ -237,8 +272,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_EUC_TW, (const char *) big5, len); + } big5 += l; len -= l; @@ -256,14 +295,17 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) } } *p = '\0'; + + return big5 - start; } /* * EUC_TW ---> MIC */ -static void -euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -274,8 +316,12 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -304,22 +350,29 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_TW */ -static void -mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -330,8 +383,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -339,8 +396,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1) { *p++ = mic[1]; @@ -362,20 +423,27 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[3]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_TW, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * Big5 ---> MIC */ -static void -big52mic(const unsigned char *big5, unsigned char *p, int len) +static int +big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -389,8 +457,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } *p++ = c1; big5++; len--; @@ -398,8 +470,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); if (lc != 0) @@ -412,20 +488,27 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_MULE_INTERNAL, (const char *) big5, len); + } big5 += l; len -= l; } *p = '\0'; + + return big5 - start; } /* * MIC ---> Big5 */ -static void -mic2big5(const unsigned char *mic, unsigned char *p, int len) +static int +mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -438,8 +521,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -447,8 +534,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1 || c1 == LC_CNS11643_2 || c1 == LCPRV2_B) { if (c1 == LCPRV2_B) @@ -462,16 +553,26 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } big5buf = CNStoBIG5(cnsBuf, c1); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c index 2e28e6780a5..8610fcb69aa 100644 --- a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c +++ b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(win1250_to_latin2); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -82,12 +85,14 @@ latin2_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -96,12 +101,14 @@ mic_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN2); - mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -110,13 +117,15 @@ win1250_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - win1250_2_iso88592); + converted = latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -125,13 +134,15 @@ mic_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1250); - mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - iso88592_2_win1250); + converted = mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -140,12 +151,15 @@ latin2_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_WIN1250); - local2local(src, dest, len, PG_LATIN2, PG_WIN1250, iso88592_2_win1250); + converted = local2local(src, dest, len, PG_LATIN2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -154,10 +168,13 @@ win1250_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_LATIN2); - local2local(src, dest, len, PG_WIN1250, PG_LATIN2, win1250_2_iso88592); + converted = local2local(src, dest, len, PG_WIN1250, PG_LATIN2, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c index bc651410f21..bff27d1c295 100644 --- a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(mic_to_latin4); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -42,12 +45,14 @@ latin1_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,12 +61,14 @@ mic_to_latin1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN1); - mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -70,12 +77,14 @@ latin3_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN3, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -84,12 +93,14 @@ mic_to_latin3(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN3); - mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,12 +109,14 @@ latin4_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN4, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -112,10 +125,12 @@ mic_to_latin4(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN4); - mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c index d6067cdc24e..3838b15cab9 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ big5_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_UTF8); - LocalToUtf(src, len, dest, - &big5_to_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = LocalToUtf(src, len, dest, + &big5_to_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_BIG5); - UtfToLocal(src, len, dest, - &big5_from_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = UtfToLocal(src, len, dest, + &big5_from_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c index ed90e8e682e..75719fe5f1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c @@ -33,8 +33,11 @@ PG_FUNCTION_INFO_V1(koi8u_to_utf8); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -44,16 +47,19 @@ utf8_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8R); - UtfToLocal(src, len, dest, - &koi8r_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = UtfToLocal(src, len, dest, + &koi8r_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -62,16 +68,19 @@ koi8r_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8r_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = LocalToUtf(src, len, dest, + &koi8r_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -80,16 +89,19 @@ utf8_to_koi8u(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8U); - UtfToLocal(src, len, dest, - &koi8u_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = UtfToLocal(src, len, dest, + &koi8u_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,14 +110,17 @@ koi8u_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8U, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8u_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = LocalToUtf(src, len, dest, + &koi8u_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c index d699affce47..5391001951a 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jis_2004_to_unicode_tree, - LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = LocalToUtf(src, len, dest, + &euc_jis_2004_to_unicode_tree, + LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JIS_2004); - UtfToLocal(src, len, dest, - &euc_jis_2004_from_unicode_tree, - ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = UtfToLocal(src, len, dest, + &euc_jis_2004_from_unicode_tree, + ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c index d7c0ba6a58b..c87d1bf2398 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_cn_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_cn_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = LocalToUtf(src, len, dest, + &euc_cn_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_CN); - UtfToLocal(src, len, dest, - &euc_cn_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = UtfToLocal(src, len, dest, + &euc_cn_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c index 13a3a23e77b..6a55134db21 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jp); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jp_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jp_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = LocalToUtf(src, len, dest, + &euc_jp_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JP); - UtfToLocal(src, len, dest, - &euc_jp_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = UtfToLocal(src, len, dest, + &euc_jp_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c index 1bbb8aaef7b..fe1924e2fec 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_kr_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_kr_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = LocalToUtf(src, len, dest, + &euc_kr_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_KR); - UtfToLocal(src, len, dest, - &euc_kr_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = UtfToLocal(src, len, dest, + &euc_kr_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c index 9830045dccd..68215659b57 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_tw); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_tw_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_tw_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = LocalToUtf(src, len, dest, + &euc_tw_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_TW); - UtfToLocal(src, len, dest, - &euc_tw_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = UtfToLocal(src, len, dest, + &euc_tw_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c index f86ecf27424..e1a59c39a4d 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c @@ -183,8 +183,11 @@ conv_utf8_to_18030(uint32 code) * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -193,16 +196,19 @@ gb18030_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GB18030, PG_UTF8); - LocalToUtf(src, len, dest, - &gb18030_to_unicode_tree, - NULL, 0, - conv_18030_to_utf8, - PG_GB18030); + converted = LocalToUtf(src, len, dest, + &gb18030_to_unicode_tree, + NULL, 0, + conv_18030_to_utf8, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -211,14 +217,17 @@ utf8_to_gb18030(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GB18030); - UtfToLocal(src, len, dest, - &gb18030_from_unicode_tree, - NULL, 0, - conv_utf8_to_18030, - PG_GB18030); + converted = UtfToLocal(src, len, dest, + &gb18030_from_unicode_tree, + NULL, 0, + conv_utf8_to_18030, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c index 2ab8b16c8a8..881386d5347 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_gbk); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ gbk_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GBK, PG_UTF8); - LocalToUtf(src, len, dest, - &gbk_to_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = LocalToUtf(src, len, dest, + &gbk_to_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_gbk(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GBK); - UtfToLocal(src, len, dest, - &gbk_from_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = UtfToLocal(src, len, dest, + &gbk_from_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c index 3e49f67ea2f..d93a521badf 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c @@ -52,8 +52,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -100,6 +103,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -108,12 +112,15 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -122,7 +129,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -132,6 +139,7 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -140,12 +148,15 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -154,5 +165,5 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c index 67e713cca11..8ac93604a1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c @@ -26,8 +26,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859_1); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -37,6 +40,8 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_UTF8); @@ -45,7 +50,11 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_LATIN1, (const char *) src, len); + } if (!IS_HIGHBIT_SET(c)) *dest++ = c; else @@ -58,7 +67,7 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } Datum @@ -67,6 +76,8 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c, c1; @@ -76,7 +87,11 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_UTF8, (const char *) src, len); + } /* fast path for ASCII-subset characters */ if (!IS_HIGHBIT_SET(c)) { @@ -102,11 +117,15 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) len -= 2; } else + { + if (noError) + break; report_untranslatable_char(PG_UTF8, PG_LATIN1, (const char *) src, len); + } } } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c index 578f5df4e7f..317daa2d5ee 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_johab); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ johab_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_JOHAB, PG_UTF8); - LocalToUtf(src, len, dest, - &johab_to_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = LocalToUtf(src, len, dest, + &johab_to_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_johab(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_JOHAB); - UtfToLocal(src, len, dest, - &johab_from_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = UtfToLocal(src, len, dest, + &johab_from_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c index dd9fc2975ad..4c9348aba59 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ sjis_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_UTF8); - LocalToUtf(src, len, dest, - &sjis_to_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = LocalToUtf(src, len, dest, + &sjis_to_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SJIS); - UtfToLocal(src, len, dest, - &sjis_from_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = UtfToLocal(src, len, dest, + &sjis_from_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c index 4bcc886d674..1fffdc5930c 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_shift_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ shift_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &shift_jis_2004_to_unicode_tree, - LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = LocalToUtf(src, len, dest, + &shift_jis_2004_to_unicode_tree, + LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SHIFT_JIS_2004); - UtfToLocal(src, len, dest, - &shift_jis_2004_from_unicode_tree, - ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = UtfToLocal(src, len, dest, + &shift_jis_2004_from_unicode_tree, + ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c index c8e512994a1..d9471dad097 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_uhc); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ uhc_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UHC, PG_UTF8); - LocalToUtf(src, len, dest, - &uhc_to_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = LocalToUtf(src, len, dest, + &uhc_to_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_uhc(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_UHC); - UtfToLocal(src, len, dest, - &uhc_from_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = UtfToLocal(src, len, dest, + &uhc_from_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c index 0c9493dee56..110ba5677d0 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c @@ -48,8 +48,11 @@ PG_FUNCTION_INFO_V1(utf8_to_win); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -81,6 +84,7 @@ win_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -89,12 +93,15 @@ win_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -103,7 +110,7 @@ win_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -113,6 +120,7 @@ utf8_to_win(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -121,12 +129,15 @@ utf8_to_win(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -135,5 +146,5 @@ utf8_to_win(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/mbutils.c b/src/backend/utils/mb/mbutils.c index 2578573b0ab..65753860e35 100644 --- a/src/backend/utils/mb/mbutils.c +++ b/src/backend/utils/mb/mbutils.c @@ -406,12 +406,13 @@ pg_do_encoding_conversion(unsigned char *src, int len, MemoryContextAllocHuge(CurrentMemoryContext, (Size) len * MAX_CONVERSION_GROWTH + 1); - OidFunctionCall5(proc, - Int32GetDatum(src_encoding), - Int32GetDatum(dest_encoding), - CStringGetDatum(src), - CStringGetDatum(result), - Int32GetDatum(len)); + (void) OidFunctionCall6(proc, + Int32GetDatum(src_encoding), + Int32GetDatum(dest_encoding), + CStringGetDatum(src), + CStringGetDatum(result), + Int32GetDatum(len), + BoolGetDatum(false)); /* * If the result is large, it's worth repalloc'ing to release any extra @@ -849,12 +850,13 @@ pg_unicode_to_server(pg_wchar c, unsigned char *s) c_as_utf8[c_as_utf8_len] = '\0'; /* Convert, or throw error if we can't */ - FunctionCall5(Utf8ToServerConvProc, + FunctionCall6(Utf8ToServerConvProc, Int32GetDatum(PG_UTF8), Int32GetDatum(server_encoding), CStringGetDatum(c_as_utf8), CStringGetDatum(s), - Int32GetDatum(c_as_utf8_len)); + Int32GetDatum(c_as_utf8_len), + BoolGetDatum(false)); } diff --git a/src/bin/pg_upgrade/check.c b/src/bin/pg_upgrade/check.c index 43fc297eb69..ee6be95b08d 100644 --- a/src/bin/pg_upgrade/check.c +++ b/src/bin/pg_upgrade/check.c @@ -28,6 +28,7 @@ static void check_for_reg_data_type_usage(ClusterInfo *cluster); static void check_for_jsonb_9_4_usage(ClusterInfo *cluster); static void check_for_pg_role_prefix(ClusterInfo *cluster); static void check_for_new_tablespace_dir(ClusterInfo *new_cluster); +static void check_for_user_defined_encoding_conversions(ClusterInfo *cluster); static char *get_canonical_locale_name(int category, const char *locale); @@ -102,6 +103,15 @@ check_and_dump_old_cluster(bool live_check) check_for_reg_data_type_usage(&old_cluster); check_for_isn_and_int8_passing_mismatch(&old_cluster); + /* + * PG 14 changed the function signature of encoding conversion functions. + * Conversions from older versions cannot be upgraded automatically + * because the user-defined functions used by the encoding conversions + * need to changed to match the new signature. + */ + if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1300) + check_for_user_defined_encoding_conversions(&old_cluster); + /* * Pre-PG 14 allowed user defined postfix operators, which are not * supported anymore. Verify there are none, iff applicable. @@ -1268,6 +1278,91 @@ check_for_pg_role_prefix(ClusterInfo *cluster) check_ok(); } +/* + * Verify that no user-defined encoding conversions exist. + */ +static void +check_for_user_defined_encoding_conversions(ClusterInfo *cluster) +{ + int dbnum; + FILE *script = NULL; + bool found = false; + char output_path[MAXPGPATH]; + + prep_status("Checking for user-defined encoding conversions"); + + snprintf(output_path, sizeof(output_path), + "encoding_conversions.txt"); + + /* Find any user defined encoding conversions */ + for (dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++) + { + PGresult *res; + bool db_used = false; + int ntups; + int rowno; + int i_conoid, + i_conname, + i_nspname; + DbInfo *active_db = &cluster->dbarr.dbs[dbnum]; + PGconn *conn = connectToServer(cluster, active_db->db_name); + + /* + * The query below hardcodes FirstNormalObjectId as 16384 rather than + * interpolating that C #define into the query because, if that + * #define is ever changed, the cutoff we want to use is the value + * used by pre-version 14 servers, not that of some future version. + */ + res = executeQueryOrDie(conn, + "SELECT c.oid as conoid, c.conname, n.nspname " + "FROM pg_catalog.pg_conversion c, " + " pg_catalog.pg_namespace n " + "WHERE c.connamespace = n.oid AND " + " c.oid >= 16384"); + ntups = PQntuples(res); + i_conoid = PQfnumber(res, "conoid"); + i_conname = PQfnumber(res, "conname"); + i_nspname = PQfnumber(res, "nspname"); + for (rowno = 0; rowno < ntups; rowno++) + { + found = true; + if (script == NULL && + (script = fopen_priv(output_path, "w")) == NULL) + pg_fatal("could not open file \"%s\": %s\n", + output_path, strerror(errno)); + if (!db_used) + { + fprintf(script, "In database: %s\n", active_db->db_name); + db_used = true; + } + fprintf(script, " (oid=%s) %s.%s\n", + PQgetvalue(res, rowno, i_conoid), + PQgetvalue(res, rowno, i_nspname), + PQgetvalue(res, rowno, i_conname)); + } + + PQclear(res); + + PQfinish(conn); + } + + if (script) + fclose(script); + + if (found) + { + pg_log(PG_REPORT, "fatal\n"); + pg_fatal("Your installation contains user-defined encoding conversions.\n" + "The conversion function parameters changed in PostgreSQL version 14\n" + "so this cluster cannot currently be upgraded. You can remove the\n" + "encoding conversions in the old cluster and restart the upgrade.\n" + "A list of user-defined encoding conversions is in the file:\n" + " %s\n\n", output_path); + } + else + check_ok(); +} + /* * get_canonical_locale_name diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index f8174061ef3..75b829e8514 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10766,388 +10766,388 @@ # conversion functions { oid => '4302', descr => 'internal conversion function for KOI8R to MULE_INTERNAL', - proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_mic', + proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4303', descr => 'internal conversion function for MULE_INTERNAL to KOI8R', - proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_koi8r', + proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4304', descr => 'internal conversion function for ISO-8859-5 to MULE_INTERNAL', - proname => 'iso_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_mic', + proname => 'iso_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4305', descr => 'internal conversion function for MULE_INTERNAL to ISO-8859-5', - proname => 'mic_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_iso', + proname => 'mic_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4306', descr => 'internal conversion function for WIN1251 to MULE_INTERNAL', - proname => 'win1251_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_mic', + proname => 'win1251_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4307', descr => 'internal conversion function for MULE_INTERNAL to WIN1251', - proname => 'mic_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1251', + proname => 'mic_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4308', descr => 'internal conversion function for WIN866 to MULE_INTERNAL', - proname => 'win866_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_mic', + proname => 'win866_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4309', descr => 'internal conversion function for MULE_INTERNAL to WIN866', - proname => 'mic_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win866', + proname => 'mic_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4310', descr => 'internal conversion function for KOI8R to WIN1251', - proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4311', descr => 'internal conversion function for WIN1251 to KOI8R', - proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4312', descr => 'internal conversion function for KOI8R to WIN866', - proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_win866', + proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4313', descr => 'internal conversion function for WIN866 to KOI8R', - proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_koi8r', + proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4314', descr => 'internal conversion function for WIN866 to WIN1251', - proname => 'win866_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win866_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4315', descr => 'internal conversion function for WIN1251 to WIN866', - proname => 'win1251_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4316', descr => 'internal conversion function for ISO-8859-5 to KOI8R', - proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_koi8r', + proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4317', descr => 'internal conversion function for KOI8R to ISO-8859-5', - proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_iso', + proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4318', descr => 'internal conversion function for ISO-8859-5 to WIN1251', - proname => 'iso_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win1251', + proname => 'iso_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4319', descr => 'internal conversion function for WIN1251 to ISO-8859-5', - proname => 'win1251_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_iso', + proname => 'win1251_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4320', descr => 'internal conversion function for ISO-8859-5 to WIN866', - proname => 'iso_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win866', + proname => 'iso_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4321', descr => 'internal conversion function for WIN866 to ISO-8859-5', - proname => 'win866_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_iso', + proname => 'win866_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4322', descr => 'internal conversion function for EUC_CN to MULE_INTERNAL', - proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_mic', + proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_mic', probin => '$libdir/euc_cn_and_mic' }, { oid => '4323', descr => 'internal conversion function for MULE_INTERNAL to EUC_CN', - proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_cn', + proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_cn', probin => '$libdir/euc_cn_and_mic' }, { oid => '4324', descr => 'internal conversion function for EUC_JP to SJIS', - proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_sjis', + proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4325', descr => 'internal conversion function for SJIS to EUC_JP', - proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_euc_jp', + proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4326', descr => 'internal conversion function for EUC_JP to MULE_INTERNAL', - proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_mic', + proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4327', descr => 'internal conversion function for SJIS to MULE_INTERNAL', - proname => 'sjis_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_mic', + proname => 'sjis_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4328', descr => 'internal conversion function for MULE_INTERNAL to EUC_JP', - proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_jp', + proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4329', descr => 'internal conversion function for MULE_INTERNAL to SJIS', - proname => 'mic_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_sjis', + proname => 'mic_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4330', descr => 'internal conversion function for EUC_KR to MULE_INTERNAL', - proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_mic', + proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_mic', probin => '$libdir/euc_kr_and_mic' }, { oid => '4331', descr => 'internal conversion function for MULE_INTERNAL to EUC_KR', - proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_kr', + proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_kr', probin => '$libdir/euc_kr_and_mic' }, { oid => '4332', descr => 'internal conversion function for EUC_TW to BIG5', - proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_big5', + proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4333', descr => 'internal conversion function for BIG5 to EUC_TW', - proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_euc_tw', + proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4334', descr => 'internal conversion function for EUC_TW to MULE_INTERNAL', - proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_mic', + proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4335', descr => 'internal conversion function for BIG5 to MULE_INTERNAL', - proname => 'big5_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_mic', + proname => 'big5_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4336', descr => 'internal conversion function for MULE_INTERNAL to EUC_TW', - proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_tw', + proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4337', descr => 'internal conversion function for MULE_INTERNAL to BIG5', - proname => 'mic_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_big5', + proname => 'mic_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4338', descr => 'internal conversion function for LATIN2 to MULE_INTERNAL', - proname => 'latin2_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin2_to_mic', + proname => 'latin2_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4339', descr => 'internal conversion function for MULE_INTERNAL to LATIN2', - proname => 'mic_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin2', + proname => 'mic_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4340', descr => 'internal conversion function for WIN1250 to MULE_INTERNAL', - proname => 'win1250_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1250_to_mic', + proname => 'win1250_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4341', descr => 'internal conversion function for MULE_INTERNAL to WIN1250', - proname => 'mic_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1250', + proname => 'mic_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4342', descr => 'internal conversion function for LATIN2 to WIN1250', - proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4343', descr => 'internal conversion function for WIN1250 to LATIN2', - proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4344', descr => 'internal conversion function for LATIN1 to MULE_INTERNAL', - proname => 'latin1_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin1_to_mic', + proname => 'latin1_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin1_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4345', descr => 'internal conversion function for MULE_INTERNAL to LATIN1', - proname => 'mic_to_latin1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin1', + proname => 'mic_to_latin1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin1', probin => '$libdir/latin_and_mic' }, { oid => '4346', descr => 'internal conversion function for LATIN3 to MULE_INTERNAL', - proname => 'latin3_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin3_to_mic', + proname => 'latin3_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin3_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4347', descr => 'internal conversion function for MULE_INTERNAL to LATIN3', - proname => 'mic_to_latin3', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin3', + proname => 'mic_to_latin3', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin3', probin => '$libdir/latin_and_mic' }, { oid => '4348', descr => 'internal conversion function for LATIN4 to MULE_INTERNAL', - proname => 'latin4_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin4_to_mic', + proname => 'latin4_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin4_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4349', descr => 'internal conversion function for MULE_INTERNAL to LATIN4', - proname => 'mic_to_latin4', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin4', + proname => 'mic_to_latin4', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin4', probin => '$libdir/latin_and_mic' }, { oid => '4352', descr => 'internal conversion function for BIG5 to UTF8', - proname => 'big5_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_utf8', + proname => 'big5_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_utf8', probin => '$libdir/utf8_and_big5' }, { oid => '4353', descr => 'internal conversion function for UTF8 to BIG5', - proname => 'utf8_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_big5', + proname => 'utf8_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_big5', probin => '$libdir/utf8_and_big5' }, { oid => '4354', descr => 'internal conversion function for UTF8 to KOI8R', - proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8r', + proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8r', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4355', descr => 'internal conversion function for KOI8R to UTF8', - proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_utf8', + proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4356', descr => 'internal conversion function for UTF8 to KOI8U', - proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8u', + proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8u', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4357', descr => 'internal conversion function for KOI8U to UTF8', - proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8u_to_utf8', + proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8u_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4358', descr => 'internal conversion function for UTF8 to WIN', - proname => 'utf8_to_win', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_win', + proname => 'utf8_to_win', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_win', probin => '$libdir/utf8_and_win' }, { oid => '4359', descr => 'internal conversion function for WIN to UTF8', - proname => 'win_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win_to_utf8', + proname => 'win_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win_to_utf8', probin => '$libdir/utf8_and_win' }, { oid => '4360', descr => 'internal conversion function for EUC_CN to UTF8', - proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_utf8', + proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_utf8', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4361', descr => 'internal conversion function for UTF8 to EUC_CN', - proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_cn', + proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_cn', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4362', descr => 'internal conversion function for EUC_JP to UTF8', - proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_utf8', + proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_utf8', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4363', descr => 'internal conversion function for UTF8 to EUC_JP', - proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_jp', + proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jp', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4364', descr => 'internal conversion function for EUC_KR to UTF8', - proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_utf8', + proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_utf8', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4365', descr => 'internal conversion function for UTF8 to EUC_KR', - proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_kr', + proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_kr', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4366', descr => 'internal conversion function for EUC_TW to UTF8', - proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_utf8', + proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_utf8', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4367', descr => 'internal conversion function for UTF8 to EUC_TW', - proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_tw', + proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_tw', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4368', descr => 'internal conversion function for GB18030 to UTF8', - proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gb18030_to_utf8', + proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gb18030_to_utf8', probin => '$libdir/utf8_and_gb18030' }, { oid => '4369', descr => 'internal conversion function for UTF8 to GB18030', - proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gb18030', + proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gb18030', probin => '$libdir/utf8_and_gb18030' }, { oid => '4370', descr => 'internal conversion function for GBK to UTF8', - proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gbk_to_utf8', + proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gbk_to_utf8', probin => '$libdir/utf8_and_gbk' }, { oid => '4371', descr => 'internal conversion function for UTF8 to GBK', - proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gbk', + proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gbk', probin => '$libdir/utf8_and_gbk' }, { oid => '4372', descr => 'internal conversion function for UTF8 to ISO-8859 2-16', - proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_iso8859', + proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859', probin => '$libdir/utf8_and_iso8859' }, { oid => '4373', descr => 'internal conversion function for ISO-8859 2-16 to UTF8', - proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso8859_to_utf8', + proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_to_utf8', probin => '$libdir/utf8_and_iso8859' }, { oid => '4374', descr => 'internal conversion function for LATIN1 to UTF8', - proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_1_to_utf8', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4375', descr => 'internal conversion function for UTF8 to LATIN1', - proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859_1', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4376', descr => 'internal conversion function for JOHAB to UTF8', - proname => 'johab_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'johab_to_utf8', + proname => 'johab_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'johab_to_utf8', probin => '$libdir/utf8_and_johab' }, { oid => '4377', descr => 'internal conversion function for UTF8 to JOHAB', - proname => 'utf8_to_johab', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_johab', + proname => 'utf8_to_johab', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_johab', probin => '$libdir/utf8_and_johab' }, { oid => '4378', descr => 'internal conversion function for SJIS to UTF8', - proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_utf8', + proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_utf8', probin => '$libdir/utf8_and_sjis' }, { oid => '4379', descr => 'internal conversion function for UTF8 to SJIS', - proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_sjis', + proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_sjis', probin => '$libdir/utf8_and_sjis' }, { oid => '4380', descr => 'internal conversion function for UHC to UTF8', - proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'uhc_to_utf8', + proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'uhc_to_utf8', probin => '$libdir/utf8_and_uhc' }, { oid => '4381', descr => 'internal conversion function for UTF8 to UHC', - proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_uhc', + proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_uhc', probin => '$libdir/utf8_and_uhc' }, { oid => '4382', descr => 'internal conversion function for EUC_JIS_2004 to UTF8', - proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_utf8', probin => '$libdir/utf8_and_euc2004' }, { oid => '4383', descr => 'internal conversion function for UTF8 to EUC_JIS_2004', - proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jis_2004', probin => '$libdir/utf8_and_euc2004' }, { oid => '4384', descr => 'internal conversion function for SHIFT_JIS_2004 to UTF8', - proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_utf8', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4385', descr => 'internal conversion function for UTF8 to SHIFT_JIS_2004', - proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_shift_jis_2004', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4386', descr => 'internal conversion function for EUC_JIS_2004 to SHIFT_JIS_2004', proname => 'euc_jis_2004_to_shift_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_shift_jis_2004', probin => '$libdir/euc2004_sjis2004' }, { oid => '4387', descr => 'internal conversion function for SHIFT_JIS_2004 to EUC_JIS_2004', proname => 'shift_jis_2004_to_euc_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_euc_jis_2004', probin => '$libdir/euc2004_sjis2004' }, diff --git a/src/include/mb/pg_wchar.h b/src/include/mb/pg_wchar.h index 64b22e4b0d4..346a41a1f3d 100644 --- a/src/include/mb/pg_wchar.h +++ b/src/include/mb/pg_wchar.h @@ -627,18 +627,18 @@ extern void pg_unicode_to_server(pg_wchar c, unsigned char *s); extern unsigned short BIG5toCNS(unsigned short big5, unsigned char *lc); extern unsigned short CNStoBIG5(unsigned short cns, unsigned char lc); -extern void UtfToLocal(const unsigned char *utf, int len, - unsigned char *iso, - const pg_mb_radix_tree *map, - const pg_utf_to_local_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); -extern void LocalToUtf(const unsigned char *iso, int len, - unsigned char *utf, - const pg_mb_radix_tree *map, - const pg_local_to_utf_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); +extern int UtfToLocal(const unsigned char *utf, int len, + unsigned char *iso, + const pg_mb_radix_tree *map, + const pg_utf_to_local_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); +extern int LocalToUtf(const unsigned char *iso, int len, + unsigned char *utf, + const pg_mb_radix_tree *map, + const pg_local_to_utf_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); extern bool pg_verifymbstr(const char *mbstr, int len, bool noError); extern bool pg_verify_mbstr(int encoding, const char *mbstr, int len, @@ -656,18 +656,19 @@ extern void report_invalid_encoding(int encoding, const char *mbstr, int len) pg extern void report_untranslatable_char(int src_encoding, int dest_encoding, const char *mbstr, int len) pg_attribute_noreturn(); -extern void local2local(const unsigned char *l, unsigned char *p, int len, - int src_encoding, int dest_encoding, const unsigned char *tab); -extern void latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding); -extern void mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding); -extern void latin2mic_with_table(const unsigned char *l, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); -extern void mic2latin_with_table(const unsigned char *mic, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); +extern int local2local(const unsigned char *l, unsigned char *p, int len, + int src_encoding, int dest_encoding, const unsigned char *tab, + bool noError); +extern int latin2mic(const unsigned char *l, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int mic2latin(const unsigned char *mic, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int latin2mic_with_table(const unsigned char *l, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); +extern int mic2latin_with_table(const unsigned char *mic, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); #ifdef WIN32 extern WCHAR *pgwin32_message_to_UTF16(const char *str, int len, int *utf16len); diff --git a/src/test/regress/expected/opr_sanity.out b/src/test/regress/expected/opr_sanity.out index 254ca06d3dd..23ba60e395f 100644 --- a/src/test/regress/expected/opr_sanity.out +++ b/src/test/regress/expected/opr_sanity.out @@ -1052,13 +1052,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); oid | proname | oid | conname -----+---------+-----+--------- (0 rows) diff --git a/src/test/regress/sql/opr_sanity.sql b/src/test/regress/sql/opr_sanity.sql index bbd3834b634..04691745981 100644 --- a/src/test/regress/sql/opr_sanity.sql +++ b/src/test/regress/sql/opr_sanity.sql @@ -556,13 +556,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); -- Check for conprocs that don't perform the specific conversion that -- pg_conversion alleges they do, by trying to invoke each conversion -- 2.29.2 --------------39E46EF15EBFAA37D53332E5 Content-Type: text/x-patch; charset=UTF-8; name="v3-0003-Add-tests-for-the-new-noError-variants-of-built-i.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="v3-0003-Add-tests-for-the-new-noError-variants-of-built-i.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 34+ messages in thread
* [PATCH v3 2/5] Change conversion function signature. @ 2021-01-28 16:42 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 34+ messages in thread From: Heikki Linnakangas @ 2021-01-28 16:42 UTC (permalink / raw) Add a 'noError' argument, so that we can try to convert a buffer without knowing the character boundaries beforehand. The functions now need to return the number of input bytes successfully converted. This is is a backwards-incompatible change, if you have created a custom encoding conversion with CREATE CONVERSION. This adds a check to pg_upgrade for that, refusing the upgrade if there are any user-defined encoding conversions. --- doc/src/sgml/ref/create_conversion.sgml | 5 +- src/backend/commands/conversioncmds.c | 27 +- src/backend/utils/error/elog.c | 2 + src/backend/utils/mb/conv.c | 112 +++++- .../cyrillic_and_mic/cyrillic_and_mic.c | 127 ++++--- .../euc2004_sjis2004/euc2004_sjis2004.c | 96 ++++- .../euc_cn_and_mic/euc_cn_and_mic.c | 57 ++- .../euc_jp_and_sjis/euc_jp_and_sjis.c | 153 ++++++-- .../euc_kr_and_mic/euc_kr_and_mic.c | 57 ++- .../euc_tw_and_big5/euc_tw_and_big5.c | 165 +++++++-- .../latin2_and_win1250/latin2_and_win1250.c | 49 ++- .../latin_and_mic/latin_and_mic.c | 43 ++- .../utf8_and_big5/utf8_and_big5.c | 37 +- .../utf8_and_cyrillic/utf8_and_cyrillic.c | 67 ++-- .../utf8_and_euc2004/utf8_and_euc2004.c | 37 +- .../utf8_and_euc_cn/utf8_and_euc_cn.c | 37 +- .../utf8_and_euc_jp/utf8_and_euc_jp.c | 37 +- .../utf8_and_euc_kr/utf8_and_euc_kr.c | 37 +- .../utf8_and_euc_tw/utf8_and_euc_tw.c | 37 +- .../utf8_and_gb18030/utf8_and_gb18030.c | 37 +- .../utf8_and_gbk/utf8_and_gbk.c | 37 +- .../utf8_and_iso8859/utf8_and_iso8859.c | 43 ++- .../utf8_and_iso8859_1/utf8_and_iso8859_1.c | 27 +- .../utf8_and_johab/utf8_and_johab.c | 37 +- .../utf8_and_sjis/utf8_and_sjis.c | 37 +- .../utf8_and_sjis2004/utf8_and_sjis2004.c | 37 +- .../utf8_and_uhc/utf8_and_uhc.c | 37 +- .../utf8_and_win/utf8_and_win.c | 43 ++- src/backend/utils/mb/mbutils.c | 18 +- src/bin/pg_upgrade/check.c | 95 +++++ src/include/catalog/pg_proc.dat | 332 +++++++++--------- src/include/mb/pg_wchar.h | 49 +-- src/test/regress/expected/opr_sanity.out | 7 +- src/test/regress/sql/opr_sanity.sql | 7 +- 34 files changed, 1390 insertions(+), 635 deletions(-) diff --git a/doc/src/sgml/ref/create_conversion.sgml b/doc/src/sgml/ref/create_conversion.sgml index e7700fecfc5..f014a676c88 100644 --- a/doc/src/sgml/ref/create_conversion.sgml +++ b/doc/src/sgml/ref/create_conversion.sgml @@ -117,8 +117,9 @@ conv_proc( integer, -- destination encoding ID cstring, -- source string (null terminated C string) internal, -- destination (fill with a null terminated C string) - integer -- source string length -) RETURNS void; + integer, -- source string length + boolean -- if true, don't throw an error if conversion fails +) RETURNS integer; </programlisting></para> </listitem> </varlistentry> diff --git a/src/backend/commands/conversioncmds.c b/src/backend/commands/conversioncmds.c index f7ff321de71..d2041466911 100644 --- a/src/backend/commands/conversioncmds.c +++ b/src/backend/commands/conversioncmds.c @@ -45,8 +45,9 @@ CreateConversionCommand(CreateConversionStmt *stmt) const char *from_encoding_name = stmt->for_encoding_name; const char *to_encoding_name = stmt->to_encoding_name; List *func_name = stmt->func_name; - static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID}; + static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID, BOOLOID}; char result[1]; + Datum funcresult; /* Convert list of names to a name and namespace */ namespaceId = QualifiedNameGetCreationNamespace(stmt->conversion_name, @@ -92,8 +93,8 @@ CreateConversionCommand(CreateConversionStmt *stmt) funcoid = LookupFuncName(func_name, sizeof(funcargs) / sizeof(Oid), funcargs, false); - /* Check it returns VOID, else it's probably the wrong function */ - if (get_func_rettype(funcoid) != VOIDOID) + /* Check it returns int4, else it's probably the wrong function */ + if (get_func_rettype(funcoid) != INT4OID) ereport(ERROR, (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), errmsg("encoding conversion function %s must return type %s", @@ -111,12 +112,20 @@ CreateConversionCommand(CreateConversionStmt *stmt) * string; the conversion function should throw an error if it can't * perform the requested conversion. */ - OidFunctionCall5(funcoid, - Int32GetDatum(from_encoding), - Int32GetDatum(to_encoding), - CStringGetDatum(""), - CStringGetDatum(result), - Int32GetDatum(0)); + funcresult = OidFunctionCall6(funcoid, + Int32GetDatum(from_encoding), + Int32GetDatum(to_encoding), + CStringGetDatum(""), + CStringGetDatum(result), + Int32GetDatum(0), + BoolGetDatum(false)); + + /* The function should return 0 for empty input. Might as well check that, too. */ + if (DatumGetInt32(funcresult) != 0) + ereport(ERROR, + (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), + errmsg("encoding conversion function %s returned incorrect result for empty input", + NameListToString(func_name)))); /* * All seem ok, go ahead (possible failure would be a duplicate conversion diff --git a/src/backend/utils/error/elog.c b/src/backend/utils/error/elog.c index 80c26724612..762f77d533c 100644 --- a/src/backend/utils/error/elog.c +++ b/src/backend/utils/error/elog.c @@ -2280,6 +2280,8 @@ write_console(const char *line, int len) * Conversion on non-win32 platforms is not implemented yet. It requires * non-throw version of pg_do_encoding_conversion(), that converts * unconvertable characters to '?' without errors. + * + * XXX: We have a no-throw version now. It doesn't convert to '?' though. */ #endif diff --git a/src/backend/utils/mb/conv.c b/src/backend/utils/mb/conv.c index a07b54bd3b8..b83358bc7a5 100644 --- a/src/backend/utils/mb/conv.c +++ b/src/backend/utils/mb/conv.c @@ -26,14 +26,16 @@ * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the target charset, or 0 if there is no equivalent code. */ -void +int local2local(const unsigned char *l, unsigned char *p, int len, int src_encoding, int dest_encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -41,7 +43,11 @@ local2local(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(src_encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -50,13 +56,19 @@ local2local(const unsigned char *l, if (c2) *p++ = c2; else + { + if (noError) + break; report_untranslatable_char(src_encoding, dest_encoding, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -67,17 +79,22 @@ local2local(const unsigned char *l, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = l; int c1; while (len > 0) { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (IS_HIGHBIT_SET(c1)) *p++ = lc; *p++ = c1; @@ -85,6 +102,8 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, len--; } *p = '\0'; + + return l - start; } /* @@ -95,17 +114,22 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -118,17 +142,27 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1])) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); + } *p++ = mic[1]; mic += 2; len -= 2; } } *p = '\0'; + + return mic - start; } @@ -144,14 +178,16 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the mule encoding, or 0 if there is no equivalent code. */ -void +int latin2mic_with_table(const unsigned char *l, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -159,7 +195,11 @@ latin2mic_with_table(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -171,13 +211,19 @@ latin2mic_with_table(const unsigned char *l, *p++ = c2; } else + { + if (noError) + break; report_untranslatable_char(encoding, PG_MULE_INTERNAL, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -192,14 +238,16 @@ latin2mic_with_table(const unsigned char *l, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the local charset, or 0 if there is no equivalent code. */ -void +int mic2latin_with_table(const unsigned char *mic, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = mic; unsigned char c1, c2; @@ -207,7 +255,11 @@ mic2latin_with_table(const unsigned char *mic, { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -220,11 +272,17 @@ mic2latin_with_table(const unsigned char *mic, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1]) || (c2 = tab[mic[1] - HIGHBIT]) == 0) { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); break; /* keep compiler quiet */ @@ -235,6 +293,8 @@ mic2latin_with_table(const unsigned char *mic, } } *p = '\0'; + + return mic - start; } /* @@ -425,17 +485,19 @@ pg_mb_radix_conv(const pg_mb_radix_tree *rt, * * See pg_wchar.h for more details about the data structures used here. */ -void +int UtfToLocal(const unsigned char *utf, int len, unsigned char *iso, const pg_mb_radix_tree *map, const pg_utf_to_local_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, bool noError) { uint32 iutf; int l; const pg_utf_to_local_combined *cp; + const unsigned char *start = utf; + const unsigned char *cur = utf; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -449,6 +511,8 @@ UtfToLocal(const unsigned char *utf, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*utf == '\0') break; @@ -584,15 +648,19 @@ UtfToLocal(const unsigned char *utf, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(PG_UTF8, encoding, (const char *) (utf - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(PG_UTF8, (const char *) utf, len); *iso = '\0'; + + return cur - start; } /* @@ -616,18 +684,24 @@ UtfToLocal(const unsigned char *utf, int len, * (if provided) is applied. An error is raised if no match is found. * * See pg_wchar.h for more details about the data structures used here. + * + * Returns the number of input bytes consumed. If noError is true, this can + * be less than 'len'. */ -void +int LocalToUtf(const unsigned char *iso, int len, unsigned char *utf, const pg_mb_radix_tree *map, const pg_local_to_utf_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, + bool noError) { uint32 iiso; int l; const pg_local_to_utf_combined *cp; + const unsigned char *start = iso; + const unsigned char *cur = iso; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -641,6 +715,8 @@ LocalToUtf(const unsigned char *iso, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*iso == '\0') break; @@ -723,13 +799,17 @@ LocalToUtf(const unsigned char *iso, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(encoding, PG_UTF8, (const char *) (iso - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(encoding, (const char *) iso, len); *utf = '\0'; + + return cur - start; } diff --git a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c index 4c5b02654de..368c2deb5e4 100644 --- a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c @@ -44,8 +44,11 @@ PG_FUNCTION_INFO_V1(win866_to_iso); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -306,12 +309,14 @@ koi8r_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -320,12 +325,14 @@ mic_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_KOI8R); - mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -334,12 +341,14 @@ iso_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -348,12 +357,14 @@ mic_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_ISO_8859_5); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -362,12 +373,14 @@ win1251_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -376,12 +389,14 @@ mic_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1251); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -390,12 +405,14 @@ win866_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -404,12 +421,14 @@ mic_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN866); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -418,12 +437,14 @@ koi8r_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN1251); - local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -432,12 +453,14 @@ win1251_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_KOI8R); - local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi); + converted = local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -446,12 +469,14 @@ koi8r_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN866); - local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -460,12 +485,14 @@ win866_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_KOI8R); - local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi); + converted = local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -474,12 +501,14 @@ win866_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_WIN1251); - local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251); + converted = local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -488,12 +517,14 @@ win1251_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_WIN866); - local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866); + converted = local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -502,12 +533,14 @@ iso_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_KOI8R); - local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -516,12 +549,14 @@ koi8r_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_ISO_8859_5); - local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso); + converted = local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -530,12 +565,14 @@ iso_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN1251); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -544,12 +581,14 @@ win1251_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso); + converted = local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -558,12 +597,14 @@ iso_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN866); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -572,10 +613,12 @@ win866_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso); + converted = local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c index 4d7fb116cfd..88529c644cf 100644 --- a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c @@ -19,8 +19,8 @@ PG_MODULE_MAGIC; PG_FUNCTION_INFO_V1(euc_jis_2004_to_shift_jis_2004); PG_FUNCTION_INFO_V1(shift_jis_2004_to_euc_jis_2004); -static void euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len); -static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len); +static int euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError); /* ---------- * conv_proc( @@ -28,8 +28,11 @@ static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -39,12 +42,14 @@ euc_jis_2004_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_SHIFT_JIS_2004); - euc_jis_20042shift_jis_2004(src, dest, len); + converted = euc_jis_20042shift_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -53,20 +58,23 @@ shift_jis_2004_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_EUC_JIS_2004); - shift_jis_20042euc_jis_2004(src, dest, len); + converted = shift_jis_20042euc_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_JIS_2004 -> SHIFT_JIS_2004 */ -static void -euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, ku, ten; @@ -79,8 +87,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -90,8 +102,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) l = pg_encoding_verifymbchar(PG_EUC_JIS_2004, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (c1 == SS2 && l == 2) /* JIS X 0201 kana? */ { @@ -121,8 +137,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) *p++ = (ku + 0x19b) >> 1; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } if (ku % 2) @@ -132,8 +152,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; @@ -149,8 +173,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ku >= 63 && ku <= 94) *p++ = (ku + 0x181) >> 1; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (ku % 2) { @@ -159,20 +187,30 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else - report_invalid_encoding(PG_EUC_JIS_2004, + { + if (noError) + break; + report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } euc += l; len -= l; } *p = '\0'; + + return euc - start; } /* @@ -212,9 +250,10 @@ get_ten(int b, int *ku) * SHIFT_JIS_2004 ---> EUC_JIS_2004 */ -static void -shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len) +static int +shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1; int ku, ten, @@ -230,8 +269,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -241,8 +284,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len l = pg_encoding_verifymbchar(PG_SHIFT_JIS_2004, (const char *) sjis, len); if (l < 0 || l > len) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf && l == 1) { @@ -266,8 +313,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x100; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xe0 && c1 <= 0xef) /* plane 1 62ku-94ku */ @@ -275,9 +326,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x180; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, - (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xf0 && c1 <= 0xf3) /* plane 2 @@ -286,8 +340,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } switch (c1) { case 0xf0: @@ -309,16 +367,24 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 == 0xf4 && kubun == 1) ku = 15; else ku = (c1 << 1) - 0x19a - kubun; } else + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (plane == 2) *p++ = SS3; @@ -330,4 +396,6 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c index e9bb896935f..a8da733803d 100644 --- a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_cn2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_cn(const unsigned char *mic, unsigned char *p, int len); +static int euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_cn_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_cn_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_MULE_INTERNAL); - euc_cn2mic(src, dest, len); + converted = euc_cn2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_CN); - mic2euc_cn(src, dest, len); + converted = mic2euc_cn(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_CN ---> MIC */ -static void -euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; while (len > 0) @@ -76,7 +84,11 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (len < 2 || !IS_HIGHBIT_SET(euc[1])) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = LC_GB2312_80; *p++ = c1; *p++ = euc[1]; @@ -86,21 +98,28 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_CN */ -static void -mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) @@ -109,11 +128,19 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (c1 != LC_GB2312_80) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_CN, (const char *) mic, len); + } if (len < 3 || !IS_HIGHBIT_SET(mic[1]) || !IS_HIGHBIT_SET(mic[2])) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } mic++; *p++ = *mic++; *p++ = *mic++; @@ -122,12 +149,18 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; } } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c index 5059f917a98..cc4817dc4cd 100644 --- a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c @@ -42,17 +42,20 @@ PG_FUNCTION_INFO_V1(mic_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void sjis2mic(const unsigned char *sjis, unsigned char *p, int len); -static void mic2sjis(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_jp(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len); -static void sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len); +static int sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError); +static int mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_jp_to_sjis(PG_FUNCTION_ARGS) @@ -60,12 +63,14 @@ euc_jp_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_SJIS); - euc_jp2sjis(src, dest, len); + converted = euc_jp2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -74,12 +79,14 @@ sjis_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_EUC_JP); - sjis2euc_jp(src, dest, len); + converted = sjis2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -88,12 +95,14 @@ euc_jp_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_MULE_INTERNAL); - euc_jp2mic(src, dest, len); + converted = euc_jp2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -102,12 +111,14 @@ mic_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_JP); - mic2euc_jp(src, dest, len); + converted = mic2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -116,12 +127,14 @@ sjis_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_MULE_INTERNAL); - sjis2mic(src, dest, len); + converted = sjis2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -130,20 +143,23 @@ mic_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_SJIS); - mic2sjis(src, dest, len); + converted = mic2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * SJIS ---> MIC */ -static void -sjis2mic(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -167,7 +183,11 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) * JIS X0208, X0212, user defined extended characters */ if (len < 2 || !ISSJISHEAD(c1) || !ISSJISTAIL(sjis[1])) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } c2 = sjis[1]; k = (c1 << 8) + c2; if (k >= 0xed40 && k < 0xf040) @@ -257,21 +277,28 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; } } *p = '\0'; + + return sjis - start; } /* * MIC ---> SJIS */ -static void -mic2sjis(const unsigned char *mic, unsigned char *p, int len) +static int +mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1, c2, k, @@ -284,8 +311,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -293,8 +324,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) *p++ = mic[1]; else if (c1 == LC_JISX0208) @@ -350,20 +385,27 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_SJIS, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP ---> MIC */ -static void -euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -374,8 +416,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -383,8 +429,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* 1 byte kana? */ *p++ = LC_JISX0201K; @@ -406,14 +456,17 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_JP */ -static void -mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -424,8 +477,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -433,8 +490,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) { *p++ = SS2; @@ -452,20 +513,27 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_JP, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP -> SJIS */ -static void -euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, c2, k; @@ -478,8 +546,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -487,8 +559,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* hankaku kana? */ @@ -551,14 +627,17 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * SJIS ---> EUC_JP */ -static void -sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -573,8 +652,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -582,8 +665,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_SJIS, (const char *) sjis, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf) { /* JIS X0201 (1 byte kana) */ @@ -680,4 +767,6 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c index ac823d6c270..a5b51617e52 100644 --- a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_kr2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_kr(const unsigned char *mic, unsigned char *p, int len); +static int euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_kr_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_kr_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_MULE_INTERNAL); - euc_kr2mic(src, dest, len); + converted = euc_kr2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_KR); - mic2euc_kr(src, dest, len); + converted = mic2euc_kr(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_KR ---> MIC */ -static void -euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -78,8 +86,12 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_KR, (const char *) euc, len); if (l != 2) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = LC_KS5601; *p++ = c1; *p++ = euc[1]; @@ -89,22 +101,29 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_KR */ -static void -mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -115,8 +134,12 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -124,18 +147,28 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_KS5601) { *p++ = mic[1]; *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_KR, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c index 66c242d7f36..ebb4e0acd53 100644 --- a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c @@ -32,17 +32,20 @@ PG_FUNCTION_INFO_V1(mic_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_tw2big5(const unsigned char *euc, unsigned char *p, int len); -static void big52euc_tw(const unsigned char *euc, unsigned char *p, int len); -static void big52mic(const unsigned char *big5, unsigned char *p, int len); -static void mic2big5(const unsigned char *mic, unsigned char *p, int len); -static void euc_tw2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_tw(const unsigned char *mic, unsigned char *p, int len); +static int euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52euc_tw(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError); +static int mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_tw_to_big5(PG_FUNCTION_ARGS) @@ -50,12 +53,14 @@ euc_tw_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_BIG5); - euc_tw2big5(src, dest, len); + converted = euc_tw2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -64,12 +69,14 @@ big5_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_EUC_TW); - big52euc_tw(src, dest, len); + converted = big52euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -78,12 +85,14 @@ euc_tw_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_MULE_INTERNAL); - euc_tw2mic(src, dest, len); + converted = euc_tw2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -92,12 +101,14 @@ mic_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_TW); - mic2euc_tw(src, dest, len); + converted = mic2euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -106,12 +117,14 @@ big5_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_MULE_INTERNAL); - big52mic(src, dest, len); + converted = big52mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -120,21 +133,24 @@ mic_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_BIG5); - mic2big5(src, dest, len); + converted = mic2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_TW ---> Big5 */ -static void -euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; unsigned char c1; unsigned short big5buf, cnsBuf; @@ -149,8 +165,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Verify and decode the next EUC_TW input character */ l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -171,8 +191,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Write it out in Big5 */ big5buf = CNStoBIG5(cnsBuf, lc); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_EUC_TW, PG_BIG5, (const char *) euc, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; @@ -182,22 +206,29 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * Big5 ---> EUC_TW */ -static void -big52euc_tw(const unsigned char *big5, unsigned char *p, int len) +static int +big52euc_tw(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -212,8 +243,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); @@ -237,8 +272,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_EUC_TW, (const char *) big5, len); + } big5 += l; len -= l; @@ -256,14 +295,17 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) } } *p = '\0'; + + return big5 - start; } /* * EUC_TW ---> MIC */ -static void -euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -274,8 +316,12 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -304,22 +350,29 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_TW */ -static void -mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -330,8 +383,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -339,8 +396,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1) { *p++ = mic[1]; @@ -362,20 +423,27 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[3]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_TW, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * Big5 ---> MIC */ -static void -big52mic(const unsigned char *big5, unsigned char *p, int len) +static int +big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -389,8 +457,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } *p++ = c1; big5++; len--; @@ -398,8 +470,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); if (lc != 0) @@ -412,20 +488,27 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_MULE_INTERNAL, (const char *) big5, len); + } big5 += l; len -= l; } *p = '\0'; + + return big5 - start; } /* * MIC ---> Big5 */ -static void -mic2big5(const unsigned char *mic, unsigned char *p, int len) +static int +mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -438,8 +521,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -447,8 +534,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1 || c1 == LC_CNS11643_2 || c1 == LCPRV2_B) { if (c1 == LCPRV2_B) @@ -462,16 +553,26 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } big5buf = CNStoBIG5(cnsBuf, c1); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c index 2e28e6780a5..8610fcb69aa 100644 --- a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c +++ b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(win1250_to_latin2); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -82,12 +85,14 @@ latin2_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -96,12 +101,14 @@ mic_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN2); - mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -110,13 +117,15 @@ win1250_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - win1250_2_iso88592); + converted = latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -125,13 +134,15 @@ mic_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1250); - mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - iso88592_2_win1250); + converted = mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -140,12 +151,15 @@ latin2_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_WIN1250); - local2local(src, dest, len, PG_LATIN2, PG_WIN1250, iso88592_2_win1250); + converted = local2local(src, dest, len, PG_LATIN2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -154,10 +168,13 @@ win1250_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_LATIN2); - local2local(src, dest, len, PG_WIN1250, PG_LATIN2, win1250_2_iso88592); + converted = local2local(src, dest, len, PG_WIN1250, PG_LATIN2, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c index bc651410f21..bff27d1c295 100644 --- a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(mic_to_latin4); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -42,12 +45,14 @@ latin1_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,12 +61,14 @@ mic_to_latin1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN1); - mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -70,12 +77,14 @@ latin3_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN3, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -84,12 +93,14 @@ mic_to_latin3(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN3); - mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,12 +109,14 @@ latin4_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN4, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -112,10 +125,12 @@ mic_to_latin4(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN4); - mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c index d6067cdc24e..3838b15cab9 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ big5_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_UTF8); - LocalToUtf(src, len, dest, - &big5_to_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = LocalToUtf(src, len, dest, + &big5_to_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_BIG5); - UtfToLocal(src, len, dest, - &big5_from_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = UtfToLocal(src, len, dest, + &big5_from_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c index ed90e8e682e..75719fe5f1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c @@ -33,8 +33,11 @@ PG_FUNCTION_INFO_V1(koi8u_to_utf8); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -44,16 +47,19 @@ utf8_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8R); - UtfToLocal(src, len, dest, - &koi8r_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = UtfToLocal(src, len, dest, + &koi8r_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -62,16 +68,19 @@ koi8r_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8r_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = LocalToUtf(src, len, dest, + &koi8r_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -80,16 +89,19 @@ utf8_to_koi8u(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8U); - UtfToLocal(src, len, dest, - &koi8u_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = UtfToLocal(src, len, dest, + &koi8u_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,14 +110,17 @@ koi8u_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8U, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8u_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = LocalToUtf(src, len, dest, + &koi8u_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c index d699affce47..5391001951a 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jis_2004_to_unicode_tree, - LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = LocalToUtf(src, len, dest, + &euc_jis_2004_to_unicode_tree, + LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JIS_2004); - UtfToLocal(src, len, dest, - &euc_jis_2004_from_unicode_tree, - ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = UtfToLocal(src, len, dest, + &euc_jis_2004_from_unicode_tree, + ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c index d7c0ba6a58b..c87d1bf2398 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_cn_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_cn_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = LocalToUtf(src, len, dest, + &euc_cn_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_CN); - UtfToLocal(src, len, dest, - &euc_cn_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = UtfToLocal(src, len, dest, + &euc_cn_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c index 13a3a23e77b..6a55134db21 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jp); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jp_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jp_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = LocalToUtf(src, len, dest, + &euc_jp_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JP); - UtfToLocal(src, len, dest, - &euc_jp_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = UtfToLocal(src, len, dest, + &euc_jp_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c index 1bbb8aaef7b..fe1924e2fec 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_kr_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_kr_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = LocalToUtf(src, len, dest, + &euc_kr_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_KR); - UtfToLocal(src, len, dest, - &euc_kr_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = UtfToLocal(src, len, dest, + &euc_kr_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c index 9830045dccd..68215659b57 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_tw); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_tw_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_tw_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = LocalToUtf(src, len, dest, + &euc_tw_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_TW); - UtfToLocal(src, len, dest, - &euc_tw_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = UtfToLocal(src, len, dest, + &euc_tw_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c index f86ecf27424..e1a59c39a4d 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c @@ -183,8 +183,11 @@ conv_utf8_to_18030(uint32 code) * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -193,16 +196,19 @@ gb18030_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GB18030, PG_UTF8); - LocalToUtf(src, len, dest, - &gb18030_to_unicode_tree, - NULL, 0, - conv_18030_to_utf8, - PG_GB18030); + converted = LocalToUtf(src, len, dest, + &gb18030_to_unicode_tree, + NULL, 0, + conv_18030_to_utf8, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -211,14 +217,17 @@ utf8_to_gb18030(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GB18030); - UtfToLocal(src, len, dest, - &gb18030_from_unicode_tree, - NULL, 0, - conv_utf8_to_18030, - PG_GB18030); + converted = UtfToLocal(src, len, dest, + &gb18030_from_unicode_tree, + NULL, 0, + conv_utf8_to_18030, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c index 2ab8b16c8a8..881386d5347 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_gbk); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ gbk_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GBK, PG_UTF8); - LocalToUtf(src, len, dest, - &gbk_to_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = LocalToUtf(src, len, dest, + &gbk_to_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_gbk(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GBK); - UtfToLocal(src, len, dest, - &gbk_from_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = UtfToLocal(src, len, dest, + &gbk_from_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c index 3e49f67ea2f..d93a521badf 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c @@ -52,8 +52,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -100,6 +103,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -108,12 +112,15 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -122,7 +129,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -132,6 +139,7 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -140,12 +148,15 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -154,5 +165,5 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c index 67e713cca11..8ac93604a1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c @@ -26,8 +26,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859_1); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -37,6 +40,8 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_UTF8); @@ -45,7 +50,11 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_LATIN1, (const char *) src, len); + } if (!IS_HIGHBIT_SET(c)) *dest++ = c; else @@ -58,7 +67,7 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } Datum @@ -67,6 +76,8 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c, c1; @@ -76,7 +87,11 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_UTF8, (const char *) src, len); + } /* fast path for ASCII-subset characters */ if (!IS_HIGHBIT_SET(c)) { @@ -102,11 +117,15 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) len -= 2; } else + { + if (noError) + break; report_untranslatable_char(PG_UTF8, PG_LATIN1, (const char *) src, len); + } } } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c index 578f5df4e7f..317daa2d5ee 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_johab); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ johab_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_JOHAB, PG_UTF8); - LocalToUtf(src, len, dest, - &johab_to_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = LocalToUtf(src, len, dest, + &johab_to_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_johab(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_JOHAB); - UtfToLocal(src, len, dest, - &johab_from_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = UtfToLocal(src, len, dest, + &johab_from_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c index dd9fc2975ad..4c9348aba59 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ sjis_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_UTF8); - LocalToUtf(src, len, dest, - &sjis_to_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = LocalToUtf(src, len, dest, + &sjis_to_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SJIS); - UtfToLocal(src, len, dest, - &sjis_from_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = UtfToLocal(src, len, dest, + &sjis_from_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c index 4bcc886d674..1fffdc5930c 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_shift_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ shift_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &shift_jis_2004_to_unicode_tree, - LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = LocalToUtf(src, len, dest, + &shift_jis_2004_to_unicode_tree, + LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SHIFT_JIS_2004); - UtfToLocal(src, len, dest, - &shift_jis_2004_from_unicode_tree, - ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = UtfToLocal(src, len, dest, + &shift_jis_2004_from_unicode_tree, + ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c index c8e512994a1..d9471dad097 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_uhc); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ uhc_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UHC, PG_UTF8); - LocalToUtf(src, len, dest, - &uhc_to_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = LocalToUtf(src, len, dest, + &uhc_to_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_uhc(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_UHC); - UtfToLocal(src, len, dest, - &uhc_from_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = UtfToLocal(src, len, dest, + &uhc_from_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c index 0c9493dee56..110ba5677d0 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c @@ -48,8 +48,11 @@ PG_FUNCTION_INFO_V1(utf8_to_win); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -81,6 +84,7 @@ win_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -89,12 +93,15 @@ win_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -103,7 +110,7 @@ win_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -113,6 +120,7 @@ utf8_to_win(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -121,12 +129,15 @@ utf8_to_win(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -135,5 +146,5 @@ utf8_to_win(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/mbutils.c b/src/backend/utils/mb/mbutils.c index 2578573b0ab..65753860e35 100644 --- a/src/backend/utils/mb/mbutils.c +++ b/src/backend/utils/mb/mbutils.c @@ -406,12 +406,13 @@ pg_do_encoding_conversion(unsigned char *src, int len, MemoryContextAllocHuge(CurrentMemoryContext, (Size) len * MAX_CONVERSION_GROWTH + 1); - OidFunctionCall5(proc, - Int32GetDatum(src_encoding), - Int32GetDatum(dest_encoding), - CStringGetDatum(src), - CStringGetDatum(result), - Int32GetDatum(len)); + (void) OidFunctionCall6(proc, + Int32GetDatum(src_encoding), + Int32GetDatum(dest_encoding), + CStringGetDatum(src), + CStringGetDatum(result), + Int32GetDatum(len), + BoolGetDatum(false)); /* * If the result is large, it's worth repalloc'ing to release any extra @@ -849,12 +850,13 @@ pg_unicode_to_server(pg_wchar c, unsigned char *s) c_as_utf8[c_as_utf8_len] = '\0'; /* Convert, or throw error if we can't */ - FunctionCall5(Utf8ToServerConvProc, + FunctionCall6(Utf8ToServerConvProc, Int32GetDatum(PG_UTF8), Int32GetDatum(server_encoding), CStringGetDatum(c_as_utf8), CStringGetDatum(s), - Int32GetDatum(c_as_utf8_len)); + Int32GetDatum(c_as_utf8_len), + BoolGetDatum(false)); } diff --git a/src/bin/pg_upgrade/check.c b/src/bin/pg_upgrade/check.c index 43fc297eb69..ee6be95b08d 100644 --- a/src/bin/pg_upgrade/check.c +++ b/src/bin/pg_upgrade/check.c @@ -28,6 +28,7 @@ static void check_for_reg_data_type_usage(ClusterInfo *cluster); static void check_for_jsonb_9_4_usage(ClusterInfo *cluster); static void check_for_pg_role_prefix(ClusterInfo *cluster); static void check_for_new_tablespace_dir(ClusterInfo *new_cluster); +static void check_for_user_defined_encoding_conversions(ClusterInfo *cluster); static char *get_canonical_locale_name(int category, const char *locale); @@ -102,6 +103,15 @@ check_and_dump_old_cluster(bool live_check) check_for_reg_data_type_usage(&old_cluster); check_for_isn_and_int8_passing_mismatch(&old_cluster); + /* + * PG 14 changed the function signature of encoding conversion functions. + * Conversions from older versions cannot be upgraded automatically + * because the user-defined functions used by the encoding conversions + * need to changed to match the new signature. + */ + if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1300) + check_for_user_defined_encoding_conversions(&old_cluster); + /* * Pre-PG 14 allowed user defined postfix operators, which are not * supported anymore. Verify there are none, iff applicable. @@ -1268,6 +1278,91 @@ check_for_pg_role_prefix(ClusterInfo *cluster) check_ok(); } +/* + * Verify that no user-defined encoding conversions exist. + */ +static void +check_for_user_defined_encoding_conversions(ClusterInfo *cluster) +{ + int dbnum; + FILE *script = NULL; + bool found = false; + char output_path[MAXPGPATH]; + + prep_status("Checking for user-defined encoding conversions"); + + snprintf(output_path, sizeof(output_path), + "encoding_conversions.txt"); + + /* Find any user defined encoding conversions */ + for (dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++) + { + PGresult *res; + bool db_used = false; + int ntups; + int rowno; + int i_conoid, + i_conname, + i_nspname; + DbInfo *active_db = &cluster->dbarr.dbs[dbnum]; + PGconn *conn = connectToServer(cluster, active_db->db_name); + + /* + * The query below hardcodes FirstNormalObjectId as 16384 rather than + * interpolating that C #define into the query because, if that + * #define is ever changed, the cutoff we want to use is the value + * used by pre-version 14 servers, not that of some future version. + */ + res = executeQueryOrDie(conn, + "SELECT c.oid as conoid, c.conname, n.nspname " + "FROM pg_catalog.pg_conversion c, " + " pg_catalog.pg_namespace n " + "WHERE c.connamespace = n.oid AND " + " c.oid >= 16384"); + ntups = PQntuples(res); + i_conoid = PQfnumber(res, "conoid"); + i_conname = PQfnumber(res, "conname"); + i_nspname = PQfnumber(res, "nspname"); + for (rowno = 0; rowno < ntups; rowno++) + { + found = true; + if (script == NULL && + (script = fopen_priv(output_path, "w")) == NULL) + pg_fatal("could not open file \"%s\": %s\n", + output_path, strerror(errno)); + if (!db_used) + { + fprintf(script, "In database: %s\n", active_db->db_name); + db_used = true; + } + fprintf(script, " (oid=%s) %s.%s\n", + PQgetvalue(res, rowno, i_conoid), + PQgetvalue(res, rowno, i_nspname), + PQgetvalue(res, rowno, i_conname)); + } + + PQclear(res); + + PQfinish(conn); + } + + if (script) + fclose(script); + + if (found) + { + pg_log(PG_REPORT, "fatal\n"); + pg_fatal("Your installation contains user-defined encoding conversions.\n" + "The conversion function parameters changed in PostgreSQL version 14\n" + "so this cluster cannot currently be upgraded. You can remove the\n" + "encoding conversions in the old cluster and restart the upgrade.\n" + "A list of user-defined encoding conversions is in the file:\n" + " %s\n\n", output_path); + } + else + check_ok(); +} + /* * get_canonical_locale_name diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index f8174061ef3..75b829e8514 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10766,388 +10766,388 @@ # conversion functions { oid => '4302', descr => 'internal conversion function for KOI8R to MULE_INTERNAL', - proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_mic', + proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4303', descr => 'internal conversion function for MULE_INTERNAL to KOI8R', - proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_koi8r', + proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4304', descr => 'internal conversion function for ISO-8859-5 to MULE_INTERNAL', - proname => 'iso_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_mic', + proname => 'iso_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4305', descr => 'internal conversion function for MULE_INTERNAL to ISO-8859-5', - proname => 'mic_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_iso', + proname => 'mic_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4306', descr => 'internal conversion function for WIN1251 to MULE_INTERNAL', - proname => 'win1251_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_mic', + proname => 'win1251_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4307', descr => 'internal conversion function for MULE_INTERNAL to WIN1251', - proname => 'mic_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1251', + proname => 'mic_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4308', descr => 'internal conversion function for WIN866 to MULE_INTERNAL', - proname => 'win866_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_mic', + proname => 'win866_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4309', descr => 'internal conversion function for MULE_INTERNAL to WIN866', - proname => 'mic_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win866', + proname => 'mic_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4310', descr => 'internal conversion function for KOI8R to WIN1251', - proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4311', descr => 'internal conversion function for WIN1251 to KOI8R', - proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4312', descr => 'internal conversion function for KOI8R to WIN866', - proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_win866', + proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4313', descr => 'internal conversion function for WIN866 to KOI8R', - proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_koi8r', + proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4314', descr => 'internal conversion function for WIN866 to WIN1251', - proname => 'win866_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win866_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4315', descr => 'internal conversion function for WIN1251 to WIN866', - proname => 'win1251_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4316', descr => 'internal conversion function for ISO-8859-5 to KOI8R', - proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_koi8r', + proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4317', descr => 'internal conversion function for KOI8R to ISO-8859-5', - proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_iso', + proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4318', descr => 'internal conversion function for ISO-8859-5 to WIN1251', - proname => 'iso_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win1251', + proname => 'iso_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4319', descr => 'internal conversion function for WIN1251 to ISO-8859-5', - proname => 'win1251_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_iso', + proname => 'win1251_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4320', descr => 'internal conversion function for ISO-8859-5 to WIN866', - proname => 'iso_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win866', + proname => 'iso_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4321', descr => 'internal conversion function for WIN866 to ISO-8859-5', - proname => 'win866_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_iso', + proname => 'win866_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4322', descr => 'internal conversion function for EUC_CN to MULE_INTERNAL', - proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_mic', + proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_mic', probin => '$libdir/euc_cn_and_mic' }, { oid => '4323', descr => 'internal conversion function for MULE_INTERNAL to EUC_CN', - proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_cn', + proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_cn', probin => '$libdir/euc_cn_and_mic' }, { oid => '4324', descr => 'internal conversion function for EUC_JP to SJIS', - proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_sjis', + proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4325', descr => 'internal conversion function for SJIS to EUC_JP', - proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_euc_jp', + proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4326', descr => 'internal conversion function for EUC_JP to MULE_INTERNAL', - proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_mic', + proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4327', descr => 'internal conversion function for SJIS to MULE_INTERNAL', - proname => 'sjis_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_mic', + proname => 'sjis_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4328', descr => 'internal conversion function for MULE_INTERNAL to EUC_JP', - proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_jp', + proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4329', descr => 'internal conversion function for MULE_INTERNAL to SJIS', - proname => 'mic_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_sjis', + proname => 'mic_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4330', descr => 'internal conversion function for EUC_KR to MULE_INTERNAL', - proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_mic', + proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_mic', probin => '$libdir/euc_kr_and_mic' }, { oid => '4331', descr => 'internal conversion function for MULE_INTERNAL to EUC_KR', - proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_kr', + proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_kr', probin => '$libdir/euc_kr_and_mic' }, { oid => '4332', descr => 'internal conversion function for EUC_TW to BIG5', - proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_big5', + proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4333', descr => 'internal conversion function for BIG5 to EUC_TW', - proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_euc_tw', + proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4334', descr => 'internal conversion function for EUC_TW to MULE_INTERNAL', - proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_mic', + proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4335', descr => 'internal conversion function for BIG5 to MULE_INTERNAL', - proname => 'big5_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_mic', + proname => 'big5_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4336', descr => 'internal conversion function for MULE_INTERNAL to EUC_TW', - proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_tw', + proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4337', descr => 'internal conversion function for MULE_INTERNAL to BIG5', - proname => 'mic_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_big5', + proname => 'mic_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4338', descr => 'internal conversion function for LATIN2 to MULE_INTERNAL', - proname => 'latin2_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin2_to_mic', + proname => 'latin2_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4339', descr => 'internal conversion function for MULE_INTERNAL to LATIN2', - proname => 'mic_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin2', + proname => 'mic_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4340', descr => 'internal conversion function for WIN1250 to MULE_INTERNAL', - proname => 'win1250_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1250_to_mic', + proname => 'win1250_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4341', descr => 'internal conversion function for MULE_INTERNAL to WIN1250', - proname => 'mic_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1250', + proname => 'mic_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4342', descr => 'internal conversion function for LATIN2 to WIN1250', - proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4343', descr => 'internal conversion function for WIN1250 to LATIN2', - proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4344', descr => 'internal conversion function for LATIN1 to MULE_INTERNAL', - proname => 'latin1_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin1_to_mic', + proname => 'latin1_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin1_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4345', descr => 'internal conversion function for MULE_INTERNAL to LATIN1', - proname => 'mic_to_latin1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin1', + proname => 'mic_to_latin1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin1', probin => '$libdir/latin_and_mic' }, { oid => '4346', descr => 'internal conversion function for LATIN3 to MULE_INTERNAL', - proname => 'latin3_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin3_to_mic', + proname => 'latin3_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin3_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4347', descr => 'internal conversion function for MULE_INTERNAL to LATIN3', - proname => 'mic_to_latin3', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin3', + proname => 'mic_to_latin3', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin3', probin => '$libdir/latin_and_mic' }, { oid => '4348', descr => 'internal conversion function for LATIN4 to MULE_INTERNAL', - proname => 'latin4_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin4_to_mic', + proname => 'latin4_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin4_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4349', descr => 'internal conversion function for MULE_INTERNAL to LATIN4', - proname => 'mic_to_latin4', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin4', + proname => 'mic_to_latin4', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin4', probin => '$libdir/latin_and_mic' }, { oid => '4352', descr => 'internal conversion function for BIG5 to UTF8', - proname => 'big5_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_utf8', + proname => 'big5_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_utf8', probin => '$libdir/utf8_and_big5' }, { oid => '4353', descr => 'internal conversion function for UTF8 to BIG5', - proname => 'utf8_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_big5', + proname => 'utf8_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_big5', probin => '$libdir/utf8_and_big5' }, { oid => '4354', descr => 'internal conversion function for UTF8 to KOI8R', - proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8r', + proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8r', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4355', descr => 'internal conversion function for KOI8R to UTF8', - proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_utf8', + proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4356', descr => 'internal conversion function for UTF8 to KOI8U', - proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8u', + proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8u', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4357', descr => 'internal conversion function for KOI8U to UTF8', - proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8u_to_utf8', + proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8u_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4358', descr => 'internal conversion function for UTF8 to WIN', - proname => 'utf8_to_win', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_win', + proname => 'utf8_to_win', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_win', probin => '$libdir/utf8_and_win' }, { oid => '4359', descr => 'internal conversion function for WIN to UTF8', - proname => 'win_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win_to_utf8', + proname => 'win_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win_to_utf8', probin => '$libdir/utf8_and_win' }, { oid => '4360', descr => 'internal conversion function for EUC_CN to UTF8', - proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_utf8', + proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_utf8', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4361', descr => 'internal conversion function for UTF8 to EUC_CN', - proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_cn', + proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_cn', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4362', descr => 'internal conversion function for EUC_JP to UTF8', - proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_utf8', + proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_utf8', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4363', descr => 'internal conversion function for UTF8 to EUC_JP', - proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_jp', + proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jp', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4364', descr => 'internal conversion function for EUC_KR to UTF8', - proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_utf8', + proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_utf8', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4365', descr => 'internal conversion function for UTF8 to EUC_KR', - proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_kr', + proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_kr', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4366', descr => 'internal conversion function for EUC_TW to UTF8', - proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_utf8', + proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_utf8', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4367', descr => 'internal conversion function for UTF8 to EUC_TW', - proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_tw', + proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_tw', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4368', descr => 'internal conversion function for GB18030 to UTF8', - proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gb18030_to_utf8', + proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gb18030_to_utf8', probin => '$libdir/utf8_and_gb18030' }, { oid => '4369', descr => 'internal conversion function for UTF8 to GB18030', - proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gb18030', + proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gb18030', probin => '$libdir/utf8_and_gb18030' }, { oid => '4370', descr => 'internal conversion function for GBK to UTF8', - proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gbk_to_utf8', + proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gbk_to_utf8', probin => '$libdir/utf8_and_gbk' }, { oid => '4371', descr => 'internal conversion function for UTF8 to GBK', - proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gbk', + proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gbk', probin => '$libdir/utf8_and_gbk' }, { oid => '4372', descr => 'internal conversion function for UTF8 to ISO-8859 2-16', - proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_iso8859', + proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859', probin => '$libdir/utf8_and_iso8859' }, { oid => '4373', descr => 'internal conversion function for ISO-8859 2-16 to UTF8', - proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso8859_to_utf8', + proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_to_utf8', probin => '$libdir/utf8_and_iso8859' }, { oid => '4374', descr => 'internal conversion function for LATIN1 to UTF8', - proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_1_to_utf8', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4375', descr => 'internal conversion function for UTF8 to LATIN1', - proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859_1', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4376', descr => 'internal conversion function for JOHAB to UTF8', - proname => 'johab_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'johab_to_utf8', + proname => 'johab_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'johab_to_utf8', probin => '$libdir/utf8_and_johab' }, { oid => '4377', descr => 'internal conversion function for UTF8 to JOHAB', - proname => 'utf8_to_johab', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_johab', + proname => 'utf8_to_johab', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_johab', probin => '$libdir/utf8_and_johab' }, { oid => '4378', descr => 'internal conversion function for SJIS to UTF8', - proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_utf8', + proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_utf8', probin => '$libdir/utf8_and_sjis' }, { oid => '4379', descr => 'internal conversion function for UTF8 to SJIS', - proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_sjis', + proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_sjis', probin => '$libdir/utf8_and_sjis' }, { oid => '4380', descr => 'internal conversion function for UHC to UTF8', - proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'uhc_to_utf8', + proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'uhc_to_utf8', probin => '$libdir/utf8_and_uhc' }, { oid => '4381', descr => 'internal conversion function for UTF8 to UHC', - proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_uhc', + proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_uhc', probin => '$libdir/utf8_and_uhc' }, { oid => '4382', descr => 'internal conversion function for EUC_JIS_2004 to UTF8', - proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_utf8', probin => '$libdir/utf8_and_euc2004' }, { oid => '4383', descr => 'internal conversion function for UTF8 to EUC_JIS_2004', - proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jis_2004', probin => '$libdir/utf8_and_euc2004' }, { oid => '4384', descr => 'internal conversion function for SHIFT_JIS_2004 to UTF8', - proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_utf8', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4385', descr => 'internal conversion function for UTF8 to SHIFT_JIS_2004', - proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_shift_jis_2004', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4386', descr => 'internal conversion function for EUC_JIS_2004 to SHIFT_JIS_2004', proname => 'euc_jis_2004_to_shift_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_shift_jis_2004', probin => '$libdir/euc2004_sjis2004' }, { oid => '4387', descr => 'internal conversion function for SHIFT_JIS_2004 to EUC_JIS_2004', proname => 'shift_jis_2004_to_euc_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_euc_jis_2004', probin => '$libdir/euc2004_sjis2004' }, diff --git a/src/include/mb/pg_wchar.h b/src/include/mb/pg_wchar.h index 64b22e4b0d4..346a41a1f3d 100644 --- a/src/include/mb/pg_wchar.h +++ b/src/include/mb/pg_wchar.h @@ -627,18 +627,18 @@ extern void pg_unicode_to_server(pg_wchar c, unsigned char *s); extern unsigned short BIG5toCNS(unsigned short big5, unsigned char *lc); extern unsigned short CNStoBIG5(unsigned short cns, unsigned char lc); -extern void UtfToLocal(const unsigned char *utf, int len, - unsigned char *iso, - const pg_mb_radix_tree *map, - const pg_utf_to_local_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); -extern void LocalToUtf(const unsigned char *iso, int len, - unsigned char *utf, - const pg_mb_radix_tree *map, - const pg_local_to_utf_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); +extern int UtfToLocal(const unsigned char *utf, int len, + unsigned char *iso, + const pg_mb_radix_tree *map, + const pg_utf_to_local_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); +extern int LocalToUtf(const unsigned char *iso, int len, + unsigned char *utf, + const pg_mb_radix_tree *map, + const pg_local_to_utf_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); extern bool pg_verifymbstr(const char *mbstr, int len, bool noError); extern bool pg_verify_mbstr(int encoding, const char *mbstr, int len, @@ -656,18 +656,19 @@ extern void report_invalid_encoding(int encoding, const char *mbstr, int len) pg extern void report_untranslatable_char(int src_encoding, int dest_encoding, const char *mbstr, int len) pg_attribute_noreturn(); -extern void local2local(const unsigned char *l, unsigned char *p, int len, - int src_encoding, int dest_encoding, const unsigned char *tab); -extern void latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding); -extern void mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding); -extern void latin2mic_with_table(const unsigned char *l, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); -extern void mic2latin_with_table(const unsigned char *mic, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); +extern int local2local(const unsigned char *l, unsigned char *p, int len, + int src_encoding, int dest_encoding, const unsigned char *tab, + bool noError); +extern int latin2mic(const unsigned char *l, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int mic2latin(const unsigned char *mic, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int latin2mic_with_table(const unsigned char *l, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); +extern int mic2latin_with_table(const unsigned char *mic, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); #ifdef WIN32 extern WCHAR *pgwin32_message_to_UTF16(const char *str, int len, int *utf16len); diff --git a/src/test/regress/expected/opr_sanity.out b/src/test/regress/expected/opr_sanity.out index 254ca06d3dd..23ba60e395f 100644 --- a/src/test/regress/expected/opr_sanity.out +++ b/src/test/regress/expected/opr_sanity.out @@ -1052,13 +1052,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); oid | proname | oid | conname -----+---------+-----+--------- (0 rows) diff --git a/src/test/regress/sql/opr_sanity.sql b/src/test/regress/sql/opr_sanity.sql index bbd3834b634..04691745981 100644 --- a/src/test/regress/sql/opr_sanity.sql +++ b/src/test/regress/sql/opr_sanity.sql @@ -556,13 +556,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); -- Check for conprocs that don't perform the specific conversion that -- pg_conversion alleges they do, by trying to invoke each conversion -- 2.29.2 --------------39E46EF15EBFAA37D53332E5 Content-Type: text/x-patch; charset=UTF-8; name="v3-0003-Add-tests-for-the-new-noError-variants-of-built-i.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="v3-0003-Add-tests-for-the-new-noError-variants-of-built-i.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 34+ messages in thread
* [PATCH v3 2/5] Change conversion function signature. @ 2021-01-28 16:42 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 34+ messages in thread From: Heikki Linnakangas @ 2021-01-28 16:42 UTC (permalink / raw) Add a 'noError' argument, so that we can try to convert a buffer without knowing the character boundaries beforehand. The functions now need to return the number of input bytes successfully converted. This is is a backwards-incompatible change, if you have created a custom encoding conversion with CREATE CONVERSION. This adds a check to pg_upgrade for that, refusing the upgrade if there are any user-defined encoding conversions. --- doc/src/sgml/ref/create_conversion.sgml | 5 +- src/backend/commands/conversioncmds.c | 27 +- src/backend/utils/error/elog.c | 2 + src/backend/utils/mb/conv.c | 112 +++++- .../cyrillic_and_mic/cyrillic_and_mic.c | 127 ++++--- .../euc2004_sjis2004/euc2004_sjis2004.c | 96 ++++- .../euc_cn_and_mic/euc_cn_and_mic.c | 57 ++- .../euc_jp_and_sjis/euc_jp_and_sjis.c | 153 ++++++-- .../euc_kr_and_mic/euc_kr_and_mic.c | 57 ++- .../euc_tw_and_big5/euc_tw_and_big5.c | 165 +++++++-- .../latin2_and_win1250/latin2_and_win1250.c | 49 ++- .../latin_and_mic/latin_and_mic.c | 43 ++- .../utf8_and_big5/utf8_and_big5.c | 37 +- .../utf8_and_cyrillic/utf8_and_cyrillic.c | 67 ++-- .../utf8_and_euc2004/utf8_and_euc2004.c | 37 +- .../utf8_and_euc_cn/utf8_and_euc_cn.c | 37 +- .../utf8_and_euc_jp/utf8_and_euc_jp.c | 37 +- .../utf8_and_euc_kr/utf8_and_euc_kr.c | 37 +- .../utf8_and_euc_tw/utf8_and_euc_tw.c | 37 +- .../utf8_and_gb18030/utf8_and_gb18030.c | 37 +- .../utf8_and_gbk/utf8_and_gbk.c | 37 +- .../utf8_and_iso8859/utf8_and_iso8859.c | 43 ++- .../utf8_and_iso8859_1/utf8_and_iso8859_1.c | 27 +- .../utf8_and_johab/utf8_and_johab.c | 37 +- .../utf8_and_sjis/utf8_and_sjis.c | 37 +- .../utf8_and_sjis2004/utf8_and_sjis2004.c | 37 +- .../utf8_and_uhc/utf8_and_uhc.c | 37 +- .../utf8_and_win/utf8_and_win.c | 43 ++- src/backend/utils/mb/mbutils.c | 18 +- src/bin/pg_upgrade/check.c | 95 +++++ src/include/catalog/pg_proc.dat | 332 +++++++++--------- src/include/mb/pg_wchar.h | 49 +-- src/test/regress/expected/opr_sanity.out | 7 +- src/test/regress/sql/opr_sanity.sql | 7 +- 34 files changed, 1390 insertions(+), 635 deletions(-) diff --git a/doc/src/sgml/ref/create_conversion.sgml b/doc/src/sgml/ref/create_conversion.sgml index e7700fecfc5..f014a676c88 100644 --- a/doc/src/sgml/ref/create_conversion.sgml +++ b/doc/src/sgml/ref/create_conversion.sgml @@ -117,8 +117,9 @@ conv_proc( integer, -- destination encoding ID cstring, -- source string (null terminated C string) internal, -- destination (fill with a null terminated C string) - integer -- source string length -) RETURNS void; + integer, -- source string length + boolean -- if true, don't throw an error if conversion fails +) RETURNS integer; </programlisting></para> </listitem> </varlistentry> diff --git a/src/backend/commands/conversioncmds.c b/src/backend/commands/conversioncmds.c index f7ff321de71..d2041466911 100644 --- a/src/backend/commands/conversioncmds.c +++ b/src/backend/commands/conversioncmds.c @@ -45,8 +45,9 @@ CreateConversionCommand(CreateConversionStmt *stmt) const char *from_encoding_name = stmt->for_encoding_name; const char *to_encoding_name = stmt->to_encoding_name; List *func_name = stmt->func_name; - static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID}; + static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID, BOOLOID}; char result[1]; + Datum funcresult; /* Convert list of names to a name and namespace */ namespaceId = QualifiedNameGetCreationNamespace(stmt->conversion_name, @@ -92,8 +93,8 @@ CreateConversionCommand(CreateConversionStmt *stmt) funcoid = LookupFuncName(func_name, sizeof(funcargs) / sizeof(Oid), funcargs, false); - /* Check it returns VOID, else it's probably the wrong function */ - if (get_func_rettype(funcoid) != VOIDOID) + /* Check it returns int4, else it's probably the wrong function */ + if (get_func_rettype(funcoid) != INT4OID) ereport(ERROR, (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), errmsg("encoding conversion function %s must return type %s", @@ -111,12 +112,20 @@ CreateConversionCommand(CreateConversionStmt *stmt) * string; the conversion function should throw an error if it can't * perform the requested conversion. */ - OidFunctionCall5(funcoid, - Int32GetDatum(from_encoding), - Int32GetDatum(to_encoding), - CStringGetDatum(""), - CStringGetDatum(result), - Int32GetDatum(0)); + funcresult = OidFunctionCall6(funcoid, + Int32GetDatum(from_encoding), + Int32GetDatum(to_encoding), + CStringGetDatum(""), + CStringGetDatum(result), + Int32GetDatum(0), + BoolGetDatum(false)); + + /* The function should return 0 for empty input. Might as well check that, too. */ + if (DatumGetInt32(funcresult) != 0) + ereport(ERROR, + (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), + errmsg("encoding conversion function %s returned incorrect result for empty input", + NameListToString(func_name)))); /* * All seem ok, go ahead (possible failure would be a duplicate conversion diff --git a/src/backend/utils/error/elog.c b/src/backend/utils/error/elog.c index 80c26724612..762f77d533c 100644 --- a/src/backend/utils/error/elog.c +++ b/src/backend/utils/error/elog.c @@ -2280,6 +2280,8 @@ write_console(const char *line, int len) * Conversion on non-win32 platforms is not implemented yet. It requires * non-throw version of pg_do_encoding_conversion(), that converts * unconvertable characters to '?' without errors. + * + * XXX: We have a no-throw version now. It doesn't convert to '?' though. */ #endif diff --git a/src/backend/utils/mb/conv.c b/src/backend/utils/mb/conv.c index a07b54bd3b8..b83358bc7a5 100644 --- a/src/backend/utils/mb/conv.c +++ b/src/backend/utils/mb/conv.c @@ -26,14 +26,16 @@ * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the target charset, or 0 if there is no equivalent code. */ -void +int local2local(const unsigned char *l, unsigned char *p, int len, int src_encoding, int dest_encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -41,7 +43,11 @@ local2local(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(src_encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -50,13 +56,19 @@ local2local(const unsigned char *l, if (c2) *p++ = c2; else + { + if (noError) + break; report_untranslatable_char(src_encoding, dest_encoding, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -67,17 +79,22 @@ local2local(const unsigned char *l, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = l; int c1; while (len > 0) { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (IS_HIGHBIT_SET(c1)) *p++ = lc; *p++ = c1; @@ -85,6 +102,8 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, len--; } *p = '\0'; + + return l - start; } /* @@ -95,17 +114,22 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -118,17 +142,27 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1])) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); + } *p++ = mic[1]; mic += 2; len -= 2; } } *p = '\0'; + + return mic - start; } @@ -144,14 +178,16 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the mule encoding, or 0 if there is no equivalent code. */ -void +int latin2mic_with_table(const unsigned char *l, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -159,7 +195,11 @@ latin2mic_with_table(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -171,13 +211,19 @@ latin2mic_with_table(const unsigned char *l, *p++ = c2; } else + { + if (noError) + break; report_untranslatable_char(encoding, PG_MULE_INTERNAL, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -192,14 +238,16 @@ latin2mic_with_table(const unsigned char *l, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the local charset, or 0 if there is no equivalent code. */ -void +int mic2latin_with_table(const unsigned char *mic, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = mic; unsigned char c1, c2; @@ -207,7 +255,11 @@ mic2latin_with_table(const unsigned char *mic, { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -220,11 +272,17 @@ mic2latin_with_table(const unsigned char *mic, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1]) || (c2 = tab[mic[1] - HIGHBIT]) == 0) { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); break; /* keep compiler quiet */ @@ -235,6 +293,8 @@ mic2latin_with_table(const unsigned char *mic, } } *p = '\0'; + + return mic - start; } /* @@ -425,17 +485,19 @@ pg_mb_radix_conv(const pg_mb_radix_tree *rt, * * See pg_wchar.h for more details about the data structures used here. */ -void +int UtfToLocal(const unsigned char *utf, int len, unsigned char *iso, const pg_mb_radix_tree *map, const pg_utf_to_local_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, bool noError) { uint32 iutf; int l; const pg_utf_to_local_combined *cp; + const unsigned char *start = utf; + const unsigned char *cur = utf; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -449,6 +511,8 @@ UtfToLocal(const unsigned char *utf, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*utf == '\0') break; @@ -584,15 +648,19 @@ UtfToLocal(const unsigned char *utf, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(PG_UTF8, encoding, (const char *) (utf - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(PG_UTF8, (const char *) utf, len); *iso = '\0'; + + return cur - start; } /* @@ -616,18 +684,24 @@ UtfToLocal(const unsigned char *utf, int len, * (if provided) is applied. An error is raised if no match is found. * * See pg_wchar.h for more details about the data structures used here. + * + * Returns the number of input bytes consumed. If noError is true, this can + * be less than 'len'. */ -void +int LocalToUtf(const unsigned char *iso, int len, unsigned char *utf, const pg_mb_radix_tree *map, const pg_local_to_utf_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, + bool noError) { uint32 iiso; int l; const pg_local_to_utf_combined *cp; + const unsigned char *start = iso; + const unsigned char *cur = iso; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -641,6 +715,8 @@ LocalToUtf(const unsigned char *iso, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*iso == '\0') break; @@ -723,13 +799,17 @@ LocalToUtf(const unsigned char *iso, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(encoding, PG_UTF8, (const char *) (iso - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(encoding, (const char *) iso, len); *utf = '\0'; + + return cur - start; } diff --git a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c index 4c5b02654de..368c2deb5e4 100644 --- a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c @@ -44,8 +44,11 @@ PG_FUNCTION_INFO_V1(win866_to_iso); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -306,12 +309,14 @@ koi8r_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -320,12 +325,14 @@ mic_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_KOI8R); - mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -334,12 +341,14 @@ iso_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -348,12 +357,14 @@ mic_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_ISO_8859_5); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -362,12 +373,14 @@ win1251_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -376,12 +389,14 @@ mic_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1251); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -390,12 +405,14 @@ win866_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -404,12 +421,14 @@ mic_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN866); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -418,12 +437,14 @@ koi8r_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN1251); - local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -432,12 +453,14 @@ win1251_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_KOI8R); - local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi); + converted = local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -446,12 +469,14 @@ koi8r_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN866); - local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -460,12 +485,14 @@ win866_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_KOI8R); - local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi); + converted = local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -474,12 +501,14 @@ win866_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_WIN1251); - local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251); + converted = local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -488,12 +517,14 @@ win1251_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_WIN866); - local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866); + converted = local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -502,12 +533,14 @@ iso_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_KOI8R); - local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -516,12 +549,14 @@ koi8r_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_ISO_8859_5); - local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso); + converted = local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -530,12 +565,14 @@ iso_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN1251); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -544,12 +581,14 @@ win1251_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso); + converted = local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -558,12 +597,14 @@ iso_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN866); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -572,10 +613,12 @@ win866_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso); + converted = local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c index 4d7fb116cfd..88529c644cf 100644 --- a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c @@ -19,8 +19,8 @@ PG_MODULE_MAGIC; PG_FUNCTION_INFO_V1(euc_jis_2004_to_shift_jis_2004); PG_FUNCTION_INFO_V1(shift_jis_2004_to_euc_jis_2004); -static void euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len); -static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len); +static int euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError); /* ---------- * conv_proc( @@ -28,8 +28,11 @@ static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -39,12 +42,14 @@ euc_jis_2004_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_SHIFT_JIS_2004); - euc_jis_20042shift_jis_2004(src, dest, len); + converted = euc_jis_20042shift_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -53,20 +58,23 @@ shift_jis_2004_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_EUC_JIS_2004); - shift_jis_20042euc_jis_2004(src, dest, len); + converted = shift_jis_20042euc_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_JIS_2004 -> SHIFT_JIS_2004 */ -static void -euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, ku, ten; @@ -79,8 +87,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -90,8 +102,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) l = pg_encoding_verifymbchar(PG_EUC_JIS_2004, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (c1 == SS2 && l == 2) /* JIS X 0201 kana? */ { @@ -121,8 +137,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) *p++ = (ku + 0x19b) >> 1; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } if (ku % 2) @@ -132,8 +152,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; @@ -149,8 +173,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ku >= 63 && ku <= 94) *p++ = (ku + 0x181) >> 1; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (ku % 2) { @@ -159,20 +187,30 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else - report_invalid_encoding(PG_EUC_JIS_2004, + { + if (noError) + break; + report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } euc += l; len -= l; } *p = '\0'; + + return euc - start; } /* @@ -212,9 +250,10 @@ get_ten(int b, int *ku) * SHIFT_JIS_2004 ---> EUC_JIS_2004 */ -static void -shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len) +static int +shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1; int ku, ten, @@ -230,8 +269,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -241,8 +284,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len l = pg_encoding_verifymbchar(PG_SHIFT_JIS_2004, (const char *) sjis, len); if (l < 0 || l > len) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf && l == 1) { @@ -266,8 +313,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x100; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xe0 && c1 <= 0xef) /* plane 1 62ku-94ku */ @@ -275,9 +326,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x180; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, - (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xf0 && c1 <= 0xf3) /* plane 2 @@ -286,8 +340,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } switch (c1) { case 0xf0: @@ -309,16 +367,24 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 == 0xf4 && kubun == 1) ku = 15; else ku = (c1 << 1) - 0x19a - kubun; } else + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (plane == 2) *p++ = SS3; @@ -330,4 +396,6 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c index e9bb896935f..a8da733803d 100644 --- a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_cn2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_cn(const unsigned char *mic, unsigned char *p, int len); +static int euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_cn_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_cn_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_MULE_INTERNAL); - euc_cn2mic(src, dest, len); + converted = euc_cn2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_CN); - mic2euc_cn(src, dest, len); + converted = mic2euc_cn(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_CN ---> MIC */ -static void -euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; while (len > 0) @@ -76,7 +84,11 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (len < 2 || !IS_HIGHBIT_SET(euc[1])) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = LC_GB2312_80; *p++ = c1; *p++ = euc[1]; @@ -86,21 +98,28 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_CN */ -static void -mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) @@ -109,11 +128,19 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (c1 != LC_GB2312_80) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_CN, (const char *) mic, len); + } if (len < 3 || !IS_HIGHBIT_SET(mic[1]) || !IS_HIGHBIT_SET(mic[2])) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } mic++; *p++ = *mic++; *p++ = *mic++; @@ -122,12 +149,18 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; } } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c index 5059f917a98..cc4817dc4cd 100644 --- a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c @@ -42,17 +42,20 @@ PG_FUNCTION_INFO_V1(mic_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void sjis2mic(const unsigned char *sjis, unsigned char *p, int len); -static void mic2sjis(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_jp(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len); -static void sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len); +static int sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError); +static int mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_jp_to_sjis(PG_FUNCTION_ARGS) @@ -60,12 +63,14 @@ euc_jp_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_SJIS); - euc_jp2sjis(src, dest, len); + converted = euc_jp2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -74,12 +79,14 @@ sjis_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_EUC_JP); - sjis2euc_jp(src, dest, len); + converted = sjis2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -88,12 +95,14 @@ euc_jp_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_MULE_INTERNAL); - euc_jp2mic(src, dest, len); + converted = euc_jp2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -102,12 +111,14 @@ mic_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_JP); - mic2euc_jp(src, dest, len); + converted = mic2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -116,12 +127,14 @@ sjis_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_MULE_INTERNAL); - sjis2mic(src, dest, len); + converted = sjis2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -130,20 +143,23 @@ mic_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_SJIS); - mic2sjis(src, dest, len); + converted = mic2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * SJIS ---> MIC */ -static void -sjis2mic(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -167,7 +183,11 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) * JIS X0208, X0212, user defined extended characters */ if (len < 2 || !ISSJISHEAD(c1) || !ISSJISTAIL(sjis[1])) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } c2 = sjis[1]; k = (c1 << 8) + c2; if (k >= 0xed40 && k < 0xf040) @@ -257,21 +277,28 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; } } *p = '\0'; + + return sjis - start; } /* * MIC ---> SJIS */ -static void -mic2sjis(const unsigned char *mic, unsigned char *p, int len) +static int +mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1, c2, k, @@ -284,8 +311,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -293,8 +324,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) *p++ = mic[1]; else if (c1 == LC_JISX0208) @@ -350,20 +385,27 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_SJIS, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP ---> MIC */ -static void -euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -374,8 +416,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -383,8 +429,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* 1 byte kana? */ *p++ = LC_JISX0201K; @@ -406,14 +456,17 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_JP */ -static void -mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -424,8 +477,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -433,8 +490,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) { *p++ = SS2; @@ -452,20 +513,27 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_JP, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP -> SJIS */ -static void -euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, c2, k; @@ -478,8 +546,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -487,8 +559,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* hankaku kana? */ @@ -551,14 +627,17 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * SJIS ---> EUC_JP */ -static void -sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -573,8 +652,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -582,8 +665,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_SJIS, (const char *) sjis, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf) { /* JIS X0201 (1 byte kana) */ @@ -680,4 +767,6 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c index ac823d6c270..a5b51617e52 100644 --- a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_kr2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_kr(const unsigned char *mic, unsigned char *p, int len); +static int euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_kr_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_kr_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_MULE_INTERNAL); - euc_kr2mic(src, dest, len); + converted = euc_kr2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_KR); - mic2euc_kr(src, dest, len); + converted = mic2euc_kr(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_KR ---> MIC */ -static void -euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -78,8 +86,12 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_KR, (const char *) euc, len); if (l != 2) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = LC_KS5601; *p++ = c1; *p++ = euc[1]; @@ -89,22 +101,29 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_KR */ -static void -mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -115,8 +134,12 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -124,18 +147,28 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_KS5601) { *p++ = mic[1]; *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_KR, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c index 66c242d7f36..ebb4e0acd53 100644 --- a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c @@ -32,17 +32,20 @@ PG_FUNCTION_INFO_V1(mic_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_tw2big5(const unsigned char *euc, unsigned char *p, int len); -static void big52euc_tw(const unsigned char *euc, unsigned char *p, int len); -static void big52mic(const unsigned char *big5, unsigned char *p, int len); -static void mic2big5(const unsigned char *mic, unsigned char *p, int len); -static void euc_tw2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_tw(const unsigned char *mic, unsigned char *p, int len); +static int euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52euc_tw(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError); +static int mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_tw_to_big5(PG_FUNCTION_ARGS) @@ -50,12 +53,14 @@ euc_tw_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_BIG5); - euc_tw2big5(src, dest, len); + converted = euc_tw2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -64,12 +69,14 @@ big5_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_EUC_TW); - big52euc_tw(src, dest, len); + converted = big52euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -78,12 +85,14 @@ euc_tw_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_MULE_INTERNAL); - euc_tw2mic(src, dest, len); + converted = euc_tw2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -92,12 +101,14 @@ mic_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_TW); - mic2euc_tw(src, dest, len); + converted = mic2euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -106,12 +117,14 @@ big5_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_MULE_INTERNAL); - big52mic(src, dest, len); + converted = big52mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -120,21 +133,24 @@ mic_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_BIG5); - mic2big5(src, dest, len); + converted = mic2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_TW ---> Big5 */ -static void -euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; unsigned char c1; unsigned short big5buf, cnsBuf; @@ -149,8 +165,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Verify and decode the next EUC_TW input character */ l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -171,8 +191,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Write it out in Big5 */ big5buf = CNStoBIG5(cnsBuf, lc); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_EUC_TW, PG_BIG5, (const char *) euc, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; @@ -182,22 +206,29 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * Big5 ---> EUC_TW */ -static void -big52euc_tw(const unsigned char *big5, unsigned char *p, int len) +static int +big52euc_tw(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -212,8 +243,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); @@ -237,8 +272,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_EUC_TW, (const char *) big5, len); + } big5 += l; len -= l; @@ -256,14 +295,17 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) } } *p = '\0'; + + return big5 - start; } /* * EUC_TW ---> MIC */ -static void -euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -274,8 +316,12 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -304,22 +350,29 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_TW */ -static void -mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -330,8 +383,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -339,8 +396,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1) { *p++ = mic[1]; @@ -362,20 +423,27 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[3]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_TW, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * Big5 ---> MIC */ -static void -big52mic(const unsigned char *big5, unsigned char *p, int len) +static int +big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -389,8 +457,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } *p++ = c1; big5++; len--; @@ -398,8 +470,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); if (lc != 0) @@ -412,20 +488,27 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_MULE_INTERNAL, (const char *) big5, len); + } big5 += l; len -= l; } *p = '\0'; + + return big5 - start; } /* * MIC ---> Big5 */ -static void -mic2big5(const unsigned char *mic, unsigned char *p, int len) +static int +mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -438,8 +521,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -447,8 +534,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1 || c1 == LC_CNS11643_2 || c1 == LCPRV2_B) { if (c1 == LCPRV2_B) @@ -462,16 +553,26 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } big5buf = CNStoBIG5(cnsBuf, c1); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c index 2e28e6780a5..8610fcb69aa 100644 --- a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c +++ b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(win1250_to_latin2); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -82,12 +85,14 @@ latin2_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -96,12 +101,14 @@ mic_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN2); - mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -110,13 +117,15 @@ win1250_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - win1250_2_iso88592); + converted = latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -125,13 +134,15 @@ mic_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1250); - mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - iso88592_2_win1250); + converted = mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -140,12 +151,15 @@ latin2_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_WIN1250); - local2local(src, dest, len, PG_LATIN2, PG_WIN1250, iso88592_2_win1250); + converted = local2local(src, dest, len, PG_LATIN2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -154,10 +168,13 @@ win1250_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_LATIN2); - local2local(src, dest, len, PG_WIN1250, PG_LATIN2, win1250_2_iso88592); + converted = local2local(src, dest, len, PG_WIN1250, PG_LATIN2, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c index bc651410f21..bff27d1c295 100644 --- a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(mic_to_latin4); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -42,12 +45,14 @@ latin1_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,12 +61,14 @@ mic_to_latin1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN1); - mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -70,12 +77,14 @@ latin3_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN3, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -84,12 +93,14 @@ mic_to_latin3(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN3); - mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,12 +109,14 @@ latin4_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN4, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -112,10 +125,12 @@ mic_to_latin4(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN4); - mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c index d6067cdc24e..3838b15cab9 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ big5_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_UTF8); - LocalToUtf(src, len, dest, - &big5_to_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = LocalToUtf(src, len, dest, + &big5_to_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_BIG5); - UtfToLocal(src, len, dest, - &big5_from_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = UtfToLocal(src, len, dest, + &big5_from_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c index ed90e8e682e..75719fe5f1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c @@ -33,8 +33,11 @@ PG_FUNCTION_INFO_V1(koi8u_to_utf8); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -44,16 +47,19 @@ utf8_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8R); - UtfToLocal(src, len, dest, - &koi8r_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = UtfToLocal(src, len, dest, + &koi8r_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -62,16 +68,19 @@ koi8r_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8r_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = LocalToUtf(src, len, dest, + &koi8r_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -80,16 +89,19 @@ utf8_to_koi8u(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8U); - UtfToLocal(src, len, dest, - &koi8u_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = UtfToLocal(src, len, dest, + &koi8u_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,14 +110,17 @@ koi8u_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8U, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8u_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = LocalToUtf(src, len, dest, + &koi8u_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c index d699affce47..5391001951a 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jis_2004_to_unicode_tree, - LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = LocalToUtf(src, len, dest, + &euc_jis_2004_to_unicode_tree, + LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JIS_2004); - UtfToLocal(src, len, dest, - &euc_jis_2004_from_unicode_tree, - ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = UtfToLocal(src, len, dest, + &euc_jis_2004_from_unicode_tree, + ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c index d7c0ba6a58b..c87d1bf2398 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_cn_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_cn_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = LocalToUtf(src, len, dest, + &euc_cn_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_CN); - UtfToLocal(src, len, dest, - &euc_cn_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = UtfToLocal(src, len, dest, + &euc_cn_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c index 13a3a23e77b..6a55134db21 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jp); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jp_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jp_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = LocalToUtf(src, len, dest, + &euc_jp_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JP); - UtfToLocal(src, len, dest, - &euc_jp_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = UtfToLocal(src, len, dest, + &euc_jp_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c index 1bbb8aaef7b..fe1924e2fec 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_kr_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_kr_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = LocalToUtf(src, len, dest, + &euc_kr_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_KR); - UtfToLocal(src, len, dest, - &euc_kr_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = UtfToLocal(src, len, dest, + &euc_kr_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c index 9830045dccd..68215659b57 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_tw); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_tw_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_tw_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = LocalToUtf(src, len, dest, + &euc_tw_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_TW); - UtfToLocal(src, len, dest, - &euc_tw_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = UtfToLocal(src, len, dest, + &euc_tw_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c index f86ecf27424..e1a59c39a4d 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c @@ -183,8 +183,11 @@ conv_utf8_to_18030(uint32 code) * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -193,16 +196,19 @@ gb18030_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GB18030, PG_UTF8); - LocalToUtf(src, len, dest, - &gb18030_to_unicode_tree, - NULL, 0, - conv_18030_to_utf8, - PG_GB18030); + converted = LocalToUtf(src, len, dest, + &gb18030_to_unicode_tree, + NULL, 0, + conv_18030_to_utf8, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -211,14 +217,17 @@ utf8_to_gb18030(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GB18030); - UtfToLocal(src, len, dest, - &gb18030_from_unicode_tree, - NULL, 0, - conv_utf8_to_18030, - PG_GB18030); + converted = UtfToLocal(src, len, dest, + &gb18030_from_unicode_tree, + NULL, 0, + conv_utf8_to_18030, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c index 2ab8b16c8a8..881386d5347 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_gbk); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ gbk_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GBK, PG_UTF8); - LocalToUtf(src, len, dest, - &gbk_to_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = LocalToUtf(src, len, dest, + &gbk_to_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_gbk(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GBK); - UtfToLocal(src, len, dest, - &gbk_from_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = UtfToLocal(src, len, dest, + &gbk_from_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c index 3e49f67ea2f..d93a521badf 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c @@ -52,8 +52,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -100,6 +103,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -108,12 +112,15 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -122,7 +129,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -132,6 +139,7 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -140,12 +148,15 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -154,5 +165,5 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c index 67e713cca11..8ac93604a1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c @@ -26,8 +26,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859_1); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -37,6 +40,8 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_UTF8); @@ -45,7 +50,11 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_LATIN1, (const char *) src, len); + } if (!IS_HIGHBIT_SET(c)) *dest++ = c; else @@ -58,7 +67,7 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } Datum @@ -67,6 +76,8 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c, c1; @@ -76,7 +87,11 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_UTF8, (const char *) src, len); + } /* fast path for ASCII-subset characters */ if (!IS_HIGHBIT_SET(c)) { @@ -102,11 +117,15 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) len -= 2; } else + { + if (noError) + break; report_untranslatable_char(PG_UTF8, PG_LATIN1, (const char *) src, len); + } } } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c index 578f5df4e7f..317daa2d5ee 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_johab); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ johab_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_JOHAB, PG_UTF8); - LocalToUtf(src, len, dest, - &johab_to_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = LocalToUtf(src, len, dest, + &johab_to_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_johab(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_JOHAB); - UtfToLocal(src, len, dest, - &johab_from_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = UtfToLocal(src, len, dest, + &johab_from_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c index dd9fc2975ad..4c9348aba59 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ sjis_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_UTF8); - LocalToUtf(src, len, dest, - &sjis_to_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = LocalToUtf(src, len, dest, + &sjis_to_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SJIS); - UtfToLocal(src, len, dest, - &sjis_from_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = UtfToLocal(src, len, dest, + &sjis_from_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c index 4bcc886d674..1fffdc5930c 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_shift_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ shift_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &shift_jis_2004_to_unicode_tree, - LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = LocalToUtf(src, len, dest, + &shift_jis_2004_to_unicode_tree, + LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SHIFT_JIS_2004); - UtfToLocal(src, len, dest, - &shift_jis_2004_from_unicode_tree, - ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = UtfToLocal(src, len, dest, + &shift_jis_2004_from_unicode_tree, + ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c index c8e512994a1..d9471dad097 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_uhc); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ uhc_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UHC, PG_UTF8); - LocalToUtf(src, len, dest, - &uhc_to_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = LocalToUtf(src, len, dest, + &uhc_to_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_uhc(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_UHC); - UtfToLocal(src, len, dest, - &uhc_from_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = UtfToLocal(src, len, dest, + &uhc_from_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c index 0c9493dee56..110ba5677d0 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c @@ -48,8 +48,11 @@ PG_FUNCTION_INFO_V1(utf8_to_win); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -81,6 +84,7 @@ win_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -89,12 +93,15 @@ win_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -103,7 +110,7 @@ win_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -113,6 +120,7 @@ utf8_to_win(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -121,12 +129,15 @@ utf8_to_win(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -135,5 +146,5 @@ utf8_to_win(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/mbutils.c b/src/backend/utils/mb/mbutils.c index 2578573b0ab..65753860e35 100644 --- a/src/backend/utils/mb/mbutils.c +++ b/src/backend/utils/mb/mbutils.c @@ -406,12 +406,13 @@ pg_do_encoding_conversion(unsigned char *src, int len, MemoryContextAllocHuge(CurrentMemoryContext, (Size) len * MAX_CONVERSION_GROWTH + 1); - OidFunctionCall5(proc, - Int32GetDatum(src_encoding), - Int32GetDatum(dest_encoding), - CStringGetDatum(src), - CStringGetDatum(result), - Int32GetDatum(len)); + (void) OidFunctionCall6(proc, + Int32GetDatum(src_encoding), + Int32GetDatum(dest_encoding), + CStringGetDatum(src), + CStringGetDatum(result), + Int32GetDatum(len), + BoolGetDatum(false)); /* * If the result is large, it's worth repalloc'ing to release any extra @@ -849,12 +850,13 @@ pg_unicode_to_server(pg_wchar c, unsigned char *s) c_as_utf8[c_as_utf8_len] = '\0'; /* Convert, or throw error if we can't */ - FunctionCall5(Utf8ToServerConvProc, + FunctionCall6(Utf8ToServerConvProc, Int32GetDatum(PG_UTF8), Int32GetDatum(server_encoding), CStringGetDatum(c_as_utf8), CStringGetDatum(s), - Int32GetDatum(c_as_utf8_len)); + Int32GetDatum(c_as_utf8_len), + BoolGetDatum(false)); } diff --git a/src/bin/pg_upgrade/check.c b/src/bin/pg_upgrade/check.c index 43fc297eb69..ee6be95b08d 100644 --- a/src/bin/pg_upgrade/check.c +++ b/src/bin/pg_upgrade/check.c @@ -28,6 +28,7 @@ static void check_for_reg_data_type_usage(ClusterInfo *cluster); static void check_for_jsonb_9_4_usage(ClusterInfo *cluster); static void check_for_pg_role_prefix(ClusterInfo *cluster); static void check_for_new_tablespace_dir(ClusterInfo *new_cluster); +static void check_for_user_defined_encoding_conversions(ClusterInfo *cluster); static char *get_canonical_locale_name(int category, const char *locale); @@ -102,6 +103,15 @@ check_and_dump_old_cluster(bool live_check) check_for_reg_data_type_usage(&old_cluster); check_for_isn_and_int8_passing_mismatch(&old_cluster); + /* + * PG 14 changed the function signature of encoding conversion functions. + * Conversions from older versions cannot be upgraded automatically + * because the user-defined functions used by the encoding conversions + * need to changed to match the new signature. + */ + if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1300) + check_for_user_defined_encoding_conversions(&old_cluster); + /* * Pre-PG 14 allowed user defined postfix operators, which are not * supported anymore. Verify there are none, iff applicable. @@ -1268,6 +1278,91 @@ check_for_pg_role_prefix(ClusterInfo *cluster) check_ok(); } +/* + * Verify that no user-defined encoding conversions exist. + */ +static void +check_for_user_defined_encoding_conversions(ClusterInfo *cluster) +{ + int dbnum; + FILE *script = NULL; + bool found = false; + char output_path[MAXPGPATH]; + + prep_status("Checking for user-defined encoding conversions"); + + snprintf(output_path, sizeof(output_path), + "encoding_conversions.txt"); + + /* Find any user defined encoding conversions */ + for (dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++) + { + PGresult *res; + bool db_used = false; + int ntups; + int rowno; + int i_conoid, + i_conname, + i_nspname; + DbInfo *active_db = &cluster->dbarr.dbs[dbnum]; + PGconn *conn = connectToServer(cluster, active_db->db_name); + + /* + * The query below hardcodes FirstNormalObjectId as 16384 rather than + * interpolating that C #define into the query because, if that + * #define is ever changed, the cutoff we want to use is the value + * used by pre-version 14 servers, not that of some future version. + */ + res = executeQueryOrDie(conn, + "SELECT c.oid as conoid, c.conname, n.nspname " + "FROM pg_catalog.pg_conversion c, " + " pg_catalog.pg_namespace n " + "WHERE c.connamespace = n.oid AND " + " c.oid >= 16384"); + ntups = PQntuples(res); + i_conoid = PQfnumber(res, "conoid"); + i_conname = PQfnumber(res, "conname"); + i_nspname = PQfnumber(res, "nspname"); + for (rowno = 0; rowno < ntups; rowno++) + { + found = true; + if (script == NULL && + (script = fopen_priv(output_path, "w")) == NULL) + pg_fatal("could not open file \"%s\": %s\n", + output_path, strerror(errno)); + if (!db_used) + { + fprintf(script, "In database: %s\n", active_db->db_name); + db_used = true; + } + fprintf(script, " (oid=%s) %s.%s\n", + PQgetvalue(res, rowno, i_conoid), + PQgetvalue(res, rowno, i_nspname), + PQgetvalue(res, rowno, i_conname)); + } + + PQclear(res); + + PQfinish(conn); + } + + if (script) + fclose(script); + + if (found) + { + pg_log(PG_REPORT, "fatal\n"); + pg_fatal("Your installation contains user-defined encoding conversions.\n" + "The conversion function parameters changed in PostgreSQL version 14\n" + "so this cluster cannot currently be upgraded. You can remove the\n" + "encoding conversions in the old cluster and restart the upgrade.\n" + "A list of user-defined encoding conversions is in the file:\n" + " %s\n\n", output_path); + } + else + check_ok(); +} + /* * get_canonical_locale_name diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index f8174061ef3..75b829e8514 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10766,388 +10766,388 @@ # conversion functions { oid => '4302', descr => 'internal conversion function for KOI8R to MULE_INTERNAL', - proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_mic', + proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4303', descr => 'internal conversion function for MULE_INTERNAL to KOI8R', - proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_koi8r', + proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4304', descr => 'internal conversion function for ISO-8859-5 to MULE_INTERNAL', - proname => 'iso_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_mic', + proname => 'iso_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4305', descr => 'internal conversion function for MULE_INTERNAL to ISO-8859-5', - proname => 'mic_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_iso', + proname => 'mic_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4306', descr => 'internal conversion function for WIN1251 to MULE_INTERNAL', - proname => 'win1251_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_mic', + proname => 'win1251_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4307', descr => 'internal conversion function for MULE_INTERNAL to WIN1251', - proname => 'mic_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1251', + proname => 'mic_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4308', descr => 'internal conversion function for WIN866 to MULE_INTERNAL', - proname => 'win866_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_mic', + proname => 'win866_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4309', descr => 'internal conversion function for MULE_INTERNAL to WIN866', - proname => 'mic_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win866', + proname => 'mic_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4310', descr => 'internal conversion function for KOI8R to WIN1251', - proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4311', descr => 'internal conversion function for WIN1251 to KOI8R', - proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4312', descr => 'internal conversion function for KOI8R to WIN866', - proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_win866', + proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4313', descr => 'internal conversion function for WIN866 to KOI8R', - proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_koi8r', + proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4314', descr => 'internal conversion function for WIN866 to WIN1251', - proname => 'win866_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win866_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4315', descr => 'internal conversion function for WIN1251 to WIN866', - proname => 'win1251_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4316', descr => 'internal conversion function for ISO-8859-5 to KOI8R', - proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_koi8r', + proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4317', descr => 'internal conversion function for KOI8R to ISO-8859-5', - proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_iso', + proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4318', descr => 'internal conversion function for ISO-8859-5 to WIN1251', - proname => 'iso_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win1251', + proname => 'iso_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4319', descr => 'internal conversion function for WIN1251 to ISO-8859-5', - proname => 'win1251_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_iso', + proname => 'win1251_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4320', descr => 'internal conversion function for ISO-8859-5 to WIN866', - proname => 'iso_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win866', + proname => 'iso_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4321', descr => 'internal conversion function for WIN866 to ISO-8859-5', - proname => 'win866_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_iso', + proname => 'win866_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4322', descr => 'internal conversion function for EUC_CN to MULE_INTERNAL', - proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_mic', + proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_mic', probin => '$libdir/euc_cn_and_mic' }, { oid => '4323', descr => 'internal conversion function for MULE_INTERNAL to EUC_CN', - proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_cn', + proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_cn', probin => '$libdir/euc_cn_and_mic' }, { oid => '4324', descr => 'internal conversion function for EUC_JP to SJIS', - proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_sjis', + proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4325', descr => 'internal conversion function for SJIS to EUC_JP', - proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_euc_jp', + proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4326', descr => 'internal conversion function for EUC_JP to MULE_INTERNAL', - proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_mic', + proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4327', descr => 'internal conversion function for SJIS to MULE_INTERNAL', - proname => 'sjis_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_mic', + proname => 'sjis_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4328', descr => 'internal conversion function for MULE_INTERNAL to EUC_JP', - proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_jp', + proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4329', descr => 'internal conversion function for MULE_INTERNAL to SJIS', - proname => 'mic_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_sjis', + proname => 'mic_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4330', descr => 'internal conversion function for EUC_KR to MULE_INTERNAL', - proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_mic', + proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_mic', probin => '$libdir/euc_kr_and_mic' }, { oid => '4331', descr => 'internal conversion function for MULE_INTERNAL to EUC_KR', - proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_kr', + proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_kr', probin => '$libdir/euc_kr_and_mic' }, { oid => '4332', descr => 'internal conversion function for EUC_TW to BIG5', - proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_big5', + proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4333', descr => 'internal conversion function for BIG5 to EUC_TW', - proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_euc_tw', + proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4334', descr => 'internal conversion function for EUC_TW to MULE_INTERNAL', - proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_mic', + proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4335', descr => 'internal conversion function for BIG5 to MULE_INTERNAL', - proname => 'big5_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_mic', + proname => 'big5_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4336', descr => 'internal conversion function for MULE_INTERNAL to EUC_TW', - proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_tw', + proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4337', descr => 'internal conversion function for MULE_INTERNAL to BIG5', - proname => 'mic_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_big5', + proname => 'mic_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4338', descr => 'internal conversion function for LATIN2 to MULE_INTERNAL', - proname => 'latin2_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin2_to_mic', + proname => 'latin2_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4339', descr => 'internal conversion function for MULE_INTERNAL to LATIN2', - proname => 'mic_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin2', + proname => 'mic_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4340', descr => 'internal conversion function for WIN1250 to MULE_INTERNAL', - proname => 'win1250_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1250_to_mic', + proname => 'win1250_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4341', descr => 'internal conversion function for MULE_INTERNAL to WIN1250', - proname => 'mic_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1250', + proname => 'mic_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4342', descr => 'internal conversion function for LATIN2 to WIN1250', - proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4343', descr => 'internal conversion function for WIN1250 to LATIN2', - proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4344', descr => 'internal conversion function for LATIN1 to MULE_INTERNAL', - proname => 'latin1_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin1_to_mic', + proname => 'latin1_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin1_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4345', descr => 'internal conversion function for MULE_INTERNAL to LATIN1', - proname => 'mic_to_latin1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin1', + proname => 'mic_to_latin1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin1', probin => '$libdir/latin_and_mic' }, { oid => '4346', descr => 'internal conversion function for LATIN3 to MULE_INTERNAL', - proname => 'latin3_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin3_to_mic', + proname => 'latin3_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin3_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4347', descr => 'internal conversion function for MULE_INTERNAL to LATIN3', - proname => 'mic_to_latin3', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin3', + proname => 'mic_to_latin3', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin3', probin => '$libdir/latin_and_mic' }, { oid => '4348', descr => 'internal conversion function for LATIN4 to MULE_INTERNAL', - proname => 'latin4_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin4_to_mic', + proname => 'latin4_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin4_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4349', descr => 'internal conversion function for MULE_INTERNAL to LATIN4', - proname => 'mic_to_latin4', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin4', + proname => 'mic_to_latin4', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin4', probin => '$libdir/latin_and_mic' }, { oid => '4352', descr => 'internal conversion function for BIG5 to UTF8', - proname => 'big5_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_utf8', + proname => 'big5_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_utf8', probin => '$libdir/utf8_and_big5' }, { oid => '4353', descr => 'internal conversion function for UTF8 to BIG5', - proname => 'utf8_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_big5', + proname => 'utf8_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_big5', probin => '$libdir/utf8_and_big5' }, { oid => '4354', descr => 'internal conversion function for UTF8 to KOI8R', - proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8r', + proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8r', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4355', descr => 'internal conversion function for KOI8R to UTF8', - proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_utf8', + proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4356', descr => 'internal conversion function for UTF8 to KOI8U', - proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8u', + proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8u', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4357', descr => 'internal conversion function for KOI8U to UTF8', - proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8u_to_utf8', + proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8u_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4358', descr => 'internal conversion function for UTF8 to WIN', - proname => 'utf8_to_win', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_win', + proname => 'utf8_to_win', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_win', probin => '$libdir/utf8_and_win' }, { oid => '4359', descr => 'internal conversion function for WIN to UTF8', - proname => 'win_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win_to_utf8', + proname => 'win_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win_to_utf8', probin => '$libdir/utf8_and_win' }, { oid => '4360', descr => 'internal conversion function for EUC_CN to UTF8', - proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_utf8', + proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_utf8', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4361', descr => 'internal conversion function for UTF8 to EUC_CN', - proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_cn', + proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_cn', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4362', descr => 'internal conversion function for EUC_JP to UTF8', - proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_utf8', + proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_utf8', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4363', descr => 'internal conversion function for UTF8 to EUC_JP', - proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_jp', + proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jp', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4364', descr => 'internal conversion function for EUC_KR to UTF8', - proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_utf8', + proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_utf8', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4365', descr => 'internal conversion function for UTF8 to EUC_KR', - proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_kr', + proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_kr', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4366', descr => 'internal conversion function for EUC_TW to UTF8', - proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_utf8', + proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_utf8', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4367', descr => 'internal conversion function for UTF8 to EUC_TW', - proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_tw', + proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_tw', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4368', descr => 'internal conversion function for GB18030 to UTF8', - proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gb18030_to_utf8', + proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gb18030_to_utf8', probin => '$libdir/utf8_and_gb18030' }, { oid => '4369', descr => 'internal conversion function for UTF8 to GB18030', - proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gb18030', + proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gb18030', probin => '$libdir/utf8_and_gb18030' }, { oid => '4370', descr => 'internal conversion function for GBK to UTF8', - proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gbk_to_utf8', + proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gbk_to_utf8', probin => '$libdir/utf8_and_gbk' }, { oid => '4371', descr => 'internal conversion function for UTF8 to GBK', - proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gbk', + proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gbk', probin => '$libdir/utf8_and_gbk' }, { oid => '4372', descr => 'internal conversion function for UTF8 to ISO-8859 2-16', - proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_iso8859', + proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859', probin => '$libdir/utf8_and_iso8859' }, { oid => '4373', descr => 'internal conversion function for ISO-8859 2-16 to UTF8', - proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso8859_to_utf8', + proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_to_utf8', probin => '$libdir/utf8_and_iso8859' }, { oid => '4374', descr => 'internal conversion function for LATIN1 to UTF8', - proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_1_to_utf8', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4375', descr => 'internal conversion function for UTF8 to LATIN1', - proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859_1', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4376', descr => 'internal conversion function for JOHAB to UTF8', - proname => 'johab_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'johab_to_utf8', + proname => 'johab_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'johab_to_utf8', probin => '$libdir/utf8_and_johab' }, { oid => '4377', descr => 'internal conversion function for UTF8 to JOHAB', - proname => 'utf8_to_johab', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_johab', + proname => 'utf8_to_johab', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_johab', probin => '$libdir/utf8_and_johab' }, { oid => '4378', descr => 'internal conversion function for SJIS to UTF8', - proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_utf8', + proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_utf8', probin => '$libdir/utf8_and_sjis' }, { oid => '4379', descr => 'internal conversion function for UTF8 to SJIS', - proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_sjis', + proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_sjis', probin => '$libdir/utf8_and_sjis' }, { oid => '4380', descr => 'internal conversion function for UHC to UTF8', - proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'uhc_to_utf8', + proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'uhc_to_utf8', probin => '$libdir/utf8_and_uhc' }, { oid => '4381', descr => 'internal conversion function for UTF8 to UHC', - proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_uhc', + proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_uhc', probin => '$libdir/utf8_and_uhc' }, { oid => '4382', descr => 'internal conversion function for EUC_JIS_2004 to UTF8', - proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_utf8', probin => '$libdir/utf8_and_euc2004' }, { oid => '4383', descr => 'internal conversion function for UTF8 to EUC_JIS_2004', - proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jis_2004', probin => '$libdir/utf8_and_euc2004' }, { oid => '4384', descr => 'internal conversion function for SHIFT_JIS_2004 to UTF8', - proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_utf8', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4385', descr => 'internal conversion function for UTF8 to SHIFT_JIS_2004', - proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_shift_jis_2004', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4386', descr => 'internal conversion function for EUC_JIS_2004 to SHIFT_JIS_2004', proname => 'euc_jis_2004_to_shift_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_shift_jis_2004', probin => '$libdir/euc2004_sjis2004' }, { oid => '4387', descr => 'internal conversion function for SHIFT_JIS_2004 to EUC_JIS_2004', proname => 'shift_jis_2004_to_euc_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_euc_jis_2004', probin => '$libdir/euc2004_sjis2004' }, diff --git a/src/include/mb/pg_wchar.h b/src/include/mb/pg_wchar.h index 64b22e4b0d4..346a41a1f3d 100644 --- a/src/include/mb/pg_wchar.h +++ b/src/include/mb/pg_wchar.h @@ -627,18 +627,18 @@ extern void pg_unicode_to_server(pg_wchar c, unsigned char *s); extern unsigned short BIG5toCNS(unsigned short big5, unsigned char *lc); extern unsigned short CNStoBIG5(unsigned short cns, unsigned char lc); -extern void UtfToLocal(const unsigned char *utf, int len, - unsigned char *iso, - const pg_mb_radix_tree *map, - const pg_utf_to_local_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); -extern void LocalToUtf(const unsigned char *iso, int len, - unsigned char *utf, - const pg_mb_radix_tree *map, - const pg_local_to_utf_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); +extern int UtfToLocal(const unsigned char *utf, int len, + unsigned char *iso, + const pg_mb_radix_tree *map, + const pg_utf_to_local_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); +extern int LocalToUtf(const unsigned char *iso, int len, + unsigned char *utf, + const pg_mb_radix_tree *map, + const pg_local_to_utf_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); extern bool pg_verifymbstr(const char *mbstr, int len, bool noError); extern bool pg_verify_mbstr(int encoding, const char *mbstr, int len, @@ -656,18 +656,19 @@ extern void report_invalid_encoding(int encoding, const char *mbstr, int len) pg extern void report_untranslatable_char(int src_encoding, int dest_encoding, const char *mbstr, int len) pg_attribute_noreturn(); -extern void local2local(const unsigned char *l, unsigned char *p, int len, - int src_encoding, int dest_encoding, const unsigned char *tab); -extern void latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding); -extern void mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding); -extern void latin2mic_with_table(const unsigned char *l, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); -extern void mic2latin_with_table(const unsigned char *mic, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); +extern int local2local(const unsigned char *l, unsigned char *p, int len, + int src_encoding, int dest_encoding, const unsigned char *tab, + bool noError); +extern int latin2mic(const unsigned char *l, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int mic2latin(const unsigned char *mic, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int latin2mic_with_table(const unsigned char *l, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); +extern int mic2latin_with_table(const unsigned char *mic, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); #ifdef WIN32 extern WCHAR *pgwin32_message_to_UTF16(const char *str, int len, int *utf16len); diff --git a/src/test/regress/expected/opr_sanity.out b/src/test/regress/expected/opr_sanity.out index 254ca06d3dd..23ba60e395f 100644 --- a/src/test/regress/expected/opr_sanity.out +++ b/src/test/regress/expected/opr_sanity.out @@ -1052,13 +1052,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); oid | proname | oid | conname -----+---------+-----+--------- (0 rows) diff --git a/src/test/regress/sql/opr_sanity.sql b/src/test/regress/sql/opr_sanity.sql index bbd3834b634..04691745981 100644 --- a/src/test/regress/sql/opr_sanity.sql +++ b/src/test/regress/sql/opr_sanity.sql @@ -556,13 +556,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); -- Check for conprocs that don't perform the specific conversion that -- pg_conversion alleges they do, by trying to invoke each conversion -- 2.29.2 --------------39E46EF15EBFAA37D53332E5 Content-Type: text/x-patch; charset=UTF-8; name="v3-0003-Add-tests-for-the-new-noError-variants-of-built-i.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="v3-0003-Add-tests-for-the-new-noError-variants-of-built-i.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 34+ messages in thread
* [PATCH v3 2/5] Change conversion function signature. @ 2021-01-28 16:42 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 34+ messages in thread From: Heikki Linnakangas @ 2021-01-28 16:42 UTC (permalink / raw) Add a 'noError' argument, so that we can try to convert a buffer without knowing the character boundaries beforehand. The functions now need to return the number of input bytes successfully converted. This is is a backwards-incompatible change, if you have created a custom encoding conversion with CREATE CONVERSION. This adds a check to pg_upgrade for that, refusing the upgrade if there are any user-defined encoding conversions. --- doc/src/sgml/ref/create_conversion.sgml | 5 +- src/backend/commands/conversioncmds.c | 27 +- src/backend/utils/error/elog.c | 2 + src/backend/utils/mb/conv.c | 112 +++++- .../cyrillic_and_mic/cyrillic_and_mic.c | 127 ++++--- .../euc2004_sjis2004/euc2004_sjis2004.c | 96 ++++- .../euc_cn_and_mic/euc_cn_and_mic.c | 57 ++- .../euc_jp_and_sjis/euc_jp_and_sjis.c | 153 ++++++-- .../euc_kr_and_mic/euc_kr_and_mic.c | 57 ++- .../euc_tw_and_big5/euc_tw_and_big5.c | 165 +++++++-- .../latin2_and_win1250/latin2_and_win1250.c | 49 ++- .../latin_and_mic/latin_and_mic.c | 43 ++- .../utf8_and_big5/utf8_and_big5.c | 37 +- .../utf8_and_cyrillic/utf8_and_cyrillic.c | 67 ++-- .../utf8_and_euc2004/utf8_and_euc2004.c | 37 +- .../utf8_and_euc_cn/utf8_and_euc_cn.c | 37 +- .../utf8_and_euc_jp/utf8_and_euc_jp.c | 37 +- .../utf8_and_euc_kr/utf8_and_euc_kr.c | 37 +- .../utf8_and_euc_tw/utf8_and_euc_tw.c | 37 +- .../utf8_and_gb18030/utf8_and_gb18030.c | 37 +- .../utf8_and_gbk/utf8_and_gbk.c | 37 +- .../utf8_and_iso8859/utf8_and_iso8859.c | 43 ++- .../utf8_and_iso8859_1/utf8_and_iso8859_1.c | 27 +- .../utf8_and_johab/utf8_and_johab.c | 37 +- .../utf8_and_sjis/utf8_and_sjis.c | 37 +- .../utf8_and_sjis2004/utf8_and_sjis2004.c | 37 +- .../utf8_and_uhc/utf8_and_uhc.c | 37 +- .../utf8_and_win/utf8_and_win.c | 43 ++- src/backend/utils/mb/mbutils.c | 18 +- src/bin/pg_upgrade/check.c | 95 +++++ src/include/catalog/pg_proc.dat | 332 +++++++++--------- src/include/mb/pg_wchar.h | 49 +-- src/test/regress/expected/opr_sanity.out | 7 +- src/test/regress/sql/opr_sanity.sql | 7 +- 34 files changed, 1390 insertions(+), 635 deletions(-) diff --git a/doc/src/sgml/ref/create_conversion.sgml b/doc/src/sgml/ref/create_conversion.sgml index e7700fecfc5..f014a676c88 100644 --- a/doc/src/sgml/ref/create_conversion.sgml +++ b/doc/src/sgml/ref/create_conversion.sgml @@ -117,8 +117,9 @@ conv_proc( integer, -- destination encoding ID cstring, -- source string (null terminated C string) internal, -- destination (fill with a null terminated C string) - integer -- source string length -) RETURNS void; + integer, -- source string length + boolean -- if true, don't throw an error if conversion fails +) RETURNS integer; </programlisting></para> </listitem> </varlistentry> diff --git a/src/backend/commands/conversioncmds.c b/src/backend/commands/conversioncmds.c index f7ff321de71..d2041466911 100644 --- a/src/backend/commands/conversioncmds.c +++ b/src/backend/commands/conversioncmds.c @@ -45,8 +45,9 @@ CreateConversionCommand(CreateConversionStmt *stmt) const char *from_encoding_name = stmt->for_encoding_name; const char *to_encoding_name = stmt->to_encoding_name; List *func_name = stmt->func_name; - static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID}; + static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID, BOOLOID}; char result[1]; + Datum funcresult; /* Convert list of names to a name and namespace */ namespaceId = QualifiedNameGetCreationNamespace(stmt->conversion_name, @@ -92,8 +93,8 @@ CreateConversionCommand(CreateConversionStmt *stmt) funcoid = LookupFuncName(func_name, sizeof(funcargs) / sizeof(Oid), funcargs, false); - /* Check it returns VOID, else it's probably the wrong function */ - if (get_func_rettype(funcoid) != VOIDOID) + /* Check it returns int4, else it's probably the wrong function */ + if (get_func_rettype(funcoid) != INT4OID) ereport(ERROR, (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), errmsg("encoding conversion function %s must return type %s", @@ -111,12 +112,20 @@ CreateConversionCommand(CreateConversionStmt *stmt) * string; the conversion function should throw an error if it can't * perform the requested conversion. */ - OidFunctionCall5(funcoid, - Int32GetDatum(from_encoding), - Int32GetDatum(to_encoding), - CStringGetDatum(""), - CStringGetDatum(result), - Int32GetDatum(0)); + funcresult = OidFunctionCall6(funcoid, + Int32GetDatum(from_encoding), + Int32GetDatum(to_encoding), + CStringGetDatum(""), + CStringGetDatum(result), + Int32GetDatum(0), + BoolGetDatum(false)); + + /* The function should return 0 for empty input. Might as well check that, too. */ + if (DatumGetInt32(funcresult) != 0) + ereport(ERROR, + (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), + errmsg("encoding conversion function %s returned incorrect result for empty input", + NameListToString(func_name)))); /* * All seem ok, go ahead (possible failure would be a duplicate conversion diff --git a/src/backend/utils/error/elog.c b/src/backend/utils/error/elog.c index 80c26724612..762f77d533c 100644 --- a/src/backend/utils/error/elog.c +++ b/src/backend/utils/error/elog.c @@ -2280,6 +2280,8 @@ write_console(const char *line, int len) * Conversion on non-win32 platforms is not implemented yet. It requires * non-throw version of pg_do_encoding_conversion(), that converts * unconvertable characters to '?' without errors. + * + * XXX: We have a no-throw version now. It doesn't convert to '?' though. */ #endif diff --git a/src/backend/utils/mb/conv.c b/src/backend/utils/mb/conv.c index a07b54bd3b8..b83358bc7a5 100644 --- a/src/backend/utils/mb/conv.c +++ b/src/backend/utils/mb/conv.c @@ -26,14 +26,16 @@ * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the target charset, or 0 if there is no equivalent code. */ -void +int local2local(const unsigned char *l, unsigned char *p, int len, int src_encoding, int dest_encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -41,7 +43,11 @@ local2local(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(src_encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -50,13 +56,19 @@ local2local(const unsigned char *l, if (c2) *p++ = c2; else + { + if (noError) + break; report_untranslatable_char(src_encoding, dest_encoding, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -67,17 +79,22 @@ local2local(const unsigned char *l, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = l; int c1; while (len > 0) { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (IS_HIGHBIT_SET(c1)) *p++ = lc; *p++ = c1; @@ -85,6 +102,8 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, len--; } *p = '\0'; + + return l - start; } /* @@ -95,17 +114,22 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -118,17 +142,27 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1])) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); + } *p++ = mic[1]; mic += 2; len -= 2; } } *p = '\0'; + + return mic - start; } @@ -144,14 +178,16 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the mule encoding, or 0 if there is no equivalent code. */ -void +int latin2mic_with_table(const unsigned char *l, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -159,7 +195,11 @@ latin2mic_with_table(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -171,13 +211,19 @@ latin2mic_with_table(const unsigned char *l, *p++ = c2; } else + { + if (noError) + break; report_untranslatable_char(encoding, PG_MULE_INTERNAL, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -192,14 +238,16 @@ latin2mic_with_table(const unsigned char *l, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the local charset, or 0 if there is no equivalent code. */ -void +int mic2latin_with_table(const unsigned char *mic, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = mic; unsigned char c1, c2; @@ -207,7 +255,11 @@ mic2latin_with_table(const unsigned char *mic, { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -220,11 +272,17 @@ mic2latin_with_table(const unsigned char *mic, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1]) || (c2 = tab[mic[1] - HIGHBIT]) == 0) { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); break; /* keep compiler quiet */ @@ -235,6 +293,8 @@ mic2latin_with_table(const unsigned char *mic, } } *p = '\0'; + + return mic - start; } /* @@ -425,17 +485,19 @@ pg_mb_radix_conv(const pg_mb_radix_tree *rt, * * See pg_wchar.h for more details about the data structures used here. */ -void +int UtfToLocal(const unsigned char *utf, int len, unsigned char *iso, const pg_mb_radix_tree *map, const pg_utf_to_local_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, bool noError) { uint32 iutf; int l; const pg_utf_to_local_combined *cp; + const unsigned char *start = utf; + const unsigned char *cur = utf; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -449,6 +511,8 @@ UtfToLocal(const unsigned char *utf, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*utf == '\0') break; @@ -584,15 +648,19 @@ UtfToLocal(const unsigned char *utf, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(PG_UTF8, encoding, (const char *) (utf - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(PG_UTF8, (const char *) utf, len); *iso = '\0'; + + return cur - start; } /* @@ -616,18 +684,24 @@ UtfToLocal(const unsigned char *utf, int len, * (if provided) is applied. An error is raised if no match is found. * * See pg_wchar.h for more details about the data structures used here. + * + * Returns the number of input bytes consumed. If noError is true, this can + * be less than 'len'. */ -void +int LocalToUtf(const unsigned char *iso, int len, unsigned char *utf, const pg_mb_radix_tree *map, const pg_local_to_utf_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, + bool noError) { uint32 iiso; int l; const pg_local_to_utf_combined *cp; + const unsigned char *start = iso; + const unsigned char *cur = iso; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -641,6 +715,8 @@ LocalToUtf(const unsigned char *iso, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*iso == '\0') break; @@ -723,13 +799,17 @@ LocalToUtf(const unsigned char *iso, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(encoding, PG_UTF8, (const char *) (iso - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(encoding, (const char *) iso, len); *utf = '\0'; + + return cur - start; } diff --git a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c index 4c5b02654de..368c2deb5e4 100644 --- a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c @@ -44,8 +44,11 @@ PG_FUNCTION_INFO_V1(win866_to_iso); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -306,12 +309,14 @@ koi8r_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -320,12 +325,14 @@ mic_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_KOI8R); - mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -334,12 +341,14 @@ iso_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -348,12 +357,14 @@ mic_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_ISO_8859_5); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -362,12 +373,14 @@ win1251_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -376,12 +389,14 @@ mic_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1251); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -390,12 +405,14 @@ win866_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -404,12 +421,14 @@ mic_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN866); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -418,12 +437,14 @@ koi8r_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN1251); - local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -432,12 +453,14 @@ win1251_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_KOI8R); - local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi); + converted = local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -446,12 +469,14 @@ koi8r_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN866); - local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -460,12 +485,14 @@ win866_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_KOI8R); - local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi); + converted = local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -474,12 +501,14 @@ win866_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_WIN1251); - local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251); + converted = local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -488,12 +517,14 @@ win1251_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_WIN866); - local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866); + converted = local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -502,12 +533,14 @@ iso_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_KOI8R); - local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -516,12 +549,14 @@ koi8r_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_ISO_8859_5); - local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso); + converted = local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -530,12 +565,14 @@ iso_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN1251); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -544,12 +581,14 @@ win1251_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso); + converted = local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -558,12 +597,14 @@ iso_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN866); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -572,10 +613,12 @@ win866_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso); + converted = local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c index 4d7fb116cfd..88529c644cf 100644 --- a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c @@ -19,8 +19,8 @@ PG_MODULE_MAGIC; PG_FUNCTION_INFO_V1(euc_jis_2004_to_shift_jis_2004); PG_FUNCTION_INFO_V1(shift_jis_2004_to_euc_jis_2004); -static void euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len); -static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len); +static int euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError); /* ---------- * conv_proc( @@ -28,8 +28,11 @@ static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -39,12 +42,14 @@ euc_jis_2004_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_SHIFT_JIS_2004); - euc_jis_20042shift_jis_2004(src, dest, len); + converted = euc_jis_20042shift_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -53,20 +58,23 @@ shift_jis_2004_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_EUC_JIS_2004); - shift_jis_20042euc_jis_2004(src, dest, len); + converted = shift_jis_20042euc_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_JIS_2004 -> SHIFT_JIS_2004 */ -static void -euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, ku, ten; @@ -79,8 +87,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -90,8 +102,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) l = pg_encoding_verifymbchar(PG_EUC_JIS_2004, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (c1 == SS2 && l == 2) /* JIS X 0201 kana? */ { @@ -121,8 +137,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) *p++ = (ku + 0x19b) >> 1; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } if (ku % 2) @@ -132,8 +152,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; @@ -149,8 +173,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ku >= 63 && ku <= 94) *p++ = (ku + 0x181) >> 1; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (ku % 2) { @@ -159,20 +187,30 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else - report_invalid_encoding(PG_EUC_JIS_2004, + { + if (noError) + break; + report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } euc += l; len -= l; } *p = '\0'; + + return euc - start; } /* @@ -212,9 +250,10 @@ get_ten(int b, int *ku) * SHIFT_JIS_2004 ---> EUC_JIS_2004 */ -static void -shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len) +static int +shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1; int ku, ten, @@ -230,8 +269,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -241,8 +284,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len l = pg_encoding_verifymbchar(PG_SHIFT_JIS_2004, (const char *) sjis, len); if (l < 0 || l > len) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf && l == 1) { @@ -266,8 +313,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x100; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xe0 && c1 <= 0xef) /* plane 1 62ku-94ku */ @@ -275,9 +326,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x180; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, - (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xf0 && c1 <= 0xf3) /* plane 2 @@ -286,8 +340,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } switch (c1) { case 0xf0: @@ -309,16 +367,24 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 == 0xf4 && kubun == 1) ku = 15; else ku = (c1 << 1) - 0x19a - kubun; } else + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (plane == 2) *p++ = SS3; @@ -330,4 +396,6 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c index e9bb896935f..a8da733803d 100644 --- a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_cn2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_cn(const unsigned char *mic, unsigned char *p, int len); +static int euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_cn_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_cn_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_MULE_INTERNAL); - euc_cn2mic(src, dest, len); + converted = euc_cn2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_CN); - mic2euc_cn(src, dest, len); + converted = mic2euc_cn(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_CN ---> MIC */ -static void -euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; while (len > 0) @@ -76,7 +84,11 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (len < 2 || !IS_HIGHBIT_SET(euc[1])) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = LC_GB2312_80; *p++ = c1; *p++ = euc[1]; @@ -86,21 +98,28 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_CN */ -static void -mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) @@ -109,11 +128,19 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (c1 != LC_GB2312_80) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_CN, (const char *) mic, len); + } if (len < 3 || !IS_HIGHBIT_SET(mic[1]) || !IS_HIGHBIT_SET(mic[2])) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } mic++; *p++ = *mic++; *p++ = *mic++; @@ -122,12 +149,18 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; } } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c index 5059f917a98..cc4817dc4cd 100644 --- a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c @@ -42,17 +42,20 @@ PG_FUNCTION_INFO_V1(mic_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void sjis2mic(const unsigned char *sjis, unsigned char *p, int len); -static void mic2sjis(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_jp(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len); -static void sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len); +static int sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError); +static int mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_jp_to_sjis(PG_FUNCTION_ARGS) @@ -60,12 +63,14 @@ euc_jp_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_SJIS); - euc_jp2sjis(src, dest, len); + converted = euc_jp2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -74,12 +79,14 @@ sjis_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_EUC_JP); - sjis2euc_jp(src, dest, len); + converted = sjis2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -88,12 +95,14 @@ euc_jp_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_MULE_INTERNAL); - euc_jp2mic(src, dest, len); + converted = euc_jp2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -102,12 +111,14 @@ mic_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_JP); - mic2euc_jp(src, dest, len); + converted = mic2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -116,12 +127,14 @@ sjis_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_MULE_INTERNAL); - sjis2mic(src, dest, len); + converted = sjis2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -130,20 +143,23 @@ mic_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_SJIS); - mic2sjis(src, dest, len); + converted = mic2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * SJIS ---> MIC */ -static void -sjis2mic(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -167,7 +183,11 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) * JIS X0208, X0212, user defined extended characters */ if (len < 2 || !ISSJISHEAD(c1) || !ISSJISTAIL(sjis[1])) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } c2 = sjis[1]; k = (c1 << 8) + c2; if (k >= 0xed40 && k < 0xf040) @@ -257,21 +277,28 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; } } *p = '\0'; + + return sjis - start; } /* * MIC ---> SJIS */ -static void -mic2sjis(const unsigned char *mic, unsigned char *p, int len) +static int +mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1, c2, k, @@ -284,8 +311,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -293,8 +324,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) *p++ = mic[1]; else if (c1 == LC_JISX0208) @@ -350,20 +385,27 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_SJIS, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP ---> MIC */ -static void -euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -374,8 +416,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -383,8 +429,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* 1 byte kana? */ *p++ = LC_JISX0201K; @@ -406,14 +456,17 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_JP */ -static void -mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -424,8 +477,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -433,8 +490,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) { *p++ = SS2; @@ -452,20 +513,27 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_JP, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP -> SJIS */ -static void -euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, c2, k; @@ -478,8 +546,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -487,8 +559,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* hankaku kana? */ @@ -551,14 +627,17 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * SJIS ---> EUC_JP */ -static void -sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -573,8 +652,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -582,8 +665,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_SJIS, (const char *) sjis, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf) { /* JIS X0201 (1 byte kana) */ @@ -680,4 +767,6 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c index ac823d6c270..a5b51617e52 100644 --- a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_kr2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_kr(const unsigned char *mic, unsigned char *p, int len); +static int euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_kr_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_kr_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_MULE_INTERNAL); - euc_kr2mic(src, dest, len); + converted = euc_kr2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_KR); - mic2euc_kr(src, dest, len); + converted = mic2euc_kr(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_KR ---> MIC */ -static void -euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -78,8 +86,12 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_KR, (const char *) euc, len); if (l != 2) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = LC_KS5601; *p++ = c1; *p++ = euc[1]; @@ -89,22 +101,29 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_KR */ -static void -mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -115,8 +134,12 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -124,18 +147,28 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_KS5601) { *p++ = mic[1]; *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_KR, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c index 66c242d7f36..ebb4e0acd53 100644 --- a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c @@ -32,17 +32,20 @@ PG_FUNCTION_INFO_V1(mic_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_tw2big5(const unsigned char *euc, unsigned char *p, int len); -static void big52euc_tw(const unsigned char *euc, unsigned char *p, int len); -static void big52mic(const unsigned char *big5, unsigned char *p, int len); -static void mic2big5(const unsigned char *mic, unsigned char *p, int len); -static void euc_tw2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_tw(const unsigned char *mic, unsigned char *p, int len); +static int euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52euc_tw(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError); +static int mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_tw_to_big5(PG_FUNCTION_ARGS) @@ -50,12 +53,14 @@ euc_tw_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_BIG5); - euc_tw2big5(src, dest, len); + converted = euc_tw2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -64,12 +69,14 @@ big5_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_EUC_TW); - big52euc_tw(src, dest, len); + converted = big52euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -78,12 +85,14 @@ euc_tw_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_MULE_INTERNAL); - euc_tw2mic(src, dest, len); + converted = euc_tw2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -92,12 +101,14 @@ mic_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_TW); - mic2euc_tw(src, dest, len); + converted = mic2euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -106,12 +117,14 @@ big5_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_MULE_INTERNAL); - big52mic(src, dest, len); + converted = big52mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -120,21 +133,24 @@ mic_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_BIG5); - mic2big5(src, dest, len); + converted = mic2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_TW ---> Big5 */ -static void -euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; unsigned char c1; unsigned short big5buf, cnsBuf; @@ -149,8 +165,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Verify and decode the next EUC_TW input character */ l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -171,8 +191,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Write it out in Big5 */ big5buf = CNStoBIG5(cnsBuf, lc); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_EUC_TW, PG_BIG5, (const char *) euc, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; @@ -182,22 +206,29 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * Big5 ---> EUC_TW */ -static void -big52euc_tw(const unsigned char *big5, unsigned char *p, int len) +static int +big52euc_tw(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -212,8 +243,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); @@ -237,8 +272,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_EUC_TW, (const char *) big5, len); + } big5 += l; len -= l; @@ -256,14 +295,17 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) } } *p = '\0'; + + return big5 - start; } /* * EUC_TW ---> MIC */ -static void -euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -274,8 +316,12 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -304,22 +350,29 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_TW */ -static void -mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -330,8 +383,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -339,8 +396,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1) { *p++ = mic[1]; @@ -362,20 +423,27 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[3]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_TW, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * Big5 ---> MIC */ -static void -big52mic(const unsigned char *big5, unsigned char *p, int len) +static int +big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -389,8 +457,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } *p++ = c1; big5++; len--; @@ -398,8 +470,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); if (lc != 0) @@ -412,20 +488,27 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_MULE_INTERNAL, (const char *) big5, len); + } big5 += l; len -= l; } *p = '\0'; + + return big5 - start; } /* * MIC ---> Big5 */ -static void -mic2big5(const unsigned char *mic, unsigned char *p, int len) +static int +mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -438,8 +521,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -447,8 +534,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1 || c1 == LC_CNS11643_2 || c1 == LCPRV2_B) { if (c1 == LCPRV2_B) @@ -462,16 +553,26 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } big5buf = CNStoBIG5(cnsBuf, c1); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c index 2e28e6780a5..8610fcb69aa 100644 --- a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c +++ b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(win1250_to_latin2); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -82,12 +85,14 @@ latin2_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -96,12 +101,14 @@ mic_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN2); - mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -110,13 +117,15 @@ win1250_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - win1250_2_iso88592); + converted = latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -125,13 +134,15 @@ mic_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1250); - mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - iso88592_2_win1250); + converted = mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -140,12 +151,15 @@ latin2_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_WIN1250); - local2local(src, dest, len, PG_LATIN2, PG_WIN1250, iso88592_2_win1250); + converted = local2local(src, dest, len, PG_LATIN2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -154,10 +168,13 @@ win1250_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_LATIN2); - local2local(src, dest, len, PG_WIN1250, PG_LATIN2, win1250_2_iso88592); + converted = local2local(src, dest, len, PG_WIN1250, PG_LATIN2, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c index bc651410f21..bff27d1c295 100644 --- a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(mic_to_latin4); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -42,12 +45,14 @@ latin1_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,12 +61,14 @@ mic_to_latin1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN1); - mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -70,12 +77,14 @@ latin3_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN3, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -84,12 +93,14 @@ mic_to_latin3(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN3); - mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,12 +109,14 @@ latin4_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN4, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -112,10 +125,12 @@ mic_to_latin4(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN4); - mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c index d6067cdc24e..3838b15cab9 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ big5_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_UTF8); - LocalToUtf(src, len, dest, - &big5_to_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = LocalToUtf(src, len, dest, + &big5_to_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_BIG5); - UtfToLocal(src, len, dest, - &big5_from_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = UtfToLocal(src, len, dest, + &big5_from_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c index ed90e8e682e..75719fe5f1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c @@ -33,8 +33,11 @@ PG_FUNCTION_INFO_V1(koi8u_to_utf8); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -44,16 +47,19 @@ utf8_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8R); - UtfToLocal(src, len, dest, - &koi8r_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = UtfToLocal(src, len, dest, + &koi8r_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -62,16 +68,19 @@ koi8r_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8r_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = LocalToUtf(src, len, dest, + &koi8r_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -80,16 +89,19 @@ utf8_to_koi8u(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8U); - UtfToLocal(src, len, dest, - &koi8u_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = UtfToLocal(src, len, dest, + &koi8u_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,14 +110,17 @@ koi8u_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8U, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8u_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = LocalToUtf(src, len, dest, + &koi8u_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c index d699affce47..5391001951a 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jis_2004_to_unicode_tree, - LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = LocalToUtf(src, len, dest, + &euc_jis_2004_to_unicode_tree, + LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JIS_2004); - UtfToLocal(src, len, dest, - &euc_jis_2004_from_unicode_tree, - ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = UtfToLocal(src, len, dest, + &euc_jis_2004_from_unicode_tree, + ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c index d7c0ba6a58b..c87d1bf2398 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_cn_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_cn_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = LocalToUtf(src, len, dest, + &euc_cn_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_CN); - UtfToLocal(src, len, dest, - &euc_cn_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = UtfToLocal(src, len, dest, + &euc_cn_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c index 13a3a23e77b..6a55134db21 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jp); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jp_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jp_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = LocalToUtf(src, len, dest, + &euc_jp_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JP); - UtfToLocal(src, len, dest, - &euc_jp_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = UtfToLocal(src, len, dest, + &euc_jp_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c index 1bbb8aaef7b..fe1924e2fec 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_kr_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_kr_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = LocalToUtf(src, len, dest, + &euc_kr_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_KR); - UtfToLocal(src, len, dest, - &euc_kr_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = UtfToLocal(src, len, dest, + &euc_kr_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c index 9830045dccd..68215659b57 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_tw); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_tw_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_tw_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = LocalToUtf(src, len, dest, + &euc_tw_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_TW); - UtfToLocal(src, len, dest, - &euc_tw_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = UtfToLocal(src, len, dest, + &euc_tw_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c index f86ecf27424..e1a59c39a4d 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c @@ -183,8 +183,11 @@ conv_utf8_to_18030(uint32 code) * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -193,16 +196,19 @@ gb18030_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GB18030, PG_UTF8); - LocalToUtf(src, len, dest, - &gb18030_to_unicode_tree, - NULL, 0, - conv_18030_to_utf8, - PG_GB18030); + converted = LocalToUtf(src, len, dest, + &gb18030_to_unicode_tree, + NULL, 0, + conv_18030_to_utf8, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -211,14 +217,17 @@ utf8_to_gb18030(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GB18030); - UtfToLocal(src, len, dest, - &gb18030_from_unicode_tree, - NULL, 0, - conv_utf8_to_18030, - PG_GB18030); + converted = UtfToLocal(src, len, dest, + &gb18030_from_unicode_tree, + NULL, 0, + conv_utf8_to_18030, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c index 2ab8b16c8a8..881386d5347 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_gbk); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ gbk_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GBK, PG_UTF8); - LocalToUtf(src, len, dest, - &gbk_to_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = LocalToUtf(src, len, dest, + &gbk_to_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_gbk(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GBK); - UtfToLocal(src, len, dest, - &gbk_from_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = UtfToLocal(src, len, dest, + &gbk_from_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c index 3e49f67ea2f..d93a521badf 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c @@ -52,8 +52,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -100,6 +103,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -108,12 +112,15 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -122,7 +129,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -132,6 +139,7 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -140,12 +148,15 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -154,5 +165,5 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c index 67e713cca11..8ac93604a1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c @@ -26,8 +26,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859_1); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -37,6 +40,8 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_UTF8); @@ -45,7 +50,11 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_LATIN1, (const char *) src, len); + } if (!IS_HIGHBIT_SET(c)) *dest++ = c; else @@ -58,7 +67,7 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } Datum @@ -67,6 +76,8 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c, c1; @@ -76,7 +87,11 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_UTF8, (const char *) src, len); + } /* fast path for ASCII-subset characters */ if (!IS_HIGHBIT_SET(c)) { @@ -102,11 +117,15 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) len -= 2; } else + { + if (noError) + break; report_untranslatable_char(PG_UTF8, PG_LATIN1, (const char *) src, len); + } } } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c index 578f5df4e7f..317daa2d5ee 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_johab); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ johab_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_JOHAB, PG_UTF8); - LocalToUtf(src, len, dest, - &johab_to_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = LocalToUtf(src, len, dest, + &johab_to_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_johab(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_JOHAB); - UtfToLocal(src, len, dest, - &johab_from_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = UtfToLocal(src, len, dest, + &johab_from_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c index dd9fc2975ad..4c9348aba59 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ sjis_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_UTF8); - LocalToUtf(src, len, dest, - &sjis_to_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = LocalToUtf(src, len, dest, + &sjis_to_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SJIS); - UtfToLocal(src, len, dest, - &sjis_from_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = UtfToLocal(src, len, dest, + &sjis_from_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c index 4bcc886d674..1fffdc5930c 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_shift_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ shift_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &shift_jis_2004_to_unicode_tree, - LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = LocalToUtf(src, len, dest, + &shift_jis_2004_to_unicode_tree, + LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SHIFT_JIS_2004); - UtfToLocal(src, len, dest, - &shift_jis_2004_from_unicode_tree, - ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = UtfToLocal(src, len, dest, + &shift_jis_2004_from_unicode_tree, + ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c index c8e512994a1..d9471dad097 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_uhc); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ uhc_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UHC, PG_UTF8); - LocalToUtf(src, len, dest, - &uhc_to_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = LocalToUtf(src, len, dest, + &uhc_to_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_uhc(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_UHC); - UtfToLocal(src, len, dest, - &uhc_from_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = UtfToLocal(src, len, dest, + &uhc_from_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c index 0c9493dee56..110ba5677d0 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c @@ -48,8 +48,11 @@ PG_FUNCTION_INFO_V1(utf8_to_win); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -81,6 +84,7 @@ win_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -89,12 +93,15 @@ win_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -103,7 +110,7 @@ win_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -113,6 +120,7 @@ utf8_to_win(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -121,12 +129,15 @@ utf8_to_win(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -135,5 +146,5 @@ utf8_to_win(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/mbutils.c b/src/backend/utils/mb/mbutils.c index 2578573b0ab..65753860e35 100644 --- a/src/backend/utils/mb/mbutils.c +++ b/src/backend/utils/mb/mbutils.c @@ -406,12 +406,13 @@ pg_do_encoding_conversion(unsigned char *src, int len, MemoryContextAllocHuge(CurrentMemoryContext, (Size) len * MAX_CONVERSION_GROWTH + 1); - OidFunctionCall5(proc, - Int32GetDatum(src_encoding), - Int32GetDatum(dest_encoding), - CStringGetDatum(src), - CStringGetDatum(result), - Int32GetDatum(len)); + (void) OidFunctionCall6(proc, + Int32GetDatum(src_encoding), + Int32GetDatum(dest_encoding), + CStringGetDatum(src), + CStringGetDatum(result), + Int32GetDatum(len), + BoolGetDatum(false)); /* * If the result is large, it's worth repalloc'ing to release any extra @@ -849,12 +850,13 @@ pg_unicode_to_server(pg_wchar c, unsigned char *s) c_as_utf8[c_as_utf8_len] = '\0'; /* Convert, or throw error if we can't */ - FunctionCall5(Utf8ToServerConvProc, + FunctionCall6(Utf8ToServerConvProc, Int32GetDatum(PG_UTF8), Int32GetDatum(server_encoding), CStringGetDatum(c_as_utf8), CStringGetDatum(s), - Int32GetDatum(c_as_utf8_len)); + Int32GetDatum(c_as_utf8_len), + BoolGetDatum(false)); } diff --git a/src/bin/pg_upgrade/check.c b/src/bin/pg_upgrade/check.c index 43fc297eb69..ee6be95b08d 100644 --- a/src/bin/pg_upgrade/check.c +++ b/src/bin/pg_upgrade/check.c @@ -28,6 +28,7 @@ static void check_for_reg_data_type_usage(ClusterInfo *cluster); static void check_for_jsonb_9_4_usage(ClusterInfo *cluster); static void check_for_pg_role_prefix(ClusterInfo *cluster); static void check_for_new_tablespace_dir(ClusterInfo *new_cluster); +static void check_for_user_defined_encoding_conversions(ClusterInfo *cluster); static char *get_canonical_locale_name(int category, const char *locale); @@ -102,6 +103,15 @@ check_and_dump_old_cluster(bool live_check) check_for_reg_data_type_usage(&old_cluster); check_for_isn_and_int8_passing_mismatch(&old_cluster); + /* + * PG 14 changed the function signature of encoding conversion functions. + * Conversions from older versions cannot be upgraded automatically + * because the user-defined functions used by the encoding conversions + * need to changed to match the new signature. + */ + if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1300) + check_for_user_defined_encoding_conversions(&old_cluster); + /* * Pre-PG 14 allowed user defined postfix operators, which are not * supported anymore. Verify there are none, iff applicable. @@ -1268,6 +1278,91 @@ check_for_pg_role_prefix(ClusterInfo *cluster) check_ok(); } +/* + * Verify that no user-defined encoding conversions exist. + */ +static void +check_for_user_defined_encoding_conversions(ClusterInfo *cluster) +{ + int dbnum; + FILE *script = NULL; + bool found = false; + char output_path[MAXPGPATH]; + + prep_status("Checking for user-defined encoding conversions"); + + snprintf(output_path, sizeof(output_path), + "encoding_conversions.txt"); + + /* Find any user defined encoding conversions */ + for (dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++) + { + PGresult *res; + bool db_used = false; + int ntups; + int rowno; + int i_conoid, + i_conname, + i_nspname; + DbInfo *active_db = &cluster->dbarr.dbs[dbnum]; + PGconn *conn = connectToServer(cluster, active_db->db_name); + + /* + * The query below hardcodes FirstNormalObjectId as 16384 rather than + * interpolating that C #define into the query because, if that + * #define is ever changed, the cutoff we want to use is the value + * used by pre-version 14 servers, not that of some future version. + */ + res = executeQueryOrDie(conn, + "SELECT c.oid as conoid, c.conname, n.nspname " + "FROM pg_catalog.pg_conversion c, " + " pg_catalog.pg_namespace n " + "WHERE c.connamespace = n.oid AND " + " c.oid >= 16384"); + ntups = PQntuples(res); + i_conoid = PQfnumber(res, "conoid"); + i_conname = PQfnumber(res, "conname"); + i_nspname = PQfnumber(res, "nspname"); + for (rowno = 0; rowno < ntups; rowno++) + { + found = true; + if (script == NULL && + (script = fopen_priv(output_path, "w")) == NULL) + pg_fatal("could not open file \"%s\": %s\n", + output_path, strerror(errno)); + if (!db_used) + { + fprintf(script, "In database: %s\n", active_db->db_name); + db_used = true; + } + fprintf(script, " (oid=%s) %s.%s\n", + PQgetvalue(res, rowno, i_conoid), + PQgetvalue(res, rowno, i_nspname), + PQgetvalue(res, rowno, i_conname)); + } + + PQclear(res); + + PQfinish(conn); + } + + if (script) + fclose(script); + + if (found) + { + pg_log(PG_REPORT, "fatal\n"); + pg_fatal("Your installation contains user-defined encoding conversions.\n" + "The conversion function parameters changed in PostgreSQL version 14\n" + "so this cluster cannot currently be upgraded. You can remove the\n" + "encoding conversions in the old cluster and restart the upgrade.\n" + "A list of user-defined encoding conversions is in the file:\n" + " %s\n\n", output_path); + } + else + check_ok(); +} + /* * get_canonical_locale_name diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index f8174061ef3..75b829e8514 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10766,388 +10766,388 @@ # conversion functions { oid => '4302', descr => 'internal conversion function for KOI8R to MULE_INTERNAL', - proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_mic', + proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4303', descr => 'internal conversion function for MULE_INTERNAL to KOI8R', - proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_koi8r', + proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4304', descr => 'internal conversion function for ISO-8859-5 to MULE_INTERNAL', - proname => 'iso_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_mic', + proname => 'iso_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4305', descr => 'internal conversion function for MULE_INTERNAL to ISO-8859-5', - proname => 'mic_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_iso', + proname => 'mic_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4306', descr => 'internal conversion function for WIN1251 to MULE_INTERNAL', - proname => 'win1251_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_mic', + proname => 'win1251_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4307', descr => 'internal conversion function for MULE_INTERNAL to WIN1251', - proname => 'mic_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1251', + proname => 'mic_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4308', descr => 'internal conversion function for WIN866 to MULE_INTERNAL', - proname => 'win866_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_mic', + proname => 'win866_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4309', descr => 'internal conversion function for MULE_INTERNAL to WIN866', - proname => 'mic_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win866', + proname => 'mic_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4310', descr => 'internal conversion function for KOI8R to WIN1251', - proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4311', descr => 'internal conversion function for WIN1251 to KOI8R', - proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4312', descr => 'internal conversion function for KOI8R to WIN866', - proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_win866', + proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4313', descr => 'internal conversion function for WIN866 to KOI8R', - proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_koi8r', + proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4314', descr => 'internal conversion function for WIN866 to WIN1251', - proname => 'win866_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win866_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4315', descr => 'internal conversion function for WIN1251 to WIN866', - proname => 'win1251_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4316', descr => 'internal conversion function for ISO-8859-5 to KOI8R', - proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_koi8r', + proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4317', descr => 'internal conversion function for KOI8R to ISO-8859-5', - proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_iso', + proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4318', descr => 'internal conversion function for ISO-8859-5 to WIN1251', - proname => 'iso_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win1251', + proname => 'iso_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4319', descr => 'internal conversion function for WIN1251 to ISO-8859-5', - proname => 'win1251_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_iso', + proname => 'win1251_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4320', descr => 'internal conversion function for ISO-8859-5 to WIN866', - proname => 'iso_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win866', + proname => 'iso_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4321', descr => 'internal conversion function for WIN866 to ISO-8859-5', - proname => 'win866_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_iso', + proname => 'win866_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4322', descr => 'internal conversion function for EUC_CN to MULE_INTERNAL', - proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_mic', + proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_mic', probin => '$libdir/euc_cn_and_mic' }, { oid => '4323', descr => 'internal conversion function for MULE_INTERNAL to EUC_CN', - proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_cn', + proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_cn', probin => '$libdir/euc_cn_and_mic' }, { oid => '4324', descr => 'internal conversion function for EUC_JP to SJIS', - proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_sjis', + proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4325', descr => 'internal conversion function for SJIS to EUC_JP', - proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_euc_jp', + proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4326', descr => 'internal conversion function for EUC_JP to MULE_INTERNAL', - proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_mic', + proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4327', descr => 'internal conversion function for SJIS to MULE_INTERNAL', - proname => 'sjis_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_mic', + proname => 'sjis_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4328', descr => 'internal conversion function for MULE_INTERNAL to EUC_JP', - proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_jp', + proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4329', descr => 'internal conversion function for MULE_INTERNAL to SJIS', - proname => 'mic_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_sjis', + proname => 'mic_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4330', descr => 'internal conversion function for EUC_KR to MULE_INTERNAL', - proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_mic', + proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_mic', probin => '$libdir/euc_kr_and_mic' }, { oid => '4331', descr => 'internal conversion function for MULE_INTERNAL to EUC_KR', - proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_kr', + proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_kr', probin => '$libdir/euc_kr_and_mic' }, { oid => '4332', descr => 'internal conversion function for EUC_TW to BIG5', - proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_big5', + proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4333', descr => 'internal conversion function for BIG5 to EUC_TW', - proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_euc_tw', + proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4334', descr => 'internal conversion function for EUC_TW to MULE_INTERNAL', - proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_mic', + proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4335', descr => 'internal conversion function for BIG5 to MULE_INTERNAL', - proname => 'big5_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_mic', + proname => 'big5_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4336', descr => 'internal conversion function for MULE_INTERNAL to EUC_TW', - proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_tw', + proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4337', descr => 'internal conversion function for MULE_INTERNAL to BIG5', - proname => 'mic_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_big5', + proname => 'mic_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4338', descr => 'internal conversion function for LATIN2 to MULE_INTERNAL', - proname => 'latin2_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin2_to_mic', + proname => 'latin2_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4339', descr => 'internal conversion function for MULE_INTERNAL to LATIN2', - proname => 'mic_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin2', + proname => 'mic_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4340', descr => 'internal conversion function for WIN1250 to MULE_INTERNAL', - proname => 'win1250_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1250_to_mic', + proname => 'win1250_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4341', descr => 'internal conversion function for MULE_INTERNAL to WIN1250', - proname => 'mic_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1250', + proname => 'mic_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4342', descr => 'internal conversion function for LATIN2 to WIN1250', - proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4343', descr => 'internal conversion function for WIN1250 to LATIN2', - proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4344', descr => 'internal conversion function for LATIN1 to MULE_INTERNAL', - proname => 'latin1_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin1_to_mic', + proname => 'latin1_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin1_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4345', descr => 'internal conversion function for MULE_INTERNAL to LATIN1', - proname => 'mic_to_latin1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin1', + proname => 'mic_to_latin1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin1', probin => '$libdir/latin_and_mic' }, { oid => '4346', descr => 'internal conversion function for LATIN3 to MULE_INTERNAL', - proname => 'latin3_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin3_to_mic', + proname => 'latin3_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin3_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4347', descr => 'internal conversion function for MULE_INTERNAL to LATIN3', - proname => 'mic_to_latin3', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin3', + proname => 'mic_to_latin3', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin3', probin => '$libdir/latin_and_mic' }, { oid => '4348', descr => 'internal conversion function for LATIN4 to MULE_INTERNAL', - proname => 'latin4_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin4_to_mic', + proname => 'latin4_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin4_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4349', descr => 'internal conversion function for MULE_INTERNAL to LATIN4', - proname => 'mic_to_latin4', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin4', + proname => 'mic_to_latin4', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin4', probin => '$libdir/latin_and_mic' }, { oid => '4352', descr => 'internal conversion function for BIG5 to UTF8', - proname => 'big5_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_utf8', + proname => 'big5_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_utf8', probin => '$libdir/utf8_and_big5' }, { oid => '4353', descr => 'internal conversion function for UTF8 to BIG5', - proname => 'utf8_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_big5', + proname => 'utf8_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_big5', probin => '$libdir/utf8_and_big5' }, { oid => '4354', descr => 'internal conversion function for UTF8 to KOI8R', - proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8r', + proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8r', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4355', descr => 'internal conversion function for KOI8R to UTF8', - proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_utf8', + proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4356', descr => 'internal conversion function for UTF8 to KOI8U', - proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8u', + proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8u', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4357', descr => 'internal conversion function for KOI8U to UTF8', - proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8u_to_utf8', + proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8u_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4358', descr => 'internal conversion function for UTF8 to WIN', - proname => 'utf8_to_win', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_win', + proname => 'utf8_to_win', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_win', probin => '$libdir/utf8_and_win' }, { oid => '4359', descr => 'internal conversion function for WIN to UTF8', - proname => 'win_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win_to_utf8', + proname => 'win_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win_to_utf8', probin => '$libdir/utf8_and_win' }, { oid => '4360', descr => 'internal conversion function for EUC_CN to UTF8', - proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_utf8', + proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_utf8', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4361', descr => 'internal conversion function for UTF8 to EUC_CN', - proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_cn', + proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_cn', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4362', descr => 'internal conversion function for EUC_JP to UTF8', - proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_utf8', + proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_utf8', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4363', descr => 'internal conversion function for UTF8 to EUC_JP', - proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_jp', + proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jp', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4364', descr => 'internal conversion function for EUC_KR to UTF8', - proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_utf8', + proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_utf8', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4365', descr => 'internal conversion function for UTF8 to EUC_KR', - proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_kr', + proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_kr', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4366', descr => 'internal conversion function for EUC_TW to UTF8', - proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_utf8', + proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_utf8', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4367', descr => 'internal conversion function for UTF8 to EUC_TW', - proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_tw', + proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_tw', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4368', descr => 'internal conversion function for GB18030 to UTF8', - proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gb18030_to_utf8', + proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gb18030_to_utf8', probin => '$libdir/utf8_and_gb18030' }, { oid => '4369', descr => 'internal conversion function for UTF8 to GB18030', - proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gb18030', + proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gb18030', probin => '$libdir/utf8_and_gb18030' }, { oid => '4370', descr => 'internal conversion function for GBK to UTF8', - proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gbk_to_utf8', + proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gbk_to_utf8', probin => '$libdir/utf8_and_gbk' }, { oid => '4371', descr => 'internal conversion function for UTF8 to GBK', - proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gbk', + proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gbk', probin => '$libdir/utf8_and_gbk' }, { oid => '4372', descr => 'internal conversion function for UTF8 to ISO-8859 2-16', - proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_iso8859', + proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859', probin => '$libdir/utf8_and_iso8859' }, { oid => '4373', descr => 'internal conversion function for ISO-8859 2-16 to UTF8', - proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso8859_to_utf8', + proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_to_utf8', probin => '$libdir/utf8_and_iso8859' }, { oid => '4374', descr => 'internal conversion function for LATIN1 to UTF8', - proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_1_to_utf8', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4375', descr => 'internal conversion function for UTF8 to LATIN1', - proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859_1', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4376', descr => 'internal conversion function for JOHAB to UTF8', - proname => 'johab_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'johab_to_utf8', + proname => 'johab_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'johab_to_utf8', probin => '$libdir/utf8_and_johab' }, { oid => '4377', descr => 'internal conversion function for UTF8 to JOHAB', - proname => 'utf8_to_johab', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_johab', + proname => 'utf8_to_johab', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_johab', probin => '$libdir/utf8_and_johab' }, { oid => '4378', descr => 'internal conversion function for SJIS to UTF8', - proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_utf8', + proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_utf8', probin => '$libdir/utf8_and_sjis' }, { oid => '4379', descr => 'internal conversion function for UTF8 to SJIS', - proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_sjis', + proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_sjis', probin => '$libdir/utf8_and_sjis' }, { oid => '4380', descr => 'internal conversion function for UHC to UTF8', - proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'uhc_to_utf8', + proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'uhc_to_utf8', probin => '$libdir/utf8_and_uhc' }, { oid => '4381', descr => 'internal conversion function for UTF8 to UHC', - proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_uhc', + proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_uhc', probin => '$libdir/utf8_and_uhc' }, { oid => '4382', descr => 'internal conversion function for EUC_JIS_2004 to UTF8', - proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_utf8', probin => '$libdir/utf8_and_euc2004' }, { oid => '4383', descr => 'internal conversion function for UTF8 to EUC_JIS_2004', - proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jis_2004', probin => '$libdir/utf8_and_euc2004' }, { oid => '4384', descr => 'internal conversion function for SHIFT_JIS_2004 to UTF8', - proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_utf8', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4385', descr => 'internal conversion function for UTF8 to SHIFT_JIS_2004', - proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_shift_jis_2004', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4386', descr => 'internal conversion function for EUC_JIS_2004 to SHIFT_JIS_2004', proname => 'euc_jis_2004_to_shift_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_shift_jis_2004', probin => '$libdir/euc2004_sjis2004' }, { oid => '4387', descr => 'internal conversion function for SHIFT_JIS_2004 to EUC_JIS_2004', proname => 'shift_jis_2004_to_euc_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_euc_jis_2004', probin => '$libdir/euc2004_sjis2004' }, diff --git a/src/include/mb/pg_wchar.h b/src/include/mb/pg_wchar.h index 64b22e4b0d4..346a41a1f3d 100644 --- a/src/include/mb/pg_wchar.h +++ b/src/include/mb/pg_wchar.h @@ -627,18 +627,18 @@ extern void pg_unicode_to_server(pg_wchar c, unsigned char *s); extern unsigned short BIG5toCNS(unsigned short big5, unsigned char *lc); extern unsigned short CNStoBIG5(unsigned short cns, unsigned char lc); -extern void UtfToLocal(const unsigned char *utf, int len, - unsigned char *iso, - const pg_mb_radix_tree *map, - const pg_utf_to_local_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); -extern void LocalToUtf(const unsigned char *iso, int len, - unsigned char *utf, - const pg_mb_radix_tree *map, - const pg_local_to_utf_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); +extern int UtfToLocal(const unsigned char *utf, int len, + unsigned char *iso, + const pg_mb_radix_tree *map, + const pg_utf_to_local_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); +extern int LocalToUtf(const unsigned char *iso, int len, + unsigned char *utf, + const pg_mb_radix_tree *map, + const pg_local_to_utf_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); extern bool pg_verifymbstr(const char *mbstr, int len, bool noError); extern bool pg_verify_mbstr(int encoding, const char *mbstr, int len, @@ -656,18 +656,19 @@ extern void report_invalid_encoding(int encoding, const char *mbstr, int len) pg extern void report_untranslatable_char(int src_encoding, int dest_encoding, const char *mbstr, int len) pg_attribute_noreturn(); -extern void local2local(const unsigned char *l, unsigned char *p, int len, - int src_encoding, int dest_encoding, const unsigned char *tab); -extern void latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding); -extern void mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding); -extern void latin2mic_with_table(const unsigned char *l, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); -extern void mic2latin_with_table(const unsigned char *mic, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); +extern int local2local(const unsigned char *l, unsigned char *p, int len, + int src_encoding, int dest_encoding, const unsigned char *tab, + bool noError); +extern int latin2mic(const unsigned char *l, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int mic2latin(const unsigned char *mic, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int latin2mic_with_table(const unsigned char *l, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); +extern int mic2latin_with_table(const unsigned char *mic, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); #ifdef WIN32 extern WCHAR *pgwin32_message_to_UTF16(const char *str, int len, int *utf16len); diff --git a/src/test/regress/expected/opr_sanity.out b/src/test/regress/expected/opr_sanity.out index 254ca06d3dd..23ba60e395f 100644 --- a/src/test/regress/expected/opr_sanity.out +++ b/src/test/regress/expected/opr_sanity.out @@ -1052,13 +1052,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); oid | proname | oid | conname -----+---------+-----+--------- (0 rows) diff --git a/src/test/regress/sql/opr_sanity.sql b/src/test/regress/sql/opr_sanity.sql index bbd3834b634..04691745981 100644 --- a/src/test/regress/sql/opr_sanity.sql +++ b/src/test/regress/sql/opr_sanity.sql @@ -556,13 +556,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); -- Check for conprocs that don't perform the specific conversion that -- pg_conversion alleges they do, by trying to invoke each conversion -- 2.29.2 --------------39E46EF15EBFAA37D53332E5 Content-Type: text/x-patch; charset=UTF-8; name="v3-0003-Add-tests-for-the-new-noError-variants-of-built-i.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="v3-0003-Add-tests-for-the-new-noError-variants-of-built-i.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 34+ messages in thread
* [PATCH v3 2/5] Change conversion function signature. @ 2021-01-28 16:42 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 34+ messages in thread From: Heikki Linnakangas @ 2021-01-28 16:42 UTC (permalink / raw) Add a 'noError' argument, so that we can try to convert a buffer without knowing the character boundaries beforehand. The functions now need to return the number of input bytes successfully converted. This is is a backwards-incompatible change, if you have created a custom encoding conversion with CREATE CONVERSION. This adds a check to pg_upgrade for that, refusing the upgrade if there are any user-defined encoding conversions. --- doc/src/sgml/ref/create_conversion.sgml | 5 +- src/backend/commands/conversioncmds.c | 27 +- src/backend/utils/error/elog.c | 2 + src/backend/utils/mb/conv.c | 112 +++++- .../cyrillic_and_mic/cyrillic_and_mic.c | 127 ++++--- .../euc2004_sjis2004/euc2004_sjis2004.c | 96 ++++- .../euc_cn_and_mic/euc_cn_and_mic.c | 57 ++- .../euc_jp_and_sjis/euc_jp_and_sjis.c | 153 ++++++-- .../euc_kr_and_mic/euc_kr_and_mic.c | 57 ++- .../euc_tw_and_big5/euc_tw_and_big5.c | 165 +++++++-- .../latin2_and_win1250/latin2_and_win1250.c | 49 ++- .../latin_and_mic/latin_and_mic.c | 43 ++- .../utf8_and_big5/utf8_and_big5.c | 37 +- .../utf8_and_cyrillic/utf8_and_cyrillic.c | 67 ++-- .../utf8_and_euc2004/utf8_and_euc2004.c | 37 +- .../utf8_and_euc_cn/utf8_and_euc_cn.c | 37 +- .../utf8_and_euc_jp/utf8_and_euc_jp.c | 37 +- .../utf8_and_euc_kr/utf8_and_euc_kr.c | 37 +- .../utf8_and_euc_tw/utf8_and_euc_tw.c | 37 +- .../utf8_and_gb18030/utf8_and_gb18030.c | 37 +- .../utf8_and_gbk/utf8_and_gbk.c | 37 +- .../utf8_and_iso8859/utf8_and_iso8859.c | 43 ++- .../utf8_and_iso8859_1/utf8_and_iso8859_1.c | 27 +- .../utf8_and_johab/utf8_and_johab.c | 37 +- .../utf8_and_sjis/utf8_and_sjis.c | 37 +- .../utf8_and_sjis2004/utf8_and_sjis2004.c | 37 +- .../utf8_and_uhc/utf8_and_uhc.c | 37 +- .../utf8_and_win/utf8_and_win.c | 43 ++- src/backend/utils/mb/mbutils.c | 18 +- src/bin/pg_upgrade/check.c | 95 +++++ src/include/catalog/pg_proc.dat | 332 +++++++++--------- src/include/mb/pg_wchar.h | 49 +-- src/test/regress/expected/opr_sanity.out | 7 +- src/test/regress/sql/opr_sanity.sql | 7 +- 34 files changed, 1390 insertions(+), 635 deletions(-) diff --git a/doc/src/sgml/ref/create_conversion.sgml b/doc/src/sgml/ref/create_conversion.sgml index e7700fecfc5..f014a676c88 100644 --- a/doc/src/sgml/ref/create_conversion.sgml +++ b/doc/src/sgml/ref/create_conversion.sgml @@ -117,8 +117,9 @@ conv_proc( integer, -- destination encoding ID cstring, -- source string (null terminated C string) internal, -- destination (fill with a null terminated C string) - integer -- source string length -) RETURNS void; + integer, -- source string length + boolean -- if true, don't throw an error if conversion fails +) RETURNS integer; </programlisting></para> </listitem> </varlistentry> diff --git a/src/backend/commands/conversioncmds.c b/src/backend/commands/conversioncmds.c index f7ff321de71..d2041466911 100644 --- a/src/backend/commands/conversioncmds.c +++ b/src/backend/commands/conversioncmds.c @@ -45,8 +45,9 @@ CreateConversionCommand(CreateConversionStmt *stmt) const char *from_encoding_name = stmt->for_encoding_name; const char *to_encoding_name = stmt->to_encoding_name; List *func_name = stmt->func_name; - static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID}; + static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID, BOOLOID}; char result[1]; + Datum funcresult; /* Convert list of names to a name and namespace */ namespaceId = QualifiedNameGetCreationNamespace(stmt->conversion_name, @@ -92,8 +93,8 @@ CreateConversionCommand(CreateConversionStmt *stmt) funcoid = LookupFuncName(func_name, sizeof(funcargs) / sizeof(Oid), funcargs, false); - /* Check it returns VOID, else it's probably the wrong function */ - if (get_func_rettype(funcoid) != VOIDOID) + /* Check it returns int4, else it's probably the wrong function */ + if (get_func_rettype(funcoid) != INT4OID) ereport(ERROR, (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), errmsg("encoding conversion function %s must return type %s", @@ -111,12 +112,20 @@ CreateConversionCommand(CreateConversionStmt *stmt) * string; the conversion function should throw an error if it can't * perform the requested conversion. */ - OidFunctionCall5(funcoid, - Int32GetDatum(from_encoding), - Int32GetDatum(to_encoding), - CStringGetDatum(""), - CStringGetDatum(result), - Int32GetDatum(0)); + funcresult = OidFunctionCall6(funcoid, + Int32GetDatum(from_encoding), + Int32GetDatum(to_encoding), + CStringGetDatum(""), + CStringGetDatum(result), + Int32GetDatum(0), + BoolGetDatum(false)); + + /* The function should return 0 for empty input. Might as well check that, too. */ + if (DatumGetInt32(funcresult) != 0) + ereport(ERROR, + (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), + errmsg("encoding conversion function %s returned incorrect result for empty input", + NameListToString(func_name)))); /* * All seem ok, go ahead (possible failure would be a duplicate conversion diff --git a/src/backend/utils/error/elog.c b/src/backend/utils/error/elog.c index 80c26724612..762f77d533c 100644 --- a/src/backend/utils/error/elog.c +++ b/src/backend/utils/error/elog.c @@ -2280,6 +2280,8 @@ write_console(const char *line, int len) * Conversion on non-win32 platforms is not implemented yet. It requires * non-throw version of pg_do_encoding_conversion(), that converts * unconvertable characters to '?' without errors. + * + * XXX: We have a no-throw version now. It doesn't convert to '?' though. */ #endif diff --git a/src/backend/utils/mb/conv.c b/src/backend/utils/mb/conv.c index a07b54bd3b8..b83358bc7a5 100644 --- a/src/backend/utils/mb/conv.c +++ b/src/backend/utils/mb/conv.c @@ -26,14 +26,16 @@ * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the target charset, or 0 if there is no equivalent code. */ -void +int local2local(const unsigned char *l, unsigned char *p, int len, int src_encoding, int dest_encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -41,7 +43,11 @@ local2local(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(src_encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -50,13 +56,19 @@ local2local(const unsigned char *l, if (c2) *p++ = c2; else + { + if (noError) + break; report_untranslatable_char(src_encoding, dest_encoding, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -67,17 +79,22 @@ local2local(const unsigned char *l, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = l; int c1; while (len > 0) { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (IS_HIGHBIT_SET(c1)) *p++ = lc; *p++ = c1; @@ -85,6 +102,8 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, len--; } *p = '\0'; + + return l - start; } /* @@ -95,17 +114,22 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -118,17 +142,27 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1])) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); + } *p++ = mic[1]; mic += 2; len -= 2; } } *p = '\0'; + + return mic - start; } @@ -144,14 +178,16 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the mule encoding, or 0 if there is no equivalent code. */ -void +int latin2mic_with_table(const unsigned char *l, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -159,7 +195,11 @@ latin2mic_with_table(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -171,13 +211,19 @@ latin2mic_with_table(const unsigned char *l, *p++ = c2; } else + { + if (noError) + break; report_untranslatable_char(encoding, PG_MULE_INTERNAL, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -192,14 +238,16 @@ latin2mic_with_table(const unsigned char *l, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the local charset, or 0 if there is no equivalent code. */ -void +int mic2latin_with_table(const unsigned char *mic, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = mic; unsigned char c1, c2; @@ -207,7 +255,11 @@ mic2latin_with_table(const unsigned char *mic, { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -220,11 +272,17 @@ mic2latin_with_table(const unsigned char *mic, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1]) || (c2 = tab[mic[1] - HIGHBIT]) == 0) { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); break; /* keep compiler quiet */ @@ -235,6 +293,8 @@ mic2latin_with_table(const unsigned char *mic, } } *p = '\0'; + + return mic - start; } /* @@ -425,17 +485,19 @@ pg_mb_radix_conv(const pg_mb_radix_tree *rt, * * See pg_wchar.h for more details about the data structures used here. */ -void +int UtfToLocal(const unsigned char *utf, int len, unsigned char *iso, const pg_mb_radix_tree *map, const pg_utf_to_local_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, bool noError) { uint32 iutf; int l; const pg_utf_to_local_combined *cp; + const unsigned char *start = utf; + const unsigned char *cur = utf; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -449,6 +511,8 @@ UtfToLocal(const unsigned char *utf, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*utf == '\0') break; @@ -584,15 +648,19 @@ UtfToLocal(const unsigned char *utf, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(PG_UTF8, encoding, (const char *) (utf - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(PG_UTF8, (const char *) utf, len); *iso = '\0'; + + return cur - start; } /* @@ -616,18 +684,24 @@ UtfToLocal(const unsigned char *utf, int len, * (if provided) is applied. An error is raised if no match is found. * * See pg_wchar.h for more details about the data structures used here. + * + * Returns the number of input bytes consumed. If noError is true, this can + * be less than 'len'. */ -void +int LocalToUtf(const unsigned char *iso, int len, unsigned char *utf, const pg_mb_radix_tree *map, const pg_local_to_utf_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, + bool noError) { uint32 iiso; int l; const pg_local_to_utf_combined *cp; + const unsigned char *start = iso; + const unsigned char *cur = iso; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -641,6 +715,8 @@ LocalToUtf(const unsigned char *iso, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*iso == '\0') break; @@ -723,13 +799,17 @@ LocalToUtf(const unsigned char *iso, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(encoding, PG_UTF8, (const char *) (iso - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(encoding, (const char *) iso, len); *utf = '\0'; + + return cur - start; } diff --git a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c index 4c5b02654de..368c2deb5e4 100644 --- a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c @@ -44,8 +44,11 @@ PG_FUNCTION_INFO_V1(win866_to_iso); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -306,12 +309,14 @@ koi8r_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -320,12 +325,14 @@ mic_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_KOI8R); - mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -334,12 +341,14 @@ iso_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -348,12 +357,14 @@ mic_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_ISO_8859_5); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -362,12 +373,14 @@ win1251_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -376,12 +389,14 @@ mic_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1251); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -390,12 +405,14 @@ win866_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -404,12 +421,14 @@ mic_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN866); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -418,12 +437,14 @@ koi8r_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN1251); - local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -432,12 +453,14 @@ win1251_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_KOI8R); - local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi); + converted = local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -446,12 +469,14 @@ koi8r_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN866); - local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -460,12 +485,14 @@ win866_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_KOI8R); - local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi); + converted = local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -474,12 +501,14 @@ win866_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_WIN1251); - local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251); + converted = local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -488,12 +517,14 @@ win1251_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_WIN866); - local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866); + converted = local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -502,12 +533,14 @@ iso_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_KOI8R); - local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -516,12 +549,14 @@ koi8r_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_ISO_8859_5); - local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso); + converted = local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -530,12 +565,14 @@ iso_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN1251); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -544,12 +581,14 @@ win1251_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso); + converted = local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -558,12 +597,14 @@ iso_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN866); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -572,10 +613,12 @@ win866_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso); + converted = local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c index 4d7fb116cfd..88529c644cf 100644 --- a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c @@ -19,8 +19,8 @@ PG_MODULE_MAGIC; PG_FUNCTION_INFO_V1(euc_jis_2004_to_shift_jis_2004); PG_FUNCTION_INFO_V1(shift_jis_2004_to_euc_jis_2004); -static void euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len); -static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len); +static int euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError); /* ---------- * conv_proc( @@ -28,8 +28,11 @@ static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -39,12 +42,14 @@ euc_jis_2004_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_SHIFT_JIS_2004); - euc_jis_20042shift_jis_2004(src, dest, len); + converted = euc_jis_20042shift_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -53,20 +58,23 @@ shift_jis_2004_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_EUC_JIS_2004); - shift_jis_20042euc_jis_2004(src, dest, len); + converted = shift_jis_20042euc_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_JIS_2004 -> SHIFT_JIS_2004 */ -static void -euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, ku, ten; @@ -79,8 +87,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -90,8 +102,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) l = pg_encoding_verifymbchar(PG_EUC_JIS_2004, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (c1 == SS2 && l == 2) /* JIS X 0201 kana? */ { @@ -121,8 +137,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) *p++ = (ku + 0x19b) >> 1; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } if (ku % 2) @@ -132,8 +152,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; @@ -149,8 +173,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ku >= 63 && ku <= 94) *p++ = (ku + 0x181) >> 1; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (ku % 2) { @@ -159,20 +187,30 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else - report_invalid_encoding(PG_EUC_JIS_2004, + { + if (noError) + break; + report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } euc += l; len -= l; } *p = '\0'; + + return euc - start; } /* @@ -212,9 +250,10 @@ get_ten(int b, int *ku) * SHIFT_JIS_2004 ---> EUC_JIS_2004 */ -static void -shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len) +static int +shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1; int ku, ten, @@ -230,8 +269,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -241,8 +284,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len l = pg_encoding_verifymbchar(PG_SHIFT_JIS_2004, (const char *) sjis, len); if (l < 0 || l > len) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf && l == 1) { @@ -266,8 +313,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x100; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xe0 && c1 <= 0xef) /* plane 1 62ku-94ku */ @@ -275,9 +326,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x180; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, - (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xf0 && c1 <= 0xf3) /* plane 2 @@ -286,8 +340,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } switch (c1) { case 0xf0: @@ -309,16 +367,24 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 == 0xf4 && kubun == 1) ku = 15; else ku = (c1 << 1) - 0x19a - kubun; } else + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (plane == 2) *p++ = SS3; @@ -330,4 +396,6 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c index e9bb896935f..a8da733803d 100644 --- a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_cn2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_cn(const unsigned char *mic, unsigned char *p, int len); +static int euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_cn_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_cn_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_MULE_INTERNAL); - euc_cn2mic(src, dest, len); + converted = euc_cn2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_CN); - mic2euc_cn(src, dest, len); + converted = mic2euc_cn(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_CN ---> MIC */ -static void -euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; while (len > 0) @@ -76,7 +84,11 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (len < 2 || !IS_HIGHBIT_SET(euc[1])) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = LC_GB2312_80; *p++ = c1; *p++ = euc[1]; @@ -86,21 +98,28 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_CN */ -static void -mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) @@ -109,11 +128,19 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (c1 != LC_GB2312_80) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_CN, (const char *) mic, len); + } if (len < 3 || !IS_HIGHBIT_SET(mic[1]) || !IS_HIGHBIT_SET(mic[2])) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } mic++; *p++ = *mic++; *p++ = *mic++; @@ -122,12 +149,18 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; } } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c index 5059f917a98..cc4817dc4cd 100644 --- a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c @@ -42,17 +42,20 @@ PG_FUNCTION_INFO_V1(mic_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void sjis2mic(const unsigned char *sjis, unsigned char *p, int len); -static void mic2sjis(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_jp(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len); -static void sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len); +static int sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError); +static int mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_jp_to_sjis(PG_FUNCTION_ARGS) @@ -60,12 +63,14 @@ euc_jp_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_SJIS); - euc_jp2sjis(src, dest, len); + converted = euc_jp2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -74,12 +79,14 @@ sjis_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_EUC_JP); - sjis2euc_jp(src, dest, len); + converted = sjis2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -88,12 +95,14 @@ euc_jp_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_MULE_INTERNAL); - euc_jp2mic(src, dest, len); + converted = euc_jp2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -102,12 +111,14 @@ mic_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_JP); - mic2euc_jp(src, dest, len); + converted = mic2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -116,12 +127,14 @@ sjis_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_MULE_INTERNAL); - sjis2mic(src, dest, len); + converted = sjis2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -130,20 +143,23 @@ mic_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_SJIS); - mic2sjis(src, dest, len); + converted = mic2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * SJIS ---> MIC */ -static void -sjis2mic(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -167,7 +183,11 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) * JIS X0208, X0212, user defined extended characters */ if (len < 2 || !ISSJISHEAD(c1) || !ISSJISTAIL(sjis[1])) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } c2 = sjis[1]; k = (c1 << 8) + c2; if (k >= 0xed40 && k < 0xf040) @@ -257,21 +277,28 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; } } *p = '\0'; + + return sjis - start; } /* * MIC ---> SJIS */ -static void -mic2sjis(const unsigned char *mic, unsigned char *p, int len) +static int +mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1, c2, k, @@ -284,8 +311,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -293,8 +324,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) *p++ = mic[1]; else if (c1 == LC_JISX0208) @@ -350,20 +385,27 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_SJIS, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP ---> MIC */ -static void -euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -374,8 +416,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -383,8 +429,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* 1 byte kana? */ *p++ = LC_JISX0201K; @@ -406,14 +456,17 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_JP */ -static void -mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -424,8 +477,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -433,8 +490,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) { *p++ = SS2; @@ -452,20 +513,27 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_JP, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP -> SJIS */ -static void -euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, c2, k; @@ -478,8 +546,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -487,8 +559,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* hankaku kana? */ @@ -551,14 +627,17 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * SJIS ---> EUC_JP */ -static void -sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -573,8 +652,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -582,8 +665,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_SJIS, (const char *) sjis, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf) { /* JIS X0201 (1 byte kana) */ @@ -680,4 +767,6 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c index ac823d6c270..a5b51617e52 100644 --- a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_kr2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_kr(const unsigned char *mic, unsigned char *p, int len); +static int euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_kr_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_kr_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_MULE_INTERNAL); - euc_kr2mic(src, dest, len); + converted = euc_kr2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_KR); - mic2euc_kr(src, dest, len); + converted = mic2euc_kr(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_KR ---> MIC */ -static void -euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -78,8 +86,12 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_KR, (const char *) euc, len); if (l != 2) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = LC_KS5601; *p++ = c1; *p++ = euc[1]; @@ -89,22 +101,29 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_KR */ -static void -mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -115,8 +134,12 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -124,18 +147,28 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_KS5601) { *p++ = mic[1]; *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_KR, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c index 66c242d7f36..ebb4e0acd53 100644 --- a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c @@ -32,17 +32,20 @@ PG_FUNCTION_INFO_V1(mic_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_tw2big5(const unsigned char *euc, unsigned char *p, int len); -static void big52euc_tw(const unsigned char *euc, unsigned char *p, int len); -static void big52mic(const unsigned char *big5, unsigned char *p, int len); -static void mic2big5(const unsigned char *mic, unsigned char *p, int len); -static void euc_tw2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_tw(const unsigned char *mic, unsigned char *p, int len); +static int euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52euc_tw(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError); +static int mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_tw_to_big5(PG_FUNCTION_ARGS) @@ -50,12 +53,14 @@ euc_tw_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_BIG5); - euc_tw2big5(src, dest, len); + converted = euc_tw2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -64,12 +69,14 @@ big5_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_EUC_TW); - big52euc_tw(src, dest, len); + converted = big52euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -78,12 +85,14 @@ euc_tw_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_MULE_INTERNAL); - euc_tw2mic(src, dest, len); + converted = euc_tw2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -92,12 +101,14 @@ mic_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_TW); - mic2euc_tw(src, dest, len); + converted = mic2euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -106,12 +117,14 @@ big5_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_MULE_INTERNAL); - big52mic(src, dest, len); + converted = big52mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -120,21 +133,24 @@ mic_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_BIG5); - mic2big5(src, dest, len); + converted = mic2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_TW ---> Big5 */ -static void -euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; unsigned char c1; unsigned short big5buf, cnsBuf; @@ -149,8 +165,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Verify and decode the next EUC_TW input character */ l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -171,8 +191,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Write it out in Big5 */ big5buf = CNStoBIG5(cnsBuf, lc); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_EUC_TW, PG_BIG5, (const char *) euc, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; @@ -182,22 +206,29 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * Big5 ---> EUC_TW */ -static void -big52euc_tw(const unsigned char *big5, unsigned char *p, int len) +static int +big52euc_tw(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -212,8 +243,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); @@ -237,8 +272,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_EUC_TW, (const char *) big5, len); + } big5 += l; len -= l; @@ -256,14 +295,17 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) } } *p = '\0'; + + return big5 - start; } /* * EUC_TW ---> MIC */ -static void -euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -274,8 +316,12 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -304,22 +350,29 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_TW */ -static void -mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -330,8 +383,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -339,8 +396,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1) { *p++ = mic[1]; @@ -362,20 +423,27 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[3]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_TW, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * Big5 ---> MIC */ -static void -big52mic(const unsigned char *big5, unsigned char *p, int len) +static int +big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -389,8 +457,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } *p++ = c1; big5++; len--; @@ -398,8 +470,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); if (lc != 0) @@ -412,20 +488,27 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_MULE_INTERNAL, (const char *) big5, len); + } big5 += l; len -= l; } *p = '\0'; + + return big5 - start; } /* * MIC ---> Big5 */ -static void -mic2big5(const unsigned char *mic, unsigned char *p, int len) +static int +mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -438,8 +521,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -447,8 +534,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1 || c1 == LC_CNS11643_2 || c1 == LCPRV2_B) { if (c1 == LCPRV2_B) @@ -462,16 +553,26 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } big5buf = CNStoBIG5(cnsBuf, c1); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c index 2e28e6780a5..8610fcb69aa 100644 --- a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c +++ b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(win1250_to_latin2); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -82,12 +85,14 @@ latin2_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -96,12 +101,14 @@ mic_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN2); - mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -110,13 +117,15 @@ win1250_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - win1250_2_iso88592); + converted = latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -125,13 +134,15 @@ mic_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1250); - mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - iso88592_2_win1250); + converted = mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -140,12 +151,15 @@ latin2_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_WIN1250); - local2local(src, dest, len, PG_LATIN2, PG_WIN1250, iso88592_2_win1250); + converted = local2local(src, dest, len, PG_LATIN2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -154,10 +168,13 @@ win1250_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_LATIN2); - local2local(src, dest, len, PG_WIN1250, PG_LATIN2, win1250_2_iso88592); + converted = local2local(src, dest, len, PG_WIN1250, PG_LATIN2, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c index bc651410f21..bff27d1c295 100644 --- a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(mic_to_latin4); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -42,12 +45,14 @@ latin1_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,12 +61,14 @@ mic_to_latin1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN1); - mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -70,12 +77,14 @@ latin3_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN3, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -84,12 +93,14 @@ mic_to_latin3(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN3); - mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,12 +109,14 @@ latin4_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN4, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -112,10 +125,12 @@ mic_to_latin4(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN4); - mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c index d6067cdc24e..3838b15cab9 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ big5_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_UTF8); - LocalToUtf(src, len, dest, - &big5_to_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = LocalToUtf(src, len, dest, + &big5_to_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_BIG5); - UtfToLocal(src, len, dest, - &big5_from_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = UtfToLocal(src, len, dest, + &big5_from_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c index ed90e8e682e..75719fe5f1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c @@ -33,8 +33,11 @@ PG_FUNCTION_INFO_V1(koi8u_to_utf8); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -44,16 +47,19 @@ utf8_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8R); - UtfToLocal(src, len, dest, - &koi8r_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = UtfToLocal(src, len, dest, + &koi8r_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -62,16 +68,19 @@ koi8r_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8r_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = LocalToUtf(src, len, dest, + &koi8r_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -80,16 +89,19 @@ utf8_to_koi8u(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8U); - UtfToLocal(src, len, dest, - &koi8u_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = UtfToLocal(src, len, dest, + &koi8u_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,14 +110,17 @@ koi8u_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8U, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8u_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = LocalToUtf(src, len, dest, + &koi8u_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c index d699affce47..5391001951a 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jis_2004_to_unicode_tree, - LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = LocalToUtf(src, len, dest, + &euc_jis_2004_to_unicode_tree, + LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JIS_2004); - UtfToLocal(src, len, dest, - &euc_jis_2004_from_unicode_tree, - ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = UtfToLocal(src, len, dest, + &euc_jis_2004_from_unicode_tree, + ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c index d7c0ba6a58b..c87d1bf2398 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_cn_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_cn_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = LocalToUtf(src, len, dest, + &euc_cn_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_CN); - UtfToLocal(src, len, dest, - &euc_cn_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = UtfToLocal(src, len, dest, + &euc_cn_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c index 13a3a23e77b..6a55134db21 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jp); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jp_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jp_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = LocalToUtf(src, len, dest, + &euc_jp_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JP); - UtfToLocal(src, len, dest, - &euc_jp_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = UtfToLocal(src, len, dest, + &euc_jp_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c index 1bbb8aaef7b..fe1924e2fec 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_kr_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_kr_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = LocalToUtf(src, len, dest, + &euc_kr_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_KR); - UtfToLocal(src, len, dest, - &euc_kr_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = UtfToLocal(src, len, dest, + &euc_kr_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c index 9830045dccd..68215659b57 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_tw); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_tw_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_tw_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = LocalToUtf(src, len, dest, + &euc_tw_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_TW); - UtfToLocal(src, len, dest, - &euc_tw_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = UtfToLocal(src, len, dest, + &euc_tw_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c index f86ecf27424..e1a59c39a4d 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c @@ -183,8 +183,11 @@ conv_utf8_to_18030(uint32 code) * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -193,16 +196,19 @@ gb18030_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GB18030, PG_UTF8); - LocalToUtf(src, len, dest, - &gb18030_to_unicode_tree, - NULL, 0, - conv_18030_to_utf8, - PG_GB18030); + converted = LocalToUtf(src, len, dest, + &gb18030_to_unicode_tree, + NULL, 0, + conv_18030_to_utf8, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -211,14 +217,17 @@ utf8_to_gb18030(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GB18030); - UtfToLocal(src, len, dest, - &gb18030_from_unicode_tree, - NULL, 0, - conv_utf8_to_18030, - PG_GB18030); + converted = UtfToLocal(src, len, dest, + &gb18030_from_unicode_tree, + NULL, 0, + conv_utf8_to_18030, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c index 2ab8b16c8a8..881386d5347 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_gbk); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ gbk_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GBK, PG_UTF8); - LocalToUtf(src, len, dest, - &gbk_to_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = LocalToUtf(src, len, dest, + &gbk_to_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_gbk(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GBK); - UtfToLocal(src, len, dest, - &gbk_from_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = UtfToLocal(src, len, dest, + &gbk_from_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c index 3e49f67ea2f..d93a521badf 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c @@ -52,8 +52,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -100,6 +103,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -108,12 +112,15 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -122,7 +129,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -132,6 +139,7 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -140,12 +148,15 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -154,5 +165,5 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c index 67e713cca11..8ac93604a1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c @@ -26,8 +26,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859_1); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -37,6 +40,8 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_UTF8); @@ -45,7 +50,11 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_LATIN1, (const char *) src, len); + } if (!IS_HIGHBIT_SET(c)) *dest++ = c; else @@ -58,7 +67,7 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } Datum @@ -67,6 +76,8 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c, c1; @@ -76,7 +87,11 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_UTF8, (const char *) src, len); + } /* fast path for ASCII-subset characters */ if (!IS_HIGHBIT_SET(c)) { @@ -102,11 +117,15 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) len -= 2; } else + { + if (noError) + break; report_untranslatable_char(PG_UTF8, PG_LATIN1, (const char *) src, len); + } } } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c index 578f5df4e7f..317daa2d5ee 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_johab); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ johab_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_JOHAB, PG_UTF8); - LocalToUtf(src, len, dest, - &johab_to_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = LocalToUtf(src, len, dest, + &johab_to_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_johab(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_JOHAB); - UtfToLocal(src, len, dest, - &johab_from_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = UtfToLocal(src, len, dest, + &johab_from_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c index dd9fc2975ad..4c9348aba59 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ sjis_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_UTF8); - LocalToUtf(src, len, dest, - &sjis_to_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = LocalToUtf(src, len, dest, + &sjis_to_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SJIS); - UtfToLocal(src, len, dest, - &sjis_from_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = UtfToLocal(src, len, dest, + &sjis_from_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c index 4bcc886d674..1fffdc5930c 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_shift_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ shift_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &shift_jis_2004_to_unicode_tree, - LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = LocalToUtf(src, len, dest, + &shift_jis_2004_to_unicode_tree, + LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SHIFT_JIS_2004); - UtfToLocal(src, len, dest, - &shift_jis_2004_from_unicode_tree, - ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = UtfToLocal(src, len, dest, + &shift_jis_2004_from_unicode_tree, + ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c index c8e512994a1..d9471dad097 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_uhc); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ uhc_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UHC, PG_UTF8); - LocalToUtf(src, len, dest, - &uhc_to_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = LocalToUtf(src, len, dest, + &uhc_to_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_uhc(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_UHC); - UtfToLocal(src, len, dest, - &uhc_from_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = UtfToLocal(src, len, dest, + &uhc_from_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c index 0c9493dee56..110ba5677d0 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c @@ -48,8 +48,11 @@ PG_FUNCTION_INFO_V1(utf8_to_win); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -81,6 +84,7 @@ win_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -89,12 +93,15 @@ win_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -103,7 +110,7 @@ win_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -113,6 +120,7 @@ utf8_to_win(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -121,12 +129,15 @@ utf8_to_win(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -135,5 +146,5 @@ utf8_to_win(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/mbutils.c b/src/backend/utils/mb/mbutils.c index 2578573b0ab..65753860e35 100644 --- a/src/backend/utils/mb/mbutils.c +++ b/src/backend/utils/mb/mbutils.c @@ -406,12 +406,13 @@ pg_do_encoding_conversion(unsigned char *src, int len, MemoryContextAllocHuge(CurrentMemoryContext, (Size) len * MAX_CONVERSION_GROWTH + 1); - OidFunctionCall5(proc, - Int32GetDatum(src_encoding), - Int32GetDatum(dest_encoding), - CStringGetDatum(src), - CStringGetDatum(result), - Int32GetDatum(len)); + (void) OidFunctionCall6(proc, + Int32GetDatum(src_encoding), + Int32GetDatum(dest_encoding), + CStringGetDatum(src), + CStringGetDatum(result), + Int32GetDatum(len), + BoolGetDatum(false)); /* * If the result is large, it's worth repalloc'ing to release any extra @@ -849,12 +850,13 @@ pg_unicode_to_server(pg_wchar c, unsigned char *s) c_as_utf8[c_as_utf8_len] = '\0'; /* Convert, or throw error if we can't */ - FunctionCall5(Utf8ToServerConvProc, + FunctionCall6(Utf8ToServerConvProc, Int32GetDatum(PG_UTF8), Int32GetDatum(server_encoding), CStringGetDatum(c_as_utf8), CStringGetDatum(s), - Int32GetDatum(c_as_utf8_len)); + Int32GetDatum(c_as_utf8_len), + BoolGetDatum(false)); } diff --git a/src/bin/pg_upgrade/check.c b/src/bin/pg_upgrade/check.c index 43fc297eb69..ee6be95b08d 100644 --- a/src/bin/pg_upgrade/check.c +++ b/src/bin/pg_upgrade/check.c @@ -28,6 +28,7 @@ static void check_for_reg_data_type_usage(ClusterInfo *cluster); static void check_for_jsonb_9_4_usage(ClusterInfo *cluster); static void check_for_pg_role_prefix(ClusterInfo *cluster); static void check_for_new_tablespace_dir(ClusterInfo *new_cluster); +static void check_for_user_defined_encoding_conversions(ClusterInfo *cluster); static char *get_canonical_locale_name(int category, const char *locale); @@ -102,6 +103,15 @@ check_and_dump_old_cluster(bool live_check) check_for_reg_data_type_usage(&old_cluster); check_for_isn_and_int8_passing_mismatch(&old_cluster); + /* + * PG 14 changed the function signature of encoding conversion functions. + * Conversions from older versions cannot be upgraded automatically + * because the user-defined functions used by the encoding conversions + * need to changed to match the new signature. + */ + if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1300) + check_for_user_defined_encoding_conversions(&old_cluster); + /* * Pre-PG 14 allowed user defined postfix operators, which are not * supported anymore. Verify there are none, iff applicable. @@ -1268,6 +1278,91 @@ check_for_pg_role_prefix(ClusterInfo *cluster) check_ok(); } +/* + * Verify that no user-defined encoding conversions exist. + */ +static void +check_for_user_defined_encoding_conversions(ClusterInfo *cluster) +{ + int dbnum; + FILE *script = NULL; + bool found = false; + char output_path[MAXPGPATH]; + + prep_status("Checking for user-defined encoding conversions"); + + snprintf(output_path, sizeof(output_path), + "encoding_conversions.txt"); + + /* Find any user defined encoding conversions */ + for (dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++) + { + PGresult *res; + bool db_used = false; + int ntups; + int rowno; + int i_conoid, + i_conname, + i_nspname; + DbInfo *active_db = &cluster->dbarr.dbs[dbnum]; + PGconn *conn = connectToServer(cluster, active_db->db_name); + + /* + * The query below hardcodes FirstNormalObjectId as 16384 rather than + * interpolating that C #define into the query because, if that + * #define is ever changed, the cutoff we want to use is the value + * used by pre-version 14 servers, not that of some future version. + */ + res = executeQueryOrDie(conn, + "SELECT c.oid as conoid, c.conname, n.nspname " + "FROM pg_catalog.pg_conversion c, " + " pg_catalog.pg_namespace n " + "WHERE c.connamespace = n.oid AND " + " c.oid >= 16384"); + ntups = PQntuples(res); + i_conoid = PQfnumber(res, "conoid"); + i_conname = PQfnumber(res, "conname"); + i_nspname = PQfnumber(res, "nspname"); + for (rowno = 0; rowno < ntups; rowno++) + { + found = true; + if (script == NULL && + (script = fopen_priv(output_path, "w")) == NULL) + pg_fatal("could not open file \"%s\": %s\n", + output_path, strerror(errno)); + if (!db_used) + { + fprintf(script, "In database: %s\n", active_db->db_name); + db_used = true; + } + fprintf(script, " (oid=%s) %s.%s\n", + PQgetvalue(res, rowno, i_conoid), + PQgetvalue(res, rowno, i_nspname), + PQgetvalue(res, rowno, i_conname)); + } + + PQclear(res); + + PQfinish(conn); + } + + if (script) + fclose(script); + + if (found) + { + pg_log(PG_REPORT, "fatal\n"); + pg_fatal("Your installation contains user-defined encoding conversions.\n" + "The conversion function parameters changed in PostgreSQL version 14\n" + "so this cluster cannot currently be upgraded. You can remove the\n" + "encoding conversions in the old cluster and restart the upgrade.\n" + "A list of user-defined encoding conversions is in the file:\n" + " %s\n\n", output_path); + } + else + check_ok(); +} + /* * get_canonical_locale_name diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index f8174061ef3..75b829e8514 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10766,388 +10766,388 @@ # conversion functions { oid => '4302', descr => 'internal conversion function for KOI8R to MULE_INTERNAL', - proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_mic', + proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4303', descr => 'internal conversion function for MULE_INTERNAL to KOI8R', - proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_koi8r', + proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4304', descr => 'internal conversion function for ISO-8859-5 to MULE_INTERNAL', - proname => 'iso_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_mic', + proname => 'iso_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4305', descr => 'internal conversion function for MULE_INTERNAL to ISO-8859-5', - proname => 'mic_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_iso', + proname => 'mic_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4306', descr => 'internal conversion function for WIN1251 to MULE_INTERNAL', - proname => 'win1251_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_mic', + proname => 'win1251_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4307', descr => 'internal conversion function for MULE_INTERNAL to WIN1251', - proname => 'mic_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1251', + proname => 'mic_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4308', descr => 'internal conversion function for WIN866 to MULE_INTERNAL', - proname => 'win866_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_mic', + proname => 'win866_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4309', descr => 'internal conversion function for MULE_INTERNAL to WIN866', - proname => 'mic_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win866', + proname => 'mic_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4310', descr => 'internal conversion function for KOI8R to WIN1251', - proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4311', descr => 'internal conversion function for WIN1251 to KOI8R', - proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4312', descr => 'internal conversion function for KOI8R to WIN866', - proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_win866', + proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4313', descr => 'internal conversion function for WIN866 to KOI8R', - proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_koi8r', + proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4314', descr => 'internal conversion function for WIN866 to WIN1251', - proname => 'win866_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win866_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4315', descr => 'internal conversion function for WIN1251 to WIN866', - proname => 'win1251_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4316', descr => 'internal conversion function for ISO-8859-5 to KOI8R', - proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_koi8r', + proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4317', descr => 'internal conversion function for KOI8R to ISO-8859-5', - proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_iso', + proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4318', descr => 'internal conversion function for ISO-8859-5 to WIN1251', - proname => 'iso_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win1251', + proname => 'iso_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4319', descr => 'internal conversion function for WIN1251 to ISO-8859-5', - proname => 'win1251_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_iso', + proname => 'win1251_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4320', descr => 'internal conversion function for ISO-8859-5 to WIN866', - proname => 'iso_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win866', + proname => 'iso_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4321', descr => 'internal conversion function for WIN866 to ISO-8859-5', - proname => 'win866_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_iso', + proname => 'win866_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4322', descr => 'internal conversion function for EUC_CN to MULE_INTERNAL', - proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_mic', + proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_mic', probin => '$libdir/euc_cn_and_mic' }, { oid => '4323', descr => 'internal conversion function for MULE_INTERNAL to EUC_CN', - proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_cn', + proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_cn', probin => '$libdir/euc_cn_and_mic' }, { oid => '4324', descr => 'internal conversion function for EUC_JP to SJIS', - proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_sjis', + proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4325', descr => 'internal conversion function for SJIS to EUC_JP', - proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_euc_jp', + proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4326', descr => 'internal conversion function for EUC_JP to MULE_INTERNAL', - proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_mic', + proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4327', descr => 'internal conversion function for SJIS to MULE_INTERNAL', - proname => 'sjis_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_mic', + proname => 'sjis_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4328', descr => 'internal conversion function for MULE_INTERNAL to EUC_JP', - proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_jp', + proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4329', descr => 'internal conversion function for MULE_INTERNAL to SJIS', - proname => 'mic_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_sjis', + proname => 'mic_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4330', descr => 'internal conversion function for EUC_KR to MULE_INTERNAL', - proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_mic', + proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_mic', probin => '$libdir/euc_kr_and_mic' }, { oid => '4331', descr => 'internal conversion function for MULE_INTERNAL to EUC_KR', - proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_kr', + proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_kr', probin => '$libdir/euc_kr_and_mic' }, { oid => '4332', descr => 'internal conversion function for EUC_TW to BIG5', - proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_big5', + proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4333', descr => 'internal conversion function for BIG5 to EUC_TW', - proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_euc_tw', + proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4334', descr => 'internal conversion function for EUC_TW to MULE_INTERNAL', - proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_mic', + proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4335', descr => 'internal conversion function for BIG5 to MULE_INTERNAL', - proname => 'big5_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_mic', + proname => 'big5_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4336', descr => 'internal conversion function for MULE_INTERNAL to EUC_TW', - proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_tw', + proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4337', descr => 'internal conversion function for MULE_INTERNAL to BIG5', - proname => 'mic_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_big5', + proname => 'mic_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4338', descr => 'internal conversion function for LATIN2 to MULE_INTERNAL', - proname => 'latin2_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin2_to_mic', + proname => 'latin2_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4339', descr => 'internal conversion function for MULE_INTERNAL to LATIN2', - proname => 'mic_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin2', + proname => 'mic_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4340', descr => 'internal conversion function for WIN1250 to MULE_INTERNAL', - proname => 'win1250_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1250_to_mic', + proname => 'win1250_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4341', descr => 'internal conversion function for MULE_INTERNAL to WIN1250', - proname => 'mic_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1250', + proname => 'mic_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4342', descr => 'internal conversion function for LATIN2 to WIN1250', - proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4343', descr => 'internal conversion function for WIN1250 to LATIN2', - proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4344', descr => 'internal conversion function for LATIN1 to MULE_INTERNAL', - proname => 'latin1_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin1_to_mic', + proname => 'latin1_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin1_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4345', descr => 'internal conversion function for MULE_INTERNAL to LATIN1', - proname => 'mic_to_latin1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin1', + proname => 'mic_to_latin1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin1', probin => '$libdir/latin_and_mic' }, { oid => '4346', descr => 'internal conversion function for LATIN3 to MULE_INTERNAL', - proname => 'latin3_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin3_to_mic', + proname => 'latin3_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin3_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4347', descr => 'internal conversion function for MULE_INTERNAL to LATIN3', - proname => 'mic_to_latin3', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin3', + proname => 'mic_to_latin3', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin3', probin => '$libdir/latin_and_mic' }, { oid => '4348', descr => 'internal conversion function for LATIN4 to MULE_INTERNAL', - proname => 'latin4_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin4_to_mic', + proname => 'latin4_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin4_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4349', descr => 'internal conversion function for MULE_INTERNAL to LATIN4', - proname => 'mic_to_latin4', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin4', + proname => 'mic_to_latin4', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin4', probin => '$libdir/latin_and_mic' }, { oid => '4352', descr => 'internal conversion function for BIG5 to UTF8', - proname => 'big5_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_utf8', + proname => 'big5_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_utf8', probin => '$libdir/utf8_and_big5' }, { oid => '4353', descr => 'internal conversion function for UTF8 to BIG5', - proname => 'utf8_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_big5', + proname => 'utf8_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_big5', probin => '$libdir/utf8_and_big5' }, { oid => '4354', descr => 'internal conversion function for UTF8 to KOI8R', - proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8r', + proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8r', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4355', descr => 'internal conversion function for KOI8R to UTF8', - proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_utf8', + proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4356', descr => 'internal conversion function for UTF8 to KOI8U', - proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8u', + proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8u', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4357', descr => 'internal conversion function for KOI8U to UTF8', - proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8u_to_utf8', + proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8u_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4358', descr => 'internal conversion function for UTF8 to WIN', - proname => 'utf8_to_win', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_win', + proname => 'utf8_to_win', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_win', probin => '$libdir/utf8_and_win' }, { oid => '4359', descr => 'internal conversion function for WIN to UTF8', - proname => 'win_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win_to_utf8', + proname => 'win_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win_to_utf8', probin => '$libdir/utf8_and_win' }, { oid => '4360', descr => 'internal conversion function for EUC_CN to UTF8', - proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_utf8', + proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_utf8', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4361', descr => 'internal conversion function for UTF8 to EUC_CN', - proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_cn', + proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_cn', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4362', descr => 'internal conversion function for EUC_JP to UTF8', - proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_utf8', + proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_utf8', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4363', descr => 'internal conversion function for UTF8 to EUC_JP', - proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_jp', + proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jp', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4364', descr => 'internal conversion function for EUC_KR to UTF8', - proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_utf8', + proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_utf8', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4365', descr => 'internal conversion function for UTF8 to EUC_KR', - proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_kr', + proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_kr', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4366', descr => 'internal conversion function for EUC_TW to UTF8', - proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_utf8', + proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_utf8', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4367', descr => 'internal conversion function for UTF8 to EUC_TW', - proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_tw', + proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_tw', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4368', descr => 'internal conversion function for GB18030 to UTF8', - proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gb18030_to_utf8', + proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gb18030_to_utf8', probin => '$libdir/utf8_and_gb18030' }, { oid => '4369', descr => 'internal conversion function for UTF8 to GB18030', - proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gb18030', + proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gb18030', probin => '$libdir/utf8_and_gb18030' }, { oid => '4370', descr => 'internal conversion function for GBK to UTF8', - proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gbk_to_utf8', + proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gbk_to_utf8', probin => '$libdir/utf8_and_gbk' }, { oid => '4371', descr => 'internal conversion function for UTF8 to GBK', - proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gbk', + proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gbk', probin => '$libdir/utf8_and_gbk' }, { oid => '4372', descr => 'internal conversion function for UTF8 to ISO-8859 2-16', - proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_iso8859', + proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859', probin => '$libdir/utf8_and_iso8859' }, { oid => '4373', descr => 'internal conversion function for ISO-8859 2-16 to UTF8', - proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso8859_to_utf8', + proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_to_utf8', probin => '$libdir/utf8_and_iso8859' }, { oid => '4374', descr => 'internal conversion function for LATIN1 to UTF8', - proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_1_to_utf8', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4375', descr => 'internal conversion function for UTF8 to LATIN1', - proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859_1', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4376', descr => 'internal conversion function for JOHAB to UTF8', - proname => 'johab_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'johab_to_utf8', + proname => 'johab_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'johab_to_utf8', probin => '$libdir/utf8_and_johab' }, { oid => '4377', descr => 'internal conversion function for UTF8 to JOHAB', - proname => 'utf8_to_johab', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_johab', + proname => 'utf8_to_johab', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_johab', probin => '$libdir/utf8_and_johab' }, { oid => '4378', descr => 'internal conversion function for SJIS to UTF8', - proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_utf8', + proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_utf8', probin => '$libdir/utf8_and_sjis' }, { oid => '4379', descr => 'internal conversion function for UTF8 to SJIS', - proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_sjis', + proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_sjis', probin => '$libdir/utf8_and_sjis' }, { oid => '4380', descr => 'internal conversion function for UHC to UTF8', - proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'uhc_to_utf8', + proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'uhc_to_utf8', probin => '$libdir/utf8_and_uhc' }, { oid => '4381', descr => 'internal conversion function for UTF8 to UHC', - proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_uhc', + proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_uhc', probin => '$libdir/utf8_and_uhc' }, { oid => '4382', descr => 'internal conversion function for EUC_JIS_2004 to UTF8', - proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_utf8', probin => '$libdir/utf8_and_euc2004' }, { oid => '4383', descr => 'internal conversion function for UTF8 to EUC_JIS_2004', - proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jis_2004', probin => '$libdir/utf8_and_euc2004' }, { oid => '4384', descr => 'internal conversion function for SHIFT_JIS_2004 to UTF8', - proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_utf8', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4385', descr => 'internal conversion function for UTF8 to SHIFT_JIS_2004', - proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_shift_jis_2004', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4386', descr => 'internal conversion function for EUC_JIS_2004 to SHIFT_JIS_2004', proname => 'euc_jis_2004_to_shift_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_shift_jis_2004', probin => '$libdir/euc2004_sjis2004' }, { oid => '4387', descr => 'internal conversion function for SHIFT_JIS_2004 to EUC_JIS_2004', proname => 'shift_jis_2004_to_euc_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_euc_jis_2004', probin => '$libdir/euc2004_sjis2004' }, diff --git a/src/include/mb/pg_wchar.h b/src/include/mb/pg_wchar.h index 64b22e4b0d4..346a41a1f3d 100644 --- a/src/include/mb/pg_wchar.h +++ b/src/include/mb/pg_wchar.h @@ -627,18 +627,18 @@ extern void pg_unicode_to_server(pg_wchar c, unsigned char *s); extern unsigned short BIG5toCNS(unsigned short big5, unsigned char *lc); extern unsigned short CNStoBIG5(unsigned short cns, unsigned char lc); -extern void UtfToLocal(const unsigned char *utf, int len, - unsigned char *iso, - const pg_mb_radix_tree *map, - const pg_utf_to_local_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); -extern void LocalToUtf(const unsigned char *iso, int len, - unsigned char *utf, - const pg_mb_radix_tree *map, - const pg_local_to_utf_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); +extern int UtfToLocal(const unsigned char *utf, int len, + unsigned char *iso, + const pg_mb_radix_tree *map, + const pg_utf_to_local_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); +extern int LocalToUtf(const unsigned char *iso, int len, + unsigned char *utf, + const pg_mb_radix_tree *map, + const pg_local_to_utf_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); extern bool pg_verifymbstr(const char *mbstr, int len, bool noError); extern bool pg_verify_mbstr(int encoding, const char *mbstr, int len, @@ -656,18 +656,19 @@ extern void report_invalid_encoding(int encoding, const char *mbstr, int len) pg extern void report_untranslatable_char(int src_encoding, int dest_encoding, const char *mbstr, int len) pg_attribute_noreturn(); -extern void local2local(const unsigned char *l, unsigned char *p, int len, - int src_encoding, int dest_encoding, const unsigned char *tab); -extern void latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding); -extern void mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding); -extern void latin2mic_with_table(const unsigned char *l, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); -extern void mic2latin_with_table(const unsigned char *mic, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); +extern int local2local(const unsigned char *l, unsigned char *p, int len, + int src_encoding, int dest_encoding, const unsigned char *tab, + bool noError); +extern int latin2mic(const unsigned char *l, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int mic2latin(const unsigned char *mic, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int latin2mic_with_table(const unsigned char *l, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); +extern int mic2latin_with_table(const unsigned char *mic, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); #ifdef WIN32 extern WCHAR *pgwin32_message_to_UTF16(const char *str, int len, int *utf16len); diff --git a/src/test/regress/expected/opr_sanity.out b/src/test/regress/expected/opr_sanity.out index 254ca06d3dd..23ba60e395f 100644 --- a/src/test/regress/expected/opr_sanity.out +++ b/src/test/regress/expected/opr_sanity.out @@ -1052,13 +1052,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); oid | proname | oid | conname -----+---------+-----+--------- (0 rows) diff --git a/src/test/regress/sql/opr_sanity.sql b/src/test/regress/sql/opr_sanity.sql index bbd3834b634..04691745981 100644 --- a/src/test/regress/sql/opr_sanity.sql +++ b/src/test/regress/sql/opr_sanity.sql @@ -556,13 +556,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); -- Check for conprocs that don't perform the specific conversion that -- pg_conversion alleges they do, by trying to invoke each conversion -- 2.29.2 --------------39E46EF15EBFAA37D53332E5 Content-Type: text/x-patch; charset=UTF-8; name="v3-0003-Add-tests-for-the-new-noError-variants-of-built-i.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="v3-0003-Add-tests-for-the-new-noError-variants-of-built-i.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 34+ messages in thread
* [PATCH v3 2/5] Change conversion function signature. @ 2021-01-28 16:42 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 34+ messages in thread From: Heikki Linnakangas @ 2021-01-28 16:42 UTC (permalink / raw) Add a 'noError' argument, so that we can try to convert a buffer without knowing the character boundaries beforehand. The functions now need to return the number of input bytes successfully converted. This is is a backwards-incompatible change, if you have created a custom encoding conversion with CREATE CONVERSION. This adds a check to pg_upgrade for that, refusing the upgrade if there are any user-defined encoding conversions. --- doc/src/sgml/ref/create_conversion.sgml | 5 +- src/backend/commands/conversioncmds.c | 27 +- src/backend/utils/error/elog.c | 2 + src/backend/utils/mb/conv.c | 112 +++++- .../cyrillic_and_mic/cyrillic_and_mic.c | 127 ++++--- .../euc2004_sjis2004/euc2004_sjis2004.c | 96 ++++- .../euc_cn_and_mic/euc_cn_and_mic.c | 57 ++- .../euc_jp_and_sjis/euc_jp_and_sjis.c | 153 ++++++-- .../euc_kr_and_mic/euc_kr_and_mic.c | 57 ++- .../euc_tw_and_big5/euc_tw_and_big5.c | 165 +++++++-- .../latin2_and_win1250/latin2_and_win1250.c | 49 ++- .../latin_and_mic/latin_and_mic.c | 43 ++- .../utf8_and_big5/utf8_and_big5.c | 37 +- .../utf8_and_cyrillic/utf8_and_cyrillic.c | 67 ++-- .../utf8_and_euc2004/utf8_and_euc2004.c | 37 +- .../utf8_and_euc_cn/utf8_and_euc_cn.c | 37 +- .../utf8_and_euc_jp/utf8_and_euc_jp.c | 37 +- .../utf8_and_euc_kr/utf8_and_euc_kr.c | 37 +- .../utf8_and_euc_tw/utf8_and_euc_tw.c | 37 +- .../utf8_and_gb18030/utf8_and_gb18030.c | 37 +- .../utf8_and_gbk/utf8_and_gbk.c | 37 +- .../utf8_and_iso8859/utf8_and_iso8859.c | 43 ++- .../utf8_and_iso8859_1/utf8_and_iso8859_1.c | 27 +- .../utf8_and_johab/utf8_and_johab.c | 37 +- .../utf8_and_sjis/utf8_and_sjis.c | 37 +- .../utf8_and_sjis2004/utf8_and_sjis2004.c | 37 +- .../utf8_and_uhc/utf8_and_uhc.c | 37 +- .../utf8_and_win/utf8_and_win.c | 43 ++- src/backend/utils/mb/mbutils.c | 18 +- src/bin/pg_upgrade/check.c | 95 +++++ src/include/catalog/pg_proc.dat | 332 +++++++++--------- src/include/mb/pg_wchar.h | 49 +-- src/test/regress/expected/opr_sanity.out | 7 +- src/test/regress/sql/opr_sanity.sql | 7 +- 34 files changed, 1390 insertions(+), 635 deletions(-) diff --git a/doc/src/sgml/ref/create_conversion.sgml b/doc/src/sgml/ref/create_conversion.sgml index e7700fecfc5..f014a676c88 100644 --- a/doc/src/sgml/ref/create_conversion.sgml +++ b/doc/src/sgml/ref/create_conversion.sgml @@ -117,8 +117,9 @@ conv_proc( integer, -- destination encoding ID cstring, -- source string (null terminated C string) internal, -- destination (fill with a null terminated C string) - integer -- source string length -) RETURNS void; + integer, -- source string length + boolean -- if true, don't throw an error if conversion fails +) RETURNS integer; </programlisting></para> </listitem> </varlistentry> diff --git a/src/backend/commands/conversioncmds.c b/src/backend/commands/conversioncmds.c index f7ff321de71..d2041466911 100644 --- a/src/backend/commands/conversioncmds.c +++ b/src/backend/commands/conversioncmds.c @@ -45,8 +45,9 @@ CreateConversionCommand(CreateConversionStmt *stmt) const char *from_encoding_name = stmt->for_encoding_name; const char *to_encoding_name = stmt->to_encoding_name; List *func_name = stmt->func_name; - static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID}; + static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID, BOOLOID}; char result[1]; + Datum funcresult; /* Convert list of names to a name and namespace */ namespaceId = QualifiedNameGetCreationNamespace(stmt->conversion_name, @@ -92,8 +93,8 @@ CreateConversionCommand(CreateConversionStmt *stmt) funcoid = LookupFuncName(func_name, sizeof(funcargs) / sizeof(Oid), funcargs, false); - /* Check it returns VOID, else it's probably the wrong function */ - if (get_func_rettype(funcoid) != VOIDOID) + /* Check it returns int4, else it's probably the wrong function */ + if (get_func_rettype(funcoid) != INT4OID) ereport(ERROR, (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), errmsg("encoding conversion function %s must return type %s", @@ -111,12 +112,20 @@ CreateConversionCommand(CreateConversionStmt *stmt) * string; the conversion function should throw an error if it can't * perform the requested conversion. */ - OidFunctionCall5(funcoid, - Int32GetDatum(from_encoding), - Int32GetDatum(to_encoding), - CStringGetDatum(""), - CStringGetDatum(result), - Int32GetDatum(0)); + funcresult = OidFunctionCall6(funcoid, + Int32GetDatum(from_encoding), + Int32GetDatum(to_encoding), + CStringGetDatum(""), + CStringGetDatum(result), + Int32GetDatum(0), + BoolGetDatum(false)); + + /* The function should return 0 for empty input. Might as well check that, too. */ + if (DatumGetInt32(funcresult) != 0) + ereport(ERROR, + (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), + errmsg("encoding conversion function %s returned incorrect result for empty input", + NameListToString(func_name)))); /* * All seem ok, go ahead (possible failure would be a duplicate conversion diff --git a/src/backend/utils/error/elog.c b/src/backend/utils/error/elog.c index 80c26724612..762f77d533c 100644 --- a/src/backend/utils/error/elog.c +++ b/src/backend/utils/error/elog.c @@ -2280,6 +2280,8 @@ write_console(const char *line, int len) * Conversion on non-win32 platforms is not implemented yet. It requires * non-throw version of pg_do_encoding_conversion(), that converts * unconvertable characters to '?' without errors. + * + * XXX: We have a no-throw version now. It doesn't convert to '?' though. */ #endif diff --git a/src/backend/utils/mb/conv.c b/src/backend/utils/mb/conv.c index a07b54bd3b8..b83358bc7a5 100644 --- a/src/backend/utils/mb/conv.c +++ b/src/backend/utils/mb/conv.c @@ -26,14 +26,16 @@ * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the target charset, or 0 if there is no equivalent code. */ -void +int local2local(const unsigned char *l, unsigned char *p, int len, int src_encoding, int dest_encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -41,7 +43,11 @@ local2local(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(src_encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -50,13 +56,19 @@ local2local(const unsigned char *l, if (c2) *p++ = c2; else + { + if (noError) + break; report_untranslatable_char(src_encoding, dest_encoding, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -67,17 +79,22 @@ local2local(const unsigned char *l, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = l; int c1; while (len > 0) { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (IS_HIGHBIT_SET(c1)) *p++ = lc; *p++ = c1; @@ -85,6 +102,8 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, len--; } *p = '\0'; + + return l - start; } /* @@ -95,17 +114,22 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -118,17 +142,27 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1])) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); + } *p++ = mic[1]; mic += 2; len -= 2; } } *p = '\0'; + + return mic - start; } @@ -144,14 +178,16 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the mule encoding, or 0 if there is no equivalent code. */ -void +int latin2mic_with_table(const unsigned char *l, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -159,7 +195,11 @@ latin2mic_with_table(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -171,13 +211,19 @@ latin2mic_with_table(const unsigned char *l, *p++ = c2; } else + { + if (noError) + break; report_untranslatable_char(encoding, PG_MULE_INTERNAL, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -192,14 +238,16 @@ latin2mic_with_table(const unsigned char *l, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the local charset, or 0 if there is no equivalent code. */ -void +int mic2latin_with_table(const unsigned char *mic, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = mic; unsigned char c1, c2; @@ -207,7 +255,11 @@ mic2latin_with_table(const unsigned char *mic, { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -220,11 +272,17 @@ mic2latin_with_table(const unsigned char *mic, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1]) || (c2 = tab[mic[1] - HIGHBIT]) == 0) { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); break; /* keep compiler quiet */ @@ -235,6 +293,8 @@ mic2latin_with_table(const unsigned char *mic, } } *p = '\0'; + + return mic - start; } /* @@ -425,17 +485,19 @@ pg_mb_radix_conv(const pg_mb_radix_tree *rt, * * See pg_wchar.h for more details about the data structures used here. */ -void +int UtfToLocal(const unsigned char *utf, int len, unsigned char *iso, const pg_mb_radix_tree *map, const pg_utf_to_local_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, bool noError) { uint32 iutf; int l; const pg_utf_to_local_combined *cp; + const unsigned char *start = utf; + const unsigned char *cur = utf; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -449,6 +511,8 @@ UtfToLocal(const unsigned char *utf, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*utf == '\0') break; @@ -584,15 +648,19 @@ UtfToLocal(const unsigned char *utf, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(PG_UTF8, encoding, (const char *) (utf - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(PG_UTF8, (const char *) utf, len); *iso = '\0'; + + return cur - start; } /* @@ -616,18 +684,24 @@ UtfToLocal(const unsigned char *utf, int len, * (if provided) is applied. An error is raised if no match is found. * * See pg_wchar.h for more details about the data structures used here. + * + * Returns the number of input bytes consumed. If noError is true, this can + * be less than 'len'. */ -void +int LocalToUtf(const unsigned char *iso, int len, unsigned char *utf, const pg_mb_radix_tree *map, const pg_local_to_utf_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, + bool noError) { uint32 iiso; int l; const pg_local_to_utf_combined *cp; + const unsigned char *start = iso; + const unsigned char *cur = iso; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -641,6 +715,8 @@ LocalToUtf(const unsigned char *iso, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*iso == '\0') break; @@ -723,13 +799,17 @@ LocalToUtf(const unsigned char *iso, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(encoding, PG_UTF8, (const char *) (iso - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(encoding, (const char *) iso, len); *utf = '\0'; + + return cur - start; } diff --git a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c index 4c5b02654de..368c2deb5e4 100644 --- a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c @@ -44,8 +44,11 @@ PG_FUNCTION_INFO_V1(win866_to_iso); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -306,12 +309,14 @@ koi8r_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -320,12 +325,14 @@ mic_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_KOI8R); - mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -334,12 +341,14 @@ iso_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -348,12 +357,14 @@ mic_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_ISO_8859_5); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -362,12 +373,14 @@ win1251_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -376,12 +389,14 @@ mic_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1251); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -390,12 +405,14 @@ win866_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -404,12 +421,14 @@ mic_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN866); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -418,12 +437,14 @@ koi8r_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN1251); - local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -432,12 +453,14 @@ win1251_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_KOI8R); - local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi); + converted = local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -446,12 +469,14 @@ koi8r_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN866); - local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -460,12 +485,14 @@ win866_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_KOI8R); - local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi); + converted = local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -474,12 +501,14 @@ win866_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_WIN1251); - local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251); + converted = local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -488,12 +517,14 @@ win1251_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_WIN866); - local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866); + converted = local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -502,12 +533,14 @@ iso_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_KOI8R); - local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -516,12 +549,14 @@ koi8r_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_ISO_8859_5); - local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso); + converted = local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -530,12 +565,14 @@ iso_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN1251); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -544,12 +581,14 @@ win1251_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso); + converted = local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -558,12 +597,14 @@ iso_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN866); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -572,10 +613,12 @@ win866_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso); + converted = local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c index 4d7fb116cfd..88529c644cf 100644 --- a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c @@ -19,8 +19,8 @@ PG_MODULE_MAGIC; PG_FUNCTION_INFO_V1(euc_jis_2004_to_shift_jis_2004); PG_FUNCTION_INFO_V1(shift_jis_2004_to_euc_jis_2004); -static void euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len); -static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len); +static int euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError); /* ---------- * conv_proc( @@ -28,8 +28,11 @@ static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -39,12 +42,14 @@ euc_jis_2004_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_SHIFT_JIS_2004); - euc_jis_20042shift_jis_2004(src, dest, len); + converted = euc_jis_20042shift_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -53,20 +58,23 @@ shift_jis_2004_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_EUC_JIS_2004); - shift_jis_20042euc_jis_2004(src, dest, len); + converted = shift_jis_20042euc_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_JIS_2004 -> SHIFT_JIS_2004 */ -static void -euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, ku, ten; @@ -79,8 +87,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -90,8 +102,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) l = pg_encoding_verifymbchar(PG_EUC_JIS_2004, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (c1 == SS2 && l == 2) /* JIS X 0201 kana? */ { @@ -121,8 +137,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) *p++ = (ku + 0x19b) >> 1; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } if (ku % 2) @@ -132,8 +152,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; @@ -149,8 +173,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ku >= 63 && ku <= 94) *p++ = (ku + 0x181) >> 1; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (ku % 2) { @@ -159,20 +187,30 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else - report_invalid_encoding(PG_EUC_JIS_2004, + { + if (noError) + break; + report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } euc += l; len -= l; } *p = '\0'; + + return euc - start; } /* @@ -212,9 +250,10 @@ get_ten(int b, int *ku) * SHIFT_JIS_2004 ---> EUC_JIS_2004 */ -static void -shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len) +static int +shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1; int ku, ten, @@ -230,8 +269,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -241,8 +284,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len l = pg_encoding_verifymbchar(PG_SHIFT_JIS_2004, (const char *) sjis, len); if (l < 0 || l > len) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf && l == 1) { @@ -266,8 +313,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x100; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xe0 && c1 <= 0xef) /* plane 1 62ku-94ku */ @@ -275,9 +326,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x180; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, - (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xf0 && c1 <= 0xf3) /* plane 2 @@ -286,8 +340,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } switch (c1) { case 0xf0: @@ -309,16 +367,24 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 == 0xf4 && kubun == 1) ku = 15; else ku = (c1 << 1) - 0x19a - kubun; } else + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (plane == 2) *p++ = SS3; @@ -330,4 +396,6 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c index e9bb896935f..a8da733803d 100644 --- a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_cn2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_cn(const unsigned char *mic, unsigned char *p, int len); +static int euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_cn_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_cn_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_MULE_INTERNAL); - euc_cn2mic(src, dest, len); + converted = euc_cn2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_CN); - mic2euc_cn(src, dest, len); + converted = mic2euc_cn(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_CN ---> MIC */ -static void -euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; while (len > 0) @@ -76,7 +84,11 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (len < 2 || !IS_HIGHBIT_SET(euc[1])) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = LC_GB2312_80; *p++ = c1; *p++ = euc[1]; @@ -86,21 +98,28 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_CN */ -static void -mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) @@ -109,11 +128,19 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (c1 != LC_GB2312_80) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_CN, (const char *) mic, len); + } if (len < 3 || !IS_HIGHBIT_SET(mic[1]) || !IS_HIGHBIT_SET(mic[2])) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } mic++; *p++ = *mic++; *p++ = *mic++; @@ -122,12 +149,18 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; } } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c index 5059f917a98..cc4817dc4cd 100644 --- a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c @@ -42,17 +42,20 @@ PG_FUNCTION_INFO_V1(mic_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void sjis2mic(const unsigned char *sjis, unsigned char *p, int len); -static void mic2sjis(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_jp(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len); -static void sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len); +static int sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError); +static int mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_jp_to_sjis(PG_FUNCTION_ARGS) @@ -60,12 +63,14 @@ euc_jp_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_SJIS); - euc_jp2sjis(src, dest, len); + converted = euc_jp2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -74,12 +79,14 @@ sjis_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_EUC_JP); - sjis2euc_jp(src, dest, len); + converted = sjis2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -88,12 +95,14 @@ euc_jp_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_MULE_INTERNAL); - euc_jp2mic(src, dest, len); + converted = euc_jp2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -102,12 +111,14 @@ mic_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_JP); - mic2euc_jp(src, dest, len); + converted = mic2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -116,12 +127,14 @@ sjis_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_MULE_INTERNAL); - sjis2mic(src, dest, len); + converted = sjis2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -130,20 +143,23 @@ mic_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_SJIS); - mic2sjis(src, dest, len); + converted = mic2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * SJIS ---> MIC */ -static void -sjis2mic(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -167,7 +183,11 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) * JIS X0208, X0212, user defined extended characters */ if (len < 2 || !ISSJISHEAD(c1) || !ISSJISTAIL(sjis[1])) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } c2 = sjis[1]; k = (c1 << 8) + c2; if (k >= 0xed40 && k < 0xf040) @@ -257,21 +277,28 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; } } *p = '\0'; + + return sjis - start; } /* * MIC ---> SJIS */ -static void -mic2sjis(const unsigned char *mic, unsigned char *p, int len) +static int +mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1, c2, k, @@ -284,8 +311,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -293,8 +324,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) *p++ = mic[1]; else if (c1 == LC_JISX0208) @@ -350,20 +385,27 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_SJIS, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP ---> MIC */ -static void -euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -374,8 +416,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -383,8 +429,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* 1 byte kana? */ *p++ = LC_JISX0201K; @@ -406,14 +456,17 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_JP */ -static void -mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -424,8 +477,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -433,8 +490,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) { *p++ = SS2; @@ -452,20 +513,27 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_JP, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP -> SJIS */ -static void -euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, c2, k; @@ -478,8 +546,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -487,8 +559,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* hankaku kana? */ @@ -551,14 +627,17 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * SJIS ---> EUC_JP */ -static void -sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -573,8 +652,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -582,8 +665,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_SJIS, (const char *) sjis, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf) { /* JIS X0201 (1 byte kana) */ @@ -680,4 +767,6 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c index ac823d6c270..a5b51617e52 100644 --- a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_kr2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_kr(const unsigned char *mic, unsigned char *p, int len); +static int euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_kr_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_kr_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_MULE_INTERNAL); - euc_kr2mic(src, dest, len); + converted = euc_kr2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_KR); - mic2euc_kr(src, dest, len); + converted = mic2euc_kr(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_KR ---> MIC */ -static void -euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -78,8 +86,12 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_KR, (const char *) euc, len); if (l != 2) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = LC_KS5601; *p++ = c1; *p++ = euc[1]; @@ -89,22 +101,29 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_KR */ -static void -mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -115,8 +134,12 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -124,18 +147,28 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_KS5601) { *p++ = mic[1]; *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_KR, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c index 66c242d7f36..ebb4e0acd53 100644 --- a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c @@ -32,17 +32,20 @@ PG_FUNCTION_INFO_V1(mic_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_tw2big5(const unsigned char *euc, unsigned char *p, int len); -static void big52euc_tw(const unsigned char *euc, unsigned char *p, int len); -static void big52mic(const unsigned char *big5, unsigned char *p, int len); -static void mic2big5(const unsigned char *mic, unsigned char *p, int len); -static void euc_tw2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_tw(const unsigned char *mic, unsigned char *p, int len); +static int euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52euc_tw(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError); +static int mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_tw_to_big5(PG_FUNCTION_ARGS) @@ -50,12 +53,14 @@ euc_tw_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_BIG5); - euc_tw2big5(src, dest, len); + converted = euc_tw2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -64,12 +69,14 @@ big5_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_EUC_TW); - big52euc_tw(src, dest, len); + converted = big52euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -78,12 +85,14 @@ euc_tw_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_MULE_INTERNAL); - euc_tw2mic(src, dest, len); + converted = euc_tw2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -92,12 +101,14 @@ mic_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_TW); - mic2euc_tw(src, dest, len); + converted = mic2euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -106,12 +117,14 @@ big5_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_MULE_INTERNAL); - big52mic(src, dest, len); + converted = big52mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -120,21 +133,24 @@ mic_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_BIG5); - mic2big5(src, dest, len); + converted = mic2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_TW ---> Big5 */ -static void -euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; unsigned char c1; unsigned short big5buf, cnsBuf; @@ -149,8 +165,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Verify and decode the next EUC_TW input character */ l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -171,8 +191,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Write it out in Big5 */ big5buf = CNStoBIG5(cnsBuf, lc); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_EUC_TW, PG_BIG5, (const char *) euc, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; @@ -182,22 +206,29 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * Big5 ---> EUC_TW */ -static void -big52euc_tw(const unsigned char *big5, unsigned char *p, int len) +static int +big52euc_tw(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -212,8 +243,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); @@ -237,8 +272,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_EUC_TW, (const char *) big5, len); + } big5 += l; len -= l; @@ -256,14 +295,17 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) } } *p = '\0'; + + return big5 - start; } /* * EUC_TW ---> MIC */ -static void -euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -274,8 +316,12 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -304,22 +350,29 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_TW */ -static void -mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -330,8 +383,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -339,8 +396,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1) { *p++ = mic[1]; @@ -362,20 +423,27 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[3]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_TW, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * Big5 ---> MIC */ -static void -big52mic(const unsigned char *big5, unsigned char *p, int len) +static int +big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -389,8 +457,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } *p++ = c1; big5++; len--; @@ -398,8 +470,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); if (lc != 0) @@ -412,20 +488,27 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_MULE_INTERNAL, (const char *) big5, len); + } big5 += l; len -= l; } *p = '\0'; + + return big5 - start; } /* * MIC ---> Big5 */ -static void -mic2big5(const unsigned char *mic, unsigned char *p, int len) +static int +mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -438,8 +521,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -447,8 +534,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1 || c1 == LC_CNS11643_2 || c1 == LCPRV2_B) { if (c1 == LCPRV2_B) @@ -462,16 +553,26 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } big5buf = CNStoBIG5(cnsBuf, c1); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c index 2e28e6780a5..8610fcb69aa 100644 --- a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c +++ b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(win1250_to_latin2); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -82,12 +85,14 @@ latin2_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -96,12 +101,14 @@ mic_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN2); - mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -110,13 +117,15 @@ win1250_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - win1250_2_iso88592); + converted = latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -125,13 +134,15 @@ mic_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1250); - mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - iso88592_2_win1250); + converted = mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -140,12 +151,15 @@ latin2_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_WIN1250); - local2local(src, dest, len, PG_LATIN2, PG_WIN1250, iso88592_2_win1250); + converted = local2local(src, dest, len, PG_LATIN2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -154,10 +168,13 @@ win1250_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_LATIN2); - local2local(src, dest, len, PG_WIN1250, PG_LATIN2, win1250_2_iso88592); + converted = local2local(src, dest, len, PG_WIN1250, PG_LATIN2, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c index bc651410f21..bff27d1c295 100644 --- a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(mic_to_latin4); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -42,12 +45,14 @@ latin1_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,12 +61,14 @@ mic_to_latin1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN1); - mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -70,12 +77,14 @@ latin3_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN3, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -84,12 +93,14 @@ mic_to_latin3(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN3); - mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,12 +109,14 @@ latin4_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN4, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -112,10 +125,12 @@ mic_to_latin4(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN4); - mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c index d6067cdc24e..3838b15cab9 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ big5_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_UTF8); - LocalToUtf(src, len, dest, - &big5_to_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = LocalToUtf(src, len, dest, + &big5_to_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_BIG5); - UtfToLocal(src, len, dest, - &big5_from_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = UtfToLocal(src, len, dest, + &big5_from_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c index ed90e8e682e..75719fe5f1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c @@ -33,8 +33,11 @@ PG_FUNCTION_INFO_V1(koi8u_to_utf8); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -44,16 +47,19 @@ utf8_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8R); - UtfToLocal(src, len, dest, - &koi8r_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = UtfToLocal(src, len, dest, + &koi8r_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -62,16 +68,19 @@ koi8r_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8r_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = LocalToUtf(src, len, dest, + &koi8r_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -80,16 +89,19 @@ utf8_to_koi8u(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8U); - UtfToLocal(src, len, dest, - &koi8u_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = UtfToLocal(src, len, dest, + &koi8u_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,14 +110,17 @@ koi8u_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8U, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8u_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = LocalToUtf(src, len, dest, + &koi8u_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c index d699affce47..5391001951a 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jis_2004_to_unicode_tree, - LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = LocalToUtf(src, len, dest, + &euc_jis_2004_to_unicode_tree, + LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JIS_2004); - UtfToLocal(src, len, dest, - &euc_jis_2004_from_unicode_tree, - ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = UtfToLocal(src, len, dest, + &euc_jis_2004_from_unicode_tree, + ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c index d7c0ba6a58b..c87d1bf2398 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_cn_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_cn_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = LocalToUtf(src, len, dest, + &euc_cn_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_CN); - UtfToLocal(src, len, dest, - &euc_cn_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = UtfToLocal(src, len, dest, + &euc_cn_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c index 13a3a23e77b..6a55134db21 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jp); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jp_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jp_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = LocalToUtf(src, len, dest, + &euc_jp_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JP); - UtfToLocal(src, len, dest, - &euc_jp_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = UtfToLocal(src, len, dest, + &euc_jp_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c index 1bbb8aaef7b..fe1924e2fec 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_kr_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_kr_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = LocalToUtf(src, len, dest, + &euc_kr_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_KR); - UtfToLocal(src, len, dest, - &euc_kr_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = UtfToLocal(src, len, dest, + &euc_kr_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c index 9830045dccd..68215659b57 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_tw); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_tw_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_tw_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = LocalToUtf(src, len, dest, + &euc_tw_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_TW); - UtfToLocal(src, len, dest, - &euc_tw_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = UtfToLocal(src, len, dest, + &euc_tw_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c index f86ecf27424..e1a59c39a4d 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c @@ -183,8 +183,11 @@ conv_utf8_to_18030(uint32 code) * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -193,16 +196,19 @@ gb18030_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GB18030, PG_UTF8); - LocalToUtf(src, len, dest, - &gb18030_to_unicode_tree, - NULL, 0, - conv_18030_to_utf8, - PG_GB18030); + converted = LocalToUtf(src, len, dest, + &gb18030_to_unicode_tree, + NULL, 0, + conv_18030_to_utf8, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -211,14 +217,17 @@ utf8_to_gb18030(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GB18030); - UtfToLocal(src, len, dest, - &gb18030_from_unicode_tree, - NULL, 0, - conv_utf8_to_18030, - PG_GB18030); + converted = UtfToLocal(src, len, dest, + &gb18030_from_unicode_tree, + NULL, 0, + conv_utf8_to_18030, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c index 2ab8b16c8a8..881386d5347 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_gbk); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ gbk_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GBK, PG_UTF8); - LocalToUtf(src, len, dest, - &gbk_to_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = LocalToUtf(src, len, dest, + &gbk_to_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_gbk(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GBK); - UtfToLocal(src, len, dest, - &gbk_from_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = UtfToLocal(src, len, dest, + &gbk_from_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c index 3e49f67ea2f..d93a521badf 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c @@ -52,8 +52,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -100,6 +103,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -108,12 +112,15 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -122,7 +129,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -132,6 +139,7 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -140,12 +148,15 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -154,5 +165,5 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c index 67e713cca11..8ac93604a1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c @@ -26,8 +26,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859_1); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -37,6 +40,8 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_UTF8); @@ -45,7 +50,11 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_LATIN1, (const char *) src, len); + } if (!IS_HIGHBIT_SET(c)) *dest++ = c; else @@ -58,7 +67,7 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } Datum @@ -67,6 +76,8 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c, c1; @@ -76,7 +87,11 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_UTF8, (const char *) src, len); + } /* fast path for ASCII-subset characters */ if (!IS_HIGHBIT_SET(c)) { @@ -102,11 +117,15 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) len -= 2; } else + { + if (noError) + break; report_untranslatable_char(PG_UTF8, PG_LATIN1, (const char *) src, len); + } } } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c index 578f5df4e7f..317daa2d5ee 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_johab); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ johab_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_JOHAB, PG_UTF8); - LocalToUtf(src, len, dest, - &johab_to_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = LocalToUtf(src, len, dest, + &johab_to_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_johab(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_JOHAB); - UtfToLocal(src, len, dest, - &johab_from_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = UtfToLocal(src, len, dest, + &johab_from_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c index dd9fc2975ad..4c9348aba59 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ sjis_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_UTF8); - LocalToUtf(src, len, dest, - &sjis_to_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = LocalToUtf(src, len, dest, + &sjis_to_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SJIS); - UtfToLocal(src, len, dest, - &sjis_from_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = UtfToLocal(src, len, dest, + &sjis_from_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c index 4bcc886d674..1fffdc5930c 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_shift_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ shift_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &shift_jis_2004_to_unicode_tree, - LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = LocalToUtf(src, len, dest, + &shift_jis_2004_to_unicode_tree, + LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SHIFT_JIS_2004); - UtfToLocal(src, len, dest, - &shift_jis_2004_from_unicode_tree, - ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = UtfToLocal(src, len, dest, + &shift_jis_2004_from_unicode_tree, + ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c index c8e512994a1..d9471dad097 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_uhc); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ uhc_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UHC, PG_UTF8); - LocalToUtf(src, len, dest, - &uhc_to_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = LocalToUtf(src, len, dest, + &uhc_to_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_uhc(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_UHC); - UtfToLocal(src, len, dest, - &uhc_from_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = UtfToLocal(src, len, dest, + &uhc_from_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c index 0c9493dee56..110ba5677d0 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c @@ -48,8 +48,11 @@ PG_FUNCTION_INFO_V1(utf8_to_win); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -81,6 +84,7 @@ win_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -89,12 +93,15 @@ win_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -103,7 +110,7 @@ win_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -113,6 +120,7 @@ utf8_to_win(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -121,12 +129,15 @@ utf8_to_win(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -135,5 +146,5 @@ utf8_to_win(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/mbutils.c b/src/backend/utils/mb/mbutils.c index 2578573b0ab..65753860e35 100644 --- a/src/backend/utils/mb/mbutils.c +++ b/src/backend/utils/mb/mbutils.c @@ -406,12 +406,13 @@ pg_do_encoding_conversion(unsigned char *src, int len, MemoryContextAllocHuge(CurrentMemoryContext, (Size) len * MAX_CONVERSION_GROWTH + 1); - OidFunctionCall5(proc, - Int32GetDatum(src_encoding), - Int32GetDatum(dest_encoding), - CStringGetDatum(src), - CStringGetDatum(result), - Int32GetDatum(len)); + (void) OidFunctionCall6(proc, + Int32GetDatum(src_encoding), + Int32GetDatum(dest_encoding), + CStringGetDatum(src), + CStringGetDatum(result), + Int32GetDatum(len), + BoolGetDatum(false)); /* * If the result is large, it's worth repalloc'ing to release any extra @@ -849,12 +850,13 @@ pg_unicode_to_server(pg_wchar c, unsigned char *s) c_as_utf8[c_as_utf8_len] = '\0'; /* Convert, or throw error if we can't */ - FunctionCall5(Utf8ToServerConvProc, + FunctionCall6(Utf8ToServerConvProc, Int32GetDatum(PG_UTF8), Int32GetDatum(server_encoding), CStringGetDatum(c_as_utf8), CStringGetDatum(s), - Int32GetDatum(c_as_utf8_len)); + Int32GetDatum(c_as_utf8_len), + BoolGetDatum(false)); } diff --git a/src/bin/pg_upgrade/check.c b/src/bin/pg_upgrade/check.c index 43fc297eb69..ee6be95b08d 100644 --- a/src/bin/pg_upgrade/check.c +++ b/src/bin/pg_upgrade/check.c @@ -28,6 +28,7 @@ static void check_for_reg_data_type_usage(ClusterInfo *cluster); static void check_for_jsonb_9_4_usage(ClusterInfo *cluster); static void check_for_pg_role_prefix(ClusterInfo *cluster); static void check_for_new_tablespace_dir(ClusterInfo *new_cluster); +static void check_for_user_defined_encoding_conversions(ClusterInfo *cluster); static char *get_canonical_locale_name(int category, const char *locale); @@ -102,6 +103,15 @@ check_and_dump_old_cluster(bool live_check) check_for_reg_data_type_usage(&old_cluster); check_for_isn_and_int8_passing_mismatch(&old_cluster); + /* + * PG 14 changed the function signature of encoding conversion functions. + * Conversions from older versions cannot be upgraded automatically + * because the user-defined functions used by the encoding conversions + * need to changed to match the new signature. + */ + if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1300) + check_for_user_defined_encoding_conversions(&old_cluster); + /* * Pre-PG 14 allowed user defined postfix operators, which are not * supported anymore. Verify there are none, iff applicable. @@ -1268,6 +1278,91 @@ check_for_pg_role_prefix(ClusterInfo *cluster) check_ok(); } +/* + * Verify that no user-defined encoding conversions exist. + */ +static void +check_for_user_defined_encoding_conversions(ClusterInfo *cluster) +{ + int dbnum; + FILE *script = NULL; + bool found = false; + char output_path[MAXPGPATH]; + + prep_status("Checking for user-defined encoding conversions"); + + snprintf(output_path, sizeof(output_path), + "encoding_conversions.txt"); + + /* Find any user defined encoding conversions */ + for (dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++) + { + PGresult *res; + bool db_used = false; + int ntups; + int rowno; + int i_conoid, + i_conname, + i_nspname; + DbInfo *active_db = &cluster->dbarr.dbs[dbnum]; + PGconn *conn = connectToServer(cluster, active_db->db_name); + + /* + * The query below hardcodes FirstNormalObjectId as 16384 rather than + * interpolating that C #define into the query because, if that + * #define is ever changed, the cutoff we want to use is the value + * used by pre-version 14 servers, not that of some future version. + */ + res = executeQueryOrDie(conn, + "SELECT c.oid as conoid, c.conname, n.nspname " + "FROM pg_catalog.pg_conversion c, " + " pg_catalog.pg_namespace n " + "WHERE c.connamespace = n.oid AND " + " c.oid >= 16384"); + ntups = PQntuples(res); + i_conoid = PQfnumber(res, "conoid"); + i_conname = PQfnumber(res, "conname"); + i_nspname = PQfnumber(res, "nspname"); + for (rowno = 0; rowno < ntups; rowno++) + { + found = true; + if (script == NULL && + (script = fopen_priv(output_path, "w")) == NULL) + pg_fatal("could not open file \"%s\": %s\n", + output_path, strerror(errno)); + if (!db_used) + { + fprintf(script, "In database: %s\n", active_db->db_name); + db_used = true; + } + fprintf(script, " (oid=%s) %s.%s\n", + PQgetvalue(res, rowno, i_conoid), + PQgetvalue(res, rowno, i_nspname), + PQgetvalue(res, rowno, i_conname)); + } + + PQclear(res); + + PQfinish(conn); + } + + if (script) + fclose(script); + + if (found) + { + pg_log(PG_REPORT, "fatal\n"); + pg_fatal("Your installation contains user-defined encoding conversions.\n" + "The conversion function parameters changed in PostgreSQL version 14\n" + "so this cluster cannot currently be upgraded. You can remove the\n" + "encoding conversions in the old cluster and restart the upgrade.\n" + "A list of user-defined encoding conversions is in the file:\n" + " %s\n\n", output_path); + } + else + check_ok(); +} + /* * get_canonical_locale_name diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index f8174061ef3..75b829e8514 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10766,388 +10766,388 @@ # conversion functions { oid => '4302', descr => 'internal conversion function for KOI8R to MULE_INTERNAL', - proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_mic', + proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4303', descr => 'internal conversion function for MULE_INTERNAL to KOI8R', - proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_koi8r', + proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4304', descr => 'internal conversion function for ISO-8859-5 to MULE_INTERNAL', - proname => 'iso_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_mic', + proname => 'iso_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4305', descr => 'internal conversion function for MULE_INTERNAL to ISO-8859-5', - proname => 'mic_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_iso', + proname => 'mic_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4306', descr => 'internal conversion function for WIN1251 to MULE_INTERNAL', - proname => 'win1251_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_mic', + proname => 'win1251_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4307', descr => 'internal conversion function for MULE_INTERNAL to WIN1251', - proname => 'mic_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1251', + proname => 'mic_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4308', descr => 'internal conversion function for WIN866 to MULE_INTERNAL', - proname => 'win866_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_mic', + proname => 'win866_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4309', descr => 'internal conversion function for MULE_INTERNAL to WIN866', - proname => 'mic_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win866', + proname => 'mic_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4310', descr => 'internal conversion function for KOI8R to WIN1251', - proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4311', descr => 'internal conversion function for WIN1251 to KOI8R', - proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4312', descr => 'internal conversion function for KOI8R to WIN866', - proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_win866', + proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4313', descr => 'internal conversion function for WIN866 to KOI8R', - proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_koi8r', + proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4314', descr => 'internal conversion function for WIN866 to WIN1251', - proname => 'win866_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win866_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4315', descr => 'internal conversion function for WIN1251 to WIN866', - proname => 'win1251_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4316', descr => 'internal conversion function for ISO-8859-5 to KOI8R', - proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_koi8r', + proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4317', descr => 'internal conversion function for KOI8R to ISO-8859-5', - proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_iso', + proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4318', descr => 'internal conversion function for ISO-8859-5 to WIN1251', - proname => 'iso_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win1251', + proname => 'iso_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4319', descr => 'internal conversion function for WIN1251 to ISO-8859-5', - proname => 'win1251_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_iso', + proname => 'win1251_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4320', descr => 'internal conversion function for ISO-8859-5 to WIN866', - proname => 'iso_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win866', + proname => 'iso_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4321', descr => 'internal conversion function for WIN866 to ISO-8859-5', - proname => 'win866_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_iso', + proname => 'win866_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4322', descr => 'internal conversion function for EUC_CN to MULE_INTERNAL', - proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_mic', + proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_mic', probin => '$libdir/euc_cn_and_mic' }, { oid => '4323', descr => 'internal conversion function for MULE_INTERNAL to EUC_CN', - proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_cn', + proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_cn', probin => '$libdir/euc_cn_and_mic' }, { oid => '4324', descr => 'internal conversion function for EUC_JP to SJIS', - proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_sjis', + proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4325', descr => 'internal conversion function for SJIS to EUC_JP', - proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_euc_jp', + proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4326', descr => 'internal conversion function for EUC_JP to MULE_INTERNAL', - proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_mic', + proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4327', descr => 'internal conversion function for SJIS to MULE_INTERNAL', - proname => 'sjis_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_mic', + proname => 'sjis_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4328', descr => 'internal conversion function for MULE_INTERNAL to EUC_JP', - proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_jp', + proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4329', descr => 'internal conversion function for MULE_INTERNAL to SJIS', - proname => 'mic_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_sjis', + proname => 'mic_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4330', descr => 'internal conversion function for EUC_KR to MULE_INTERNAL', - proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_mic', + proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_mic', probin => '$libdir/euc_kr_and_mic' }, { oid => '4331', descr => 'internal conversion function for MULE_INTERNAL to EUC_KR', - proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_kr', + proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_kr', probin => '$libdir/euc_kr_and_mic' }, { oid => '4332', descr => 'internal conversion function for EUC_TW to BIG5', - proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_big5', + proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4333', descr => 'internal conversion function for BIG5 to EUC_TW', - proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_euc_tw', + proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4334', descr => 'internal conversion function for EUC_TW to MULE_INTERNAL', - proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_mic', + proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4335', descr => 'internal conversion function for BIG5 to MULE_INTERNAL', - proname => 'big5_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_mic', + proname => 'big5_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4336', descr => 'internal conversion function for MULE_INTERNAL to EUC_TW', - proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_tw', + proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4337', descr => 'internal conversion function for MULE_INTERNAL to BIG5', - proname => 'mic_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_big5', + proname => 'mic_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4338', descr => 'internal conversion function for LATIN2 to MULE_INTERNAL', - proname => 'latin2_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin2_to_mic', + proname => 'latin2_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4339', descr => 'internal conversion function for MULE_INTERNAL to LATIN2', - proname => 'mic_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin2', + proname => 'mic_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4340', descr => 'internal conversion function for WIN1250 to MULE_INTERNAL', - proname => 'win1250_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1250_to_mic', + proname => 'win1250_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4341', descr => 'internal conversion function for MULE_INTERNAL to WIN1250', - proname => 'mic_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1250', + proname => 'mic_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4342', descr => 'internal conversion function for LATIN2 to WIN1250', - proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4343', descr => 'internal conversion function for WIN1250 to LATIN2', - proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4344', descr => 'internal conversion function for LATIN1 to MULE_INTERNAL', - proname => 'latin1_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin1_to_mic', + proname => 'latin1_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin1_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4345', descr => 'internal conversion function for MULE_INTERNAL to LATIN1', - proname => 'mic_to_latin1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin1', + proname => 'mic_to_latin1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin1', probin => '$libdir/latin_and_mic' }, { oid => '4346', descr => 'internal conversion function for LATIN3 to MULE_INTERNAL', - proname => 'latin3_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin3_to_mic', + proname => 'latin3_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin3_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4347', descr => 'internal conversion function for MULE_INTERNAL to LATIN3', - proname => 'mic_to_latin3', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin3', + proname => 'mic_to_latin3', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin3', probin => '$libdir/latin_and_mic' }, { oid => '4348', descr => 'internal conversion function for LATIN4 to MULE_INTERNAL', - proname => 'latin4_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin4_to_mic', + proname => 'latin4_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin4_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4349', descr => 'internal conversion function for MULE_INTERNAL to LATIN4', - proname => 'mic_to_latin4', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin4', + proname => 'mic_to_latin4', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin4', probin => '$libdir/latin_and_mic' }, { oid => '4352', descr => 'internal conversion function for BIG5 to UTF8', - proname => 'big5_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_utf8', + proname => 'big5_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_utf8', probin => '$libdir/utf8_and_big5' }, { oid => '4353', descr => 'internal conversion function for UTF8 to BIG5', - proname => 'utf8_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_big5', + proname => 'utf8_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_big5', probin => '$libdir/utf8_and_big5' }, { oid => '4354', descr => 'internal conversion function for UTF8 to KOI8R', - proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8r', + proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8r', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4355', descr => 'internal conversion function for KOI8R to UTF8', - proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_utf8', + proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4356', descr => 'internal conversion function for UTF8 to KOI8U', - proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8u', + proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8u', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4357', descr => 'internal conversion function for KOI8U to UTF8', - proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8u_to_utf8', + proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8u_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4358', descr => 'internal conversion function for UTF8 to WIN', - proname => 'utf8_to_win', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_win', + proname => 'utf8_to_win', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_win', probin => '$libdir/utf8_and_win' }, { oid => '4359', descr => 'internal conversion function for WIN to UTF8', - proname => 'win_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win_to_utf8', + proname => 'win_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win_to_utf8', probin => '$libdir/utf8_and_win' }, { oid => '4360', descr => 'internal conversion function for EUC_CN to UTF8', - proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_utf8', + proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_utf8', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4361', descr => 'internal conversion function for UTF8 to EUC_CN', - proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_cn', + proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_cn', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4362', descr => 'internal conversion function for EUC_JP to UTF8', - proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_utf8', + proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_utf8', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4363', descr => 'internal conversion function for UTF8 to EUC_JP', - proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_jp', + proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jp', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4364', descr => 'internal conversion function for EUC_KR to UTF8', - proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_utf8', + proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_utf8', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4365', descr => 'internal conversion function for UTF8 to EUC_KR', - proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_kr', + proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_kr', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4366', descr => 'internal conversion function for EUC_TW to UTF8', - proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_utf8', + proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_utf8', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4367', descr => 'internal conversion function for UTF8 to EUC_TW', - proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_tw', + proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_tw', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4368', descr => 'internal conversion function for GB18030 to UTF8', - proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gb18030_to_utf8', + proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gb18030_to_utf8', probin => '$libdir/utf8_and_gb18030' }, { oid => '4369', descr => 'internal conversion function for UTF8 to GB18030', - proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gb18030', + proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gb18030', probin => '$libdir/utf8_and_gb18030' }, { oid => '4370', descr => 'internal conversion function for GBK to UTF8', - proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gbk_to_utf8', + proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gbk_to_utf8', probin => '$libdir/utf8_and_gbk' }, { oid => '4371', descr => 'internal conversion function for UTF8 to GBK', - proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gbk', + proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gbk', probin => '$libdir/utf8_and_gbk' }, { oid => '4372', descr => 'internal conversion function for UTF8 to ISO-8859 2-16', - proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_iso8859', + proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859', probin => '$libdir/utf8_and_iso8859' }, { oid => '4373', descr => 'internal conversion function for ISO-8859 2-16 to UTF8', - proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso8859_to_utf8', + proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_to_utf8', probin => '$libdir/utf8_and_iso8859' }, { oid => '4374', descr => 'internal conversion function for LATIN1 to UTF8', - proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_1_to_utf8', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4375', descr => 'internal conversion function for UTF8 to LATIN1', - proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859_1', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4376', descr => 'internal conversion function for JOHAB to UTF8', - proname => 'johab_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'johab_to_utf8', + proname => 'johab_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'johab_to_utf8', probin => '$libdir/utf8_and_johab' }, { oid => '4377', descr => 'internal conversion function for UTF8 to JOHAB', - proname => 'utf8_to_johab', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_johab', + proname => 'utf8_to_johab', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_johab', probin => '$libdir/utf8_and_johab' }, { oid => '4378', descr => 'internal conversion function for SJIS to UTF8', - proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_utf8', + proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_utf8', probin => '$libdir/utf8_and_sjis' }, { oid => '4379', descr => 'internal conversion function for UTF8 to SJIS', - proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_sjis', + proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_sjis', probin => '$libdir/utf8_and_sjis' }, { oid => '4380', descr => 'internal conversion function for UHC to UTF8', - proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'uhc_to_utf8', + proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'uhc_to_utf8', probin => '$libdir/utf8_and_uhc' }, { oid => '4381', descr => 'internal conversion function for UTF8 to UHC', - proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_uhc', + proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_uhc', probin => '$libdir/utf8_and_uhc' }, { oid => '4382', descr => 'internal conversion function for EUC_JIS_2004 to UTF8', - proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_utf8', probin => '$libdir/utf8_and_euc2004' }, { oid => '4383', descr => 'internal conversion function for UTF8 to EUC_JIS_2004', - proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jis_2004', probin => '$libdir/utf8_and_euc2004' }, { oid => '4384', descr => 'internal conversion function for SHIFT_JIS_2004 to UTF8', - proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_utf8', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4385', descr => 'internal conversion function for UTF8 to SHIFT_JIS_2004', - proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_shift_jis_2004', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4386', descr => 'internal conversion function for EUC_JIS_2004 to SHIFT_JIS_2004', proname => 'euc_jis_2004_to_shift_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_shift_jis_2004', probin => '$libdir/euc2004_sjis2004' }, { oid => '4387', descr => 'internal conversion function for SHIFT_JIS_2004 to EUC_JIS_2004', proname => 'shift_jis_2004_to_euc_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_euc_jis_2004', probin => '$libdir/euc2004_sjis2004' }, diff --git a/src/include/mb/pg_wchar.h b/src/include/mb/pg_wchar.h index 64b22e4b0d4..346a41a1f3d 100644 --- a/src/include/mb/pg_wchar.h +++ b/src/include/mb/pg_wchar.h @@ -627,18 +627,18 @@ extern void pg_unicode_to_server(pg_wchar c, unsigned char *s); extern unsigned short BIG5toCNS(unsigned short big5, unsigned char *lc); extern unsigned short CNStoBIG5(unsigned short cns, unsigned char lc); -extern void UtfToLocal(const unsigned char *utf, int len, - unsigned char *iso, - const pg_mb_radix_tree *map, - const pg_utf_to_local_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); -extern void LocalToUtf(const unsigned char *iso, int len, - unsigned char *utf, - const pg_mb_radix_tree *map, - const pg_local_to_utf_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); +extern int UtfToLocal(const unsigned char *utf, int len, + unsigned char *iso, + const pg_mb_radix_tree *map, + const pg_utf_to_local_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); +extern int LocalToUtf(const unsigned char *iso, int len, + unsigned char *utf, + const pg_mb_radix_tree *map, + const pg_local_to_utf_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); extern bool pg_verifymbstr(const char *mbstr, int len, bool noError); extern bool pg_verify_mbstr(int encoding, const char *mbstr, int len, @@ -656,18 +656,19 @@ extern void report_invalid_encoding(int encoding, const char *mbstr, int len) pg extern void report_untranslatable_char(int src_encoding, int dest_encoding, const char *mbstr, int len) pg_attribute_noreturn(); -extern void local2local(const unsigned char *l, unsigned char *p, int len, - int src_encoding, int dest_encoding, const unsigned char *tab); -extern void latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding); -extern void mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding); -extern void latin2mic_with_table(const unsigned char *l, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); -extern void mic2latin_with_table(const unsigned char *mic, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); +extern int local2local(const unsigned char *l, unsigned char *p, int len, + int src_encoding, int dest_encoding, const unsigned char *tab, + bool noError); +extern int latin2mic(const unsigned char *l, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int mic2latin(const unsigned char *mic, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int latin2mic_with_table(const unsigned char *l, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); +extern int mic2latin_with_table(const unsigned char *mic, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); #ifdef WIN32 extern WCHAR *pgwin32_message_to_UTF16(const char *str, int len, int *utf16len); diff --git a/src/test/regress/expected/opr_sanity.out b/src/test/regress/expected/opr_sanity.out index 254ca06d3dd..23ba60e395f 100644 --- a/src/test/regress/expected/opr_sanity.out +++ b/src/test/regress/expected/opr_sanity.out @@ -1052,13 +1052,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); oid | proname | oid | conname -----+---------+-----+--------- (0 rows) diff --git a/src/test/regress/sql/opr_sanity.sql b/src/test/regress/sql/opr_sanity.sql index bbd3834b634..04691745981 100644 --- a/src/test/regress/sql/opr_sanity.sql +++ b/src/test/regress/sql/opr_sanity.sql @@ -556,13 +556,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); -- Check for conprocs that don't perform the specific conversion that -- pg_conversion alleges they do, by trying to invoke each conversion -- 2.29.2 --------------39E46EF15EBFAA37D53332E5 Content-Type: text/x-patch; charset=UTF-8; name="v3-0003-Add-tests-for-the-new-noError-variants-of-built-i.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="v3-0003-Add-tests-for-the-new-noError-variants-of-built-i.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 34+ messages in thread
* [PATCH v3 2/5] Change conversion function signature. @ 2021-01-28 16:42 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 34+ messages in thread From: Heikki Linnakangas @ 2021-01-28 16:42 UTC (permalink / raw) Add a 'noError' argument, so that we can try to convert a buffer without knowing the character boundaries beforehand. The functions now need to return the number of input bytes successfully converted. This is is a backwards-incompatible change, if you have created a custom encoding conversion with CREATE CONVERSION. This adds a check to pg_upgrade for that, refusing the upgrade if there are any user-defined encoding conversions. --- doc/src/sgml/ref/create_conversion.sgml | 5 +- src/backend/commands/conversioncmds.c | 27 +- src/backend/utils/error/elog.c | 2 + src/backend/utils/mb/conv.c | 112 +++++- .../cyrillic_and_mic/cyrillic_and_mic.c | 127 ++++--- .../euc2004_sjis2004/euc2004_sjis2004.c | 96 ++++- .../euc_cn_and_mic/euc_cn_and_mic.c | 57 ++- .../euc_jp_and_sjis/euc_jp_and_sjis.c | 153 ++++++-- .../euc_kr_and_mic/euc_kr_and_mic.c | 57 ++- .../euc_tw_and_big5/euc_tw_and_big5.c | 165 +++++++-- .../latin2_and_win1250/latin2_and_win1250.c | 49 ++- .../latin_and_mic/latin_and_mic.c | 43 ++- .../utf8_and_big5/utf8_and_big5.c | 37 +- .../utf8_and_cyrillic/utf8_and_cyrillic.c | 67 ++-- .../utf8_and_euc2004/utf8_and_euc2004.c | 37 +- .../utf8_and_euc_cn/utf8_and_euc_cn.c | 37 +- .../utf8_and_euc_jp/utf8_and_euc_jp.c | 37 +- .../utf8_and_euc_kr/utf8_and_euc_kr.c | 37 +- .../utf8_and_euc_tw/utf8_and_euc_tw.c | 37 +- .../utf8_and_gb18030/utf8_and_gb18030.c | 37 +- .../utf8_and_gbk/utf8_and_gbk.c | 37 +- .../utf8_and_iso8859/utf8_and_iso8859.c | 43 ++- .../utf8_and_iso8859_1/utf8_and_iso8859_1.c | 27 +- .../utf8_and_johab/utf8_and_johab.c | 37 +- .../utf8_and_sjis/utf8_and_sjis.c | 37 +- .../utf8_and_sjis2004/utf8_and_sjis2004.c | 37 +- .../utf8_and_uhc/utf8_and_uhc.c | 37 +- .../utf8_and_win/utf8_and_win.c | 43 ++- src/backend/utils/mb/mbutils.c | 18 +- src/bin/pg_upgrade/check.c | 95 +++++ src/include/catalog/pg_proc.dat | 332 +++++++++--------- src/include/mb/pg_wchar.h | 49 +-- src/test/regress/expected/opr_sanity.out | 7 +- src/test/regress/sql/opr_sanity.sql | 7 +- 34 files changed, 1390 insertions(+), 635 deletions(-) diff --git a/doc/src/sgml/ref/create_conversion.sgml b/doc/src/sgml/ref/create_conversion.sgml index e7700fecfc5..f014a676c88 100644 --- a/doc/src/sgml/ref/create_conversion.sgml +++ b/doc/src/sgml/ref/create_conversion.sgml @@ -117,8 +117,9 @@ conv_proc( integer, -- destination encoding ID cstring, -- source string (null terminated C string) internal, -- destination (fill with a null terminated C string) - integer -- source string length -) RETURNS void; + integer, -- source string length + boolean -- if true, don't throw an error if conversion fails +) RETURNS integer; </programlisting></para> </listitem> </varlistentry> diff --git a/src/backend/commands/conversioncmds.c b/src/backend/commands/conversioncmds.c index f7ff321de71..d2041466911 100644 --- a/src/backend/commands/conversioncmds.c +++ b/src/backend/commands/conversioncmds.c @@ -45,8 +45,9 @@ CreateConversionCommand(CreateConversionStmt *stmt) const char *from_encoding_name = stmt->for_encoding_name; const char *to_encoding_name = stmt->to_encoding_name; List *func_name = stmt->func_name; - static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID}; + static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID, BOOLOID}; char result[1]; + Datum funcresult; /* Convert list of names to a name and namespace */ namespaceId = QualifiedNameGetCreationNamespace(stmt->conversion_name, @@ -92,8 +93,8 @@ CreateConversionCommand(CreateConversionStmt *stmt) funcoid = LookupFuncName(func_name, sizeof(funcargs) / sizeof(Oid), funcargs, false); - /* Check it returns VOID, else it's probably the wrong function */ - if (get_func_rettype(funcoid) != VOIDOID) + /* Check it returns int4, else it's probably the wrong function */ + if (get_func_rettype(funcoid) != INT4OID) ereport(ERROR, (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), errmsg("encoding conversion function %s must return type %s", @@ -111,12 +112,20 @@ CreateConversionCommand(CreateConversionStmt *stmt) * string; the conversion function should throw an error if it can't * perform the requested conversion. */ - OidFunctionCall5(funcoid, - Int32GetDatum(from_encoding), - Int32GetDatum(to_encoding), - CStringGetDatum(""), - CStringGetDatum(result), - Int32GetDatum(0)); + funcresult = OidFunctionCall6(funcoid, + Int32GetDatum(from_encoding), + Int32GetDatum(to_encoding), + CStringGetDatum(""), + CStringGetDatum(result), + Int32GetDatum(0), + BoolGetDatum(false)); + + /* The function should return 0 for empty input. Might as well check that, too. */ + if (DatumGetInt32(funcresult) != 0) + ereport(ERROR, + (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), + errmsg("encoding conversion function %s returned incorrect result for empty input", + NameListToString(func_name)))); /* * All seem ok, go ahead (possible failure would be a duplicate conversion diff --git a/src/backend/utils/error/elog.c b/src/backend/utils/error/elog.c index 80c26724612..762f77d533c 100644 --- a/src/backend/utils/error/elog.c +++ b/src/backend/utils/error/elog.c @@ -2280,6 +2280,8 @@ write_console(const char *line, int len) * Conversion on non-win32 platforms is not implemented yet. It requires * non-throw version of pg_do_encoding_conversion(), that converts * unconvertable characters to '?' without errors. + * + * XXX: We have a no-throw version now. It doesn't convert to '?' though. */ #endif diff --git a/src/backend/utils/mb/conv.c b/src/backend/utils/mb/conv.c index a07b54bd3b8..b83358bc7a5 100644 --- a/src/backend/utils/mb/conv.c +++ b/src/backend/utils/mb/conv.c @@ -26,14 +26,16 @@ * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the target charset, or 0 if there is no equivalent code. */ -void +int local2local(const unsigned char *l, unsigned char *p, int len, int src_encoding, int dest_encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -41,7 +43,11 @@ local2local(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(src_encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -50,13 +56,19 @@ local2local(const unsigned char *l, if (c2) *p++ = c2; else + { + if (noError) + break; report_untranslatable_char(src_encoding, dest_encoding, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -67,17 +79,22 @@ local2local(const unsigned char *l, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = l; int c1; while (len > 0) { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (IS_HIGHBIT_SET(c1)) *p++ = lc; *p++ = c1; @@ -85,6 +102,8 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, len--; } *p = '\0'; + + return l - start; } /* @@ -95,17 +114,22 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -118,17 +142,27 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1])) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); + } *p++ = mic[1]; mic += 2; len -= 2; } } *p = '\0'; + + return mic - start; } @@ -144,14 +178,16 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the mule encoding, or 0 if there is no equivalent code. */ -void +int latin2mic_with_table(const unsigned char *l, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -159,7 +195,11 @@ latin2mic_with_table(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -171,13 +211,19 @@ latin2mic_with_table(const unsigned char *l, *p++ = c2; } else + { + if (noError) + break; report_untranslatable_char(encoding, PG_MULE_INTERNAL, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -192,14 +238,16 @@ latin2mic_with_table(const unsigned char *l, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the local charset, or 0 if there is no equivalent code. */ -void +int mic2latin_with_table(const unsigned char *mic, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = mic; unsigned char c1, c2; @@ -207,7 +255,11 @@ mic2latin_with_table(const unsigned char *mic, { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -220,11 +272,17 @@ mic2latin_with_table(const unsigned char *mic, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1]) || (c2 = tab[mic[1] - HIGHBIT]) == 0) { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); break; /* keep compiler quiet */ @@ -235,6 +293,8 @@ mic2latin_with_table(const unsigned char *mic, } } *p = '\0'; + + return mic - start; } /* @@ -425,17 +485,19 @@ pg_mb_radix_conv(const pg_mb_radix_tree *rt, * * See pg_wchar.h for more details about the data structures used here. */ -void +int UtfToLocal(const unsigned char *utf, int len, unsigned char *iso, const pg_mb_radix_tree *map, const pg_utf_to_local_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, bool noError) { uint32 iutf; int l; const pg_utf_to_local_combined *cp; + const unsigned char *start = utf; + const unsigned char *cur = utf; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -449,6 +511,8 @@ UtfToLocal(const unsigned char *utf, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*utf == '\0') break; @@ -584,15 +648,19 @@ UtfToLocal(const unsigned char *utf, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(PG_UTF8, encoding, (const char *) (utf - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(PG_UTF8, (const char *) utf, len); *iso = '\0'; + + return cur - start; } /* @@ -616,18 +684,24 @@ UtfToLocal(const unsigned char *utf, int len, * (if provided) is applied. An error is raised if no match is found. * * See pg_wchar.h for more details about the data structures used here. + * + * Returns the number of input bytes consumed. If noError is true, this can + * be less than 'len'. */ -void +int LocalToUtf(const unsigned char *iso, int len, unsigned char *utf, const pg_mb_radix_tree *map, const pg_local_to_utf_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, + bool noError) { uint32 iiso; int l; const pg_local_to_utf_combined *cp; + const unsigned char *start = iso; + const unsigned char *cur = iso; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -641,6 +715,8 @@ LocalToUtf(const unsigned char *iso, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*iso == '\0') break; @@ -723,13 +799,17 @@ LocalToUtf(const unsigned char *iso, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(encoding, PG_UTF8, (const char *) (iso - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(encoding, (const char *) iso, len); *utf = '\0'; + + return cur - start; } diff --git a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c index 4c5b02654de..368c2deb5e4 100644 --- a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c @@ -44,8 +44,11 @@ PG_FUNCTION_INFO_V1(win866_to_iso); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -306,12 +309,14 @@ koi8r_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -320,12 +325,14 @@ mic_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_KOI8R); - mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -334,12 +341,14 @@ iso_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -348,12 +357,14 @@ mic_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_ISO_8859_5); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -362,12 +373,14 @@ win1251_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -376,12 +389,14 @@ mic_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1251); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -390,12 +405,14 @@ win866_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -404,12 +421,14 @@ mic_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN866); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -418,12 +437,14 @@ koi8r_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN1251); - local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -432,12 +453,14 @@ win1251_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_KOI8R); - local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi); + converted = local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -446,12 +469,14 @@ koi8r_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN866); - local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -460,12 +485,14 @@ win866_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_KOI8R); - local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi); + converted = local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -474,12 +501,14 @@ win866_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_WIN1251); - local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251); + converted = local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -488,12 +517,14 @@ win1251_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_WIN866); - local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866); + converted = local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -502,12 +533,14 @@ iso_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_KOI8R); - local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -516,12 +549,14 @@ koi8r_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_ISO_8859_5); - local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso); + converted = local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -530,12 +565,14 @@ iso_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN1251); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -544,12 +581,14 @@ win1251_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso); + converted = local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -558,12 +597,14 @@ iso_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN866); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -572,10 +613,12 @@ win866_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso); + converted = local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c index 4d7fb116cfd..88529c644cf 100644 --- a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c @@ -19,8 +19,8 @@ PG_MODULE_MAGIC; PG_FUNCTION_INFO_V1(euc_jis_2004_to_shift_jis_2004); PG_FUNCTION_INFO_V1(shift_jis_2004_to_euc_jis_2004); -static void euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len); -static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len); +static int euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError); /* ---------- * conv_proc( @@ -28,8 +28,11 @@ static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -39,12 +42,14 @@ euc_jis_2004_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_SHIFT_JIS_2004); - euc_jis_20042shift_jis_2004(src, dest, len); + converted = euc_jis_20042shift_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -53,20 +58,23 @@ shift_jis_2004_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_EUC_JIS_2004); - shift_jis_20042euc_jis_2004(src, dest, len); + converted = shift_jis_20042euc_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_JIS_2004 -> SHIFT_JIS_2004 */ -static void -euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, ku, ten; @@ -79,8 +87,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -90,8 +102,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) l = pg_encoding_verifymbchar(PG_EUC_JIS_2004, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (c1 == SS2 && l == 2) /* JIS X 0201 kana? */ { @@ -121,8 +137,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) *p++ = (ku + 0x19b) >> 1; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } if (ku % 2) @@ -132,8 +152,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; @@ -149,8 +173,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ku >= 63 && ku <= 94) *p++ = (ku + 0x181) >> 1; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (ku % 2) { @@ -159,20 +187,30 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else - report_invalid_encoding(PG_EUC_JIS_2004, + { + if (noError) + break; + report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } euc += l; len -= l; } *p = '\0'; + + return euc - start; } /* @@ -212,9 +250,10 @@ get_ten(int b, int *ku) * SHIFT_JIS_2004 ---> EUC_JIS_2004 */ -static void -shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len) +static int +shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1; int ku, ten, @@ -230,8 +269,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -241,8 +284,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len l = pg_encoding_verifymbchar(PG_SHIFT_JIS_2004, (const char *) sjis, len); if (l < 0 || l > len) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf && l == 1) { @@ -266,8 +313,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x100; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xe0 && c1 <= 0xef) /* plane 1 62ku-94ku */ @@ -275,9 +326,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x180; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, - (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xf0 && c1 <= 0xf3) /* plane 2 @@ -286,8 +340,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } switch (c1) { case 0xf0: @@ -309,16 +367,24 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 == 0xf4 && kubun == 1) ku = 15; else ku = (c1 << 1) - 0x19a - kubun; } else + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (plane == 2) *p++ = SS3; @@ -330,4 +396,6 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c index e9bb896935f..a8da733803d 100644 --- a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_cn2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_cn(const unsigned char *mic, unsigned char *p, int len); +static int euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_cn_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_cn_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_MULE_INTERNAL); - euc_cn2mic(src, dest, len); + converted = euc_cn2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_CN); - mic2euc_cn(src, dest, len); + converted = mic2euc_cn(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_CN ---> MIC */ -static void -euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; while (len > 0) @@ -76,7 +84,11 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (len < 2 || !IS_HIGHBIT_SET(euc[1])) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = LC_GB2312_80; *p++ = c1; *p++ = euc[1]; @@ -86,21 +98,28 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_CN */ -static void -mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) @@ -109,11 +128,19 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (c1 != LC_GB2312_80) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_CN, (const char *) mic, len); + } if (len < 3 || !IS_HIGHBIT_SET(mic[1]) || !IS_HIGHBIT_SET(mic[2])) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } mic++; *p++ = *mic++; *p++ = *mic++; @@ -122,12 +149,18 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; } } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c index 5059f917a98..cc4817dc4cd 100644 --- a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c @@ -42,17 +42,20 @@ PG_FUNCTION_INFO_V1(mic_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void sjis2mic(const unsigned char *sjis, unsigned char *p, int len); -static void mic2sjis(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_jp(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len); -static void sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len); +static int sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError); +static int mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_jp_to_sjis(PG_FUNCTION_ARGS) @@ -60,12 +63,14 @@ euc_jp_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_SJIS); - euc_jp2sjis(src, dest, len); + converted = euc_jp2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -74,12 +79,14 @@ sjis_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_EUC_JP); - sjis2euc_jp(src, dest, len); + converted = sjis2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -88,12 +95,14 @@ euc_jp_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_MULE_INTERNAL); - euc_jp2mic(src, dest, len); + converted = euc_jp2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -102,12 +111,14 @@ mic_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_JP); - mic2euc_jp(src, dest, len); + converted = mic2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -116,12 +127,14 @@ sjis_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_MULE_INTERNAL); - sjis2mic(src, dest, len); + converted = sjis2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -130,20 +143,23 @@ mic_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_SJIS); - mic2sjis(src, dest, len); + converted = mic2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * SJIS ---> MIC */ -static void -sjis2mic(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -167,7 +183,11 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) * JIS X0208, X0212, user defined extended characters */ if (len < 2 || !ISSJISHEAD(c1) || !ISSJISTAIL(sjis[1])) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } c2 = sjis[1]; k = (c1 << 8) + c2; if (k >= 0xed40 && k < 0xf040) @@ -257,21 +277,28 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; } } *p = '\0'; + + return sjis - start; } /* * MIC ---> SJIS */ -static void -mic2sjis(const unsigned char *mic, unsigned char *p, int len) +static int +mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1, c2, k, @@ -284,8 +311,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -293,8 +324,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) *p++ = mic[1]; else if (c1 == LC_JISX0208) @@ -350,20 +385,27 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_SJIS, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP ---> MIC */ -static void -euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -374,8 +416,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -383,8 +429,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* 1 byte kana? */ *p++ = LC_JISX0201K; @@ -406,14 +456,17 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_JP */ -static void -mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -424,8 +477,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -433,8 +490,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) { *p++ = SS2; @@ -452,20 +513,27 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_JP, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP -> SJIS */ -static void -euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, c2, k; @@ -478,8 +546,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -487,8 +559,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* hankaku kana? */ @@ -551,14 +627,17 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * SJIS ---> EUC_JP */ -static void -sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -573,8 +652,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -582,8 +665,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_SJIS, (const char *) sjis, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf) { /* JIS X0201 (1 byte kana) */ @@ -680,4 +767,6 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c index ac823d6c270..a5b51617e52 100644 --- a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_kr2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_kr(const unsigned char *mic, unsigned char *p, int len); +static int euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_kr_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_kr_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_MULE_INTERNAL); - euc_kr2mic(src, dest, len); + converted = euc_kr2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_KR); - mic2euc_kr(src, dest, len); + converted = mic2euc_kr(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_KR ---> MIC */ -static void -euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -78,8 +86,12 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_KR, (const char *) euc, len); if (l != 2) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = LC_KS5601; *p++ = c1; *p++ = euc[1]; @@ -89,22 +101,29 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_KR */ -static void -mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -115,8 +134,12 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -124,18 +147,28 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_KS5601) { *p++ = mic[1]; *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_KR, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c index 66c242d7f36..ebb4e0acd53 100644 --- a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c @@ -32,17 +32,20 @@ PG_FUNCTION_INFO_V1(mic_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_tw2big5(const unsigned char *euc, unsigned char *p, int len); -static void big52euc_tw(const unsigned char *euc, unsigned char *p, int len); -static void big52mic(const unsigned char *big5, unsigned char *p, int len); -static void mic2big5(const unsigned char *mic, unsigned char *p, int len); -static void euc_tw2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_tw(const unsigned char *mic, unsigned char *p, int len); +static int euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52euc_tw(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError); +static int mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_tw_to_big5(PG_FUNCTION_ARGS) @@ -50,12 +53,14 @@ euc_tw_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_BIG5); - euc_tw2big5(src, dest, len); + converted = euc_tw2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -64,12 +69,14 @@ big5_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_EUC_TW); - big52euc_tw(src, dest, len); + converted = big52euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -78,12 +85,14 @@ euc_tw_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_MULE_INTERNAL); - euc_tw2mic(src, dest, len); + converted = euc_tw2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -92,12 +101,14 @@ mic_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_TW); - mic2euc_tw(src, dest, len); + converted = mic2euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -106,12 +117,14 @@ big5_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_MULE_INTERNAL); - big52mic(src, dest, len); + converted = big52mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -120,21 +133,24 @@ mic_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_BIG5); - mic2big5(src, dest, len); + converted = mic2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_TW ---> Big5 */ -static void -euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; unsigned char c1; unsigned short big5buf, cnsBuf; @@ -149,8 +165,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Verify and decode the next EUC_TW input character */ l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -171,8 +191,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Write it out in Big5 */ big5buf = CNStoBIG5(cnsBuf, lc); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_EUC_TW, PG_BIG5, (const char *) euc, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; @@ -182,22 +206,29 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * Big5 ---> EUC_TW */ -static void -big52euc_tw(const unsigned char *big5, unsigned char *p, int len) +static int +big52euc_tw(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -212,8 +243,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); @@ -237,8 +272,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_EUC_TW, (const char *) big5, len); + } big5 += l; len -= l; @@ -256,14 +295,17 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) } } *p = '\0'; + + return big5 - start; } /* * EUC_TW ---> MIC */ -static void -euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -274,8 +316,12 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -304,22 +350,29 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_TW */ -static void -mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -330,8 +383,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -339,8 +396,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1) { *p++ = mic[1]; @@ -362,20 +423,27 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[3]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_TW, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * Big5 ---> MIC */ -static void -big52mic(const unsigned char *big5, unsigned char *p, int len) +static int +big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -389,8 +457,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } *p++ = c1; big5++; len--; @@ -398,8 +470,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); if (lc != 0) @@ -412,20 +488,27 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_MULE_INTERNAL, (const char *) big5, len); + } big5 += l; len -= l; } *p = '\0'; + + return big5 - start; } /* * MIC ---> Big5 */ -static void -mic2big5(const unsigned char *mic, unsigned char *p, int len) +static int +mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -438,8 +521,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -447,8 +534,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1 || c1 == LC_CNS11643_2 || c1 == LCPRV2_B) { if (c1 == LCPRV2_B) @@ -462,16 +553,26 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } big5buf = CNStoBIG5(cnsBuf, c1); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c index 2e28e6780a5..8610fcb69aa 100644 --- a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c +++ b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(win1250_to_latin2); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -82,12 +85,14 @@ latin2_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -96,12 +101,14 @@ mic_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN2); - mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -110,13 +117,15 @@ win1250_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - win1250_2_iso88592); + converted = latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -125,13 +134,15 @@ mic_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1250); - mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - iso88592_2_win1250); + converted = mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -140,12 +151,15 @@ latin2_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_WIN1250); - local2local(src, dest, len, PG_LATIN2, PG_WIN1250, iso88592_2_win1250); + converted = local2local(src, dest, len, PG_LATIN2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -154,10 +168,13 @@ win1250_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_LATIN2); - local2local(src, dest, len, PG_WIN1250, PG_LATIN2, win1250_2_iso88592); + converted = local2local(src, dest, len, PG_WIN1250, PG_LATIN2, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c index bc651410f21..bff27d1c295 100644 --- a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(mic_to_latin4); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -42,12 +45,14 @@ latin1_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,12 +61,14 @@ mic_to_latin1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN1); - mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -70,12 +77,14 @@ latin3_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN3, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -84,12 +93,14 @@ mic_to_latin3(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN3); - mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,12 +109,14 @@ latin4_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN4, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -112,10 +125,12 @@ mic_to_latin4(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN4); - mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c index d6067cdc24e..3838b15cab9 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ big5_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_UTF8); - LocalToUtf(src, len, dest, - &big5_to_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = LocalToUtf(src, len, dest, + &big5_to_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_BIG5); - UtfToLocal(src, len, dest, - &big5_from_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = UtfToLocal(src, len, dest, + &big5_from_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c index ed90e8e682e..75719fe5f1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c @@ -33,8 +33,11 @@ PG_FUNCTION_INFO_V1(koi8u_to_utf8); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -44,16 +47,19 @@ utf8_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8R); - UtfToLocal(src, len, dest, - &koi8r_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = UtfToLocal(src, len, dest, + &koi8r_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -62,16 +68,19 @@ koi8r_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8r_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = LocalToUtf(src, len, dest, + &koi8r_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -80,16 +89,19 @@ utf8_to_koi8u(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8U); - UtfToLocal(src, len, dest, - &koi8u_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = UtfToLocal(src, len, dest, + &koi8u_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,14 +110,17 @@ koi8u_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8U, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8u_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = LocalToUtf(src, len, dest, + &koi8u_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c index d699affce47..5391001951a 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jis_2004_to_unicode_tree, - LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = LocalToUtf(src, len, dest, + &euc_jis_2004_to_unicode_tree, + LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JIS_2004); - UtfToLocal(src, len, dest, - &euc_jis_2004_from_unicode_tree, - ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = UtfToLocal(src, len, dest, + &euc_jis_2004_from_unicode_tree, + ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c index d7c0ba6a58b..c87d1bf2398 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_cn_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_cn_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = LocalToUtf(src, len, dest, + &euc_cn_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_CN); - UtfToLocal(src, len, dest, - &euc_cn_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = UtfToLocal(src, len, dest, + &euc_cn_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c index 13a3a23e77b..6a55134db21 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jp); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jp_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jp_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = LocalToUtf(src, len, dest, + &euc_jp_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JP); - UtfToLocal(src, len, dest, - &euc_jp_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = UtfToLocal(src, len, dest, + &euc_jp_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c index 1bbb8aaef7b..fe1924e2fec 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_kr_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_kr_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = LocalToUtf(src, len, dest, + &euc_kr_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_KR); - UtfToLocal(src, len, dest, - &euc_kr_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = UtfToLocal(src, len, dest, + &euc_kr_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c index 9830045dccd..68215659b57 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_tw); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_tw_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_tw_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = LocalToUtf(src, len, dest, + &euc_tw_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_TW); - UtfToLocal(src, len, dest, - &euc_tw_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = UtfToLocal(src, len, dest, + &euc_tw_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c index f86ecf27424..e1a59c39a4d 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c @@ -183,8 +183,11 @@ conv_utf8_to_18030(uint32 code) * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -193,16 +196,19 @@ gb18030_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GB18030, PG_UTF8); - LocalToUtf(src, len, dest, - &gb18030_to_unicode_tree, - NULL, 0, - conv_18030_to_utf8, - PG_GB18030); + converted = LocalToUtf(src, len, dest, + &gb18030_to_unicode_tree, + NULL, 0, + conv_18030_to_utf8, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -211,14 +217,17 @@ utf8_to_gb18030(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GB18030); - UtfToLocal(src, len, dest, - &gb18030_from_unicode_tree, - NULL, 0, - conv_utf8_to_18030, - PG_GB18030); + converted = UtfToLocal(src, len, dest, + &gb18030_from_unicode_tree, + NULL, 0, + conv_utf8_to_18030, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c index 2ab8b16c8a8..881386d5347 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_gbk); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ gbk_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GBK, PG_UTF8); - LocalToUtf(src, len, dest, - &gbk_to_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = LocalToUtf(src, len, dest, + &gbk_to_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_gbk(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GBK); - UtfToLocal(src, len, dest, - &gbk_from_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = UtfToLocal(src, len, dest, + &gbk_from_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c index 3e49f67ea2f..d93a521badf 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c @@ -52,8 +52,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -100,6 +103,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -108,12 +112,15 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -122,7 +129,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -132,6 +139,7 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -140,12 +148,15 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -154,5 +165,5 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c index 67e713cca11..8ac93604a1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c @@ -26,8 +26,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859_1); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -37,6 +40,8 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_UTF8); @@ -45,7 +50,11 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_LATIN1, (const char *) src, len); + } if (!IS_HIGHBIT_SET(c)) *dest++ = c; else @@ -58,7 +67,7 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } Datum @@ -67,6 +76,8 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c, c1; @@ -76,7 +87,11 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_UTF8, (const char *) src, len); + } /* fast path for ASCII-subset characters */ if (!IS_HIGHBIT_SET(c)) { @@ -102,11 +117,15 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) len -= 2; } else + { + if (noError) + break; report_untranslatable_char(PG_UTF8, PG_LATIN1, (const char *) src, len); + } } } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c index 578f5df4e7f..317daa2d5ee 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_johab); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ johab_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_JOHAB, PG_UTF8); - LocalToUtf(src, len, dest, - &johab_to_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = LocalToUtf(src, len, dest, + &johab_to_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_johab(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_JOHAB); - UtfToLocal(src, len, dest, - &johab_from_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = UtfToLocal(src, len, dest, + &johab_from_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c index dd9fc2975ad..4c9348aba59 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ sjis_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_UTF8); - LocalToUtf(src, len, dest, - &sjis_to_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = LocalToUtf(src, len, dest, + &sjis_to_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SJIS); - UtfToLocal(src, len, dest, - &sjis_from_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = UtfToLocal(src, len, dest, + &sjis_from_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c index 4bcc886d674..1fffdc5930c 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_shift_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ shift_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &shift_jis_2004_to_unicode_tree, - LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = LocalToUtf(src, len, dest, + &shift_jis_2004_to_unicode_tree, + LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SHIFT_JIS_2004); - UtfToLocal(src, len, dest, - &shift_jis_2004_from_unicode_tree, - ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = UtfToLocal(src, len, dest, + &shift_jis_2004_from_unicode_tree, + ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c index c8e512994a1..d9471dad097 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_uhc); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ uhc_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UHC, PG_UTF8); - LocalToUtf(src, len, dest, - &uhc_to_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = LocalToUtf(src, len, dest, + &uhc_to_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_uhc(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_UHC); - UtfToLocal(src, len, dest, - &uhc_from_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = UtfToLocal(src, len, dest, + &uhc_from_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c index 0c9493dee56..110ba5677d0 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c @@ -48,8 +48,11 @@ PG_FUNCTION_INFO_V1(utf8_to_win); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -81,6 +84,7 @@ win_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -89,12 +93,15 @@ win_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -103,7 +110,7 @@ win_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -113,6 +120,7 @@ utf8_to_win(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -121,12 +129,15 @@ utf8_to_win(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -135,5 +146,5 @@ utf8_to_win(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/mbutils.c b/src/backend/utils/mb/mbutils.c index 2578573b0ab..65753860e35 100644 --- a/src/backend/utils/mb/mbutils.c +++ b/src/backend/utils/mb/mbutils.c @@ -406,12 +406,13 @@ pg_do_encoding_conversion(unsigned char *src, int len, MemoryContextAllocHuge(CurrentMemoryContext, (Size) len * MAX_CONVERSION_GROWTH + 1); - OidFunctionCall5(proc, - Int32GetDatum(src_encoding), - Int32GetDatum(dest_encoding), - CStringGetDatum(src), - CStringGetDatum(result), - Int32GetDatum(len)); + (void) OidFunctionCall6(proc, + Int32GetDatum(src_encoding), + Int32GetDatum(dest_encoding), + CStringGetDatum(src), + CStringGetDatum(result), + Int32GetDatum(len), + BoolGetDatum(false)); /* * If the result is large, it's worth repalloc'ing to release any extra @@ -849,12 +850,13 @@ pg_unicode_to_server(pg_wchar c, unsigned char *s) c_as_utf8[c_as_utf8_len] = '\0'; /* Convert, or throw error if we can't */ - FunctionCall5(Utf8ToServerConvProc, + FunctionCall6(Utf8ToServerConvProc, Int32GetDatum(PG_UTF8), Int32GetDatum(server_encoding), CStringGetDatum(c_as_utf8), CStringGetDatum(s), - Int32GetDatum(c_as_utf8_len)); + Int32GetDatum(c_as_utf8_len), + BoolGetDatum(false)); } diff --git a/src/bin/pg_upgrade/check.c b/src/bin/pg_upgrade/check.c index 43fc297eb69..ee6be95b08d 100644 --- a/src/bin/pg_upgrade/check.c +++ b/src/bin/pg_upgrade/check.c @@ -28,6 +28,7 @@ static void check_for_reg_data_type_usage(ClusterInfo *cluster); static void check_for_jsonb_9_4_usage(ClusterInfo *cluster); static void check_for_pg_role_prefix(ClusterInfo *cluster); static void check_for_new_tablespace_dir(ClusterInfo *new_cluster); +static void check_for_user_defined_encoding_conversions(ClusterInfo *cluster); static char *get_canonical_locale_name(int category, const char *locale); @@ -102,6 +103,15 @@ check_and_dump_old_cluster(bool live_check) check_for_reg_data_type_usage(&old_cluster); check_for_isn_and_int8_passing_mismatch(&old_cluster); + /* + * PG 14 changed the function signature of encoding conversion functions. + * Conversions from older versions cannot be upgraded automatically + * because the user-defined functions used by the encoding conversions + * need to changed to match the new signature. + */ + if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1300) + check_for_user_defined_encoding_conversions(&old_cluster); + /* * Pre-PG 14 allowed user defined postfix operators, which are not * supported anymore. Verify there are none, iff applicable. @@ -1268,6 +1278,91 @@ check_for_pg_role_prefix(ClusterInfo *cluster) check_ok(); } +/* + * Verify that no user-defined encoding conversions exist. + */ +static void +check_for_user_defined_encoding_conversions(ClusterInfo *cluster) +{ + int dbnum; + FILE *script = NULL; + bool found = false; + char output_path[MAXPGPATH]; + + prep_status("Checking for user-defined encoding conversions"); + + snprintf(output_path, sizeof(output_path), + "encoding_conversions.txt"); + + /* Find any user defined encoding conversions */ + for (dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++) + { + PGresult *res; + bool db_used = false; + int ntups; + int rowno; + int i_conoid, + i_conname, + i_nspname; + DbInfo *active_db = &cluster->dbarr.dbs[dbnum]; + PGconn *conn = connectToServer(cluster, active_db->db_name); + + /* + * The query below hardcodes FirstNormalObjectId as 16384 rather than + * interpolating that C #define into the query because, if that + * #define is ever changed, the cutoff we want to use is the value + * used by pre-version 14 servers, not that of some future version. + */ + res = executeQueryOrDie(conn, + "SELECT c.oid as conoid, c.conname, n.nspname " + "FROM pg_catalog.pg_conversion c, " + " pg_catalog.pg_namespace n " + "WHERE c.connamespace = n.oid AND " + " c.oid >= 16384"); + ntups = PQntuples(res); + i_conoid = PQfnumber(res, "conoid"); + i_conname = PQfnumber(res, "conname"); + i_nspname = PQfnumber(res, "nspname"); + for (rowno = 0; rowno < ntups; rowno++) + { + found = true; + if (script == NULL && + (script = fopen_priv(output_path, "w")) == NULL) + pg_fatal("could not open file \"%s\": %s\n", + output_path, strerror(errno)); + if (!db_used) + { + fprintf(script, "In database: %s\n", active_db->db_name); + db_used = true; + } + fprintf(script, " (oid=%s) %s.%s\n", + PQgetvalue(res, rowno, i_conoid), + PQgetvalue(res, rowno, i_nspname), + PQgetvalue(res, rowno, i_conname)); + } + + PQclear(res); + + PQfinish(conn); + } + + if (script) + fclose(script); + + if (found) + { + pg_log(PG_REPORT, "fatal\n"); + pg_fatal("Your installation contains user-defined encoding conversions.\n" + "The conversion function parameters changed in PostgreSQL version 14\n" + "so this cluster cannot currently be upgraded. You can remove the\n" + "encoding conversions in the old cluster and restart the upgrade.\n" + "A list of user-defined encoding conversions is in the file:\n" + " %s\n\n", output_path); + } + else + check_ok(); +} + /* * get_canonical_locale_name diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index f8174061ef3..75b829e8514 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10766,388 +10766,388 @@ # conversion functions { oid => '4302', descr => 'internal conversion function for KOI8R to MULE_INTERNAL', - proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_mic', + proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4303', descr => 'internal conversion function for MULE_INTERNAL to KOI8R', - proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_koi8r', + proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4304', descr => 'internal conversion function for ISO-8859-5 to MULE_INTERNAL', - proname => 'iso_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_mic', + proname => 'iso_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4305', descr => 'internal conversion function for MULE_INTERNAL to ISO-8859-5', - proname => 'mic_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_iso', + proname => 'mic_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4306', descr => 'internal conversion function for WIN1251 to MULE_INTERNAL', - proname => 'win1251_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_mic', + proname => 'win1251_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4307', descr => 'internal conversion function for MULE_INTERNAL to WIN1251', - proname => 'mic_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1251', + proname => 'mic_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4308', descr => 'internal conversion function for WIN866 to MULE_INTERNAL', - proname => 'win866_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_mic', + proname => 'win866_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4309', descr => 'internal conversion function for MULE_INTERNAL to WIN866', - proname => 'mic_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win866', + proname => 'mic_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4310', descr => 'internal conversion function for KOI8R to WIN1251', - proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4311', descr => 'internal conversion function for WIN1251 to KOI8R', - proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4312', descr => 'internal conversion function for KOI8R to WIN866', - proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_win866', + proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4313', descr => 'internal conversion function for WIN866 to KOI8R', - proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_koi8r', + proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4314', descr => 'internal conversion function for WIN866 to WIN1251', - proname => 'win866_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win866_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4315', descr => 'internal conversion function for WIN1251 to WIN866', - proname => 'win1251_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4316', descr => 'internal conversion function for ISO-8859-5 to KOI8R', - proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_koi8r', + proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4317', descr => 'internal conversion function for KOI8R to ISO-8859-5', - proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_iso', + proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4318', descr => 'internal conversion function for ISO-8859-5 to WIN1251', - proname => 'iso_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win1251', + proname => 'iso_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4319', descr => 'internal conversion function for WIN1251 to ISO-8859-5', - proname => 'win1251_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_iso', + proname => 'win1251_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4320', descr => 'internal conversion function for ISO-8859-5 to WIN866', - proname => 'iso_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win866', + proname => 'iso_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4321', descr => 'internal conversion function for WIN866 to ISO-8859-5', - proname => 'win866_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_iso', + proname => 'win866_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4322', descr => 'internal conversion function for EUC_CN to MULE_INTERNAL', - proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_mic', + proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_mic', probin => '$libdir/euc_cn_and_mic' }, { oid => '4323', descr => 'internal conversion function for MULE_INTERNAL to EUC_CN', - proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_cn', + proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_cn', probin => '$libdir/euc_cn_and_mic' }, { oid => '4324', descr => 'internal conversion function for EUC_JP to SJIS', - proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_sjis', + proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4325', descr => 'internal conversion function for SJIS to EUC_JP', - proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_euc_jp', + proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4326', descr => 'internal conversion function for EUC_JP to MULE_INTERNAL', - proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_mic', + proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4327', descr => 'internal conversion function for SJIS to MULE_INTERNAL', - proname => 'sjis_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_mic', + proname => 'sjis_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4328', descr => 'internal conversion function for MULE_INTERNAL to EUC_JP', - proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_jp', + proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4329', descr => 'internal conversion function for MULE_INTERNAL to SJIS', - proname => 'mic_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_sjis', + proname => 'mic_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4330', descr => 'internal conversion function for EUC_KR to MULE_INTERNAL', - proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_mic', + proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_mic', probin => '$libdir/euc_kr_and_mic' }, { oid => '4331', descr => 'internal conversion function for MULE_INTERNAL to EUC_KR', - proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_kr', + proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_kr', probin => '$libdir/euc_kr_and_mic' }, { oid => '4332', descr => 'internal conversion function for EUC_TW to BIG5', - proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_big5', + proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4333', descr => 'internal conversion function for BIG5 to EUC_TW', - proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_euc_tw', + proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4334', descr => 'internal conversion function for EUC_TW to MULE_INTERNAL', - proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_mic', + proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4335', descr => 'internal conversion function for BIG5 to MULE_INTERNAL', - proname => 'big5_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_mic', + proname => 'big5_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4336', descr => 'internal conversion function for MULE_INTERNAL to EUC_TW', - proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_tw', + proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4337', descr => 'internal conversion function for MULE_INTERNAL to BIG5', - proname => 'mic_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_big5', + proname => 'mic_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4338', descr => 'internal conversion function for LATIN2 to MULE_INTERNAL', - proname => 'latin2_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin2_to_mic', + proname => 'latin2_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4339', descr => 'internal conversion function for MULE_INTERNAL to LATIN2', - proname => 'mic_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin2', + proname => 'mic_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4340', descr => 'internal conversion function for WIN1250 to MULE_INTERNAL', - proname => 'win1250_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1250_to_mic', + proname => 'win1250_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4341', descr => 'internal conversion function for MULE_INTERNAL to WIN1250', - proname => 'mic_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1250', + proname => 'mic_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4342', descr => 'internal conversion function for LATIN2 to WIN1250', - proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4343', descr => 'internal conversion function for WIN1250 to LATIN2', - proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4344', descr => 'internal conversion function for LATIN1 to MULE_INTERNAL', - proname => 'latin1_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin1_to_mic', + proname => 'latin1_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin1_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4345', descr => 'internal conversion function for MULE_INTERNAL to LATIN1', - proname => 'mic_to_latin1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin1', + proname => 'mic_to_latin1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin1', probin => '$libdir/latin_and_mic' }, { oid => '4346', descr => 'internal conversion function for LATIN3 to MULE_INTERNAL', - proname => 'latin3_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin3_to_mic', + proname => 'latin3_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin3_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4347', descr => 'internal conversion function for MULE_INTERNAL to LATIN3', - proname => 'mic_to_latin3', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin3', + proname => 'mic_to_latin3', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin3', probin => '$libdir/latin_and_mic' }, { oid => '4348', descr => 'internal conversion function for LATIN4 to MULE_INTERNAL', - proname => 'latin4_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin4_to_mic', + proname => 'latin4_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin4_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4349', descr => 'internal conversion function for MULE_INTERNAL to LATIN4', - proname => 'mic_to_latin4', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin4', + proname => 'mic_to_latin4', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin4', probin => '$libdir/latin_and_mic' }, { oid => '4352', descr => 'internal conversion function for BIG5 to UTF8', - proname => 'big5_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_utf8', + proname => 'big5_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_utf8', probin => '$libdir/utf8_and_big5' }, { oid => '4353', descr => 'internal conversion function for UTF8 to BIG5', - proname => 'utf8_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_big5', + proname => 'utf8_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_big5', probin => '$libdir/utf8_and_big5' }, { oid => '4354', descr => 'internal conversion function for UTF8 to KOI8R', - proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8r', + proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8r', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4355', descr => 'internal conversion function for KOI8R to UTF8', - proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_utf8', + proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4356', descr => 'internal conversion function for UTF8 to KOI8U', - proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8u', + proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8u', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4357', descr => 'internal conversion function for KOI8U to UTF8', - proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8u_to_utf8', + proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8u_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4358', descr => 'internal conversion function for UTF8 to WIN', - proname => 'utf8_to_win', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_win', + proname => 'utf8_to_win', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_win', probin => '$libdir/utf8_and_win' }, { oid => '4359', descr => 'internal conversion function for WIN to UTF8', - proname => 'win_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win_to_utf8', + proname => 'win_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win_to_utf8', probin => '$libdir/utf8_and_win' }, { oid => '4360', descr => 'internal conversion function for EUC_CN to UTF8', - proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_utf8', + proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_utf8', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4361', descr => 'internal conversion function for UTF8 to EUC_CN', - proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_cn', + proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_cn', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4362', descr => 'internal conversion function for EUC_JP to UTF8', - proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_utf8', + proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_utf8', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4363', descr => 'internal conversion function for UTF8 to EUC_JP', - proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_jp', + proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jp', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4364', descr => 'internal conversion function for EUC_KR to UTF8', - proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_utf8', + proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_utf8', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4365', descr => 'internal conversion function for UTF8 to EUC_KR', - proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_kr', + proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_kr', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4366', descr => 'internal conversion function for EUC_TW to UTF8', - proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_utf8', + proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_utf8', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4367', descr => 'internal conversion function for UTF8 to EUC_TW', - proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_tw', + proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_tw', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4368', descr => 'internal conversion function for GB18030 to UTF8', - proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gb18030_to_utf8', + proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gb18030_to_utf8', probin => '$libdir/utf8_and_gb18030' }, { oid => '4369', descr => 'internal conversion function for UTF8 to GB18030', - proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gb18030', + proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gb18030', probin => '$libdir/utf8_and_gb18030' }, { oid => '4370', descr => 'internal conversion function for GBK to UTF8', - proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gbk_to_utf8', + proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gbk_to_utf8', probin => '$libdir/utf8_and_gbk' }, { oid => '4371', descr => 'internal conversion function for UTF8 to GBK', - proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gbk', + proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gbk', probin => '$libdir/utf8_and_gbk' }, { oid => '4372', descr => 'internal conversion function for UTF8 to ISO-8859 2-16', - proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_iso8859', + proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859', probin => '$libdir/utf8_and_iso8859' }, { oid => '4373', descr => 'internal conversion function for ISO-8859 2-16 to UTF8', - proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso8859_to_utf8', + proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_to_utf8', probin => '$libdir/utf8_and_iso8859' }, { oid => '4374', descr => 'internal conversion function for LATIN1 to UTF8', - proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_1_to_utf8', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4375', descr => 'internal conversion function for UTF8 to LATIN1', - proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859_1', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4376', descr => 'internal conversion function for JOHAB to UTF8', - proname => 'johab_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'johab_to_utf8', + proname => 'johab_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'johab_to_utf8', probin => '$libdir/utf8_and_johab' }, { oid => '4377', descr => 'internal conversion function for UTF8 to JOHAB', - proname => 'utf8_to_johab', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_johab', + proname => 'utf8_to_johab', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_johab', probin => '$libdir/utf8_and_johab' }, { oid => '4378', descr => 'internal conversion function for SJIS to UTF8', - proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_utf8', + proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_utf8', probin => '$libdir/utf8_and_sjis' }, { oid => '4379', descr => 'internal conversion function for UTF8 to SJIS', - proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_sjis', + proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_sjis', probin => '$libdir/utf8_and_sjis' }, { oid => '4380', descr => 'internal conversion function for UHC to UTF8', - proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'uhc_to_utf8', + proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'uhc_to_utf8', probin => '$libdir/utf8_and_uhc' }, { oid => '4381', descr => 'internal conversion function for UTF8 to UHC', - proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_uhc', + proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_uhc', probin => '$libdir/utf8_and_uhc' }, { oid => '4382', descr => 'internal conversion function for EUC_JIS_2004 to UTF8', - proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_utf8', probin => '$libdir/utf8_and_euc2004' }, { oid => '4383', descr => 'internal conversion function for UTF8 to EUC_JIS_2004', - proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jis_2004', probin => '$libdir/utf8_and_euc2004' }, { oid => '4384', descr => 'internal conversion function for SHIFT_JIS_2004 to UTF8', - proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_utf8', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4385', descr => 'internal conversion function for UTF8 to SHIFT_JIS_2004', - proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_shift_jis_2004', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4386', descr => 'internal conversion function for EUC_JIS_2004 to SHIFT_JIS_2004', proname => 'euc_jis_2004_to_shift_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_shift_jis_2004', probin => '$libdir/euc2004_sjis2004' }, { oid => '4387', descr => 'internal conversion function for SHIFT_JIS_2004 to EUC_JIS_2004', proname => 'shift_jis_2004_to_euc_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_euc_jis_2004', probin => '$libdir/euc2004_sjis2004' }, diff --git a/src/include/mb/pg_wchar.h b/src/include/mb/pg_wchar.h index 64b22e4b0d4..346a41a1f3d 100644 --- a/src/include/mb/pg_wchar.h +++ b/src/include/mb/pg_wchar.h @@ -627,18 +627,18 @@ extern void pg_unicode_to_server(pg_wchar c, unsigned char *s); extern unsigned short BIG5toCNS(unsigned short big5, unsigned char *lc); extern unsigned short CNStoBIG5(unsigned short cns, unsigned char lc); -extern void UtfToLocal(const unsigned char *utf, int len, - unsigned char *iso, - const pg_mb_radix_tree *map, - const pg_utf_to_local_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); -extern void LocalToUtf(const unsigned char *iso, int len, - unsigned char *utf, - const pg_mb_radix_tree *map, - const pg_local_to_utf_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); +extern int UtfToLocal(const unsigned char *utf, int len, + unsigned char *iso, + const pg_mb_radix_tree *map, + const pg_utf_to_local_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); +extern int LocalToUtf(const unsigned char *iso, int len, + unsigned char *utf, + const pg_mb_radix_tree *map, + const pg_local_to_utf_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); extern bool pg_verifymbstr(const char *mbstr, int len, bool noError); extern bool pg_verify_mbstr(int encoding, const char *mbstr, int len, @@ -656,18 +656,19 @@ extern void report_invalid_encoding(int encoding, const char *mbstr, int len) pg extern void report_untranslatable_char(int src_encoding, int dest_encoding, const char *mbstr, int len) pg_attribute_noreturn(); -extern void local2local(const unsigned char *l, unsigned char *p, int len, - int src_encoding, int dest_encoding, const unsigned char *tab); -extern void latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding); -extern void mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding); -extern void latin2mic_with_table(const unsigned char *l, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); -extern void mic2latin_with_table(const unsigned char *mic, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); +extern int local2local(const unsigned char *l, unsigned char *p, int len, + int src_encoding, int dest_encoding, const unsigned char *tab, + bool noError); +extern int latin2mic(const unsigned char *l, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int mic2latin(const unsigned char *mic, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int latin2mic_with_table(const unsigned char *l, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); +extern int mic2latin_with_table(const unsigned char *mic, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); #ifdef WIN32 extern WCHAR *pgwin32_message_to_UTF16(const char *str, int len, int *utf16len); diff --git a/src/test/regress/expected/opr_sanity.out b/src/test/regress/expected/opr_sanity.out index 254ca06d3dd..23ba60e395f 100644 --- a/src/test/regress/expected/opr_sanity.out +++ b/src/test/regress/expected/opr_sanity.out @@ -1052,13 +1052,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); oid | proname | oid | conname -----+---------+-----+--------- (0 rows) diff --git a/src/test/regress/sql/opr_sanity.sql b/src/test/regress/sql/opr_sanity.sql index bbd3834b634..04691745981 100644 --- a/src/test/regress/sql/opr_sanity.sql +++ b/src/test/regress/sql/opr_sanity.sql @@ -556,13 +556,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); -- Check for conprocs that don't perform the specific conversion that -- pg_conversion alleges they do, by trying to invoke each conversion -- 2.29.2 --------------39E46EF15EBFAA37D53332E5 Content-Type: text/x-patch; charset=UTF-8; name="v3-0003-Add-tests-for-the-new-noError-variants-of-built-i.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="v3-0003-Add-tests-for-the-new-noError-variants-of-built-i.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 34+ messages in thread
* [PATCH v3 2/5] Change conversion function signature. @ 2021-01-28 16:42 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 34+ messages in thread From: Heikki Linnakangas @ 2021-01-28 16:42 UTC (permalink / raw) Add a 'noError' argument, so that we can try to convert a buffer without knowing the character boundaries beforehand. The functions now need to return the number of input bytes successfully converted. This is is a backwards-incompatible change, if you have created a custom encoding conversion with CREATE CONVERSION. This adds a check to pg_upgrade for that, refusing the upgrade if there are any user-defined encoding conversions. --- doc/src/sgml/ref/create_conversion.sgml | 5 +- src/backend/commands/conversioncmds.c | 27 +- src/backend/utils/error/elog.c | 2 + src/backend/utils/mb/conv.c | 112 +++++- .../cyrillic_and_mic/cyrillic_and_mic.c | 127 ++++--- .../euc2004_sjis2004/euc2004_sjis2004.c | 96 ++++- .../euc_cn_and_mic/euc_cn_and_mic.c | 57 ++- .../euc_jp_and_sjis/euc_jp_and_sjis.c | 153 ++++++-- .../euc_kr_and_mic/euc_kr_and_mic.c | 57 ++- .../euc_tw_and_big5/euc_tw_and_big5.c | 165 +++++++-- .../latin2_and_win1250/latin2_and_win1250.c | 49 ++- .../latin_and_mic/latin_and_mic.c | 43 ++- .../utf8_and_big5/utf8_and_big5.c | 37 +- .../utf8_and_cyrillic/utf8_and_cyrillic.c | 67 ++-- .../utf8_and_euc2004/utf8_and_euc2004.c | 37 +- .../utf8_and_euc_cn/utf8_and_euc_cn.c | 37 +- .../utf8_and_euc_jp/utf8_and_euc_jp.c | 37 +- .../utf8_and_euc_kr/utf8_and_euc_kr.c | 37 +- .../utf8_and_euc_tw/utf8_and_euc_tw.c | 37 +- .../utf8_and_gb18030/utf8_and_gb18030.c | 37 +- .../utf8_and_gbk/utf8_and_gbk.c | 37 +- .../utf8_and_iso8859/utf8_and_iso8859.c | 43 ++- .../utf8_and_iso8859_1/utf8_and_iso8859_1.c | 27 +- .../utf8_and_johab/utf8_and_johab.c | 37 +- .../utf8_and_sjis/utf8_and_sjis.c | 37 +- .../utf8_and_sjis2004/utf8_and_sjis2004.c | 37 +- .../utf8_and_uhc/utf8_and_uhc.c | 37 +- .../utf8_and_win/utf8_and_win.c | 43 ++- src/backend/utils/mb/mbutils.c | 18 +- src/bin/pg_upgrade/check.c | 95 +++++ src/include/catalog/pg_proc.dat | 332 +++++++++--------- src/include/mb/pg_wchar.h | 49 +-- src/test/regress/expected/opr_sanity.out | 7 +- src/test/regress/sql/opr_sanity.sql | 7 +- 34 files changed, 1390 insertions(+), 635 deletions(-) diff --git a/doc/src/sgml/ref/create_conversion.sgml b/doc/src/sgml/ref/create_conversion.sgml index e7700fecfc5..f014a676c88 100644 --- a/doc/src/sgml/ref/create_conversion.sgml +++ b/doc/src/sgml/ref/create_conversion.sgml @@ -117,8 +117,9 @@ conv_proc( integer, -- destination encoding ID cstring, -- source string (null terminated C string) internal, -- destination (fill with a null terminated C string) - integer -- source string length -) RETURNS void; + integer, -- source string length + boolean -- if true, don't throw an error if conversion fails +) RETURNS integer; </programlisting></para> </listitem> </varlistentry> diff --git a/src/backend/commands/conversioncmds.c b/src/backend/commands/conversioncmds.c index f7ff321de71..d2041466911 100644 --- a/src/backend/commands/conversioncmds.c +++ b/src/backend/commands/conversioncmds.c @@ -45,8 +45,9 @@ CreateConversionCommand(CreateConversionStmt *stmt) const char *from_encoding_name = stmt->for_encoding_name; const char *to_encoding_name = stmt->to_encoding_name; List *func_name = stmt->func_name; - static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID}; + static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID, BOOLOID}; char result[1]; + Datum funcresult; /* Convert list of names to a name and namespace */ namespaceId = QualifiedNameGetCreationNamespace(stmt->conversion_name, @@ -92,8 +93,8 @@ CreateConversionCommand(CreateConversionStmt *stmt) funcoid = LookupFuncName(func_name, sizeof(funcargs) / sizeof(Oid), funcargs, false); - /* Check it returns VOID, else it's probably the wrong function */ - if (get_func_rettype(funcoid) != VOIDOID) + /* Check it returns int4, else it's probably the wrong function */ + if (get_func_rettype(funcoid) != INT4OID) ereport(ERROR, (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), errmsg("encoding conversion function %s must return type %s", @@ -111,12 +112,20 @@ CreateConversionCommand(CreateConversionStmt *stmt) * string; the conversion function should throw an error if it can't * perform the requested conversion. */ - OidFunctionCall5(funcoid, - Int32GetDatum(from_encoding), - Int32GetDatum(to_encoding), - CStringGetDatum(""), - CStringGetDatum(result), - Int32GetDatum(0)); + funcresult = OidFunctionCall6(funcoid, + Int32GetDatum(from_encoding), + Int32GetDatum(to_encoding), + CStringGetDatum(""), + CStringGetDatum(result), + Int32GetDatum(0), + BoolGetDatum(false)); + + /* The function should return 0 for empty input. Might as well check that, too. */ + if (DatumGetInt32(funcresult) != 0) + ereport(ERROR, + (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), + errmsg("encoding conversion function %s returned incorrect result for empty input", + NameListToString(func_name)))); /* * All seem ok, go ahead (possible failure would be a duplicate conversion diff --git a/src/backend/utils/error/elog.c b/src/backend/utils/error/elog.c index 80c26724612..762f77d533c 100644 --- a/src/backend/utils/error/elog.c +++ b/src/backend/utils/error/elog.c @@ -2280,6 +2280,8 @@ write_console(const char *line, int len) * Conversion on non-win32 platforms is not implemented yet. It requires * non-throw version of pg_do_encoding_conversion(), that converts * unconvertable characters to '?' without errors. + * + * XXX: We have a no-throw version now. It doesn't convert to '?' though. */ #endif diff --git a/src/backend/utils/mb/conv.c b/src/backend/utils/mb/conv.c index a07b54bd3b8..b83358bc7a5 100644 --- a/src/backend/utils/mb/conv.c +++ b/src/backend/utils/mb/conv.c @@ -26,14 +26,16 @@ * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the target charset, or 0 if there is no equivalent code. */ -void +int local2local(const unsigned char *l, unsigned char *p, int len, int src_encoding, int dest_encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -41,7 +43,11 @@ local2local(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(src_encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -50,13 +56,19 @@ local2local(const unsigned char *l, if (c2) *p++ = c2; else + { + if (noError) + break; report_untranslatable_char(src_encoding, dest_encoding, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -67,17 +79,22 @@ local2local(const unsigned char *l, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = l; int c1; while (len > 0) { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (IS_HIGHBIT_SET(c1)) *p++ = lc; *p++ = c1; @@ -85,6 +102,8 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, len--; } *p = '\0'; + + return l - start; } /* @@ -95,17 +114,22 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -118,17 +142,27 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1])) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); + } *p++ = mic[1]; mic += 2; len -= 2; } } *p = '\0'; + + return mic - start; } @@ -144,14 +178,16 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the mule encoding, or 0 if there is no equivalent code. */ -void +int latin2mic_with_table(const unsigned char *l, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -159,7 +195,11 @@ latin2mic_with_table(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -171,13 +211,19 @@ latin2mic_with_table(const unsigned char *l, *p++ = c2; } else + { + if (noError) + break; report_untranslatable_char(encoding, PG_MULE_INTERNAL, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -192,14 +238,16 @@ latin2mic_with_table(const unsigned char *l, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the local charset, or 0 if there is no equivalent code. */ -void +int mic2latin_with_table(const unsigned char *mic, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = mic; unsigned char c1, c2; @@ -207,7 +255,11 @@ mic2latin_with_table(const unsigned char *mic, { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -220,11 +272,17 @@ mic2latin_with_table(const unsigned char *mic, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1]) || (c2 = tab[mic[1] - HIGHBIT]) == 0) { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); break; /* keep compiler quiet */ @@ -235,6 +293,8 @@ mic2latin_with_table(const unsigned char *mic, } } *p = '\0'; + + return mic - start; } /* @@ -425,17 +485,19 @@ pg_mb_radix_conv(const pg_mb_radix_tree *rt, * * See pg_wchar.h for more details about the data structures used here. */ -void +int UtfToLocal(const unsigned char *utf, int len, unsigned char *iso, const pg_mb_radix_tree *map, const pg_utf_to_local_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, bool noError) { uint32 iutf; int l; const pg_utf_to_local_combined *cp; + const unsigned char *start = utf; + const unsigned char *cur = utf; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -449,6 +511,8 @@ UtfToLocal(const unsigned char *utf, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*utf == '\0') break; @@ -584,15 +648,19 @@ UtfToLocal(const unsigned char *utf, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(PG_UTF8, encoding, (const char *) (utf - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(PG_UTF8, (const char *) utf, len); *iso = '\0'; + + return cur - start; } /* @@ -616,18 +684,24 @@ UtfToLocal(const unsigned char *utf, int len, * (if provided) is applied. An error is raised if no match is found. * * See pg_wchar.h for more details about the data structures used here. + * + * Returns the number of input bytes consumed. If noError is true, this can + * be less than 'len'. */ -void +int LocalToUtf(const unsigned char *iso, int len, unsigned char *utf, const pg_mb_radix_tree *map, const pg_local_to_utf_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, + bool noError) { uint32 iiso; int l; const pg_local_to_utf_combined *cp; + const unsigned char *start = iso; + const unsigned char *cur = iso; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -641,6 +715,8 @@ LocalToUtf(const unsigned char *iso, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*iso == '\0') break; @@ -723,13 +799,17 @@ LocalToUtf(const unsigned char *iso, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(encoding, PG_UTF8, (const char *) (iso - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(encoding, (const char *) iso, len); *utf = '\0'; + + return cur - start; } diff --git a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c index 4c5b02654de..368c2deb5e4 100644 --- a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c @@ -44,8 +44,11 @@ PG_FUNCTION_INFO_V1(win866_to_iso); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -306,12 +309,14 @@ koi8r_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -320,12 +325,14 @@ mic_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_KOI8R); - mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -334,12 +341,14 @@ iso_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -348,12 +357,14 @@ mic_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_ISO_8859_5); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -362,12 +373,14 @@ win1251_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -376,12 +389,14 @@ mic_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1251); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -390,12 +405,14 @@ win866_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -404,12 +421,14 @@ mic_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN866); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -418,12 +437,14 @@ koi8r_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN1251); - local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -432,12 +453,14 @@ win1251_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_KOI8R); - local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi); + converted = local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -446,12 +469,14 @@ koi8r_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN866); - local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -460,12 +485,14 @@ win866_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_KOI8R); - local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi); + converted = local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -474,12 +501,14 @@ win866_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_WIN1251); - local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251); + converted = local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -488,12 +517,14 @@ win1251_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_WIN866); - local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866); + converted = local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -502,12 +533,14 @@ iso_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_KOI8R); - local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -516,12 +549,14 @@ koi8r_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_ISO_8859_5); - local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso); + converted = local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -530,12 +565,14 @@ iso_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN1251); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -544,12 +581,14 @@ win1251_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso); + converted = local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -558,12 +597,14 @@ iso_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN866); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -572,10 +613,12 @@ win866_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso); + converted = local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c index 4d7fb116cfd..88529c644cf 100644 --- a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c @@ -19,8 +19,8 @@ PG_MODULE_MAGIC; PG_FUNCTION_INFO_V1(euc_jis_2004_to_shift_jis_2004); PG_FUNCTION_INFO_V1(shift_jis_2004_to_euc_jis_2004); -static void euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len); -static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len); +static int euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError); /* ---------- * conv_proc( @@ -28,8 +28,11 @@ static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -39,12 +42,14 @@ euc_jis_2004_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_SHIFT_JIS_2004); - euc_jis_20042shift_jis_2004(src, dest, len); + converted = euc_jis_20042shift_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -53,20 +58,23 @@ shift_jis_2004_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_EUC_JIS_2004); - shift_jis_20042euc_jis_2004(src, dest, len); + converted = shift_jis_20042euc_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_JIS_2004 -> SHIFT_JIS_2004 */ -static void -euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, ku, ten; @@ -79,8 +87,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -90,8 +102,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) l = pg_encoding_verifymbchar(PG_EUC_JIS_2004, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (c1 == SS2 && l == 2) /* JIS X 0201 kana? */ { @@ -121,8 +137,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) *p++ = (ku + 0x19b) >> 1; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } if (ku % 2) @@ -132,8 +152,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; @@ -149,8 +173,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ku >= 63 && ku <= 94) *p++ = (ku + 0x181) >> 1; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (ku % 2) { @@ -159,20 +187,30 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else - report_invalid_encoding(PG_EUC_JIS_2004, + { + if (noError) + break; + report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } euc += l; len -= l; } *p = '\0'; + + return euc - start; } /* @@ -212,9 +250,10 @@ get_ten(int b, int *ku) * SHIFT_JIS_2004 ---> EUC_JIS_2004 */ -static void -shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len) +static int +shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1; int ku, ten, @@ -230,8 +269,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -241,8 +284,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len l = pg_encoding_verifymbchar(PG_SHIFT_JIS_2004, (const char *) sjis, len); if (l < 0 || l > len) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf && l == 1) { @@ -266,8 +313,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x100; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xe0 && c1 <= 0xef) /* plane 1 62ku-94ku */ @@ -275,9 +326,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x180; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, - (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xf0 && c1 <= 0xf3) /* plane 2 @@ -286,8 +340,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } switch (c1) { case 0xf0: @@ -309,16 +367,24 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 == 0xf4 && kubun == 1) ku = 15; else ku = (c1 << 1) - 0x19a - kubun; } else + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (plane == 2) *p++ = SS3; @@ -330,4 +396,6 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c index e9bb896935f..a8da733803d 100644 --- a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_cn2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_cn(const unsigned char *mic, unsigned char *p, int len); +static int euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_cn_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_cn_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_MULE_INTERNAL); - euc_cn2mic(src, dest, len); + converted = euc_cn2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_CN); - mic2euc_cn(src, dest, len); + converted = mic2euc_cn(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_CN ---> MIC */ -static void -euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; while (len > 0) @@ -76,7 +84,11 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (len < 2 || !IS_HIGHBIT_SET(euc[1])) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = LC_GB2312_80; *p++ = c1; *p++ = euc[1]; @@ -86,21 +98,28 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_CN */ -static void -mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) @@ -109,11 +128,19 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (c1 != LC_GB2312_80) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_CN, (const char *) mic, len); + } if (len < 3 || !IS_HIGHBIT_SET(mic[1]) || !IS_HIGHBIT_SET(mic[2])) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } mic++; *p++ = *mic++; *p++ = *mic++; @@ -122,12 +149,18 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; } } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c index 5059f917a98..cc4817dc4cd 100644 --- a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c @@ -42,17 +42,20 @@ PG_FUNCTION_INFO_V1(mic_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void sjis2mic(const unsigned char *sjis, unsigned char *p, int len); -static void mic2sjis(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_jp(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len); -static void sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len); +static int sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError); +static int mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_jp_to_sjis(PG_FUNCTION_ARGS) @@ -60,12 +63,14 @@ euc_jp_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_SJIS); - euc_jp2sjis(src, dest, len); + converted = euc_jp2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -74,12 +79,14 @@ sjis_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_EUC_JP); - sjis2euc_jp(src, dest, len); + converted = sjis2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -88,12 +95,14 @@ euc_jp_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_MULE_INTERNAL); - euc_jp2mic(src, dest, len); + converted = euc_jp2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -102,12 +111,14 @@ mic_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_JP); - mic2euc_jp(src, dest, len); + converted = mic2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -116,12 +127,14 @@ sjis_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_MULE_INTERNAL); - sjis2mic(src, dest, len); + converted = sjis2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -130,20 +143,23 @@ mic_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_SJIS); - mic2sjis(src, dest, len); + converted = mic2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * SJIS ---> MIC */ -static void -sjis2mic(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -167,7 +183,11 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) * JIS X0208, X0212, user defined extended characters */ if (len < 2 || !ISSJISHEAD(c1) || !ISSJISTAIL(sjis[1])) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } c2 = sjis[1]; k = (c1 << 8) + c2; if (k >= 0xed40 && k < 0xf040) @@ -257,21 +277,28 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; } } *p = '\0'; + + return sjis - start; } /* * MIC ---> SJIS */ -static void -mic2sjis(const unsigned char *mic, unsigned char *p, int len) +static int +mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1, c2, k, @@ -284,8 +311,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -293,8 +324,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) *p++ = mic[1]; else if (c1 == LC_JISX0208) @@ -350,20 +385,27 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_SJIS, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP ---> MIC */ -static void -euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -374,8 +416,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -383,8 +429,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* 1 byte kana? */ *p++ = LC_JISX0201K; @@ -406,14 +456,17 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_JP */ -static void -mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -424,8 +477,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -433,8 +490,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) { *p++ = SS2; @@ -452,20 +513,27 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_JP, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP -> SJIS */ -static void -euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, c2, k; @@ -478,8 +546,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -487,8 +559,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* hankaku kana? */ @@ -551,14 +627,17 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * SJIS ---> EUC_JP */ -static void -sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -573,8 +652,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -582,8 +665,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_SJIS, (const char *) sjis, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf) { /* JIS X0201 (1 byte kana) */ @@ -680,4 +767,6 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c index ac823d6c270..a5b51617e52 100644 --- a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_kr2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_kr(const unsigned char *mic, unsigned char *p, int len); +static int euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_kr_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_kr_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_MULE_INTERNAL); - euc_kr2mic(src, dest, len); + converted = euc_kr2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_KR); - mic2euc_kr(src, dest, len); + converted = mic2euc_kr(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_KR ---> MIC */ -static void -euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -78,8 +86,12 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_KR, (const char *) euc, len); if (l != 2) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = LC_KS5601; *p++ = c1; *p++ = euc[1]; @@ -89,22 +101,29 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_KR */ -static void -mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -115,8 +134,12 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -124,18 +147,28 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_KS5601) { *p++ = mic[1]; *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_KR, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c index 66c242d7f36..ebb4e0acd53 100644 --- a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c @@ -32,17 +32,20 @@ PG_FUNCTION_INFO_V1(mic_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_tw2big5(const unsigned char *euc, unsigned char *p, int len); -static void big52euc_tw(const unsigned char *euc, unsigned char *p, int len); -static void big52mic(const unsigned char *big5, unsigned char *p, int len); -static void mic2big5(const unsigned char *mic, unsigned char *p, int len); -static void euc_tw2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_tw(const unsigned char *mic, unsigned char *p, int len); +static int euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52euc_tw(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError); +static int mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_tw_to_big5(PG_FUNCTION_ARGS) @@ -50,12 +53,14 @@ euc_tw_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_BIG5); - euc_tw2big5(src, dest, len); + converted = euc_tw2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -64,12 +69,14 @@ big5_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_EUC_TW); - big52euc_tw(src, dest, len); + converted = big52euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -78,12 +85,14 @@ euc_tw_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_MULE_INTERNAL); - euc_tw2mic(src, dest, len); + converted = euc_tw2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -92,12 +101,14 @@ mic_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_TW); - mic2euc_tw(src, dest, len); + converted = mic2euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -106,12 +117,14 @@ big5_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_MULE_INTERNAL); - big52mic(src, dest, len); + converted = big52mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -120,21 +133,24 @@ mic_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_BIG5); - mic2big5(src, dest, len); + converted = mic2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_TW ---> Big5 */ -static void -euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; unsigned char c1; unsigned short big5buf, cnsBuf; @@ -149,8 +165,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Verify and decode the next EUC_TW input character */ l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -171,8 +191,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Write it out in Big5 */ big5buf = CNStoBIG5(cnsBuf, lc); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_EUC_TW, PG_BIG5, (const char *) euc, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; @@ -182,22 +206,29 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * Big5 ---> EUC_TW */ -static void -big52euc_tw(const unsigned char *big5, unsigned char *p, int len) +static int +big52euc_tw(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -212,8 +243,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); @@ -237,8 +272,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_EUC_TW, (const char *) big5, len); + } big5 += l; len -= l; @@ -256,14 +295,17 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) } } *p = '\0'; + + return big5 - start; } /* * EUC_TW ---> MIC */ -static void -euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -274,8 +316,12 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -304,22 +350,29 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_TW */ -static void -mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -330,8 +383,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -339,8 +396,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1) { *p++ = mic[1]; @@ -362,20 +423,27 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[3]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_TW, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * Big5 ---> MIC */ -static void -big52mic(const unsigned char *big5, unsigned char *p, int len) +static int +big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -389,8 +457,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } *p++ = c1; big5++; len--; @@ -398,8 +470,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); if (lc != 0) @@ -412,20 +488,27 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_MULE_INTERNAL, (const char *) big5, len); + } big5 += l; len -= l; } *p = '\0'; + + return big5 - start; } /* * MIC ---> Big5 */ -static void -mic2big5(const unsigned char *mic, unsigned char *p, int len) +static int +mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -438,8 +521,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -447,8 +534,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1 || c1 == LC_CNS11643_2 || c1 == LCPRV2_B) { if (c1 == LCPRV2_B) @@ -462,16 +553,26 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } big5buf = CNStoBIG5(cnsBuf, c1); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c index 2e28e6780a5..8610fcb69aa 100644 --- a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c +++ b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(win1250_to_latin2); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -82,12 +85,14 @@ latin2_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -96,12 +101,14 @@ mic_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN2); - mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -110,13 +117,15 @@ win1250_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - win1250_2_iso88592); + converted = latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -125,13 +134,15 @@ mic_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1250); - mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - iso88592_2_win1250); + converted = mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -140,12 +151,15 @@ latin2_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_WIN1250); - local2local(src, dest, len, PG_LATIN2, PG_WIN1250, iso88592_2_win1250); + converted = local2local(src, dest, len, PG_LATIN2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -154,10 +168,13 @@ win1250_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_LATIN2); - local2local(src, dest, len, PG_WIN1250, PG_LATIN2, win1250_2_iso88592); + converted = local2local(src, dest, len, PG_WIN1250, PG_LATIN2, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c index bc651410f21..bff27d1c295 100644 --- a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(mic_to_latin4); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -42,12 +45,14 @@ latin1_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,12 +61,14 @@ mic_to_latin1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN1); - mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -70,12 +77,14 @@ latin3_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN3, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -84,12 +93,14 @@ mic_to_latin3(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN3); - mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,12 +109,14 @@ latin4_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN4, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -112,10 +125,12 @@ mic_to_latin4(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN4); - mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c index d6067cdc24e..3838b15cab9 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ big5_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_UTF8); - LocalToUtf(src, len, dest, - &big5_to_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = LocalToUtf(src, len, dest, + &big5_to_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_BIG5); - UtfToLocal(src, len, dest, - &big5_from_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = UtfToLocal(src, len, dest, + &big5_from_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c index ed90e8e682e..75719fe5f1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c @@ -33,8 +33,11 @@ PG_FUNCTION_INFO_V1(koi8u_to_utf8); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -44,16 +47,19 @@ utf8_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8R); - UtfToLocal(src, len, dest, - &koi8r_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = UtfToLocal(src, len, dest, + &koi8r_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -62,16 +68,19 @@ koi8r_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8r_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = LocalToUtf(src, len, dest, + &koi8r_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -80,16 +89,19 @@ utf8_to_koi8u(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8U); - UtfToLocal(src, len, dest, - &koi8u_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = UtfToLocal(src, len, dest, + &koi8u_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,14 +110,17 @@ koi8u_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8U, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8u_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = LocalToUtf(src, len, dest, + &koi8u_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c index d699affce47..5391001951a 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jis_2004_to_unicode_tree, - LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = LocalToUtf(src, len, dest, + &euc_jis_2004_to_unicode_tree, + LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JIS_2004); - UtfToLocal(src, len, dest, - &euc_jis_2004_from_unicode_tree, - ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = UtfToLocal(src, len, dest, + &euc_jis_2004_from_unicode_tree, + ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c index d7c0ba6a58b..c87d1bf2398 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_cn_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_cn_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = LocalToUtf(src, len, dest, + &euc_cn_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_CN); - UtfToLocal(src, len, dest, - &euc_cn_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = UtfToLocal(src, len, dest, + &euc_cn_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c index 13a3a23e77b..6a55134db21 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jp); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jp_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jp_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = LocalToUtf(src, len, dest, + &euc_jp_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JP); - UtfToLocal(src, len, dest, - &euc_jp_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = UtfToLocal(src, len, dest, + &euc_jp_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c index 1bbb8aaef7b..fe1924e2fec 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_kr_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_kr_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = LocalToUtf(src, len, dest, + &euc_kr_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_KR); - UtfToLocal(src, len, dest, - &euc_kr_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = UtfToLocal(src, len, dest, + &euc_kr_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c index 9830045dccd..68215659b57 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_tw); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_tw_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_tw_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = LocalToUtf(src, len, dest, + &euc_tw_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_TW); - UtfToLocal(src, len, dest, - &euc_tw_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = UtfToLocal(src, len, dest, + &euc_tw_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c index f86ecf27424..e1a59c39a4d 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c @@ -183,8 +183,11 @@ conv_utf8_to_18030(uint32 code) * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -193,16 +196,19 @@ gb18030_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GB18030, PG_UTF8); - LocalToUtf(src, len, dest, - &gb18030_to_unicode_tree, - NULL, 0, - conv_18030_to_utf8, - PG_GB18030); + converted = LocalToUtf(src, len, dest, + &gb18030_to_unicode_tree, + NULL, 0, + conv_18030_to_utf8, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -211,14 +217,17 @@ utf8_to_gb18030(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GB18030); - UtfToLocal(src, len, dest, - &gb18030_from_unicode_tree, - NULL, 0, - conv_utf8_to_18030, - PG_GB18030); + converted = UtfToLocal(src, len, dest, + &gb18030_from_unicode_tree, + NULL, 0, + conv_utf8_to_18030, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c index 2ab8b16c8a8..881386d5347 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_gbk); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ gbk_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GBK, PG_UTF8); - LocalToUtf(src, len, dest, - &gbk_to_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = LocalToUtf(src, len, dest, + &gbk_to_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_gbk(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GBK); - UtfToLocal(src, len, dest, - &gbk_from_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = UtfToLocal(src, len, dest, + &gbk_from_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c index 3e49f67ea2f..d93a521badf 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c @@ -52,8 +52,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -100,6 +103,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -108,12 +112,15 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -122,7 +129,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -132,6 +139,7 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -140,12 +148,15 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -154,5 +165,5 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c index 67e713cca11..8ac93604a1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c @@ -26,8 +26,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859_1); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -37,6 +40,8 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_UTF8); @@ -45,7 +50,11 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_LATIN1, (const char *) src, len); + } if (!IS_HIGHBIT_SET(c)) *dest++ = c; else @@ -58,7 +67,7 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } Datum @@ -67,6 +76,8 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c, c1; @@ -76,7 +87,11 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_UTF8, (const char *) src, len); + } /* fast path for ASCII-subset characters */ if (!IS_HIGHBIT_SET(c)) { @@ -102,11 +117,15 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) len -= 2; } else + { + if (noError) + break; report_untranslatable_char(PG_UTF8, PG_LATIN1, (const char *) src, len); + } } } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c index 578f5df4e7f..317daa2d5ee 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_johab); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ johab_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_JOHAB, PG_UTF8); - LocalToUtf(src, len, dest, - &johab_to_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = LocalToUtf(src, len, dest, + &johab_to_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_johab(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_JOHAB); - UtfToLocal(src, len, dest, - &johab_from_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = UtfToLocal(src, len, dest, + &johab_from_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c index dd9fc2975ad..4c9348aba59 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ sjis_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_UTF8); - LocalToUtf(src, len, dest, - &sjis_to_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = LocalToUtf(src, len, dest, + &sjis_to_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SJIS); - UtfToLocal(src, len, dest, - &sjis_from_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = UtfToLocal(src, len, dest, + &sjis_from_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c index 4bcc886d674..1fffdc5930c 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_shift_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ shift_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &shift_jis_2004_to_unicode_tree, - LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = LocalToUtf(src, len, dest, + &shift_jis_2004_to_unicode_tree, + LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SHIFT_JIS_2004); - UtfToLocal(src, len, dest, - &shift_jis_2004_from_unicode_tree, - ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = UtfToLocal(src, len, dest, + &shift_jis_2004_from_unicode_tree, + ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c index c8e512994a1..d9471dad097 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_uhc); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ uhc_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UHC, PG_UTF8); - LocalToUtf(src, len, dest, - &uhc_to_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = LocalToUtf(src, len, dest, + &uhc_to_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_uhc(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_UHC); - UtfToLocal(src, len, dest, - &uhc_from_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = UtfToLocal(src, len, dest, + &uhc_from_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c index 0c9493dee56..110ba5677d0 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c @@ -48,8 +48,11 @@ PG_FUNCTION_INFO_V1(utf8_to_win); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -81,6 +84,7 @@ win_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -89,12 +93,15 @@ win_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -103,7 +110,7 @@ win_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -113,6 +120,7 @@ utf8_to_win(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -121,12 +129,15 @@ utf8_to_win(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -135,5 +146,5 @@ utf8_to_win(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/mbutils.c b/src/backend/utils/mb/mbutils.c index 2578573b0ab..65753860e35 100644 --- a/src/backend/utils/mb/mbutils.c +++ b/src/backend/utils/mb/mbutils.c @@ -406,12 +406,13 @@ pg_do_encoding_conversion(unsigned char *src, int len, MemoryContextAllocHuge(CurrentMemoryContext, (Size) len * MAX_CONVERSION_GROWTH + 1); - OidFunctionCall5(proc, - Int32GetDatum(src_encoding), - Int32GetDatum(dest_encoding), - CStringGetDatum(src), - CStringGetDatum(result), - Int32GetDatum(len)); + (void) OidFunctionCall6(proc, + Int32GetDatum(src_encoding), + Int32GetDatum(dest_encoding), + CStringGetDatum(src), + CStringGetDatum(result), + Int32GetDatum(len), + BoolGetDatum(false)); /* * If the result is large, it's worth repalloc'ing to release any extra @@ -849,12 +850,13 @@ pg_unicode_to_server(pg_wchar c, unsigned char *s) c_as_utf8[c_as_utf8_len] = '\0'; /* Convert, or throw error if we can't */ - FunctionCall5(Utf8ToServerConvProc, + FunctionCall6(Utf8ToServerConvProc, Int32GetDatum(PG_UTF8), Int32GetDatum(server_encoding), CStringGetDatum(c_as_utf8), CStringGetDatum(s), - Int32GetDatum(c_as_utf8_len)); + Int32GetDatum(c_as_utf8_len), + BoolGetDatum(false)); } diff --git a/src/bin/pg_upgrade/check.c b/src/bin/pg_upgrade/check.c index 43fc297eb69..ee6be95b08d 100644 --- a/src/bin/pg_upgrade/check.c +++ b/src/bin/pg_upgrade/check.c @@ -28,6 +28,7 @@ static void check_for_reg_data_type_usage(ClusterInfo *cluster); static void check_for_jsonb_9_4_usage(ClusterInfo *cluster); static void check_for_pg_role_prefix(ClusterInfo *cluster); static void check_for_new_tablespace_dir(ClusterInfo *new_cluster); +static void check_for_user_defined_encoding_conversions(ClusterInfo *cluster); static char *get_canonical_locale_name(int category, const char *locale); @@ -102,6 +103,15 @@ check_and_dump_old_cluster(bool live_check) check_for_reg_data_type_usage(&old_cluster); check_for_isn_and_int8_passing_mismatch(&old_cluster); + /* + * PG 14 changed the function signature of encoding conversion functions. + * Conversions from older versions cannot be upgraded automatically + * because the user-defined functions used by the encoding conversions + * need to changed to match the new signature. + */ + if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1300) + check_for_user_defined_encoding_conversions(&old_cluster); + /* * Pre-PG 14 allowed user defined postfix operators, which are not * supported anymore. Verify there are none, iff applicable. @@ -1268,6 +1278,91 @@ check_for_pg_role_prefix(ClusterInfo *cluster) check_ok(); } +/* + * Verify that no user-defined encoding conversions exist. + */ +static void +check_for_user_defined_encoding_conversions(ClusterInfo *cluster) +{ + int dbnum; + FILE *script = NULL; + bool found = false; + char output_path[MAXPGPATH]; + + prep_status("Checking for user-defined encoding conversions"); + + snprintf(output_path, sizeof(output_path), + "encoding_conversions.txt"); + + /* Find any user defined encoding conversions */ + for (dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++) + { + PGresult *res; + bool db_used = false; + int ntups; + int rowno; + int i_conoid, + i_conname, + i_nspname; + DbInfo *active_db = &cluster->dbarr.dbs[dbnum]; + PGconn *conn = connectToServer(cluster, active_db->db_name); + + /* + * The query below hardcodes FirstNormalObjectId as 16384 rather than + * interpolating that C #define into the query because, if that + * #define is ever changed, the cutoff we want to use is the value + * used by pre-version 14 servers, not that of some future version. + */ + res = executeQueryOrDie(conn, + "SELECT c.oid as conoid, c.conname, n.nspname " + "FROM pg_catalog.pg_conversion c, " + " pg_catalog.pg_namespace n " + "WHERE c.connamespace = n.oid AND " + " c.oid >= 16384"); + ntups = PQntuples(res); + i_conoid = PQfnumber(res, "conoid"); + i_conname = PQfnumber(res, "conname"); + i_nspname = PQfnumber(res, "nspname"); + for (rowno = 0; rowno < ntups; rowno++) + { + found = true; + if (script == NULL && + (script = fopen_priv(output_path, "w")) == NULL) + pg_fatal("could not open file \"%s\": %s\n", + output_path, strerror(errno)); + if (!db_used) + { + fprintf(script, "In database: %s\n", active_db->db_name); + db_used = true; + } + fprintf(script, " (oid=%s) %s.%s\n", + PQgetvalue(res, rowno, i_conoid), + PQgetvalue(res, rowno, i_nspname), + PQgetvalue(res, rowno, i_conname)); + } + + PQclear(res); + + PQfinish(conn); + } + + if (script) + fclose(script); + + if (found) + { + pg_log(PG_REPORT, "fatal\n"); + pg_fatal("Your installation contains user-defined encoding conversions.\n" + "The conversion function parameters changed in PostgreSQL version 14\n" + "so this cluster cannot currently be upgraded. You can remove the\n" + "encoding conversions in the old cluster and restart the upgrade.\n" + "A list of user-defined encoding conversions is in the file:\n" + " %s\n\n", output_path); + } + else + check_ok(); +} + /* * get_canonical_locale_name diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index f8174061ef3..75b829e8514 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10766,388 +10766,388 @@ # conversion functions { oid => '4302', descr => 'internal conversion function for KOI8R to MULE_INTERNAL', - proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_mic', + proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4303', descr => 'internal conversion function for MULE_INTERNAL to KOI8R', - proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_koi8r', + proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4304', descr => 'internal conversion function for ISO-8859-5 to MULE_INTERNAL', - proname => 'iso_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_mic', + proname => 'iso_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4305', descr => 'internal conversion function for MULE_INTERNAL to ISO-8859-5', - proname => 'mic_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_iso', + proname => 'mic_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4306', descr => 'internal conversion function for WIN1251 to MULE_INTERNAL', - proname => 'win1251_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_mic', + proname => 'win1251_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4307', descr => 'internal conversion function for MULE_INTERNAL to WIN1251', - proname => 'mic_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1251', + proname => 'mic_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4308', descr => 'internal conversion function for WIN866 to MULE_INTERNAL', - proname => 'win866_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_mic', + proname => 'win866_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4309', descr => 'internal conversion function for MULE_INTERNAL to WIN866', - proname => 'mic_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win866', + proname => 'mic_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4310', descr => 'internal conversion function for KOI8R to WIN1251', - proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4311', descr => 'internal conversion function for WIN1251 to KOI8R', - proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4312', descr => 'internal conversion function for KOI8R to WIN866', - proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_win866', + proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4313', descr => 'internal conversion function for WIN866 to KOI8R', - proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_koi8r', + proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4314', descr => 'internal conversion function for WIN866 to WIN1251', - proname => 'win866_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win866_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4315', descr => 'internal conversion function for WIN1251 to WIN866', - proname => 'win1251_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4316', descr => 'internal conversion function for ISO-8859-5 to KOI8R', - proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_koi8r', + proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4317', descr => 'internal conversion function for KOI8R to ISO-8859-5', - proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_iso', + proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4318', descr => 'internal conversion function for ISO-8859-5 to WIN1251', - proname => 'iso_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win1251', + proname => 'iso_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4319', descr => 'internal conversion function for WIN1251 to ISO-8859-5', - proname => 'win1251_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_iso', + proname => 'win1251_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4320', descr => 'internal conversion function for ISO-8859-5 to WIN866', - proname => 'iso_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win866', + proname => 'iso_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4321', descr => 'internal conversion function for WIN866 to ISO-8859-5', - proname => 'win866_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_iso', + proname => 'win866_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4322', descr => 'internal conversion function for EUC_CN to MULE_INTERNAL', - proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_mic', + proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_mic', probin => '$libdir/euc_cn_and_mic' }, { oid => '4323', descr => 'internal conversion function for MULE_INTERNAL to EUC_CN', - proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_cn', + proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_cn', probin => '$libdir/euc_cn_and_mic' }, { oid => '4324', descr => 'internal conversion function for EUC_JP to SJIS', - proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_sjis', + proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4325', descr => 'internal conversion function for SJIS to EUC_JP', - proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_euc_jp', + proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4326', descr => 'internal conversion function for EUC_JP to MULE_INTERNAL', - proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_mic', + proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4327', descr => 'internal conversion function for SJIS to MULE_INTERNAL', - proname => 'sjis_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_mic', + proname => 'sjis_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4328', descr => 'internal conversion function for MULE_INTERNAL to EUC_JP', - proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_jp', + proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4329', descr => 'internal conversion function for MULE_INTERNAL to SJIS', - proname => 'mic_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_sjis', + proname => 'mic_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4330', descr => 'internal conversion function for EUC_KR to MULE_INTERNAL', - proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_mic', + proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_mic', probin => '$libdir/euc_kr_and_mic' }, { oid => '4331', descr => 'internal conversion function for MULE_INTERNAL to EUC_KR', - proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_kr', + proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_kr', probin => '$libdir/euc_kr_and_mic' }, { oid => '4332', descr => 'internal conversion function for EUC_TW to BIG5', - proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_big5', + proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4333', descr => 'internal conversion function for BIG5 to EUC_TW', - proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_euc_tw', + proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4334', descr => 'internal conversion function for EUC_TW to MULE_INTERNAL', - proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_mic', + proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4335', descr => 'internal conversion function for BIG5 to MULE_INTERNAL', - proname => 'big5_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_mic', + proname => 'big5_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4336', descr => 'internal conversion function for MULE_INTERNAL to EUC_TW', - proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_tw', + proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4337', descr => 'internal conversion function for MULE_INTERNAL to BIG5', - proname => 'mic_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_big5', + proname => 'mic_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4338', descr => 'internal conversion function for LATIN2 to MULE_INTERNAL', - proname => 'latin2_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin2_to_mic', + proname => 'latin2_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4339', descr => 'internal conversion function for MULE_INTERNAL to LATIN2', - proname => 'mic_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin2', + proname => 'mic_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4340', descr => 'internal conversion function for WIN1250 to MULE_INTERNAL', - proname => 'win1250_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1250_to_mic', + proname => 'win1250_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4341', descr => 'internal conversion function for MULE_INTERNAL to WIN1250', - proname => 'mic_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1250', + proname => 'mic_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4342', descr => 'internal conversion function for LATIN2 to WIN1250', - proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4343', descr => 'internal conversion function for WIN1250 to LATIN2', - proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4344', descr => 'internal conversion function for LATIN1 to MULE_INTERNAL', - proname => 'latin1_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin1_to_mic', + proname => 'latin1_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin1_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4345', descr => 'internal conversion function for MULE_INTERNAL to LATIN1', - proname => 'mic_to_latin1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin1', + proname => 'mic_to_latin1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin1', probin => '$libdir/latin_and_mic' }, { oid => '4346', descr => 'internal conversion function for LATIN3 to MULE_INTERNAL', - proname => 'latin3_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin3_to_mic', + proname => 'latin3_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin3_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4347', descr => 'internal conversion function for MULE_INTERNAL to LATIN3', - proname => 'mic_to_latin3', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin3', + proname => 'mic_to_latin3', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin3', probin => '$libdir/latin_and_mic' }, { oid => '4348', descr => 'internal conversion function for LATIN4 to MULE_INTERNAL', - proname => 'latin4_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin4_to_mic', + proname => 'latin4_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin4_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4349', descr => 'internal conversion function for MULE_INTERNAL to LATIN4', - proname => 'mic_to_latin4', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin4', + proname => 'mic_to_latin4', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin4', probin => '$libdir/latin_and_mic' }, { oid => '4352', descr => 'internal conversion function for BIG5 to UTF8', - proname => 'big5_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_utf8', + proname => 'big5_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_utf8', probin => '$libdir/utf8_and_big5' }, { oid => '4353', descr => 'internal conversion function for UTF8 to BIG5', - proname => 'utf8_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_big5', + proname => 'utf8_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_big5', probin => '$libdir/utf8_and_big5' }, { oid => '4354', descr => 'internal conversion function for UTF8 to KOI8R', - proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8r', + proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8r', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4355', descr => 'internal conversion function for KOI8R to UTF8', - proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_utf8', + proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4356', descr => 'internal conversion function for UTF8 to KOI8U', - proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8u', + proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8u', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4357', descr => 'internal conversion function for KOI8U to UTF8', - proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8u_to_utf8', + proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8u_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4358', descr => 'internal conversion function for UTF8 to WIN', - proname => 'utf8_to_win', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_win', + proname => 'utf8_to_win', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_win', probin => '$libdir/utf8_and_win' }, { oid => '4359', descr => 'internal conversion function for WIN to UTF8', - proname => 'win_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win_to_utf8', + proname => 'win_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win_to_utf8', probin => '$libdir/utf8_and_win' }, { oid => '4360', descr => 'internal conversion function for EUC_CN to UTF8', - proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_utf8', + proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_utf8', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4361', descr => 'internal conversion function for UTF8 to EUC_CN', - proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_cn', + proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_cn', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4362', descr => 'internal conversion function for EUC_JP to UTF8', - proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_utf8', + proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_utf8', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4363', descr => 'internal conversion function for UTF8 to EUC_JP', - proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_jp', + proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jp', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4364', descr => 'internal conversion function for EUC_KR to UTF8', - proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_utf8', + proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_utf8', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4365', descr => 'internal conversion function for UTF8 to EUC_KR', - proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_kr', + proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_kr', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4366', descr => 'internal conversion function for EUC_TW to UTF8', - proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_utf8', + proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_utf8', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4367', descr => 'internal conversion function for UTF8 to EUC_TW', - proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_tw', + proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_tw', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4368', descr => 'internal conversion function for GB18030 to UTF8', - proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gb18030_to_utf8', + proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gb18030_to_utf8', probin => '$libdir/utf8_and_gb18030' }, { oid => '4369', descr => 'internal conversion function for UTF8 to GB18030', - proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gb18030', + proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gb18030', probin => '$libdir/utf8_and_gb18030' }, { oid => '4370', descr => 'internal conversion function for GBK to UTF8', - proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gbk_to_utf8', + proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gbk_to_utf8', probin => '$libdir/utf8_and_gbk' }, { oid => '4371', descr => 'internal conversion function for UTF8 to GBK', - proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gbk', + proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gbk', probin => '$libdir/utf8_and_gbk' }, { oid => '4372', descr => 'internal conversion function for UTF8 to ISO-8859 2-16', - proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_iso8859', + proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859', probin => '$libdir/utf8_and_iso8859' }, { oid => '4373', descr => 'internal conversion function for ISO-8859 2-16 to UTF8', - proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso8859_to_utf8', + proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_to_utf8', probin => '$libdir/utf8_and_iso8859' }, { oid => '4374', descr => 'internal conversion function for LATIN1 to UTF8', - proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_1_to_utf8', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4375', descr => 'internal conversion function for UTF8 to LATIN1', - proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859_1', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4376', descr => 'internal conversion function for JOHAB to UTF8', - proname => 'johab_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'johab_to_utf8', + proname => 'johab_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'johab_to_utf8', probin => '$libdir/utf8_and_johab' }, { oid => '4377', descr => 'internal conversion function for UTF8 to JOHAB', - proname => 'utf8_to_johab', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_johab', + proname => 'utf8_to_johab', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_johab', probin => '$libdir/utf8_and_johab' }, { oid => '4378', descr => 'internal conversion function for SJIS to UTF8', - proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_utf8', + proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_utf8', probin => '$libdir/utf8_and_sjis' }, { oid => '4379', descr => 'internal conversion function for UTF8 to SJIS', - proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_sjis', + proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_sjis', probin => '$libdir/utf8_and_sjis' }, { oid => '4380', descr => 'internal conversion function for UHC to UTF8', - proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'uhc_to_utf8', + proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'uhc_to_utf8', probin => '$libdir/utf8_and_uhc' }, { oid => '4381', descr => 'internal conversion function for UTF8 to UHC', - proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_uhc', + proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_uhc', probin => '$libdir/utf8_and_uhc' }, { oid => '4382', descr => 'internal conversion function for EUC_JIS_2004 to UTF8', - proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_utf8', probin => '$libdir/utf8_and_euc2004' }, { oid => '4383', descr => 'internal conversion function for UTF8 to EUC_JIS_2004', - proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jis_2004', probin => '$libdir/utf8_and_euc2004' }, { oid => '4384', descr => 'internal conversion function for SHIFT_JIS_2004 to UTF8', - proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_utf8', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4385', descr => 'internal conversion function for UTF8 to SHIFT_JIS_2004', - proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_shift_jis_2004', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4386', descr => 'internal conversion function for EUC_JIS_2004 to SHIFT_JIS_2004', proname => 'euc_jis_2004_to_shift_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_shift_jis_2004', probin => '$libdir/euc2004_sjis2004' }, { oid => '4387', descr => 'internal conversion function for SHIFT_JIS_2004 to EUC_JIS_2004', proname => 'shift_jis_2004_to_euc_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_euc_jis_2004', probin => '$libdir/euc2004_sjis2004' }, diff --git a/src/include/mb/pg_wchar.h b/src/include/mb/pg_wchar.h index 64b22e4b0d4..346a41a1f3d 100644 --- a/src/include/mb/pg_wchar.h +++ b/src/include/mb/pg_wchar.h @@ -627,18 +627,18 @@ extern void pg_unicode_to_server(pg_wchar c, unsigned char *s); extern unsigned short BIG5toCNS(unsigned short big5, unsigned char *lc); extern unsigned short CNStoBIG5(unsigned short cns, unsigned char lc); -extern void UtfToLocal(const unsigned char *utf, int len, - unsigned char *iso, - const pg_mb_radix_tree *map, - const pg_utf_to_local_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); -extern void LocalToUtf(const unsigned char *iso, int len, - unsigned char *utf, - const pg_mb_radix_tree *map, - const pg_local_to_utf_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); +extern int UtfToLocal(const unsigned char *utf, int len, + unsigned char *iso, + const pg_mb_radix_tree *map, + const pg_utf_to_local_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); +extern int LocalToUtf(const unsigned char *iso, int len, + unsigned char *utf, + const pg_mb_radix_tree *map, + const pg_local_to_utf_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); extern bool pg_verifymbstr(const char *mbstr, int len, bool noError); extern bool pg_verify_mbstr(int encoding, const char *mbstr, int len, @@ -656,18 +656,19 @@ extern void report_invalid_encoding(int encoding, const char *mbstr, int len) pg extern void report_untranslatable_char(int src_encoding, int dest_encoding, const char *mbstr, int len) pg_attribute_noreturn(); -extern void local2local(const unsigned char *l, unsigned char *p, int len, - int src_encoding, int dest_encoding, const unsigned char *tab); -extern void latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding); -extern void mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding); -extern void latin2mic_with_table(const unsigned char *l, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); -extern void mic2latin_with_table(const unsigned char *mic, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); +extern int local2local(const unsigned char *l, unsigned char *p, int len, + int src_encoding, int dest_encoding, const unsigned char *tab, + bool noError); +extern int latin2mic(const unsigned char *l, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int mic2latin(const unsigned char *mic, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int latin2mic_with_table(const unsigned char *l, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); +extern int mic2latin_with_table(const unsigned char *mic, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); #ifdef WIN32 extern WCHAR *pgwin32_message_to_UTF16(const char *str, int len, int *utf16len); diff --git a/src/test/regress/expected/opr_sanity.out b/src/test/regress/expected/opr_sanity.out index 254ca06d3dd..23ba60e395f 100644 --- a/src/test/regress/expected/opr_sanity.out +++ b/src/test/regress/expected/opr_sanity.out @@ -1052,13 +1052,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); oid | proname | oid | conname -----+---------+-----+--------- (0 rows) diff --git a/src/test/regress/sql/opr_sanity.sql b/src/test/regress/sql/opr_sanity.sql index bbd3834b634..04691745981 100644 --- a/src/test/regress/sql/opr_sanity.sql +++ b/src/test/regress/sql/opr_sanity.sql @@ -556,13 +556,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); -- Check for conprocs that don't perform the specific conversion that -- pg_conversion alleges they do, by trying to invoke each conversion -- 2.29.2 --------------39E46EF15EBFAA37D53332E5 Content-Type: text/x-patch; charset=UTF-8; name="v3-0003-Add-tests-for-the-new-noError-variants-of-built-i.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="v3-0003-Add-tests-for-the-new-noError-variants-of-built-i.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 34+ messages in thread
* [PATCH v3 2/5] Change conversion function signature. @ 2021-01-28 16:42 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 34+ messages in thread From: Heikki Linnakangas @ 2021-01-28 16:42 UTC (permalink / raw) Add a 'noError' argument, so that we can try to convert a buffer without knowing the character boundaries beforehand. The functions now need to return the number of input bytes successfully converted. This is is a backwards-incompatible change, if you have created a custom encoding conversion with CREATE CONVERSION. This adds a check to pg_upgrade for that, refusing the upgrade if there are any user-defined encoding conversions. --- doc/src/sgml/ref/create_conversion.sgml | 5 +- src/backend/commands/conversioncmds.c | 27 +- src/backend/utils/error/elog.c | 2 + src/backend/utils/mb/conv.c | 112 +++++- .../cyrillic_and_mic/cyrillic_and_mic.c | 127 ++++--- .../euc2004_sjis2004/euc2004_sjis2004.c | 96 ++++- .../euc_cn_and_mic/euc_cn_and_mic.c | 57 ++- .../euc_jp_and_sjis/euc_jp_and_sjis.c | 153 ++++++-- .../euc_kr_and_mic/euc_kr_and_mic.c | 57 ++- .../euc_tw_and_big5/euc_tw_and_big5.c | 165 +++++++-- .../latin2_and_win1250/latin2_and_win1250.c | 49 ++- .../latin_and_mic/latin_and_mic.c | 43 ++- .../utf8_and_big5/utf8_and_big5.c | 37 +- .../utf8_and_cyrillic/utf8_and_cyrillic.c | 67 ++-- .../utf8_and_euc2004/utf8_and_euc2004.c | 37 +- .../utf8_and_euc_cn/utf8_and_euc_cn.c | 37 +- .../utf8_and_euc_jp/utf8_and_euc_jp.c | 37 +- .../utf8_and_euc_kr/utf8_and_euc_kr.c | 37 +- .../utf8_and_euc_tw/utf8_and_euc_tw.c | 37 +- .../utf8_and_gb18030/utf8_and_gb18030.c | 37 +- .../utf8_and_gbk/utf8_and_gbk.c | 37 +- .../utf8_and_iso8859/utf8_and_iso8859.c | 43 ++- .../utf8_and_iso8859_1/utf8_and_iso8859_1.c | 27 +- .../utf8_and_johab/utf8_and_johab.c | 37 +- .../utf8_and_sjis/utf8_and_sjis.c | 37 +- .../utf8_and_sjis2004/utf8_and_sjis2004.c | 37 +- .../utf8_and_uhc/utf8_and_uhc.c | 37 +- .../utf8_and_win/utf8_and_win.c | 43 ++- src/backend/utils/mb/mbutils.c | 18 +- src/bin/pg_upgrade/check.c | 95 +++++ src/include/catalog/pg_proc.dat | 332 +++++++++--------- src/include/mb/pg_wchar.h | 49 +-- src/test/regress/expected/opr_sanity.out | 7 +- src/test/regress/sql/opr_sanity.sql | 7 +- 34 files changed, 1390 insertions(+), 635 deletions(-) diff --git a/doc/src/sgml/ref/create_conversion.sgml b/doc/src/sgml/ref/create_conversion.sgml index e7700fecfc5..f014a676c88 100644 --- a/doc/src/sgml/ref/create_conversion.sgml +++ b/doc/src/sgml/ref/create_conversion.sgml @@ -117,8 +117,9 @@ conv_proc( integer, -- destination encoding ID cstring, -- source string (null terminated C string) internal, -- destination (fill with a null terminated C string) - integer -- source string length -) RETURNS void; + integer, -- source string length + boolean -- if true, don't throw an error if conversion fails +) RETURNS integer; </programlisting></para> </listitem> </varlistentry> diff --git a/src/backend/commands/conversioncmds.c b/src/backend/commands/conversioncmds.c index f7ff321de71..d2041466911 100644 --- a/src/backend/commands/conversioncmds.c +++ b/src/backend/commands/conversioncmds.c @@ -45,8 +45,9 @@ CreateConversionCommand(CreateConversionStmt *stmt) const char *from_encoding_name = stmt->for_encoding_name; const char *to_encoding_name = stmt->to_encoding_name; List *func_name = stmt->func_name; - static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID}; + static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID, BOOLOID}; char result[1]; + Datum funcresult; /* Convert list of names to a name and namespace */ namespaceId = QualifiedNameGetCreationNamespace(stmt->conversion_name, @@ -92,8 +93,8 @@ CreateConversionCommand(CreateConversionStmt *stmt) funcoid = LookupFuncName(func_name, sizeof(funcargs) / sizeof(Oid), funcargs, false); - /* Check it returns VOID, else it's probably the wrong function */ - if (get_func_rettype(funcoid) != VOIDOID) + /* Check it returns int4, else it's probably the wrong function */ + if (get_func_rettype(funcoid) != INT4OID) ereport(ERROR, (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), errmsg("encoding conversion function %s must return type %s", @@ -111,12 +112,20 @@ CreateConversionCommand(CreateConversionStmt *stmt) * string; the conversion function should throw an error if it can't * perform the requested conversion. */ - OidFunctionCall5(funcoid, - Int32GetDatum(from_encoding), - Int32GetDatum(to_encoding), - CStringGetDatum(""), - CStringGetDatum(result), - Int32GetDatum(0)); + funcresult = OidFunctionCall6(funcoid, + Int32GetDatum(from_encoding), + Int32GetDatum(to_encoding), + CStringGetDatum(""), + CStringGetDatum(result), + Int32GetDatum(0), + BoolGetDatum(false)); + + /* The function should return 0 for empty input. Might as well check that, too. */ + if (DatumGetInt32(funcresult) != 0) + ereport(ERROR, + (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), + errmsg("encoding conversion function %s returned incorrect result for empty input", + NameListToString(func_name)))); /* * All seem ok, go ahead (possible failure would be a duplicate conversion diff --git a/src/backend/utils/error/elog.c b/src/backend/utils/error/elog.c index 80c26724612..762f77d533c 100644 --- a/src/backend/utils/error/elog.c +++ b/src/backend/utils/error/elog.c @@ -2280,6 +2280,8 @@ write_console(const char *line, int len) * Conversion on non-win32 platforms is not implemented yet. It requires * non-throw version of pg_do_encoding_conversion(), that converts * unconvertable characters to '?' without errors. + * + * XXX: We have a no-throw version now. It doesn't convert to '?' though. */ #endif diff --git a/src/backend/utils/mb/conv.c b/src/backend/utils/mb/conv.c index a07b54bd3b8..b83358bc7a5 100644 --- a/src/backend/utils/mb/conv.c +++ b/src/backend/utils/mb/conv.c @@ -26,14 +26,16 @@ * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the target charset, or 0 if there is no equivalent code. */ -void +int local2local(const unsigned char *l, unsigned char *p, int len, int src_encoding, int dest_encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -41,7 +43,11 @@ local2local(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(src_encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -50,13 +56,19 @@ local2local(const unsigned char *l, if (c2) *p++ = c2; else + { + if (noError) + break; report_untranslatable_char(src_encoding, dest_encoding, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -67,17 +79,22 @@ local2local(const unsigned char *l, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = l; int c1; while (len > 0) { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (IS_HIGHBIT_SET(c1)) *p++ = lc; *p++ = c1; @@ -85,6 +102,8 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, len--; } *p = '\0'; + + return l - start; } /* @@ -95,17 +114,22 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -118,17 +142,27 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1])) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); + } *p++ = mic[1]; mic += 2; len -= 2; } } *p = '\0'; + + return mic - start; } @@ -144,14 +178,16 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the mule encoding, or 0 if there is no equivalent code. */ -void +int latin2mic_with_table(const unsigned char *l, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -159,7 +195,11 @@ latin2mic_with_table(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -171,13 +211,19 @@ latin2mic_with_table(const unsigned char *l, *p++ = c2; } else + { + if (noError) + break; report_untranslatable_char(encoding, PG_MULE_INTERNAL, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -192,14 +238,16 @@ latin2mic_with_table(const unsigned char *l, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the local charset, or 0 if there is no equivalent code. */ -void +int mic2latin_with_table(const unsigned char *mic, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = mic; unsigned char c1, c2; @@ -207,7 +255,11 @@ mic2latin_with_table(const unsigned char *mic, { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -220,11 +272,17 @@ mic2latin_with_table(const unsigned char *mic, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1]) || (c2 = tab[mic[1] - HIGHBIT]) == 0) { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); break; /* keep compiler quiet */ @@ -235,6 +293,8 @@ mic2latin_with_table(const unsigned char *mic, } } *p = '\0'; + + return mic - start; } /* @@ -425,17 +485,19 @@ pg_mb_radix_conv(const pg_mb_radix_tree *rt, * * See pg_wchar.h for more details about the data structures used here. */ -void +int UtfToLocal(const unsigned char *utf, int len, unsigned char *iso, const pg_mb_radix_tree *map, const pg_utf_to_local_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, bool noError) { uint32 iutf; int l; const pg_utf_to_local_combined *cp; + const unsigned char *start = utf; + const unsigned char *cur = utf; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -449,6 +511,8 @@ UtfToLocal(const unsigned char *utf, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*utf == '\0') break; @@ -584,15 +648,19 @@ UtfToLocal(const unsigned char *utf, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(PG_UTF8, encoding, (const char *) (utf - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(PG_UTF8, (const char *) utf, len); *iso = '\0'; + + return cur - start; } /* @@ -616,18 +684,24 @@ UtfToLocal(const unsigned char *utf, int len, * (if provided) is applied. An error is raised if no match is found. * * See pg_wchar.h for more details about the data structures used here. + * + * Returns the number of input bytes consumed. If noError is true, this can + * be less than 'len'. */ -void +int LocalToUtf(const unsigned char *iso, int len, unsigned char *utf, const pg_mb_radix_tree *map, const pg_local_to_utf_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, + bool noError) { uint32 iiso; int l; const pg_local_to_utf_combined *cp; + const unsigned char *start = iso; + const unsigned char *cur = iso; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -641,6 +715,8 @@ LocalToUtf(const unsigned char *iso, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*iso == '\0') break; @@ -723,13 +799,17 @@ LocalToUtf(const unsigned char *iso, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(encoding, PG_UTF8, (const char *) (iso - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(encoding, (const char *) iso, len); *utf = '\0'; + + return cur - start; } diff --git a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c index 4c5b02654de..368c2deb5e4 100644 --- a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c @@ -44,8 +44,11 @@ PG_FUNCTION_INFO_V1(win866_to_iso); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -306,12 +309,14 @@ koi8r_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -320,12 +325,14 @@ mic_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_KOI8R); - mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -334,12 +341,14 @@ iso_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -348,12 +357,14 @@ mic_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_ISO_8859_5); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -362,12 +373,14 @@ win1251_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -376,12 +389,14 @@ mic_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1251); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -390,12 +405,14 @@ win866_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -404,12 +421,14 @@ mic_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN866); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -418,12 +437,14 @@ koi8r_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN1251); - local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -432,12 +453,14 @@ win1251_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_KOI8R); - local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi); + converted = local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -446,12 +469,14 @@ koi8r_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN866); - local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -460,12 +485,14 @@ win866_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_KOI8R); - local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi); + converted = local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -474,12 +501,14 @@ win866_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_WIN1251); - local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251); + converted = local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -488,12 +517,14 @@ win1251_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_WIN866); - local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866); + converted = local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -502,12 +533,14 @@ iso_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_KOI8R); - local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -516,12 +549,14 @@ koi8r_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_ISO_8859_5); - local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso); + converted = local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -530,12 +565,14 @@ iso_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN1251); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -544,12 +581,14 @@ win1251_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso); + converted = local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -558,12 +597,14 @@ iso_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN866); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -572,10 +613,12 @@ win866_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso); + converted = local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c index 4d7fb116cfd..88529c644cf 100644 --- a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c @@ -19,8 +19,8 @@ PG_MODULE_MAGIC; PG_FUNCTION_INFO_V1(euc_jis_2004_to_shift_jis_2004); PG_FUNCTION_INFO_V1(shift_jis_2004_to_euc_jis_2004); -static void euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len); -static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len); +static int euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError); /* ---------- * conv_proc( @@ -28,8 +28,11 @@ static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -39,12 +42,14 @@ euc_jis_2004_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_SHIFT_JIS_2004); - euc_jis_20042shift_jis_2004(src, dest, len); + converted = euc_jis_20042shift_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -53,20 +58,23 @@ shift_jis_2004_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_EUC_JIS_2004); - shift_jis_20042euc_jis_2004(src, dest, len); + converted = shift_jis_20042euc_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_JIS_2004 -> SHIFT_JIS_2004 */ -static void -euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, ku, ten; @@ -79,8 +87,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -90,8 +102,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) l = pg_encoding_verifymbchar(PG_EUC_JIS_2004, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (c1 == SS2 && l == 2) /* JIS X 0201 kana? */ { @@ -121,8 +137,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) *p++ = (ku + 0x19b) >> 1; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } if (ku % 2) @@ -132,8 +152,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; @@ -149,8 +173,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ku >= 63 && ku <= 94) *p++ = (ku + 0x181) >> 1; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (ku % 2) { @@ -159,20 +187,30 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else - report_invalid_encoding(PG_EUC_JIS_2004, + { + if (noError) + break; + report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } euc += l; len -= l; } *p = '\0'; + + return euc - start; } /* @@ -212,9 +250,10 @@ get_ten(int b, int *ku) * SHIFT_JIS_2004 ---> EUC_JIS_2004 */ -static void -shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len) +static int +shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1; int ku, ten, @@ -230,8 +269,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -241,8 +284,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len l = pg_encoding_verifymbchar(PG_SHIFT_JIS_2004, (const char *) sjis, len); if (l < 0 || l > len) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf && l == 1) { @@ -266,8 +313,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x100; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xe0 && c1 <= 0xef) /* plane 1 62ku-94ku */ @@ -275,9 +326,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x180; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, - (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xf0 && c1 <= 0xf3) /* plane 2 @@ -286,8 +340,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } switch (c1) { case 0xf0: @@ -309,16 +367,24 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 == 0xf4 && kubun == 1) ku = 15; else ku = (c1 << 1) - 0x19a - kubun; } else + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (plane == 2) *p++ = SS3; @@ -330,4 +396,6 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c index e9bb896935f..a8da733803d 100644 --- a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_cn2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_cn(const unsigned char *mic, unsigned char *p, int len); +static int euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_cn_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_cn_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_MULE_INTERNAL); - euc_cn2mic(src, dest, len); + converted = euc_cn2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_CN); - mic2euc_cn(src, dest, len); + converted = mic2euc_cn(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_CN ---> MIC */ -static void -euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; while (len > 0) @@ -76,7 +84,11 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (len < 2 || !IS_HIGHBIT_SET(euc[1])) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = LC_GB2312_80; *p++ = c1; *p++ = euc[1]; @@ -86,21 +98,28 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_CN */ -static void -mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) @@ -109,11 +128,19 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (c1 != LC_GB2312_80) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_CN, (const char *) mic, len); + } if (len < 3 || !IS_HIGHBIT_SET(mic[1]) || !IS_HIGHBIT_SET(mic[2])) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } mic++; *p++ = *mic++; *p++ = *mic++; @@ -122,12 +149,18 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; } } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c index 5059f917a98..cc4817dc4cd 100644 --- a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c @@ -42,17 +42,20 @@ PG_FUNCTION_INFO_V1(mic_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void sjis2mic(const unsigned char *sjis, unsigned char *p, int len); -static void mic2sjis(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_jp(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len); -static void sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len); +static int sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError); +static int mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_jp_to_sjis(PG_FUNCTION_ARGS) @@ -60,12 +63,14 @@ euc_jp_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_SJIS); - euc_jp2sjis(src, dest, len); + converted = euc_jp2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -74,12 +79,14 @@ sjis_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_EUC_JP); - sjis2euc_jp(src, dest, len); + converted = sjis2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -88,12 +95,14 @@ euc_jp_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_MULE_INTERNAL); - euc_jp2mic(src, dest, len); + converted = euc_jp2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -102,12 +111,14 @@ mic_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_JP); - mic2euc_jp(src, dest, len); + converted = mic2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -116,12 +127,14 @@ sjis_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_MULE_INTERNAL); - sjis2mic(src, dest, len); + converted = sjis2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -130,20 +143,23 @@ mic_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_SJIS); - mic2sjis(src, dest, len); + converted = mic2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * SJIS ---> MIC */ -static void -sjis2mic(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -167,7 +183,11 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) * JIS X0208, X0212, user defined extended characters */ if (len < 2 || !ISSJISHEAD(c1) || !ISSJISTAIL(sjis[1])) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } c2 = sjis[1]; k = (c1 << 8) + c2; if (k >= 0xed40 && k < 0xf040) @@ -257,21 +277,28 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; } } *p = '\0'; + + return sjis - start; } /* * MIC ---> SJIS */ -static void -mic2sjis(const unsigned char *mic, unsigned char *p, int len) +static int +mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1, c2, k, @@ -284,8 +311,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -293,8 +324,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) *p++ = mic[1]; else if (c1 == LC_JISX0208) @@ -350,20 +385,27 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_SJIS, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP ---> MIC */ -static void -euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -374,8 +416,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -383,8 +429,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* 1 byte kana? */ *p++ = LC_JISX0201K; @@ -406,14 +456,17 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_JP */ -static void -mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -424,8 +477,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -433,8 +490,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) { *p++ = SS2; @@ -452,20 +513,27 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_JP, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP -> SJIS */ -static void -euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, c2, k; @@ -478,8 +546,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -487,8 +559,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* hankaku kana? */ @@ -551,14 +627,17 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * SJIS ---> EUC_JP */ -static void -sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -573,8 +652,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -582,8 +665,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_SJIS, (const char *) sjis, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf) { /* JIS X0201 (1 byte kana) */ @@ -680,4 +767,6 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c index ac823d6c270..a5b51617e52 100644 --- a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_kr2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_kr(const unsigned char *mic, unsigned char *p, int len); +static int euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_kr_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_kr_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_MULE_INTERNAL); - euc_kr2mic(src, dest, len); + converted = euc_kr2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_KR); - mic2euc_kr(src, dest, len); + converted = mic2euc_kr(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_KR ---> MIC */ -static void -euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -78,8 +86,12 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_KR, (const char *) euc, len); if (l != 2) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = LC_KS5601; *p++ = c1; *p++ = euc[1]; @@ -89,22 +101,29 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_KR */ -static void -mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -115,8 +134,12 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -124,18 +147,28 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_KS5601) { *p++ = mic[1]; *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_KR, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c index 66c242d7f36..ebb4e0acd53 100644 --- a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c @@ -32,17 +32,20 @@ PG_FUNCTION_INFO_V1(mic_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_tw2big5(const unsigned char *euc, unsigned char *p, int len); -static void big52euc_tw(const unsigned char *euc, unsigned char *p, int len); -static void big52mic(const unsigned char *big5, unsigned char *p, int len); -static void mic2big5(const unsigned char *mic, unsigned char *p, int len); -static void euc_tw2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_tw(const unsigned char *mic, unsigned char *p, int len); +static int euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52euc_tw(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError); +static int mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_tw_to_big5(PG_FUNCTION_ARGS) @@ -50,12 +53,14 @@ euc_tw_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_BIG5); - euc_tw2big5(src, dest, len); + converted = euc_tw2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -64,12 +69,14 @@ big5_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_EUC_TW); - big52euc_tw(src, dest, len); + converted = big52euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -78,12 +85,14 @@ euc_tw_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_MULE_INTERNAL); - euc_tw2mic(src, dest, len); + converted = euc_tw2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -92,12 +101,14 @@ mic_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_TW); - mic2euc_tw(src, dest, len); + converted = mic2euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -106,12 +117,14 @@ big5_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_MULE_INTERNAL); - big52mic(src, dest, len); + converted = big52mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -120,21 +133,24 @@ mic_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_BIG5); - mic2big5(src, dest, len); + converted = mic2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_TW ---> Big5 */ -static void -euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; unsigned char c1; unsigned short big5buf, cnsBuf; @@ -149,8 +165,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Verify and decode the next EUC_TW input character */ l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -171,8 +191,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Write it out in Big5 */ big5buf = CNStoBIG5(cnsBuf, lc); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_EUC_TW, PG_BIG5, (const char *) euc, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; @@ -182,22 +206,29 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * Big5 ---> EUC_TW */ -static void -big52euc_tw(const unsigned char *big5, unsigned char *p, int len) +static int +big52euc_tw(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -212,8 +243,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); @@ -237,8 +272,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_EUC_TW, (const char *) big5, len); + } big5 += l; len -= l; @@ -256,14 +295,17 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) } } *p = '\0'; + + return big5 - start; } /* * EUC_TW ---> MIC */ -static void -euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -274,8 +316,12 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -304,22 +350,29 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_TW */ -static void -mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -330,8 +383,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -339,8 +396,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1) { *p++ = mic[1]; @@ -362,20 +423,27 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[3]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_TW, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * Big5 ---> MIC */ -static void -big52mic(const unsigned char *big5, unsigned char *p, int len) +static int +big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -389,8 +457,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } *p++ = c1; big5++; len--; @@ -398,8 +470,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); if (lc != 0) @@ -412,20 +488,27 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_MULE_INTERNAL, (const char *) big5, len); + } big5 += l; len -= l; } *p = '\0'; + + return big5 - start; } /* * MIC ---> Big5 */ -static void -mic2big5(const unsigned char *mic, unsigned char *p, int len) +static int +mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -438,8 +521,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -447,8 +534,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1 || c1 == LC_CNS11643_2 || c1 == LCPRV2_B) { if (c1 == LCPRV2_B) @@ -462,16 +553,26 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } big5buf = CNStoBIG5(cnsBuf, c1); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c index 2e28e6780a5..8610fcb69aa 100644 --- a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c +++ b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(win1250_to_latin2); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -82,12 +85,14 @@ latin2_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -96,12 +101,14 @@ mic_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN2); - mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -110,13 +117,15 @@ win1250_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - win1250_2_iso88592); + converted = latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -125,13 +134,15 @@ mic_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1250); - mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - iso88592_2_win1250); + converted = mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -140,12 +151,15 @@ latin2_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_WIN1250); - local2local(src, dest, len, PG_LATIN2, PG_WIN1250, iso88592_2_win1250); + converted = local2local(src, dest, len, PG_LATIN2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -154,10 +168,13 @@ win1250_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_LATIN2); - local2local(src, dest, len, PG_WIN1250, PG_LATIN2, win1250_2_iso88592); + converted = local2local(src, dest, len, PG_WIN1250, PG_LATIN2, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c index bc651410f21..bff27d1c295 100644 --- a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(mic_to_latin4); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -42,12 +45,14 @@ latin1_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,12 +61,14 @@ mic_to_latin1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN1); - mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -70,12 +77,14 @@ latin3_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN3, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -84,12 +93,14 @@ mic_to_latin3(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN3); - mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,12 +109,14 @@ latin4_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN4, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -112,10 +125,12 @@ mic_to_latin4(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN4); - mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c index d6067cdc24e..3838b15cab9 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ big5_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_UTF8); - LocalToUtf(src, len, dest, - &big5_to_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = LocalToUtf(src, len, dest, + &big5_to_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_BIG5); - UtfToLocal(src, len, dest, - &big5_from_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = UtfToLocal(src, len, dest, + &big5_from_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c index ed90e8e682e..75719fe5f1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c @@ -33,8 +33,11 @@ PG_FUNCTION_INFO_V1(koi8u_to_utf8); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -44,16 +47,19 @@ utf8_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8R); - UtfToLocal(src, len, dest, - &koi8r_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = UtfToLocal(src, len, dest, + &koi8r_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -62,16 +68,19 @@ koi8r_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8r_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = LocalToUtf(src, len, dest, + &koi8r_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -80,16 +89,19 @@ utf8_to_koi8u(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8U); - UtfToLocal(src, len, dest, - &koi8u_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = UtfToLocal(src, len, dest, + &koi8u_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,14 +110,17 @@ koi8u_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8U, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8u_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = LocalToUtf(src, len, dest, + &koi8u_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c index d699affce47..5391001951a 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jis_2004_to_unicode_tree, - LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = LocalToUtf(src, len, dest, + &euc_jis_2004_to_unicode_tree, + LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JIS_2004); - UtfToLocal(src, len, dest, - &euc_jis_2004_from_unicode_tree, - ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = UtfToLocal(src, len, dest, + &euc_jis_2004_from_unicode_tree, + ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c index d7c0ba6a58b..c87d1bf2398 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_cn_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_cn_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = LocalToUtf(src, len, dest, + &euc_cn_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_CN); - UtfToLocal(src, len, dest, - &euc_cn_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = UtfToLocal(src, len, dest, + &euc_cn_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c index 13a3a23e77b..6a55134db21 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jp); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jp_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jp_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = LocalToUtf(src, len, dest, + &euc_jp_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JP); - UtfToLocal(src, len, dest, - &euc_jp_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = UtfToLocal(src, len, dest, + &euc_jp_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c index 1bbb8aaef7b..fe1924e2fec 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_kr_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_kr_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = LocalToUtf(src, len, dest, + &euc_kr_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_KR); - UtfToLocal(src, len, dest, - &euc_kr_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = UtfToLocal(src, len, dest, + &euc_kr_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c index 9830045dccd..68215659b57 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_tw); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_tw_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_tw_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = LocalToUtf(src, len, dest, + &euc_tw_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_TW); - UtfToLocal(src, len, dest, - &euc_tw_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = UtfToLocal(src, len, dest, + &euc_tw_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c index f86ecf27424..e1a59c39a4d 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c @@ -183,8 +183,11 @@ conv_utf8_to_18030(uint32 code) * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -193,16 +196,19 @@ gb18030_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GB18030, PG_UTF8); - LocalToUtf(src, len, dest, - &gb18030_to_unicode_tree, - NULL, 0, - conv_18030_to_utf8, - PG_GB18030); + converted = LocalToUtf(src, len, dest, + &gb18030_to_unicode_tree, + NULL, 0, + conv_18030_to_utf8, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -211,14 +217,17 @@ utf8_to_gb18030(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GB18030); - UtfToLocal(src, len, dest, - &gb18030_from_unicode_tree, - NULL, 0, - conv_utf8_to_18030, - PG_GB18030); + converted = UtfToLocal(src, len, dest, + &gb18030_from_unicode_tree, + NULL, 0, + conv_utf8_to_18030, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c index 2ab8b16c8a8..881386d5347 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_gbk); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ gbk_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GBK, PG_UTF8); - LocalToUtf(src, len, dest, - &gbk_to_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = LocalToUtf(src, len, dest, + &gbk_to_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_gbk(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GBK); - UtfToLocal(src, len, dest, - &gbk_from_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = UtfToLocal(src, len, dest, + &gbk_from_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c index 3e49f67ea2f..d93a521badf 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c @@ -52,8 +52,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -100,6 +103,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -108,12 +112,15 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -122,7 +129,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -132,6 +139,7 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -140,12 +148,15 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -154,5 +165,5 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c index 67e713cca11..8ac93604a1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c @@ -26,8 +26,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859_1); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -37,6 +40,8 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_UTF8); @@ -45,7 +50,11 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_LATIN1, (const char *) src, len); + } if (!IS_HIGHBIT_SET(c)) *dest++ = c; else @@ -58,7 +67,7 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } Datum @@ -67,6 +76,8 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c, c1; @@ -76,7 +87,11 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_UTF8, (const char *) src, len); + } /* fast path for ASCII-subset characters */ if (!IS_HIGHBIT_SET(c)) { @@ -102,11 +117,15 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) len -= 2; } else + { + if (noError) + break; report_untranslatable_char(PG_UTF8, PG_LATIN1, (const char *) src, len); + } } } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c index 578f5df4e7f..317daa2d5ee 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_johab); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ johab_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_JOHAB, PG_UTF8); - LocalToUtf(src, len, dest, - &johab_to_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = LocalToUtf(src, len, dest, + &johab_to_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_johab(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_JOHAB); - UtfToLocal(src, len, dest, - &johab_from_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = UtfToLocal(src, len, dest, + &johab_from_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c index dd9fc2975ad..4c9348aba59 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ sjis_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_UTF8); - LocalToUtf(src, len, dest, - &sjis_to_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = LocalToUtf(src, len, dest, + &sjis_to_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SJIS); - UtfToLocal(src, len, dest, - &sjis_from_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = UtfToLocal(src, len, dest, + &sjis_from_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c index 4bcc886d674..1fffdc5930c 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_shift_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ shift_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &shift_jis_2004_to_unicode_tree, - LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = LocalToUtf(src, len, dest, + &shift_jis_2004_to_unicode_tree, + LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SHIFT_JIS_2004); - UtfToLocal(src, len, dest, - &shift_jis_2004_from_unicode_tree, - ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = UtfToLocal(src, len, dest, + &shift_jis_2004_from_unicode_tree, + ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c index c8e512994a1..d9471dad097 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_uhc); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ uhc_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UHC, PG_UTF8); - LocalToUtf(src, len, dest, - &uhc_to_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = LocalToUtf(src, len, dest, + &uhc_to_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_uhc(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_UHC); - UtfToLocal(src, len, dest, - &uhc_from_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = UtfToLocal(src, len, dest, + &uhc_from_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c index 0c9493dee56..110ba5677d0 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c @@ -48,8 +48,11 @@ PG_FUNCTION_INFO_V1(utf8_to_win); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -81,6 +84,7 @@ win_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -89,12 +93,15 @@ win_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -103,7 +110,7 @@ win_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -113,6 +120,7 @@ utf8_to_win(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -121,12 +129,15 @@ utf8_to_win(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -135,5 +146,5 @@ utf8_to_win(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/mbutils.c b/src/backend/utils/mb/mbutils.c index 2578573b0ab..65753860e35 100644 --- a/src/backend/utils/mb/mbutils.c +++ b/src/backend/utils/mb/mbutils.c @@ -406,12 +406,13 @@ pg_do_encoding_conversion(unsigned char *src, int len, MemoryContextAllocHuge(CurrentMemoryContext, (Size) len * MAX_CONVERSION_GROWTH + 1); - OidFunctionCall5(proc, - Int32GetDatum(src_encoding), - Int32GetDatum(dest_encoding), - CStringGetDatum(src), - CStringGetDatum(result), - Int32GetDatum(len)); + (void) OidFunctionCall6(proc, + Int32GetDatum(src_encoding), + Int32GetDatum(dest_encoding), + CStringGetDatum(src), + CStringGetDatum(result), + Int32GetDatum(len), + BoolGetDatum(false)); /* * If the result is large, it's worth repalloc'ing to release any extra @@ -849,12 +850,13 @@ pg_unicode_to_server(pg_wchar c, unsigned char *s) c_as_utf8[c_as_utf8_len] = '\0'; /* Convert, or throw error if we can't */ - FunctionCall5(Utf8ToServerConvProc, + FunctionCall6(Utf8ToServerConvProc, Int32GetDatum(PG_UTF8), Int32GetDatum(server_encoding), CStringGetDatum(c_as_utf8), CStringGetDatum(s), - Int32GetDatum(c_as_utf8_len)); + Int32GetDatum(c_as_utf8_len), + BoolGetDatum(false)); } diff --git a/src/bin/pg_upgrade/check.c b/src/bin/pg_upgrade/check.c index 43fc297eb69..ee6be95b08d 100644 --- a/src/bin/pg_upgrade/check.c +++ b/src/bin/pg_upgrade/check.c @@ -28,6 +28,7 @@ static void check_for_reg_data_type_usage(ClusterInfo *cluster); static void check_for_jsonb_9_4_usage(ClusterInfo *cluster); static void check_for_pg_role_prefix(ClusterInfo *cluster); static void check_for_new_tablespace_dir(ClusterInfo *new_cluster); +static void check_for_user_defined_encoding_conversions(ClusterInfo *cluster); static char *get_canonical_locale_name(int category, const char *locale); @@ -102,6 +103,15 @@ check_and_dump_old_cluster(bool live_check) check_for_reg_data_type_usage(&old_cluster); check_for_isn_and_int8_passing_mismatch(&old_cluster); + /* + * PG 14 changed the function signature of encoding conversion functions. + * Conversions from older versions cannot be upgraded automatically + * because the user-defined functions used by the encoding conversions + * need to changed to match the new signature. + */ + if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1300) + check_for_user_defined_encoding_conversions(&old_cluster); + /* * Pre-PG 14 allowed user defined postfix operators, which are not * supported anymore. Verify there are none, iff applicable. @@ -1268,6 +1278,91 @@ check_for_pg_role_prefix(ClusterInfo *cluster) check_ok(); } +/* + * Verify that no user-defined encoding conversions exist. + */ +static void +check_for_user_defined_encoding_conversions(ClusterInfo *cluster) +{ + int dbnum; + FILE *script = NULL; + bool found = false; + char output_path[MAXPGPATH]; + + prep_status("Checking for user-defined encoding conversions"); + + snprintf(output_path, sizeof(output_path), + "encoding_conversions.txt"); + + /* Find any user defined encoding conversions */ + for (dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++) + { + PGresult *res; + bool db_used = false; + int ntups; + int rowno; + int i_conoid, + i_conname, + i_nspname; + DbInfo *active_db = &cluster->dbarr.dbs[dbnum]; + PGconn *conn = connectToServer(cluster, active_db->db_name); + + /* + * The query below hardcodes FirstNormalObjectId as 16384 rather than + * interpolating that C #define into the query because, if that + * #define is ever changed, the cutoff we want to use is the value + * used by pre-version 14 servers, not that of some future version. + */ + res = executeQueryOrDie(conn, + "SELECT c.oid as conoid, c.conname, n.nspname " + "FROM pg_catalog.pg_conversion c, " + " pg_catalog.pg_namespace n " + "WHERE c.connamespace = n.oid AND " + " c.oid >= 16384"); + ntups = PQntuples(res); + i_conoid = PQfnumber(res, "conoid"); + i_conname = PQfnumber(res, "conname"); + i_nspname = PQfnumber(res, "nspname"); + for (rowno = 0; rowno < ntups; rowno++) + { + found = true; + if (script == NULL && + (script = fopen_priv(output_path, "w")) == NULL) + pg_fatal("could not open file \"%s\": %s\n", + output_path, strerror(errno)); + if (!db_used) + { + fprintf(script, "In database: %s\n", active_db->db_name); + db_used = true; + } + fprintf(script, " (oid=%s) %s.%s\n", + PQgetvalue(res, rowno, i_conoid), + PQgetvalue(res, rowno, i_nspname), + PQgetvalue(res, rowno, i_conname)); + } + + PQclear(res); + + PQfinish(conn); + } + + if (script) + fclose(script); + + if (found) + { + pg_log(PG_REPORT, "fatal\n"); + pg_fatal("Your installation contains user-defined encoding conversions.\n" + "The conversion function parameters changed in PostgreSQL version 14\n" + "so this cluster cannot currently be upgraded. You can remove the\n" + "encoding conversions in the old cluster and restart the upgrade.\n" + "A list of user-defined encoding conversions is in the file:\n" + " %s\n\n", output_path); + } + else + check_ok(); +} + /* * get_canonical_locale_name diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index f8174061ef3..75b829e8514 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10766,388 +10766,388 @@ # conversion functions { oid => '4302', descr => 'internal conversion function for KOI8R to MULE_INTERNAL', - proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_mic', + proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4303', descr => 'internal conversion function for MULE_INTERNAL to KOI8R', - proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_koi8r', + proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4304', descr => 'internal conversion function for ISO-8859-5 to MULE_INTERNAL', - proname => 'iso_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_mic', + proname => 'iso_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4305', descr => 'internal conversion function for MULE_INTERNAL to ISO-8859-5', - proname => 'mic_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_iso', + proname => 'mic_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4306', descr => 'internal conversion function for WIN1251 to MULE_INTERNAL', - proname => 'win1251_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_mic', + proname => 'win1251_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4307', descr => 'internal conversion function for MULE_INTERNAL to WIN1251', - proname => 'mic_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1251', + proname => 'mic_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4308', descr => 'internal conversion function for WIN866 to MULE_INTERNAL', - proname => 'win866_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_mic', + proname => 'win866_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4309', descr => 'internal conversion function for MULE_INTERNAL to WIN866', - proname => 'mic_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win866', + proname => 'mic_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4310', descr => 'internal conversion function for KOI8R to WIN1251', - proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4311', descr => 'internal conversion function for WIN1251 to KOI8R', - proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4312', descr => 'internal conversion function for KOI8R to WIN866', - proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_win866', + proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4313', descr => 'internal conversion function for WIN866 to KOI8R', - proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_koi8r', + proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4314', descr => 'internal conversion function for WIN866 to WIN1251', - proname => 'win866_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win866_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4315', descr => 'internal conversion function for WIN1251 to WIN866', - proname => 'win1251_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4316', descr => 'internal conversion function for ISO-8859-5 to KOI8R', - proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_koi8r', + proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4317', descr => 'internal conversion function for KOI8R to ISO-8859-5', - proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_iso', + proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4318', descr => 'internal conversion function for ISO-8859-5 to WIN1251', - proname => 'iso_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win1251', + proname => 'iso_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4319', descr => 'internal conversion function for WIN1251 to ISO-8859-5', - proname => 'win1251_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_iso', + proname => 'win1251_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4320', descr => 'internal conversion function for ISO-8859-5 to WIN866', - proname => 'iso_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win866', + proname => 'iso_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4321', descr => 'internal conversion function for WIN866 to ISO-8859-5', - proname => 'win866_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_iso', + proname => 'win866_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4322', descr => 'internal conversion function for EUC_CN to MULE_INTERNAL', - proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_mic', + proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_mic', probin => '$libdir/euc_cn_and_mic' }, { oid => '4323', descr => 'internal conversion function for MULE_INTERNAL to EUC_CN', - proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_cn', + proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_cn', probin => '$libdir/euc_cn_and_mic' }, { oid => '4324', descr => 'internal conversion function for EUC_JP to SJIS', - proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_sjis', + proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4325', descr => 'internal conversion function for SJIS to EUC_JP', - proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_euc_jp', + proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4326', descr => 'internal conversion function for EUC_JP to MULE_INTERNAL', - proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_mic', + proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4327', descr => 'internal conversion function for SJIS to MULE_INTERNAL', - proname => 'sjis_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_mic', + proname => 'sjis_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4328', descr => 'internal conversion function for MULE_INTERNAL to EUC_JP', - proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_jp', + proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4329', descr => 'internal conversion function for MULE_INTERNAL to SJIS', - proname => 'mic_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_sjis', + proname => 'mic_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4330', descr => 'internal conversion function for EUC_KR to MULE_INTERNAL', - proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_mic', + proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_mic', probin => '$libdir/euc_kr_and_mic' }, { oid => '4331', descr => 'internal conversion function for MULE_INTERNAL to EUC_KR', - proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_kr', + proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_kr', probin => '$libdir/euc_kr_and_mic' }, { oid => '4332', descr => 'internal conversion function for EUC_TW to BIG5', - proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_big5', + proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4333', descr => 'internal conversion function for BIG5 to EUC_TW', - proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_euc_tw', + proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4334', descr => 'internal conversion function for EUC_TW to MULE_INTERNAL', - proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_mic', + proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4335', descr => 'internal conversion function for BIG5 to MULE_INTERNAL', - proname => 'big5_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_mic', + proname => 'big5_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4336', descr => 'internal conversion function for MULE_INTERNAL to EUC_TW', - proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_tw', + proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4337', descr => 'internal conversion function for MULE_INTERNAL to BIG5', - proname => 'mic_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_big5', + proname => 'mic_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4338', descr => 'internal conversion function for LATIN2 to MULE_INTERNAL', - proname => 'latin2_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin2_to_mic', + proname => 'latin2_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4339', descr => 'internal conversion function for MULE_INTERNAL to LATIN2', - proname => 'mic_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin2', + proname => 'mic_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4340', descr => 'internal conversion function for WIN1250 to MULE_INTERNAL', - proname => 'win1250_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1250_to_mic', + proname => 'win1250_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4341', descr => 'internal conversion function for MULE_INTERNAL to WIN1250', - proname => 'mic_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1250', + proname => 'mic_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4342', descr => 'internal conversion function for LATIN2 to WIN1250', - proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4343', descr => 'internal conversion function for WIN1250 to LATIN2', - proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4344', descr => 'internal conversion function for LATIN1 to MULE_INTERNAL', - proname => 'latin1_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin1_to_mic', + proname => 'latin1_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin1_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4345', descr => 'internal conversion function for MULE_INTERNAL to LATIN1', - proname => 'mic_to_latin1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin1', + proname => 'mic_to_latin1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin1', probin => '$libdir/latin_and_mic' }, { oid => '4346', descr => 'internal conversion function for LATIN3 to MULE_INTERNAL', - proname => 'latin3_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin3_to_mic', + proname => 'latin3_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin3_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4347', descr => 'internal conversion function for MULE_INTERNAL to LATIN3', - proname => 'mic_to_latin3', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin3', + proname => 'mic_to_latin3', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin3', probin => '$libdir/latin_and_mic' }, { oid => '4348', descr => 'internal conversion function for LATIN4 to MULE_INTERNAL', - proname => 'latin4_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin4_to_mic', + proname => 'latin4_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin4_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4349', descr => 'internal conversion function for MULE_INTERNAL to LATIN4', - proname => 'mic_to_latin4', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin4', + proname => 'mic_to_latin4', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin4', probin => '$libdir/latin_and_mic' }, { oid => '4352', descr => 'internal conversion function for BIG5 to UTF8', - proname => 'big5_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_utf8', + proname => 'big5_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_utf8', probin => '$libdir/utf8_and_big5' }, { oid => '4353', descr => 'internal conversion function for UTF8 to BIG5', - proname => 'utf8_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_big5', + proname => 'utf8_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_big5', probin => '$libdir/utf8_and_big5' }, { oid => '4354', descr => 'internal conversion function for UTF8 to KOI8R', - proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8r', + proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8r', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4355', descr => 'internal conversion function for KOI8R to UTF8', - proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_utf8', + proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4356', descr => 'internal conversion function for UTF8 to KOI8U', - proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8u', + proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8u', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4357', descr => 'internal conversion function for KOI8U to UTF8', - proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8u_to_utf8', + proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8u_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4358', descr => 'internal conversion function for UTF8 to WIN', - proname => 'utf8_to_win', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_win', + proname => 'utf8_to_win', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_win', probin => '$libdir/utf8_and_win' }, { oid => '4359', descr => 'internal conversion function for WIN to UTF8', - proname => 'win_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win_to_utf8', + proname => 'win_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win_to_utf8', probin => '$libdir/utf8_and_win' }, { oid => '4360', descr => 'internal conversion function for EUC_CN to UTF8', - proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_utf8', + proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_utf8', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4361', descr => 'internal conversion function for UTF8 to EUC_CN', - proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_cn', + proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_cn', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4362', descr => 'internal conversion function for EUC_JP to UTF8', - proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_utf8', + proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_utf8', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4363', descr => 'internal conversion function for UTF8 to EUC_JP', - proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_jp', + proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jp', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4364', descr => 'internal conversion function for EUC_KR to UTF8', - proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_utf8', + proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_utf8', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4365', descr => 'internal conversion function for UTF8 to EUC_KR', - proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_kr', + proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_kr', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4366', descr => 'internal conversion function for EUC_TW to UTF8', - proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_utf8', + proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_utf8', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4367', descr => 'internal conversion function for UTF8 to EUC_TW', - proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_tw', + proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_tw', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4368', descr => 'internal conversion function for GB18030 to UTF8', - proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gb18030_to_utf8', + proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gb18030_to_utf8', probin => '$libdir/utf8_and_gb18030' }, { oid => '4369', descr => 'internal conversion function for UTF8 to GB18030', - proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gb18030', + proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gb18030', probin => '$libdir/utf8_and_gb18030' }, { oid => '4370', descr => 'internal conversion function for GBK to UTF8', - proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gbk_to_utf8', + proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gbk_to_utf8', probin => '$libdir/utf8_and_gbk' }, { oid => '4371', descr => 'internal conversion function for UTF8 to GBK', - proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gbk', + proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gbk', probin => '$libdir/utf8_and_gbk' }, { oid => '4372', descr => 'internal conversion function for UTF8 to ISO-8859 2-16', - proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_iso8859', + proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859', probin => '$libdir/utf8_and_iso8859' }, { oid => '4373', descr => 'internal conversion function for ISO-8859 2-16 to UTF8', - proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso8859_to_utf8', + proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_to_utf8', probin => '$libdir/utf8_and_iso8859' }, { oid => '4374', descr => 'internal conversion function for LATIN1 to UTF8', - proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_1_to_utf8', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4375', descr => 'internal conversion function for UTF8 to LATIN1', - proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859_1', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4376', descr => 'internal conversion function for JOHAB to UTF8', - proname => 'johab_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'johab_to_utf8', + proname => 'johab_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'johab_to_utf8', probin => '$libdir/utf8_and_johab' }, { oid => '4377', descr => 'internal conversion function for UTF8 to JOHAB', - proname => 'utf8_to_johab', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_johab', + proname => 'utf8_to_johab', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_johab', probin => '$libdir/utf8_and_johab' }, { oid => '4378', descr => 'internal conversion function for SJIS to UTF8', - proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_utf8', + proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_utf8', probin => '$libdir/utf8_and_sjis' }, { oid => '4379', descr => 'internal conversion function for UTF8 to SJIS', - proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_sjis', + proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_sjis', probin => '$libdir/utf8_and_sjis' }, { oid => '4380', descr => 'internal conversion function for UHC to UTF8', - proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'uhc_to_utf8', + proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'uhc_to_utf8', probin => '$libdir/utf8_and_uhc' }, { oid => '4381', descr => 'internal conversion function for UTF8 to UHC', - proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_uhc', + proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_uhc', probin => '$libdir/utf8_and_uhc' }, { oid => '4382', descr => 'internal conversion function for EUC_JIS_2004 to UTF8', - proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_utf8', probin => '$libdir/utf8_and_euc2004' }, { oid => '4383', descr => 'internal conversion function for UTF8 to EUC_JIS_2004', - proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jis_2004', probin => '$libdir/utf8_and_euc2004' }, { oid => '4384', descr => 'internal conversion function for SHIFT_JIS_2004 to UTF8', - proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_utf8', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4385', descr => 'internal conversion function for UTF8 to SHIFT_JIS_2004', - proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_shift_jis_2004', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4386', descr => 'internal conversion function for EUC_JIS_2004 to SHIFT_JIS_2004', proname => 'euc_jis_2004_to_shift_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_shift_jis_2004', probin => '$libdir/euc2004_sjis2004' }, { oid => '4387', descr => 'internal conversion function for SHIFT_JIS_2004 to EUC_JIS_2004', proname => 'shift_jis_2004_to_euc_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_euc_jis_2004', probin => '$libdir/euc2004_sjis2004' }, diff --git a/src/include/mb/pg_wchar.h b/src/include/mb/pg_wchar.h index 64b22e4b0d4..346a41a1f3d 100644 --- a/src/include/mb/pg_wchar.h +++ b/src/include/mb/pg_wchar.h @@ -627,18 +627,18 @@ extern void pg_unicode_to_server(pg_wchar c, unsigned char *s); extern unsigned short BIG5toCNS(unsigned short big5, unsigned char *lc); extern unsigned short CNStoBIG5(unsigned short cns, unsigned char lc); -extern void UtfToLocal(const unsigned char *utf, int len, - unsigned char *iso, - const pg_mb_radix_tree *map, - const pg_utf_to_local_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); -extern void LocalToUtf(const unsigned char *iso, int len, - unsigned char *utf, - const pg_mb_radix_tree *map, - const pg_local_to_utf_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); +extern int UtfToLocal(const unsigned char *utf, int len, + unsigned char *iso, + const pg_mb_radix_tree *map, + const pg_utf_to_local_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); +extern int LocalToUtf(const unsigned char *iso, int len, + unsigned char *utf, + const pg_mb_radix_tree *map, + const pg_local_to_utf_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); extern bool pg_verifymbstr(const char *mbstr, int len, bool noError); extern bool pg_verify_mbstr(int encoding, const char *mbstr, int len, @@ -656,18 +656,19 @@ extern void report_invalid_encoding(int encoding, const char *mbstr, int len) pg extern void report_untranslatable_char(int src_encoding, int dest_encoding, const char *mbstr, int len) pg_attribute_noreturn(); -extern void local2local(const unsigned char *l, unsigned char *p, int len, - int src_encoding, int dest_encoding, const unsigned char *tab); -extern void latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding); -extern void mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding); -extern void latin2mic_with_table(const unsigned char *l, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); -extern void mic2latin_with_table(const unsigned char *mic, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); +extern int local2local(const unsigned char *l, unsigned char *p, int len, + int src_encoding, int dest_encoding, const unsigned char *tab, + bool noError); +extern int latin2mic(const unsigned char *l, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int mic2latin(const unsigned char *mic, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int latin2mic_with_table(const unsigned char *l, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); +extern int mic2latin_with_table(const unsigned char *mic, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); #ifdef WIN32 extern WCHAR *pgwin32_message_to_UTF16(const char *str, int len, int *utf16len); diff --git a/src/test/regress/expected/opr_sanity.out b/src/test/regress/expected/opr_sanity.out index 254ca06d3dd..23ba60e395f 100644 --- a/src/test/regress/expected/opr_sanity.out +++ b/src/test/regress/expected/opr_sanity.out @@ -1052,13 +1052,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); oid | proname | oid | conname -----+---------+-----+--------- (0 rows) diff --git a/src/test/regress/sql/opr_sanity.sql b/src/test/regress/sql/opr_sanity.sql index bbd3834b634..04691745981 100644 --- a/src/test/regress/sql/opr_sanity.sql +++ b/src/test/regress/sql/opr_sanity.sql @@ -556,13 +556,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); -- Check for conprocs that don't perform the specific conversion that -- pg_conversion alleges they do, by trying to invoke each conversion -- 2.29.2 --------------39E46EF15EBFAA37D53332E5 Content-Type: text/x-patch; charset=UTF-8; name="v3-0003-Add-tests-for-the-new-noError-variants-of-built-i.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="v3-0003-Add-tests-for-the-new-noError-variants-of-built-i.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 34+ messages in thread
* [PATCH v3 2/5] Change conversion function signature. @ 2021-01-28 16:42 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 34+ messages in thread From: Heikki Linnakangas @ 2021-01-28 16:42 UTC (permalink / raw) Add a 'noError' argument, so that we can try to convert a buffer without knowing the character boundaries beforehand. The functions now need to return the number of input bytes successfully converted. This is is a backwards-incompatible change, if you have created a custom encoding conversion with CREATE CONVERSION. This adds a check to pg_upgrade for that, refusing the upgrade if there are any user-defined encoding conversions. --- doc/src/sgml/ref/create_conversion.sgml | 5 +- src/backend/commands/conversioncmds.c | 27 +- src/backend/utils/error/elog.c | 2 + src/backend/utils/mb/conv.c | 112 +++++- .../cyrillic_and_mic/cyrillic_and_mic.c | 127 ++++--- .../euc2004_sjis2004/euc2004_sjis2004.c | 96 ++++- .../euc_cn_and_mic/euc_cn_and_mic.c | 57 ++- .../euc_jp_and_sjis/euc_jp_and_sjis.c | 153 ++++++-- .../euc_kr_and_mic/euc_kr_and_mic.c | 57 ++- .../euc_tw_and_big5/euc_tw_and_big5.c | 165 +++++++-- .../latin2_and_win1250/latin2_and_win1250.c | 49 ++- .../latin_and_mic/latin_and_mic.c | 43 ++- .../utf8_and_big5/utf8_and_big5.c | 37 +- .../utf8_and_cyrillic/utf8_and_cyrillic.c | 67 ++-- .../utf8_and_euc2004/utf8_and_euc2004.c | 37 +- .../utf8_and_euc_cn/utf8_and_euc_cn.c | 37 +- .../utf8_and_euc_jp/utf8_and_euc_jp.c | 37 +- .../utf8_and_euc_kr/utf8_and_euc_kr.c | 37 +- .../utf8_and_euc_tw/utf8_and_euc_tw.c | 37 +- .../utf8_and_gb18030/utf8_and_gb18030.c | 37 +- .../utf8_and_gbk/utf8_and_gbk.c | 37 +- .../utf8_and_iso8859/utf8_and_iso8859.c | 43 ++- .../utf8_and_iso8859_1/utf8_and_iso8859_1.c | 27 +- .../utf8_and_johab/utf8_and_johab.c | 37 +- .../utf8_and_sjis/utf8_and_sjis.c | 37 +- .../utf8_and_sjis2004/utf8_and_sjis2004.c | 37 +- .../utf8_and_uhc/utf8_and_uhc.c | 37 +- .../utf8_and_win/utf8_and_win.c | 43 ++- src/backend/utils/mb/mbutils.c | 18 +- src/bin/pg_upgrade/check.c | 95 +++++ src/include/catalog/pg_proc.dat | 332 +++++++++--------- src/include/mb/pg_wchar.h | 49 +-- src/test/regress/expected/opr_sanity.out | 7 +- src/test/regress/sql/opr_sanity.sql | 7 +- 34 files changed, 1390 insertions(+), 635 deletions(-) diff --git a/doc/src/sgml/ref/create_conversion.sgml b/doc/src/sgml/ref/create_conversion.sgml index e7700fecfc5..f014a676c88 100644 --- a/doc/src/sgml/ref/create_conversion.sgml +++ b/doc/src/sgml/ref/create_conversion.sgml @@ -117,8 +117,9 @@ conv_proc( integer, -- destination encoding ID cstring, -- source string (null terminated C string) internal, -- destination (fill with a null terminated C string) - integer -- source string length -) RETURNS void; + integer, -- source string length + boolean -- if true, don't throw an error if conversion fails +) RETURNS integer; </programlisting></para> </listitem> </varlistentry> diff --git a/src/backend/commands/conversioncmds.c b/src/backend/commands/conversioncmds.c index f7ff321de71..d2041466911 100644 --- a/src/backend/commands/conversioncmds.c +++ b/src/backend/commands/conversioncmds.c @@ -45,8 +45,9 @@ CreateConversionCommand(CreateConversionStmt *stmt) const char *from_encoding_name = stmt->for_encoding_name; const char *to_encoding_name = stmt->to_encoding_name; List *func_name = stmt->func_name; - static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID}; + static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID, BOOLOID}; char result[1]; + Datum funcresult; /* Convert list of names to a name and namespace */ namespaceId = QualifiedNameGetCreationNamespace(stmt->conversion_name, @@ -92,8 +93,8 @@ CreateConversionCommand(CreateConversionStmt *stmt) funcoid = LookupFuncName(func_name, sizeof(funcargs) / sizeof(Oid), funcargs, false); - /* Check it returns VOID, else it's probably the wrong function */ - if (get_func_rettype(funcoid) != VOIDOID) + /* Check it returns int4, else it's probably the wrong function */ + if (get_func_rettype(funcoid) != INT4OID) ereport(ERROR, (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), errmsg("encoding conversion function %s must return type %s", @@ -111,12 +112,20 @@ CreateConversionCommand(CreateConversionStmt *stmt) * string; the conversion function should throw an error if it can't * perform the requested conversion. */ - OidFunctionCall5(funcoid, - Int32GetDatum(from_encoding), - Int32GetDatum(to_encoding), - CStringGetDatum(""), - CStringGetDatum(result), - Int32GetDatum(0)); + funcresult = OidFunctionCall6(funcoid, + Int32GetDatum(from_encoding), + Int32GetDatum(to_encoding), + CStringGetDatum(""), + CStringGetDatum(result), + Int32GetDatum(0), + BoolGetDatum(false)); + + /* The function should return 0 for empty input. Might as well check that, too. */ + if (DatumGetInt32(funcresult) != 0) + ereport(ERROR, + (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), + errmsg("encoding conversion function %s returned incorrect result for empty input", + NameListToString(func_name)))); /* * All seem ok, go ahead (possible failure would be a duplicate conversion diff --git a/src/backend/utils/error/elog.c b/src/backend/utils/error/elog.c index 80c26724612..762f77d533c 100644 --- a/src/backend/utils/error/elog.c +++ b/src/backend/utils/error/elog.c @@ -2280,6 +2280,8 @@ write_console(const char *line, int len) * Conversion on non-win32 platforms is not implemented yet. It requires * non-throw version of pg_do_encoding_conversion(), that converts * unconvertable characters to '?' without errors. + * + * XXX: We have a no-throw version now. It doesn't convert to '?' though. */ #endif diff --git a/src/backend/utils/mb/conv.c b/src/backend/utils/mb/conv.c index a07b54bd3b8..b83358bc7a5 100644 --- a/src/backend/utils/mb/conv.c +++ b/src/backend/utils/mb/conv.c @@ -26,14 +26,16 @@ * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the target charset, or 0 if there is no equivalent code. */ -void +int local2local(const unsigned char *l, unsigned char *p, int len, int src_encoding, int dest_encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -41,7 +43,11 @@ local2local(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(src_encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -50,13 +56,19 @@ local2local(const unsigned char *l, if (c2) *p++ = c2; else + { + if (noError) + break; report_untranslatable_char(src_encoding, dest_encoding, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -67,17 +79,22 @@ local2local(const unsigned char *l, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = l; int c1; while (len > 0) { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (IS_HIGHBIT_SET(c1)) *p++ = lc; *p++ = c1; @@ -85,6 +102,8 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, len--; } *p = '\0'; + + return l - start; } /* @@ -95,17 +114,22 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -118,17 +142,27 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1])) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); + } *p++ = mic[1]; mic += 2; len -= 2; } } *p = '\0'; + + return mic - start; } @@ -144,14 +178,16 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the mule encoding, or 0 if there is no equivalent code. */ -void +int latin2mic_with_table(const unsigned char *l, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -159,7 +195,11 @@ latin2mic_with_table(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -171,13 +211,19 @@ latin2mic_with_table(const unsigned char *l, *p++ = c2; } else + { + if (noError) + break; report_untranslatable_char(encoding, PG_MULE_INTERNAL, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -192,14 +238,16 @@ latin2mic_with_table(const unsigned char *l, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the local charset, or 0 if there is no equivalent code. */ -void +int mic2latin_with_table(const unsigned char *mic, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = mic; unsigned char c1, c2; @@ -207,7 +255,11 @@ mic2latin_with_table(const unsigned char *mic, { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -220,11 +272,17 @@ mic2latin_with_table(const unsigned char *mic, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1]) || (c2 = tab[mic[1] - HIGHBIT]) == 0) { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); break; /* keep compiler quiet */ @@ -235,6 +293,8 @@ mic2latin_with_table(const unsigned char *mic, } } *p = '\0'; + + return mic - start; } /* @@ -425,17 +485,19 @@ pg_mb_radix_conv(const pg_mb_radix_tree *rt, * * See pg_wchar.h for more details about the data structures used here. */ -void +int UtfToLocal(const unsigned char *utf, int len, unsigned char *iso, const pg_mb_radix_tree *map, const pg_utf_to_local_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, bool noError) { uint32 iutf; int l; const pg_utf_to_local_combined *cp; + const unsigned char *start = utf; + const unsigned char *cur = utf; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -449,6 +511,8 @@ UtfToLocal(const unsigned char *utf, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*utf == '\0') break; @@ -584,15 +648,19 @@ UtfToLocal(const unsigned char *utf, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(PG_UTF8, encoding, (const char *) (utf - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(PG_UTF8, (const char *) utf, len); *iso = '\0'; + + return cur - start; } /* @@ -616,18 +684,24 @@ UtfToLocal(const unsigned char *utf, int len, * (if provided) is applied. An error is raised if no match is found. * * See pg_wchar.h for more details about the data structures used here. + * + * Returns the number of input bytes consumed. If noError is true, this can + * be less than 'len'. */ -void +int LocalToUtf(const unsigned char *iso, int len, unsigned char *utf, const pg_mb_radix_tree *map, const pg_local_to_utf_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, + bool noError) { uint32 iiso; int l; const pg_local_to_utf_combined *cp; + const unsigned char *start = iso; + const unsigned char *cur = iso; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -641,6 +715,8 @@ LocalToUtf(const unsigned char *iso, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*iso == '\0') break; @@ -723,13 +799,17 @@ LocalToUtf(const unsigned char *iso, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(encoding, PG_UTF8, (const char *) (iso - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(encoding, (const char *) iso, len); *utf = '\0'; + + return cur - start; } diff --git a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c index 4c5b02654de..368c2deb5e4 100644 --- a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c @@ -44,8 +44,11 @@ PG_FUNCTION_INFO_V1(win866_to_iso); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -306,12 +309,14 @@ koi8r_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -320,12 +325,14 @@ mic_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_KOI8R); - mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -334,12 +341,14 @@ iso_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -348,12 +357,14 @@ mic_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_ISO_8859_5); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -362,12 +373,14 @@ win1251_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -376,12 +389,14 @@ mic_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1251); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -390,12 +405,14 @@ win866_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -404,12 +421,14 @@ mic_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN866); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -418,12 +437,14 @@ koi8r_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN1251); - local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -432,12 +453,14 @@ win1251_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_KOI8R); - local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi); + converted = local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -446,12 +469,14 @@ koi8r_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN866); - local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -460,12 +485,14 @@ win866_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_KOI8R); - local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi); + converted = local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -474,12 +501,14 @@ win866_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_WIN1251); - local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251); + converted = local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -488,12 +517,14 @@ win1251_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_WIN866); - local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866); + converted = local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -502,12 +533,14 @@ iso_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_KOI8R); - local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -516,12 +549,14 @@ koi8r_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_ISO_8859_5); - local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso); + converted = local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -530,12 +565,14 @@ iso_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN1251); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -544,12 +581,14 @@ win1251_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso); + converted = local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -558,12 +597,14 @@ iso_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN866); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -572,10 +613,12 @@ win866_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso); + converted = local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c index 4d7fb116cfd..88529c644cf 100644 --- a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c @@ -19,8 +19,8 @@ PG_MODULE_MAGIC; PG_FUNCTION_INFO_V1(euc_jis_2004_to_shift_jis_2004); PG_FUNCTION_INFO_V1(shift_jis_2004_to_euc_jis_2004); -static void euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len); -static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len); +static int euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError); /* ---------- * conv_proc( @@ -28,8 +28,11 @@ static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -39,12 +42,14 @@ euc_jis_2004_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_SHIFT_JIS_2004); - euc_jis_20042shift_jis_2004(src, dest, len); + converted = euc_jis_20042shift_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -53,20 +58,23 @@ shift_jis_2004_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_EUC_JIS_2004); - shift_jis_20042euc_jis_2004(src, dest, len); + converted = shift_jis_20042euc_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_JIS_2004 -> SHIFT_JIS_2004 */ -static void -euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, ku, ten; @@ -79,8 +87,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -90,8 +102,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) l = pg_encoding_verifymbchar(PG_EUC_JIS_2004, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (c1 == SS2 && l == 2) /* JIS X 0201 kana? */ { @@ -121,8 +137,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) *p++ = (ku + 0x19b) >> 1; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } if (ku % 2) @@ -132,8 +152,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; @@ -149,8 +173,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ku >= 63 && ku <= 94) *p++ = (ku + 0x181) >> 1; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (ku % 2) { @@ -159,20 +187,30 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else - report_invalid_encoding(PG_EUC_JIS_2004, + { + if (noError) + break; + report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } euc += l; len -= l; } *p = '\0'; + + return euc - start; } /* @@ -212,9 +250,10 @@ get_ten(int b, int *ku) * SHIFT_JIS_2004 ---> EUC_JIS_2004 */ -static void -shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len) +static int +shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1; int ku, ten, @@ -230,8 +269,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -241,8 +284,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len l = pg_encoding_verifymbchar(PG_SHIFT_JIS_2004, (const char *) sjis, len); if (l < 0 || l > len) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf && l == 1) { @@ -266,8 +313,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x100; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xe0 && c1 <= 0xef) /* plane 1 62ku-94ku */ @@ -275,9 +326,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x180; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, - (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xf0 && c1 <= 0xf3) /* plane 2 @@ -286,8 +340,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } switch (c1) { case 0xf0: @@ -309,16 +367,24 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 == 0xf4 && kubun == 1) ku = 15; else ku = (c1 << 1) - 0x19a - kubun; } else + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (plane == 2) *p++ = SS3; @@ -330,4 +396,6 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c index e9bb896935f..a8da733803d 100644 --- a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_cn2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_cn(const unsigned char *mic, unsigned char *p, int len); +static int euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_cn_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_cn_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_MULE_INTERNAL); - euc_cn2mic(src, dest, len); + converted = euc_cn2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_CN); - mic2euc_cn(src, dest, len); + converted = mic2euc_cn(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_CN ---> MIC */ -static void -euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; while (len > 0) @@ -76,7 +84,11 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (len < 2 || !IS_HIGHBIT_SET(euc[1])) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = LC_GB2312_80; *p++ = c1; *p++ = euc[1]; @@ -86,21 +98,28 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_CN */ -static void -mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) @@ -109,11 +128,19 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (c1 != LC_GB2312_80) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_CN, (const char *) mic, len); + } if (len < 3 || !IS_HIGHBIT_SET(mic[1]) || !IS_HIGHBIT_SET(mic[2])) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } mic++; *p++ = *mic++; *p++ = *mic++; @@ -122,12 +149,18 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; } } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c index 5059f917a98..cc4817dc4cd 100644 --- a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c @@ -42,17 +42,20 @@ PG_FUNCTION_INFO_V1(mic_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void sjis2mic(const unsigned char *sjis, unsigned char *p, int len); -static void mic2sjis(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_jp(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len); -static void sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len); +static int sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError); +static int mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_jp_to_sjis(PG_FUNCTION_ARGS) @@ -60,12 +63,14 @@ euc_jp_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_SJIS); - euc_jp2sjis(src, dest, len); + converted = euc_jp2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -74,12 +79,14 @@ sjis_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_EUC_JP); - sjis2euc_jp(src, dest, len); + converted = sjis2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -88,12 +95,14 @@ euc_jp_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_MULE_INTERNAL); - euc_jp2mic(src, dest, len); + converted = euc_jp2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -102,12 +111,14 @@ mic_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_JP); - mic2euc_jp(src, dest, len); + converted = mic2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -116,12 +127,14 @@ sjis_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_MULE_INTERNAL); - sjis2mic(src, dest, len); + converted = sjis2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -130,20 +143,23 @@ mic_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_SJIS); - mic2sjis(src, dest, len); + converted = mic2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * SJIS ---> MIC */ -static void -sjis2mic(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -167,7 +183,11 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) * JIS X0208, X0212, user defined extended characters */ if (len < 2 || !ISSJISHEAD(c1) || !ISSJISTAIL(sjis[1])) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } c2 = sjis[1]; k = (c1 << 8) + c2; if (k >= 0xed40 && k < 0xf040) @@ -257,21 +277,28 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; } } *p = '\0'; + + return sjis - start; } /* * MIC ---> SJIS */ -static void -mic2sjis(const unsigned char *mic, unsigned char *p, int len) +static int +mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1, c2, k, @@ -284,8 +311,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -293,8 +324,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) *p++ = mic[1]; else if (c1 == LC_JISX0208) @@ -350,20 +385,27 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_SJIS, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP ---> MIC */ -static void -euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -374,8 +416,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -383,8 +429,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* 1 byte kana? */ *p++ = LC_JISX0201K; @@ -406,14 +456,17 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_JP */ -static void -mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -424,8 +477,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -433,8 +490,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) { *p++ = SS2; @@ -452,20 +513,27 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_JP, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP -> SJIS */ -static void -euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, c2, k; @@ -478,8 +546,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -487,8 +559,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* hankaku kana? */ @@ -551,14 +627,17 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * SJIS ---> EUC_JP */ -static void -sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -573,8 +652,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -582,8 +665,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_SJIS, (const char *) sjis, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf) { /* JIS X0201 (1 byte kana) */ @@ -680,4 +767,6 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c index ac823d6c270..a5b51617e52 100644 --- a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_kr2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_kr(const unsigned char *mic, unsigned char *p, int len); +static int euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_kr_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_kr_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_MULE_INTERNAL); - euc_kr2mic(src, dest, len); + converted = euc_kr2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_KR); - mic2euc_kr(src, dest, len); + converted = mic2euc_kr(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_KR ---> MIC */ -static void -euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -78,8 +86,12 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_KR, (const char *) euc, len); if (l != 2) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = LC_KS5601; *p++ = c1; *p++ = euc[1]; @@ -89,22 +101,29 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_KR */ -static void -mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -115,8 +134,12 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -124,18 +147,28 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_KS5601) { *p++ = mic[1]; *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_KR, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c index 66c242d7f36..ebb4e0acd53 100644 --- a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c @@ -32,17 +32,20 @@ PG_FUNCTION_INFO_V1(mic_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_tw2big5(const unsigned char *euc, unsigned char *p, int len); -static void big52euc_tw(const unsigned char *euc, unsigned char *p, int len); -static void big52mic(const unsigned char *big5, unsigned char *p, int len); -static void mic2big5(const unsigned char *mic, unsigned char *p, int len); -static void euc_tw2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_tw(const unsigned char *mic, unsigned char *p, int len); +static int euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52euc_tw(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError); +static int mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_tw_to_big5(PG_FUNCTION_ARGS) @@ -50,12 +53,14 @@ euc_tw_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_BIG5); - euc_tw2big5(src, dest, len); + converted = euc_tw2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -64,12 +69,14 @@ big5_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_EUC_TW); - big52euc_tw(src, dest, len); + converted = big52euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -78,12 +85,14 @@ euc_tw_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_MULE_INTERNAL); - euc_tw2mic(src, dest, len); + converted = euc_tw2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -92,12 +101,14 @@ mic_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_TW); - mic2euc_tw(src, dest, len); + converted = mic2euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -106,12 +117,14 @@ big5_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_MULE_INTERNAL); - big52mic(src, dest, len); + converted = big52mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -120,21 +133,24 @@ mic_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_BIG5); - mic2big5(src, dest, len); + converted = mic2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_TW ---> Big5 */ -static void -euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; unsigned char c1; unsigned short big5buf, cnsBuf; @@ -149,8 +165,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Verify and decode the next EUC_TW input character */ l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -171,8 +191,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Write it out in Big5 */ big5buf = CNStoBIG5(cnsBuf, lc); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_EUC_TW, PG_BIG5, (const char *) euc, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; @@ -182,22 +206,29 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * Big5 ---> EUC_TW */ -static void -big52euc_tw(const unsigned char *big5, unsigned char *p, int len) +static int +big52euc_tw(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -212,8 +243,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); @@ -237,8 +272,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_EUC_TW, (const char *) big5, len); + } big5 += l; len -= l; @@ -256,14 +295,17 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) } } *p = '\0'; + + return big5 - start; } /* * EUC_TW ---> MIC */ -static void -euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -274,8 +316,12 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -304,22 +350,29 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_TW */ -static void -mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -330,8 +383,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -339,8 +396,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1) { *p++ = mic[1]; @@ -362,20 +423,27 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[3]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_TW, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * Big5 ---> MIC */ -static void -big52mic(const unsigned char *big5, unsigned char *p, int len) +static int +big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -389,8 +457,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } *p++ = c1; big5++; len--; @@ -398,8 +470,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); if (lc != 0) @@ -412,20 +488,27 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_MULE_INTERNAL, (const char *) big5, len); + } big5 += l; len -= l; } *p = '\0'; + + return big5 - start; } /* * MIC ---> Big5 */ -static void -mic2big5(const unsigned char *mic, unsigned char *p, int len) +static int +mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -438,8 +521,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -447,8 +534,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1 || c1 == LC_CNS11643_2 || c1 == LCPRV2_B) { if (c1 == LCPRV2_B) @@ -462,16 +553,26 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } big5buf = CNStoBIG5(cnsBuf, c1); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c index 2e28e6780a5..8610fcb69aa 100644 --- a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c +++ b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(win1250_to_latin2); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -82,12 +85,14 @@ latin2_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -96,12 +101,14 @@ mic_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN2); - mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -110,13 +117,15 @@ win1250_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - win1250_2_iso88592); + converted = latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -125,13 +134,15 @@ mic_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1250); - mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - iso88592_2_win1250); + converted = mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -140,12 +151,15 @@ latin2_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_WIN1250); - local2local(src, dest, len, PG_LATIN2, PG_WIN1250, iso88592_2_win1250); + converted = local2local(src, dest, len, PG_LATIN2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -154,10 +168,13 @@ win1250_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_LATIN2); - local2local(src, dest, len, PG_WIN1250, PG_LATIN2, win1250_2_iso88592); + converted = local2local(src, dest, len, PG_WIN1250, PG_LATIN2, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c index bc651410f21..bff27d1c295 100644 --- a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(mic_to_latin4); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -42,12 +45,14 @@ latin1_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,12 +61,14 @@ mic_to_latin1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN1); - mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -70,12 +77,14 @@ latin3_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN3, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -84,12 +93,14 @@ mic_to_latin3(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN3); - mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,12 +109,14 @@ latin4_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN4, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -112,10 +125,12 @@ mic_to_latin4(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN4); - mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c index d6067cdc24e..3838b15cab9 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ big5_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_UTF8); - LocalToUtf(src, len, dest, - &big5_to_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = LocalToUtf(src, len, dest, + &big5_to_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_BIG5); - UtfToLocal(src, len, dest, - &big5_from_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = UtfToLocal(src, len, dest, + &big5_from_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c index ed90e8e682e..75719fe5f1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c @@ -33,8 +33,11 @@ PG_FUNCTION_INFO_V1(koi8u_to_utf8); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -44,16 +47,19 @@ utf8_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8R); - UtfToLocal(src, len, dest, - &koi8r_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = UtfToLocal(src, len, dest, + &koi8r_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -62,16 +68,19 @@ koi8r_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8r_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = LocalToUtf(src, len, dest, + &koi8r_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -80,16 +89,19 @@ utf8_to_koi8u(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8U); - UtfToLocal(src, len, dest, - &koi8u_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = UtfToLocal(src, len, dest, + &koi8u_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,14 +110,17 @@ koi8u_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8U, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8u_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = LocalToUtf(src, len, dest, + &koi8u_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c index d699affce47..5391001951a 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jis_2004_to_unicode_tree, - LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = LocalToUtf(src, len, dest, + &euc_jis_2004_to_unicode_tree, + LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JIS_2004); - UtfToLocal(src, len, dest, - &euc_jis_2004_from_unicode_tree, - ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = UtfToLocal(src, len, dest, + &euc_jis_2004_from_unicode_tree, + ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c index d7c0ba6a58b..c87d1bf2398 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_cn_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_cn_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = LocalToUtf(src, len, dest, + &euc_cn_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_CN); - UtfToLocal(src, len, dest, - &euc_cn_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = UtfToLocal(src, len, dest, + &euc_cn_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c index 13a3a23e77b..6a55134db21 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jp); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jp_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jp_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = LocalToUtf(src, len, dest, + &euc_jp_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JP); - UtfToLocal(src, len, dest, - &euc_jp_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = UtfToLocal(src, len, dest, + &euc_jp_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c index 1bbb8aaef7b..fe1924e2fec 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_kr_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_kr_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = LocalToUtf(src, len, dest, + &euc_kr_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_KR); - UtfToLocal(src, len, dest, - &euc_kr_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = UtfToLocal(src, len, dest, + &euc_kr_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c index 9830045dccd..68215659b57 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_tw); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_tw_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_tw_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = LocalToUtf(src, len, dest, + &euc_tw_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_TW); - UtfToLocal(src, len, dest, - &euc_tw_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = UtfToLocal(src, len, dest, + &euc_tw_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c index f86ecf27424..e1a59c39a4d 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c @@ -183,8 +183,11 @@ conv_utf8_to_18030(uint32 code) * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -193,16 +196,19 @@ gb18030_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GB18030, PG_UTF8); - LocalToUtf(src, len, dest, - &gb18030_to_unicode_tree, - NULL, 0, - conv_18030_to_utf8, - PG_GB18030); + converted = LocalToUtf(src, len, dest, + &gb18030_to_unicode_tree, + NULL, 0, + conv_18030_to_utf8, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -211,14 +217,17 @@ utf8_to_gb18030(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GB18030); - UtfToLocal(src, len, dest, - &gb18030_from_unicode_tree, - NULL, 0, - conv_utf8_to_18030, - PG_GB18030); + converted = UtfToLocal(src, len, dest, + &gb18030_from_unicode_tree, + NULL, 0, + conv_utf8_to_18030, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c index 2ab8b16c8a8..881386d5347 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_gbk); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ gbk_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GBK, PG_UTF8); - LocalToUtf(src, len, dest, - &gbk_to_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = LocalToUtf(src, len, dest, + &gbk_to_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_gbk(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GBK); - UtfToLocal(src, len, dest, - &gbk_from_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = UtfToLocal(src, len, dest, + &gbk_from_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c index 3e49f67ea2f..d93a521badf 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c @@ -52,8 +52,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -100,6 +103,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -108,12 +112,15 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -122,7 +129,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -132,6 +139,7 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -140,12 +148,15 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -154,5 +165,5 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c index 67e713cca11..8ac93604a1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c @@ -26,8 +26,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859_1); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -37,6 +40,8 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_UTF8); @@ -45,7 +50,11 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_LATIN1, (const char *) src, len); + } if (!IS_HIGHBIT_SET(c)) *dest++ = c; else @@ -58,7 +67,7 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } Datum @@ -67,6 +76,8 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c, c1; @@ -76,7 +87,11 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_UTF8, (const char *) src, len); + } /* fast path for ASCII-subset characters */ if (!IS_HIGHBIT_SET(c)) { @@ -102,11 +117,15 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) len -= 2; } else + { + if (noError) + break; report_untranslatable_char(PG_UTF8, PG_LATIN1, (const char *) src, len); + } } } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c index 578f5df4e7f..317daa2d5ee 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_johab); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ johab_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_JOHAB, PG_UTF8); - LocalToUtf(src, len, dest, - &johab_to_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = LocalToUtf(src, len, dest, + &johab_to_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_johab(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_JOHAB); - UtfToLocal(src, len, dest, - &johab_from_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = UtfToLocal(src, len, dest, + &johab_from_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c index dd9fc2975ad..4c9348aba59 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ sjis_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_UTF8); - LocalToUtf(src, len, dest, - &sjis_to_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = LocalToUtf(src, len, dest, + &sjis_to_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SJIS); - UtfToLocal(src, len, dest, - &sjis_from_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = UtfToLocal(src, len, dest, + &sjis_from_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c index 4bcc886d674..1fffdc5930c 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_shift_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ shift_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &shift_jis_2004_to_unicode_tree, - LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = LocalToUtf(src, len, dest, + &shift_jis_2004_to_unicode_tree, + LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SHIFT_JIS_2004); - UtfToLocal(src, len, dest, - &shift_jis_2004_from_unicode_tree, - ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = UtfToLocal(src, len, dest, + &shift_jis_2004_from_unicode_tree, + ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c index c8e512994a1..d9471dad097 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_uhc); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ uhc_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UHC, PG_UTF8); - LocalToUtf(src, len, dest, - &uhc_to_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = LocalToUtf(src, len, dest, + &uhc_to_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_uhc(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_UHC); - UtfToLocal(src, len, dest, - &uhc_from_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = UtfToLocal(src, len, dest, + &uhc_from_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c index 0c9493dee56..110ba5677d0 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c @@ -48,8 +48,11 @@ PG_FUNCTION_INFO_V1(utf8_to_win); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -81,6 +84,7 @@ win_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -89,12 +93,15 @@ win_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -103,7 +110,7 @@ win_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -113,6 +120,7 @@ utf8_to_win(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -121,12 +129,15 @@ utf8_to_win(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -135,5 +146,5 @@ utf8_to_win(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/mbutils.c b/src/backend/utils/mb/mbutils.c index 2578573b0ab..65753860e35 100644 --- a/src/backend/utils/mb/mbutils.c +++ b/src/backend/utils/mb/mbutils.c @@ -406,12 +406,13 @@ pg_do_encoding_conversion(unsigned char *src, int len, MemoryContextAllocHuge(CurrentMemoryContext, (Size) len * MAX_CONVERSION_GROWTH + 1); - OidFunctionCall5(proc, - Int32GetDatum(src_encoding), - Int32GetDatum(dest_encoding), - CStringGetDatum(src), - CStringGetDatum(result), - Int32GetDatum(len)); + (void) OidFunctionCall6(proc, + Int32GetDatum(src_encoding), + Int32GetDatum(dest_encoding), + CStringGetDatum(src), + CStringGetDatum(result), + Int32GetDatum(len), + BoolGetDatum(false)); /* * If the result is large, it's worth repalloc'ing to release any extra @@ -849,12 +850,13 @@ pg_unicode_to_server(pg_wchar c, unsigned char *s) c_as_utf8[c_as_utf8_len] = '\0'; /* Convert, or throw error if we can't */ - FunctionCall5(Utf8ToServerConvProc, + FunctionCall6(Utf8ToServerConvProc, Int32GetDatum(PG_UTF8), Int32GetDatum(server_encoding), CStringGetDatum(c_as_utf8), CStringGetDatum(s), - Int32GetDatum(c_as_utf8_len)); + Int32GetDatum(c_as_utf8_len), + BoolGetDatum(false)); } diff --git a/src/bin/pg_upgrade/check.c b/src/bin/pg_upgrade/check.c index 43fc297eb69..ee6be95b08d 100644 --- a/src/bin/pg_upgrade/check.c +++ b/src/bin/pg_upgrade/check.c @@ -28,6 +28,7 @@ static void check_for_reg_data_type_usage(ClusterInfo *cluster); static void check_for_jsonb_9_4_usage(ClusterInfo *cluster); static void check_for_pg_role_prefix(ClusterInfo *cluster); static void check_for_new_tablespace_dir(ClusterInfo *new_cluster); +static void check_for_user_defined_encoding_conversions(ClusterInfo *cluster); static char *get_canonical_locale_name(int category, const char *locale); @@ -102,6 +103,15 @@ check_and_dump_old_cluster(bool live_check) check_for_reg_data_type_usage(&old_cluster); check_for_isn_and_int8_passing_mismatch(&old_cluster); + /* + * PG 14 changed the function signature of encoding conversion functions. + * Conversions from older versions cannot be upgraded automatically + * because the user-defined functions used by the encoding conversions + * need to changed to match the new signature. + */ + if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1300) + check_for_user_defined_encoding_conversions(&old_cluster); + /* * Pre-PG 14 allowed user defined postfix operators, which are not * supported anymore. Verify there are none, iff applicable. @@ -1268,6 +1278,91 @@ check_for_pg_role_prefix(ClusterInfo *cluster) check_ok(); } +/* + * Verify that no user-defined encoding conversions exist. + */ +static void +check_for_user_defined_encoding_conversions(ClusterInfo *cluster) +{ + int dbnum; + FILE *script = NULL; + bool found = false; + char output_path[MAXPGPATH]; + + prep_status("Checking for user-defined encoding conversions"); + + snprintf(output_path, sizeof(output_path), + "encoding_conversions.txt"); + + /* Find any user defined encoding conversions */ + for (dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++) + { + PGresult *res; + bool db_used = false; + int ntups; + int rowno; + int i_conoid, + i_conname, + i_nspname; + DbInfo *active_db = &cluster->dbarr.dbs[dbnum]; + PGconn *conn = connectToServer(cluster, active_db->db_name); + + /* + * The query below hardcodes FirstNormalObjectId as 16384 rather than + * interpolating that C #define into the query because, if that + * #define is ever changed, the cutoff we want to use is the value + * used by pre-version 14 servers, not that of some future version. + */ + res = executeQueryOrDie(conn, + "SELECT c.oid as conoid, c.conname, n.nspname " + "FROM pg_catalog.pg_conversion c, " + " pg_catalog.pg_namespace n " + "WHERE c.connamespace = n.oid AND " + " c.oid >= 16384"); + ntups = PQntuples(res); + i_conoid = PQfnumber(res, "conoid"); + i_conname = PQfnumber(res, "conname"); + i_nspname = PQfnumber(res, "nspname"); + for (rowno = 0; rowno < ntups; rowno++) + { + found = true; + if (script == NULL && + (script = fopen_priv(output_path, "w")) == NULL) + pg_fatal("could not open file \"%s\": %s\n", + output_path, strerror(errno)); + if (!db_used) + { + fprintf(script, "In database: %s\n", active_db->db_name); + db_used = true; + } + fprintf(script, " (oid=%s) %s.%s\n", + PQgetvalue(res, rowno, i_conoid), + PQgetvalue(res, rowno, i_nspname), + PQgetvalue(res, rowno, i_conname)); + } + + PQclear(res); + + PQfinish(conn); + } + + if (script) + fclose(script); + + if (found) + { + pg_log(PG_REPORT, "fatal\n"); + pg_fatal("Your installation contains user-defined encoding conversions.\n" + "The conversion function parameters changed in PostgreSQL version 14\n" + "so this cluster cannot currently be upgraded. You can remove the\n" + "encoding conversions in the old cluster and restart the upgrade.\n" + "A list of user-defined encoding conversions is in the file:\n" + " %s\n\n", output_path); + } + else + check_ok(); +} + /* * get_canonical_locale_name diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index f8174061ef3..75b829e8514 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10766,388 +10766,388 @@ # conversion functions { oid => '4302', descr => 'internal conversion function for KOI8R to MULE_INTERNAL', - proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_mic', + proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4303', descr => 'internal conversion function for MULE_INTERNAL to KOI8R', - proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_koi8r', + proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4304', descr => 'internal conversion function for ISO-8859-5 to MULE_INTERNAL', - proname => 'iso_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_mic', + proname => 'iso_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4305', descr => 'internal conversion function for MULE_INTERNAL to ISO-8859-5', - proname => 'mic_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_iso', + proname => 'mic_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4306', descr => 'internal conversion function for WIN1251 to MULE_INTERNAL', - proname => 'win1251_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_mic', + proname => 'win1251_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4307', descr => 'internal conversion function for MULE_INTERNAL to WIN1251', - proname => 'mic_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1251', + proname => 'mic_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4308', descr => 'internal conversion function for WIN866 to MULE_INTERNAL', - proname => 'win866_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_mic', + proname => 'win866_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4309', descr => 'internal conversion function for MULE_INTERNAL to WIN866', - proname => 'mic_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win866', + proname => 'mic_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4310', descr => 'internal conversion function for KOI8R to WIN1251', - proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4311', descr => 'internal conversion function for WIN1251 to KOI8R', - proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4312', descr => 'internal conversion function for KOI8R to WIN866', - proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_win866', + proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4313', descr => 'internal conversion function for WIN866 to KOI8R', - proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_koi8r', + proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4314', descr => 'internal conversion function for WIN866 to WIN1251', - proname => 'win866_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win866_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4315', descr => 'internal conversion function for WIN1251 to WIN866', - proname => 'win1251_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4316', descr => 'internal conversion function for ISO-8859-5 to KOI8R', - proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_koi8r', + proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4317', descr => 'internal conversion function for KOI8R to ISO-8859-5', - proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_iso', + proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4318', descr => 'internal conversion function for ISO-8859-5 to WIN1251', - proname => 'iso_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win1251', + proname => 'iso_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4319', descr => 'internal conversion function for WIN1251 to ISO-8859-5', - proname => 'win1251_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_iso', + proname => 'win1251_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4320', descr => 'internal conversion function for ISO-8859-5 to WIN866', - proname => 'iso_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win866', + proname => 'iso_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4321', descr => 'internal conversion function for WIN866 to ISO-8859-5', - proname => 'win866_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_iso', + proname => 'win866_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4322', descr => 'internal conversion function for EUC_CN to MULE_INTERNAL', - proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_mic', + proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_mic', probin => '$libdir/euc_cn_and_mic' }, { oid => '4323', descr => 'internal conversion function for MULE_INTERNAL to EUC_CN', - proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_cn', + proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_cn', probin => '$libdir/euc_cn_and_mic' }, { oid => '4324', descr => 'internal conversion function for EUC_JP to SJIS', - proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_sjis', + proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4325', descr => 'internal conversion function for SJIS to EUC_JP', - proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_euc_jp', + proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4326', descr => 'internal conversion function for EUC_JP to MULE_INTERNAL', - proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_mic', + proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4327', descr => 'internal conversion function for SJIS to MULE_INTERNAL', - proname => 'sjis_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_mic', + proname => 'sjis_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4328', descr => 'internal conversion function for MULE_INTERNAL to EUC_JP', - proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_jp', + proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4329', descr => 'internal conversion function for MULE_INTERNAL to SJIS', - proname => 'mic_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_sjis', + proname => 'mic_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4330', descr => 'internal conversion function for EUC_KR to MULE_INTERNAL', - proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_mic', + proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_mic', probin => '$libdir/euc_kr_and_mic' }, { oid => '4331', descr => 'internal conversion function for MULE_INTERNAL to EUC_KR', - proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_kr', + proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_kr', probin => '$libdir/euc_kr_and_mic' }, { oid => '4332', descr => 'internal conversion function for EUC_TW to BIG5', - proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_big5', + proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4333', descr => 'internal conversion function for BIG5 to EUC_TW', - proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_euc_tw', + proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4334', descr => 'internal conversion function for EUC_TW to MULE_INTERNAL', - proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_mic', + proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4335', descr => 'internal conversion function for BIG5 to MULE_INTERNAL', - proname => 'big5_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_mic', + proname => 'big5_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4336', descr => 'internal conversion function for MULE_INTERNAL to EUC_TW', - proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_tw', + proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4337', descr => 'internal conversion function for MULE_INTERNAL to BIG5', - proname => 'mic_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_big5', + proname => 'mic_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4338', descr => 'internal conversion function for LATIN2 to MULE_INTERNAL', - proname => 'latin2_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin2_to_mic', + proname => 'latin2_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4339', descr => 'internal conversion function for MULE_INTERNAL to LATIN2', - proname => 'mic_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin2', + proname => 'mic_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4340', descr => 'internal conversion function for WIN1250 to MULE_INTERNAL', - proname => 'win1250_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1250_to_mic', + proname => 'win1250_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4341', descr => 'internal conversion function for MULE_INTERNAL to WIN1250', - proname => 'mic_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1250', + proname => 'mic_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4342', descr => 'internal conversion function for LATIN2 to WIN1250', - proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4343', descr => 'internal conversion function for WIN1250 to LATIN2', - proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4344', descr => 'internal conversion function for LATIN1 to MULE_INTERNAL', - proname => 'latin1_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin1_to_mic', + proname => 'latin1_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin1_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4345', descr => 'internal conversion function for MULE_INTERNAL to LATIN1', - proname => 'mic_to_latin1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin1', + proname => 'mic_to_latin1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin1', probin => '$libdir/latin_and_mic' }, { oid => '4346', descr => 'internal conversion function for LATIN3 to MULE_INTERNAL', - proname => 'latin3_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin3_to_mic', + proname => 'latin3_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin3_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4347', descr => 'internal conversion function for MULE_INTERNAL to LATIN3', - proname => 'mic_to_latin3', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin3', + proname => 'mic_to_latin3', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin3', probin => '$libdir/latin_and_mic' }, { oid => '4348', descr => 'internal conversion function for LATIN4 to MULE_INTERNAL', - proname => 'latin4_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin4_to_mic', + proname => 'latin4_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin4_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4349', descr => 'internal conversion function for MULE_INTERNAL to LATIN4', - proname => 'mic_to_latin4', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin4', + proname => 'mic_to_latin4', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin4', probin => '$libdir/latin_and_mic' }, { oid => '4352', descr => 'internal conversion function for BIG5 to UTF8', - proname => 'big5_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_utf8', + proname => 'big5_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_utf8', probin => '$libdir/utf8_and_big5' }, { oid => '4353', descr => 'internal conversion function for UTF8 to BIG5', - proname => 'utf8_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_big5', + proname => 'utf8_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_big5', probin => '$libdir/utf8_and_big5' }, { oid => '4354', descr => 'internal conversion function for UTF8 to KOI8R', - proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8r', + proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8r', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4355', descr => 'internal conversion function for KOI8R to UTF8', - proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_utf8', + proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4356', descr => 'internal conversion function for UTF8 to KOI8U', - proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8u', + proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8u', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4357', descr => 'internal conversion function for KOI8U to UTF8', - proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8u_to_utf8', + proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8u_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4358', descr => 'internal conversion function for UTF8 to WIN', - proname => 'utf8_to_win', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_win', + proname => 'utf8_to_win', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_win', probin => '$libdir/utf8_and_win' }, { oid => '4359', descr => 'internal conversion function for WIN to UTF8', - proname => 'win_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win_to_utf8', + proname => 'win_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win_to_utf8', probin => '$libdir/utf8_and_win' }, { oid => '4360', descr => 'internal conversion function for EUC_CN to UTF8', - proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_utf8', + proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_utf8', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4361', descr => 'internal conversion function for UTF8 to EUC_CN', - proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_cn', + proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_cn', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4362', descr => 'internal conversion function for EUC_JP to UTF8', - proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_utf8', + proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_utf8', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4363', descr => 'internal conversion function for UTF8 to EUC_JP', - proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_jp', + proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jp', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4364', descr => 'internal conversion function for EUC_KR to UTF8', - proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_utf8', + proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_utf8', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4365', descr => 'internal conversion function for UTF8 to EUC_KR', - proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_kr', + proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_kr', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4366', descr => 'internal conversion function for EUC_TW to UTF8', - proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_utf8', + proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_utf8', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4367', descr => 'internal conversion function for UTF8 to EUC_TW', - proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_tw', + proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_tw', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4368', descr => 'internal conversion function for GB18030 to UTF8', - proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gb18030_to_utf8', + proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gb18030_to_utf8', probin => '$libdir/utf8_and_gb18030' }, { oid => '4369', descr => 'internal conversion function for UTF8 to GB18030', - proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gb18030', + proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gb18030', probin => '$libdir/utf8_and_gb18030' }, { oid => '4370', descr => 'internal conversion function for GBK to UTF8', - proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gbk_to_utf8', + proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gbk_to_utf8', probin => '$libdir/utf8_and_gbk' }, { oid => '4371', descr => 'internal conversion function for UTF8 to GBK', - proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gbk', + proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gbk', probin => '$libdir/utf8_and_gbk' }, { oid => '4372', descr => 'internal conversion function for UTF8 to ISO-8859 2-16', - proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_iso8859', + proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859', probin => '$libdir/utf8_and_iso8859' }, { oid => '4373', descr => 'internal conversion function for ISO-8859 2-16 to UTF8', - proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso8859_to_utf8', + proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_to_utf8', probin => '$libdir/utf8_and_iso8859' }, { oid => '4374', descr => 'internal conversion function for LATIN1 to UTF8', - proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_1_to_utf8', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4375', descr => 'internal conversion function for UTF8 to LATIN1', - proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859_1', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4376', descr => 'internal conversion function for JOHAB to UTF8', - proname => 'johab_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'johab_to_utf8', + proname => 'johab_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'johab_to_utf8', probin => '$libdir/utf8_and_johab' }, { oid => '4377', descr => 'internal conversion function for UTF8 to JOHAB', - proname => 'utf8_to_johab', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_johab', + proname => 'utf8_to_johab', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_johab', probin => '$libdir/utf8_and_johab' }, { oid => '4378', descr => 'internal conversion function for SJIS to UTF8', - proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_utf8', + proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_utf8', probin => '$libdir/utf8_and_sjis' }, { oid => '4379', descr => 'internal conversion function for UTF8 to SJIS', - proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_sjis', + proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_sjis', probin => '$libdir/utf8_and_sjis' }, { oid => '4380', descr => 'internal conversion function for UHC to UTF8', - proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'uhc_to_utf8', + proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'uhc_to_utf8', probin => '$libdir/utf8_and_uhc' }, { oid => '4381', descr => 'internal conversion function for UTF8 to UHC', - proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_uhc', + proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_uhc', probin => '$libdir/utf8_and_uhc' }, { oid => '4382', descr => 'internal conversion function for EUC_JIS_2004 to UTF8', - proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_utf8', probin => '$libdir/utf8_and_euc2004' }, { oid => '4383', descr => 'internal conversion function for UTF8 to EUC_JIS_2004', - proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jis_2004', probin => '$libdir/utf8_and_euc2004' }, { oid => '4384', descr => 'internal conversion function for SHIFT_JIS_2004 to UTF8', - proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_utf8', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4385', descr => 'internal conversion function for UTF8 to SHIFT_JIS_2004', - proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_shift_jis_2004', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4386', descr => 'internal conversion function for EUC_JIS_2004 to SHIFT_JIS_2004', proname => 'euc_jis_2004_to_shift_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_shift_jis_2004', probin => '$libdir/euc2004_sjis2004' }, { oid => '4387', descr => 'internal conversion function for SHIFT_JIS_2004 to EUC_JIS_2004', proname => 'shift_jis_2004_to_euc_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_euc_jis_2004', probin => '$libdir/euc2004_sjis2004' }, diff --git a/src/include/mb/pg_wchar.h b/src/include/mb/pg_wchar.h index 64b22e4b0d4..346a41a1f3d 100644 --- a/src/include/mb/pg_wchar.h +++ b/src/include/mb/pg_wchar.h @@ -627,18 +627,18 @@ extern void pg_unicode_to_server(pg_wchar c, unsigned char *s); extern unsigned short BIG5toCNS(unsigned short big5, unsigned char *lc); extern unsigned short CNStoBIG5(unsigned short cns, unsigned char lc); -extern void UtfToLocal(const unsigned char *utf, int len, - unsigned char *iso, - const pg_mb_radix_tree *map, - const pg_utf_to_local_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); -extern void LocalToUtf(const unsigned char *iso, int len, - unsigned char *utf, - const pg_mb_radix_tree *map, - const pg_local_to_utf_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); +extern int UtfToLocal(const unsigned char *utf, int len, + unsigned char *iso, + const pg_mb_radix_tree *map, + const pg_utf_to_local_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); +extern int LocalToUtf(const unsigned char *iso, int len, + unsigned char *utf, + const pg_mb_radix_tree *map, + const pg_local_to_utf_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); extern bool pg_verifymbstr(const char *mbstr, int len, bool noError); extern bool pg_verify_mbstr(int encoding, const char *mbstr, int len, @@ -656,18 +656,19 @@ extern void report_invalid_encoding(int encoding, const char *mbstr, int len) pg extern void report_untranslatable_char(int src_encoding, int dest_encoding, const char *mbstr, int len) pg_attribute_noreturn(); -extern void local2local(const unsigned char *l, unsigned char *p, int len, - int src_encoding, int dest_encoding, const unsigned char *tab); -extern void latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding); -extern void mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding); -extern void latin2mic_with_table(const unsigned char *l, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); -extern void mic2latin_with_table(const unsigned char *mic, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); +extern int local2local(const unsigned char *l, unsigned char *p, int len, + int src_encoding, int dest_encoding, const unsigned char *tab, + bool noError); +extern int latin2mic(const unsigned char *l, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int mic2latin(const unsigned char *mic, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int latin2mic_with_table(const unsigned char *l, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); +extern int mic2latin_with_table(const unsigned char *mic, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); #ifdef WIN32 extern WCHAR *pgwin32_message_to_UTF16(const char *str, int len, int *utf16len); diff --git a/src/test/regress/expected/opr_sanity.out b/src/test/regress/expected/opr_sanity.out index 254ca06d3dd..23ba60e395f 100644 --- a/src/test/regress/expected/opr_sanity.out +++ b/src/test/regress/expected/opr_sanity.out @@ -1052,13 +1052,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); oid | proname | oid | conname -----+---------+-----+--------- (0 rows) diff --git a/src/test/regress/sql/opr_sanity.sql b/src/test/regress/sql/opr_sanity.sql index bbd3834b634..04691745981 100644 --- a/src/test/regress/sql/opr_sanity.sql +++ b/src/test/regress/sql/opr_sanity.sql @@ -556,13 +556,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); -- Check for conprocs that don't perform the specific conversion that -- pg_conversion alleges they do, by trying to invoke each conversion -- 2.29.2 --------------39E46EF15EBFAA37D53332E5 Content-Type: text/x-patch; charset=UTF-8; name="v3-0003-Add-tests-for-the-new-noError-variants-of-built-i.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="v3-0003-Add-tests-for-the-new-noError-variants-of-built-i.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 34+ messages in thread
* [PATCH v2 1/2] Change conversion function signature. @ 2021-01-28 16:42 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 34+ messages in thread From: Heikki Linnakangas @ 2021-01-28 16:42 UTC (permalink / raw) Add a 'noError' argument, so that we can try to convert a buffer without knowing the character boundaries beforehand. The functions now need to return the number of input bytes successfully converted. This is is a backwards-incompatible change, if you have created a custom encoding conversion with CREATE CONVERSION. This adds a check to pg_upgrade for that, refusing the upgrade if there are any user-defined encoding conversions. --- doc/src/sgml/ref/create_conversion.sgml | 5 +- src/backend/commands/conversioncmds.c | 27 +- src/backend/utils/error/elog.c | 2 + src/backend/utils/mb/conv.c | 112 +++++- .../cyrillic_and_mic/cyrillic_and_mic.c | 127 ++++--- .../euc2004_sjis2004/euc2004_sjis2004.c | 96 ++++- .../euc_cn_and_mic/euc_cn_and_mic.c | 57 ++- .../euc_jp_and_sjis/euc_jp_and_sjis.c | 153 ++++++-- .../euc_kr_and_mic/euc_kr_and_mic.c | 57 ++- .../euc_tw_and_big5/euc_tw_and_big5.c | 165 +++++++-- .../latin2_and_win1250/latin2_and_win1250.c | 49 ++- .../latin_and_mic/latin_and_mic.c | 43 ++- .../utf8_and_big5/utf8_and_big5.c | 37 +- .../utf8_and_cyrillic/utf8_and_cyrillic.c | 67 ++-- .../utf8_and_euc2004/utf8_and_euc2004.c | 37 +- .../utf8_and_euc_cn/utf8_and_euc_cn.c | 37 +- .../utf8_and_euc_jp/utf8_and_euc_jp.c | 37 +- .../utf8_and_euc_kr/utf8_and_euc_kr.c | 37 +- .../utf8_and_euc_tw/utf8_and_euc_tw.c | 37 +- .../utf8_and_gb18030/utf8_and_gb18030.c | 37 +- .../utf8_and_gbk/utf8_and_gbk.c | 37 +- .../utf8_and_iso8859/utf8_and_iso8859.c | 43 ++- .../utf8_and_iso8859_1/utf8_and_iso8859_1.c | 27 +- .../utf8_and_johab/utf8_and_johab.c | 37 +- .../utf8_and_sjis/utf8_and_sjis.c | 37 +- .../utf8_and_sjis2004/utf8_and_sjis2004.c | 37 +- .../utf8_and_uhc/utf8_and_uhc.c | 37 +- .../utf8_and_win/utf8_and_win.c | 43 ++- src/backend/utils/mb/mbutils.c | 13 +- src/bin/pg_upgrade/check.c | 95 +++++ src/include/catalog/pg_proc.dat | 332 +++++++++--------- src/include/mb/pg_wchar.h | 49 +-- src/test/regress/expected/opr_sanity.out | 7 +- src/test/regress/sql/opr_sanity.sql | 7 +- 34 files changed, 1387 insertions(+), 633 deletions(-) diff --git a/doc/src/sgml/ref/create_conversion.sgml b/doc/src/sgml/ref/create_conversion.sgml index e7700fecfc5..f014a676c88 100644 --- a/doc/src/sgml/ref/create_conversion.sgml +++ b/doc/src/sgml/ref/create_conversion.sgml @@ -117,8 +117,9 @@ conv_proc( integer, -- destination encoding ID cstring, -- source string (null terminated C string) internal, -- destination (fill with a null terminated C string) - integer -- source string length -) RETURNS void; + integer, -- source string length + boolean -- if true, don't throw an error if conversion fails +) RETURNS integer; </programlisting></para> </listitem> </varlistentry> diff --git a/src/backend/commands/conversioncmds.c b/src/backend/commands/conversioncmds.c index f7ff321de71..d2041466911 100644 --- a/src/backend/commands/conversioncmds.c +++ b/src/backend/commands/conversioncmds.c @@ -45,8 +45,9 @@ CreateConversionCommand(CreateConversionStmt *stmt) const char *from_encoding_name = stmt->for_encoding_name; const char *to_encoding_name = stmt->to_encoding_name; List *func_name = stmt->func_name; - static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID}; + static const Oid funcargs[] = {INT4OID, INT4OID, CSTRINGOID, INTERNALOID, INT4OID, BOOLOID}; char result[1]; + Datum funcresult; /* Convert list of names to a name and namespace */ namespaceId = QualifiedNameGetCreationNamespace(stmt->conversion_name, @@ -92,8 +93,8 @@ CreateConversionCommand(CreateConversionStmt *stmt) funcoid = LookupFuncName(func_name, sizeof(funcargs) / sizeof(Oid), funcargs, false); - /* Check it returns VOID, else it's probably the wrong function */ - if (get_func_rettype(funcoid) != VOIDOID) + /* Check it returns int4, else it's probably the wrong function */ + if (get_func_rettype(funcoid) != INT4OID) ereport(ERROR, (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), errmsg("encoding conversion function %s must return type %s", @@ -111,12 +112,20 @@ CreateConversionCommand(CreateConversionStmt *stmt) * string; the conversion function should throw an error if it can't * perform the requested conversion. */ - OidFunctionCall5(funcoid, - Int32GetDatum(from_encoding), - Int32GetDatum(to_encoding), - CStringGetDatum(""), - CStringGetDatum(result), - Int32GetDatum(0)); + funcresult = OidFunctionCall6(funcoid, + Int32GetDatum(from_encoding), + Int32GetDatum(to_encoding), + CStringGetDatum(""), + CStringGetDatum(result), + Int32GetDatum(0), + BoolGetDatum(false)); + + /* The function should return 0 for empty input. Might as well check that, too. */ + if (DatumGetInt32(funcresult) != 0) + ereport(ERROR, + (errcode(ERRCODE_INVALID_OBJECT_DEFINITION), + errmsg("encoding conversion function %s returned incorrect result for empty input", + NameListToString(func_name)))); /* * All seem ok, go ahead (possible failure would be a duplicate conversion diff --git a/src/backend/utils/error/elog.c b/src/backend/utils/error/elog.c index 80c26724612..762f77d533c 100644 --- a/src/backend/utils/error/elog.c +++ b/src/backend/utils/error/elog.c @@ -2280,6 +2280,8 @@ write_console(const char *line, int len) * Conversion on non-win32 platforms is not implemented yet. It requires * non-throw version of pg_do_encoding_conversion(), that converts * unconvertable characters to '?' without errors. + * + * XXX: We have a no-throw version now. It doesn't convert to '?' though. */ #endif diff --git a/src/backend/utils/mb/conv.c b/src/backend/utils/mb/conv.c index a07b54bd3b8..b83358bc7a5 100644 --- a/src/backend/utils/mb/conv.c +++ b/src/backend/utils/mb/conv.c @@ -26,14 +26,16 @@ * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the target charset, or 0 if there is no equivalent code. */ -void +int local2local(const unsigned char *l, unsigned char *p, int len, int src_encoding, int dest_encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -41,7 +43,11 @@ local2local(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(src_encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -50,13 +56,19 @@ local2local(const unsigned char *l, if (c2) *p++ = c2; else + { + if (noError) + break; report_untranslatable_char(src_encoding, dest_encoding, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -67,17 +79,22 @@ local2local(const unsigned char *l, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = l; int c1; while (len > 0) { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (IS_HIGHBIT_SET(c1)) *p++ = lc; *p++ = c1; @@ -85,6 +102,8 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, len--; } *p = '\0'; + + return l - start; } /* @@ -95,17 +114,22 @@ latin2mic(const unsigned char *l, unsigned char *p, int len, * lc is the mule character set id for the local encoding * encoding is the PG identifier for the local encoding */ -void +int mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding) + int lc, int encoding, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -118,17 +142,27 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1])) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); + } *p++ = mic[1]; mic += 2; len -= 2; } } *p = '\0'; + + return mic - start; } @@ -144,14 +178,16 @@ mic2latin(const unsigned char *mic, unsigned char *p, int len, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the mule encoding, or 0 if there is no equivalent code. */ -void +int latin2mic_with_table(const unsigned char *l, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = l; unsigned char c1, c2; @@ -159,7 +195,11 @@ latin2mic_with_table(const unsigned char *l, { c1 = *l; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(encoding, (const char *) l, len); + } if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else @@ -171,13 +211,19 @@ latin2mic_with_table(const unsigned char *l, *p++ = c2; } else + { + if (noError) + break; report_untranslatable_char(encoding, PG_MULE_INTERNAL, (const char *) l, len); + } } l++; len--; } *p = '\0'; + + return l - start; } /* @@ -192,14 +238,16 @@ latin2mic_with_table(const unsigned char *l, * starting from 128 (0x80). each entry in the table holds the corresponding * code point for the local charset, or 0 if there is no equivalent code. */ -void +int mic2latin_with_table(const unsigned char *mic, unsigned char *p, int len, int lc, int encoding, - const unsigned char *tab) + const unsigned char *tab, + bool noError) { + const unsigned char *start = mic; unsigned char c1, c2; @@ -207,7 +255,11 @@ mic2latin_with_table(const unsigned char *mic, { c1 = *mic; if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (!IS_HIGHBIT_SET(c1)) { /* easy for ASCII */ @@ -220,11 +272,17 @@ mic2latin_with_table(const unsigned char *mic, int l = pg_mule_mblen(mic); if (len < l) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1]) || (c2 = tab[mic[1] - HIGHBIT]) == 0) { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, encoding, (const char *) mic, len); break; /* keep compiler quiet */ @@ -235,6 +293,8 @@ mic2latin_with_table(const unsigned char *mic, } } *p = '\0'; + + return mic - start; } /* @@ -425,17 +485,19 @@ pg_mb_radix_conv(const pg_mb_radix_tree *rt, * * See pg_wchar.h for more details about the data structures used here. */ -void +int UtfToLocal(const unsigned char *utf, int len, unsigned char *iso, const pg_mb_radix_tree *map, const pg_utf_to_local_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, bool noError) { uint32 iutf; int l; const pg_utf_to_local_combined *cp; + const unsigned char *start = utf; + const unsigned char *cur = utf; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -449,6 +511,8 @@ UtfToLocal(const unsigned char *utf, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*utf == '\0') break; @@ -584,15 +648,19 @@ UtfToLocal(const unsigned char *utf, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(PG_UTF8, encoding, (const char *) (utf - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(PG_UTF8, (const char *) utf, len); *iso = '\0'; + + return cur - start; } /* @@ -616,18 +684,24 @@ UtfToLocal(const unsigned char *utf, int len, * (if provided) is applied. An error is raised if no match is found. * * See pg_wchar.h for more details about the data structures used here. + * + * Returns the number of input bytes consumed. If noError is true, this can + * be less than 'len'. */ -void +int LocalToUtf(const unsigned char *iso, int len, unsigned char *utf, const pg_mb_radix_tree *map, const pg_local_to_utf_combined *cmap, int cmapsize, utf_local_conversion_func conv_func, - int encoding) + int encoding, + bool noError) { uint32 iiso; int l; const pg_local_to_utf_combined *cp; + const unsigned char *start = iso; + const unsigned char *cur = iso; if (!PG_VALID_ENCODING(encoding)) ereport(ERROR, @@ -641,6 +715,8 @@ LocalToUtf(const unsigned char *iso, int len, unsigned char b3 = 0; unsigned char b4 = 0; + cur = iso; + /* "break" cases all represent errors */ if (*iso == '\0') break; @@ -723,13 +799,17 @@ LocalToUtf(const unsigned char *iso, int len, } /* failed to translate this character */ + if (noError) + break; report_untranslatable_char(encoding, PG_UTF8, (const char *) (iso - l), len); } /* if we broke out of loop early, must be invalid input */ - if (len > 0) + if (len > 0 && !noError) report_invalid_encoding(encoding, (const char *) iso, len); *utf = '\0'; + + return cur - start; } diff --git a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c index 4c5b02654de..368c2deb5e4 100644 --- a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c @@ -44,8 +44,11 @@ PG_FUNCTION_INFO_V1(win866_to_iso); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -306,12 +309,14 @@ koi8r_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = latin2mic(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -320,12 +325,14 @@ mic_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_KOI8R); - mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R); + converted = mic2latin(src, dest, len, LC_KOI8_R, PG_KOI8R, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -334,12 +341,14 @@ iso_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -348,12 +357,14 @@ mic_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_ISO_8859_5); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -362,12 +373,14 @@ win1251_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -376,12 +389,14 @@ mic_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1251); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -390,12 +405,14 @@ win866_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi); + converted = latin2mic_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -404,12 +421,14 @@ mic_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN866); - mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866); + converted = mic2latin_with_table(src, dest, len, LC_KOI8_R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -418,12 +437,14 @@ koi8r_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN1251); - local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN1251, koi2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -432,12 +453,14 @@ win1251_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_KOI8R); - local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi); + converted = local2local(src, dest, len, PG_WIN1251, PG_KOI8R, win12512koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -446,12 +469,14 @@ koi8r_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_WIN866); - local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866); + converted = local2local(src, dest, len, PG_KOI8R, PG_WIN866, koi2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -460,12 +485,14 @@ win866_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_KOI8R); - local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi); + converted = local2local(src, dest, len, PG_WIN866, PG_KOI8R, win8662koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -474,12 +501,14 @@ win866_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_WIN1251); - local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251); + converted = local2local(src, dest, len, PG_WIN866, PG_WIN1251, win8662win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -488,12 +517,14 @@ win1251_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_WIN866); - local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866); + converted = local2local(src, dest, len, PG_WIN1251, PG_WIN866, win12512win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -502,12 +533,14 @@ iso_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_KOI8R); - local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_KOI8R, iso2koi, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -516,12 +549,14 @@ koi8r_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_ISO_8859_5); - local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso); + converted = local2local(src, dest, len, PG_KOI8R, PG_ISO_8859_5, koi2iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -530,12 +565,14 @@ iso_to_win1251(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN1251); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN1251, iso2win1251, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -544,12 +581,14 @@ win1251_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1251, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso); + converted = local2local(src, dest, len, PG_WIN1251, PG_ISO_8859_5, win12512iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -558,12 +597,14 @@ iso_to_win866(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_ISO_8859_5, PG_WIN866); - local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866); + converted = local2local(src, dest, len, PG_ISO_8859_5, PG_WIN866, iso2win866, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -572,10 +613,12 @@ win866_to_iso(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN866, PG_ISO_8859_5); - local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso); + converted = local2local(src, dest, len, PG_WIN866, PG_ISO_8859_5, win8662iso, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c index 4d7fb116cfd..88529c644cf 100644 --- a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c @@ -19,8 +19,8 @@ PG_MODULE_MAGIC; PG_FUNCTION_INFO_V1(euc_jis_2004_to_shift_jis_2004); PG_FUNCTION_INFO_V1(shift_jis_2004_to_euc_jis_2004); -static void euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len); -static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len); +static int euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError); /* ---------- * conv_proc( @@ -28,8 +28,11 @@ static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -39,12 +42,14 @@ euc_jis_2004_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_SHIFT_JIS_2004); - euc_jis_20042shift_jis_2004(src, dest, len); + converted = euc_jis_20042shift_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -53,20 +58,23 @@ shift_jis_2004_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_EUC_JIS_2004); - shift_jis_20042euc_jis_2004(src, dest, len); + converted = shift_jis_20042euc_jis_2004(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_JIS_2004 -> SHIFT_JIS_2004 */ -static void -euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, ku, ten; @@ -79,8 +87,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -90,8 +102,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) l = pg_encoding_verifymbchar(PG_EUC_JIS_2004, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (c1 == SS2 && l == 2) /* JIS X 0201 kana? */ { @@ -121,8 +137,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) *p++ = (ku + 0x19b) >> 1; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } if (ku % 2) @@ -132,8 +152,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; @@ -149,8 +173,12 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ku >= 63 && ku <= 94) *p++ = (ku + 0x181) >> 1; else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } if (ku % 2) { @@ -159,20 +187,30 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) else if (ten >= 64 && ten <= 94) *p++ = ten + 0x40; else - report_invalid_encoding(PG_EUC_JIS_2004, + { + if (noError) + break; + report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } } else *p++ = ten + 0x9e; } else + { + if (noError) + break; report_invalid_encoding(PG_EUC_JIS_2004, (const char *) euc, len); + } euc += l; len -= l; } *p = '\0'; + + return euc - start; } /* @@ -212,9 +250,10 @@ get_ten(int b, int *ku) * SHIFT_JIS_2004 ---> EUC_JIS_2004 */ -static void -shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len) +static int +shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1; int ku, ten, @@ -230,8 +269,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -241,8 +284,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len l = pg_encoding_verifymbchar(PG_SHIFT_JIS_2004, (const char *) sjis, len); if (l < 0 || l > len) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf && l == 1) { @@ -266,8 +313,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x100; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xe0 && c1 <= 0xef) /* plane 1 62ku-94ku */ @@ -275,9 +326,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len ku = (c1 << 1) - 0x180; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, - (const char *) sjis, len); + } ku -= kubun; } else if (c1 >= 0xf0 && c1 <= 0xf3) /* plane 2 @@ -286,8 +340,12 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } switch (c1) { case 0xf0: @@ -309,16 +367,24 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len plane = 2; ten = get_ten(c2, &kubun); if (ten < 0) + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (c1 == 0xf4 && kubun == 1) ku = 15; else ku = (c1 << 1) - 0x19a - kubun; } else + { + if (noError) + break; report_invalid_encoding(PG_SHIFT_JIS_2004, (const char *) sjis, len); + } if (plane == 2) *p++ = SS3; @@ -330,4 +396,6 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c index e9bb896935f..a8da733803d 100644 --- a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_cn2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_cn(const unsigned char *mic, unsigned char *p, int len); +static int euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_cn_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_cn_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_MULE_INTERNAL); - euc_cn2mic(src, dest, len); + converted = euc_cn2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_CN); - mic2euc_cn(src, dest, len); + converted = mic2euc_cn(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_CN ---> MIC */ -static void -euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_cn2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; while (len > 0) @@ -76,7 +84,11 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (len < 2 || !IS_HIGHBIT_SET(euc[1])) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = LC_GB2312_80; *p++ = c1; *p++ = euc[1]; @@ -86,21 +98,28 @@ euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_CN */ -static void -mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_cn(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; while (len > 0) @@ -109,11 +128,19 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) if (IS_HIGHBIT_SET(c1)) { if (c1 != LC_GB2312_80) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_CN, (const char *) mic, len); + } if (len < 3 || !IS_HIGHBIT_SET(mic[1]) || !IS_HIGHBIT_SET(mic[2])) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } mic++; *p++ = *mic++; *p++ = *mic++; @@ -122,12 +149,18 @@ mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; } } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c index 5059f917a98..cc4817dc4cd 100644 --- a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c @@ -42,17 +42,20 @@ PG_FUNCTION_INFO_V1(mic_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void sjis2mic(const unsigned char *sjis, unsigned char *p, int len); -static void mic2sjis(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_jp(const unsigned char *mic, unsigned char *p, int len); -static void euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len); -static void sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len); +static int sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError); +static int mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_jp2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int sjis2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_jp_to_sjis(PG_FUNCTION_ARGS) @@ -60,12 +63,14 @@ euc_jp_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_SJIS); - euc_jp2sjis(src, dest, len); + converted = euc_jp2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -74,12 +79,14 @@ sjis_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_EUC_JP); - sjis2euc_jp(src, dest, len); + converted = sjis2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -88,12 +95,14 @@ euc_jp_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_MULE_INTERNAL); - euc_jp2mic(src, dest, len); + converted = euc_jp2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -102,12 +111,14 @@ mic_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_JP); - mic2euc_jp(src, dest, len); + converted = mic2euc_jp(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -116,12 +127,14 @@ sjis_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_MULE_INTERNAL); - sjis2mic(src, dest, len); + converted = sjis2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -130,20 +143,23 @@ mic_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_SJIS); - mic2sjis(src, dest, len); + converted = mic2sjis(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * SJIS ---> MIC */ -static void -sjis2mic(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2mic(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -167,7 +183,11 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) * JIS X0208, X0212, user defined extended characters */ if (len < 2 || !ISSJISHEAD(c1) || !ISSJISTAIL(sjis[1])) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } c2 = sjis[1]; k = (c1 << 8) + c2; if (k >= 0xed40 && k < 0xf040) @@ -257,21 +277,28 @@ sjis2mic(const unsigned char *sjis, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; } } *p = '\0'; + + return sjis - start; } /* * MIC ---> SJIS */ -static void -mic2sjis(const unsigned char *mic, unsigned char *p, int len) +static int +mic2sjis(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1, c2, k, @@ -284,8 +311,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -293,8 +324,12 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) *p++ = mic[1]; else if (c1 == LC_JISX0208) @@ -350,20 +385,27 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) } } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_SJIS, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP ---> MIC */ -static void -euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -374,8 +416,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -383,8 +429,12 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* 1 byte kana? */ *p++ = LC_JISX0201K; @@ -406,14 +456,17 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_JP */ -static void -mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_jp(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -424,8 +477,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -433,8 +490,12 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_JISX0201K) { *p++ = SS2; @@ -452,20 +513,27 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_JP, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * EUC_JP -> SJIS */ -static void -euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) +static int +euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1, c2, k; @@ -478,8 +546,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } *p++ = c1; euc++; len--; @@ -487,8 +559,12 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); + } if (c1 == SS2) { /* hankaku kana? */ @@ -551,14 +627,17 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) len -= l; } *p = '\0'; + + return euc - start; } /* * SJIS ---> EUC_JP */ -static void -sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) +static int +sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len, bool noError) { + const unsigned char *start = sjis; int c1, c2, i, @@ -573,8 +652,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } *p++ = c1; sjis++; len--; @@ -582,8 +665,12 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_SJIS, (const char *) sjis, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + } if (c1 >= 0xa1 && c1 <= 0xdf) { /* JIS X0201 (1 byte kana) */ @@ -680,4 +767,6 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) len -= l; } *p = '\0'; + + return sjis - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c index ac823d6c270..a5b51617e52 100644 --- a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c @@ -26,13 +26,16 @@ PG_FUNCTION_INFO_V1(mic_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_kr2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_kr(const unsigned char *mic, unsigned char *p, int len); +static int euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_kr_to_mic(PG_FUNCTION_ARGS) @@ -40,12 +43,14 @@ euc_kr_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_MULE_INTERNAL); - euc_kr2mic(src, dest, len); + converted = euc_kr2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -54,20 +59,23 @@ mic_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_KR); - mic2euc_kr(src, dest, len); + converted = mic2euc_kr(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_KR ---> MIC */ -static void -euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_kr2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -78,8 +86,12 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_KR, (const char *) euc, len); if (l != 2) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = LC_KS5601; *p++ = c1; *p++ = euc[1]; @@ -89,22 +101,29 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_KR */ -static void -mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_kr(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -115,8 +134,12 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -124,18 +147,28 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_KS5601) { *p++ = mic[1]; *p++ = mic[2]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_KR, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c index 66c242d7f36..ebb4e0acd53 100644 --- a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c @@ -32,17 +32,20 @@ PG_FUNCTION_INFO_V1(mic_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ -static void euc_tw2big5(const unsigned char *euc, unsigned char *p, int len); -static void big52euc_tw(const unsigned char *euc, unsigned char *p, int len); -static void big52mic(const unsigned char *big5, unsigned char *p, int len); -static void mic2big5(const unsigned char *mic, unsigned char *p, int len); -static void euc_tw2mic(const unsigned char *euc, unsigned char *p, int len); -static void mic2euc_tw(const unsigned char *mic, unsigned char *p, int len); +static int euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52euc_tw(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError); +static int mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError); +static int euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError); +static int mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError); Datum euc_tw_to_big5(PG_FUNCTION_ARGS) @@ -50,12 +53,14 @@ euc_tw_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_BIG5); - euc_tw2big5(src, dest, len); + converted = euc_tw2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -64,12 +69,14 @@ big5_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_EUC_TW); - big52euc_tw(src, dest, len); + converted = big52euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -78,12 +85,14 @@ euc_tw_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_MULE_INTERNAL); - euc_tw2mic(src, dest, len); + converted = euc_tw2mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -92,12 +101,14 @@ mic_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_EUC_TW); - mic2euc_tw(src, dest, len); + converted = mic2euc_tw(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -106,12 +117,14 @@ big5_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_MULE_INTERNAL); - big52mic(src, dest, len); + converted = big52mic(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -120,21 +133,24 @@ mic_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_BIG5); - mic2big5(src, dest, len); + converted = mic2big5(src, dest, len, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } /* * EUC_TW ---> Big5 */ -static void -euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2big5(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; unsigned char c1; unsigned short big5buf, cnsBuf; @@ -149,8 +165,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Verify and decode the next EUC_TW input character */ l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -171,8 +191,12 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) /* Write it out in Big5 */ big5buf = CNStoBIG5(cnsBuf, lc); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_EUC_TW, PG_BIG5, (const char *) euc, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; @@ -182,22 +206,29 @@ euc_tw2big5(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * Big5 ---> EUC_TW */ -static void -big52euc_tw(const unsigned char *big5, unsigned char *p, int len) +static int +big52euc_tw(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -212,8 +243,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); @@ -237,8 +272,12 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_EUC_TW, (const char *) big5, len); + } big5 += l; len -= l; @@ -256,14 +295,17 @@ big52euc_tw(const unsigned char *big5, unsigned char *p, int len) } } *p = '\0'; + + return big5 - start; } /* * EUC_TW ---> MIC */ -static void -euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) +static int +euc_tw2mic(const unsigned char *euc, unsigned char *p, int len, bool noError) { + const unsigned char *start = euc; int c1; int l; @@ -274,8 +316,12 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) { l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } if (c1 == SS2) { c1 = euc[1]; /* plane No. */ @@ -304,22 +350,29 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) else { /* should be ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); + } *p++ = c1; euc++; len--; } } *p = '\0'; + + return euc - start; } /* * MIC ---> EUC_TW */ -static void -mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) +static int +mic2euc_tw(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; int c1; int l; @@ -330,8 +383,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -339,8 +396,12 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1) { *p++ = mic[1]; @@ -362,20 +423,27 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) *p++ = mic[3]; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_TW, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } /* * Big5 ---> MIC */ -static void -big52mic(const unsigned char *big5, unsigned char *p, int len) +static int +big52mic(const unsigned char *big5, unsigned char *p, int len, bool noError) { + const unsigned char *start = big5; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -389,8 +457,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } *p++ = c1; big5++; len--; @@ -398,8 +470,12 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_BIG5, (const char *) big5, len); + } big5buf = (c1 << 8) | big5[1]; cnsBuf = BIG5toCNS(big5buf, &lc); if (lc != 0) @@ -412,20 +488,27 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) *p++ = cnsBuf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_BIG5, PG_MULE_INTERNAL, (const char *) big5, len); + } big5 += l; len -= l; } *p = '\0'; + + return big5 - start; } /* * MIC ---> Big5 */ -static void -mic2big5(const unsigned char *mic, unsigned char *p, int len) +static int +mic2big5(const unsigned char *mic, unsigned char *p, int len, bool noError) { + const unsigned char *start = mic; unsigned short c1; unsigned short big5buf, cnsBuf; @@ -438,8 +521,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) { /* ASCII */ if (c1 == 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } *p++ = c1; mic++; len--; @@ -447,8 +534,12 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) + { + if (noError) + break; report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + } if (c1 == LC_CNS11643_1 || c1 == LC_CNS11643_2 || c1 == LCPRV2_B) { if (c1 == LCPRV2_B) @@ -462,16 +553,26 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) } big5buf = CNStoBIG5(cnsBuf, c1); if (big5buf == 0) + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } *p++ = (big5buf >> 8) & 0x00ff; *p++ = big5buf & 0x00ff; } else + { + if (noError) + break; report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, (const char *) mic, len); + } mic += l; len -= l; } *p = '\0'; + + return mic - start; } diff --git a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c index 2e28e6780a5..8610fcb69aa 100644 --- a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c +++ b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(win1250_to_latin2); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -82,12 +85,14 @@ latin2_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = latin2mic(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -96,12 +101,14 @@ mic_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN2); - mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2); + converted = mic2latin(src, dest, len, LC_ISO8859_2, PG_LATIN2, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -110,13 +117,15 @@ win1250_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_MULE_INTERNAL); - latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - win1250_2_iso88592); + converted = latin2mic_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -125,13 +134,15 @@ mic_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_WIN1250); - mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, - iso88592_2_win1250); + converted = mic2latin_with_table(src, dest, len, LC_ISO8859_2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -140,12 +151,15 @@ latin2_to_win1250(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN2, PG_WIN1250); - local2local(src, dest, len, PG_LATIN2, PG_WIN1250, iso88592_2_win1250); + converted = local2local(src, dest, len, PG_LATIN2, PG_WIN1250, + iso88592_2_win1250, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -154,10 +168,13 @@ win1250_to_latin2(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_WIN1250, PG_LATIN2); - local2local(src, dest, len, PG_WIN1250, PG_LATIN2, win1250_2_iso88592); + converted = local2local(src, dest, len, PG_WIN1250, PG_LATIN2, + win1250_2_iso88592, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c index bc651410f21..bff27d1c295 100644 --- a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c @@ -30,8 +30,11 @@ PG_FUNCTION_INFO_V1(mic_to_latin4); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -42,12 +45,14 @@ latin1_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = latin2mic(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,12 +61,14 @@ mic_to_latin1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN1); - mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1); + converted = mic2latin(src, dest, len, LC_ISO8859_1, PG_LATIN1, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -70,12 +77,14 @@ latin3_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN3, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = latin2mic(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -84,12 +93,14 @@ mic_to_latin3(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN3); - mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3); + converted = mic2latin(src, dest, len, LC_ISO8859_3, PG_LATIN3, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,12 +109,14 @@ latin4_to_mic(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN4, PG_MULE_INTERNAL); - latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = latin2mic(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -112,10 +125,12 @@ mic_to_latin4(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_MULE_INTERNAL, PG_LATIN4); - mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4); + converted = mic2latin(src, dest, len, LC_ISO8859_4, PG_LATIN4, noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c index d6067cdc24e..3838b15cab9 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_big5); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ big5_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_BIG5, PG_UTF8); - LocalToUtf(src, len, dest, - &big5_to_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = LocalToUtf(src, len, dest, + &big5_to_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_big5(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_BIG5); - UtfToLocal(src, len, dest, - &big5_from_unicode_tree, - NULL, 0, - NULL, - PG_BIG5); + converted = UtfToLocal(src, len, dest, + &big5_from_unicode_tree, + NULL, 0, + NULL, + PG_BIG5, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c index ed90e8e682e..75719fe5f1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c @@ -33,8 +33,11 @@ PG_FUNCTION_INFO_V1(koi8u_to_utf8); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -44,16 +47,19 @@ utf8_to_koi8r(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8R); - UtfToLocal(src, len, dest, - &koi8r_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = UtfToLocal(src, len, dest, + &koi8r_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -62,16 +68,19 @@ koi8r_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8R, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8r_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8R); + converted = LocalToUtf(src, len, dest, + &koi8r_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8R, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -80,16 +89,19 @@ utf8_to_koi8u(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_KOI8U); - UtfToLocal(src, len, dest, - &koi8u_from_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = UtfToLocal(src, len, dest, + &koi8u_from_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -98,14 +110,17 @@ koi8u_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_KOI8U, PG_UTF8); - LocalToUtf(src, len, dest, - &koi8u_to_unicode_tree, - NULL, 0, - NULL, - PG_KOI8U); + converted = LocalToUtf(src, len, dest, + &koi8u_to_unicode_tree, + NULL, 0, + NULL, + PG_KOI8U, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c index d699affce47..5391001951a 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc2004/utf8_and_euc2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jis_2004_to_unicode_tree, - LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = LocalToUtf(src, len, dest, + &euc_jis_2004_to_unicode_tree, + LUmapEUC_JIS_2004_combined, lengthof(LUmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JIS_2004); - UtfToLocal(src, len, dest, - &euc_jis_2004_from_unicode_tree, - ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), - NULL, - PG_EUC_JIS_2004); + converted = UtfToLocal(src, len, dest, + &euc_jis_2004_from_unicode_tree, + ULmapEUC_JIS_2004_combined, lengthof(ULmapEUC_JIS_2004_combined), + NULL, + PG_EUC_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c index d7c0ba6a58b..c87d1bf2398 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_cn); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_cn_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_CN, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_cn_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = LocalToUtf(src, len, dest, + &euc_cn_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_cn(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_CN); - UtfToLocal(src, len, dest, - &euc_cn_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_CN); + converted = UtfToLocal(src, len, dest, + &euc_cn_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_CN, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c index 13a3a23e77b..6a55134db21 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_jp); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_jp_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_JP, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_jp_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = LocalToUtf(src, len, dest, + &euc_jp_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_jp(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_JP); - UtfToLocal(src, len, dest, - &euc_jp_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_JP); + converted = UtfToLocal(src, len, dest, + &euc_jp_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_JP, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c index 1bbb8aaef7b..fe1924e2fec 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_kr); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_kr_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_KR, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_kr_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = LocalToUtf(src, len, dest, + &euc_kr_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_kr(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_KR); - UtfToLocal(src, len, dest, - &euc_kr_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_KR); + converted = UtfToLocal(src, len, dest, + &euc_kr_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_KR, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c index 9830045dccd..68215659b57 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_euc_tw); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ euc_tw_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_EUC_TW, PG_UTF8); - LocalToUtf(src, len, dest, - &euc_tw_to_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = LocalToUtf(src, len, dest, + &euc_tw_to_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_euc_tw(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_EUC_TW); - UtfToLocal(src, len, dest, - &euc_tw_from_unicode_tree, - NULL, 0, - NULL, - PG_EUC_TW); + converted = UtfToLocal(src, len, dest, + &euc_tw_from_unicode_tree, + NULL, 0, + NULL, + PG_EUC_TW, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c index f86ecf27424..e1a59c39a4d 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c @@ -183,8 +183,11 @@ conv_utf8_to_18030(uint32 code) * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -193,16 +196,19 @@ gb18030_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GB18030, PG_UTF8); - LocalToUtf(src, len, dest, - &gb18030_to_unicode_tree, - NULL, 0, - conv_18030_to_utf8, - PG_GB18030); + converted = LocalToUtf(src, len, dest, + &gb18030_to_unicode_tree, + NULL, 0, + conv_18030_to_utf8, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -211,14 +217,17 @@ utf8_to_gb18030(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GB18030); - UtfToLocal(src, len, dest, - &gb18030_from_unicode_tree, - NULL, 0, - conv_utf8_to_18030, - PG_GB18030); + converted = UtfToLocal(src, len, dest, + &gb18030_from_unicode_tree, + NULL, 0, + conv_utf8_to_18030, + PG_GB18030, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c index 2ab8b16c8a8..881386d5347 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_gbk); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ gbk_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_GBK, PG_UTF8); - LocalToUtf(src, len, dest, - &gbk_to_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = LocalToUtf(src, len, dest, + &gbk_to_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_gbk(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_GBK); - UtfToLocal(src, len, dest, - &gbk_from_unicode_tree, - NULL, 0, - NULL, - PG_GBK); + converted = UtfToLocal(src, len, dest, + &gbk_from_unicode_tree, + NULL, 0, + NULL, + PG_GBK, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c index 3e49f67ea2f..d93a521badf 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c @@ -52,8 +52,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -100,6 +103,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -108,12 +112,15 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -122,7 +129,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -132,6 +139,7 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -140,12 +148,15 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -154,5 +165,5 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for ISO 8859 character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c index 67e713cca11..8ac93604a1b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c @@ -26,8 +26,11 @@ PG_FUNCTION_INFO_V1(utf8_to_iso8859_1); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -37,6 +40,8 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c; CHECK_ENCODING_CONVERSION_ARGS(PG_LATIN1, PG_UTF8); @@ -45,7 +50,11 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_LATIN1, (const char *) src, len); + } if (!IS_HIGHBIT_SET(c)) *dest++ = c; else @@ -58,7 +67,7 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } Datum @@ -67,6 +76,8 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + unsigned char *start = src; unsigned short c, c1; @@ -76,7 +87,11 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) { c = *src; if (c == 0) + { + if (noError) + break; report_invalid_encoding(PG_UTF8, (const char *) src, len); + } /* fast path for ASCII-subset characters */ if (!IS_HIGHBIT_SET(c)) { @@ -102,11 +117,15 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) len -= 2; } else + { + if (noError) + break; report_untranslatable_char(PG_UTF8, PG_LATIN1, (const char *) src, len); + } } } *dest = '\0'; - PG_RETURN_VOID(); + PG_RETURN_INT32(src - start); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c index 578f5df4e7f..317daa2d5ee 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_johab); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ johab_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_JOHAB, PG_UTF8); - LocalToUtf(src, len, dest, - &johab_to_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = LocalToUtf(src, len, dest, + &johab_to_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_johab(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_JOHAB); - UtfToLocal(src, len, dest, - &johab_from_unicode_tree, - NULL, 0, - NULL, - PG_JOHAB); + converted = UtfToLocal(src, len, dest, + &johab_from_unicode_tree, + NULL, 0, + NULL, + PG_JOHAB, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c index dd9fc2975ad..4c9348aba59 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_sjis); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ sjis_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SJIS, PG_UTF8); - LocalToUtf(src, len, dest, - &sjis_to_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = LocalToUtf(src, len, dest, + &sjis_to_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_sjis(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SJIS); - UtfToLocal(src, len, dest, - &sjis_from_unicode_tree, - NULL, 0, - NULL, - PG_SJIS); + converted = UtfToLocal(src, len, dest, + &sjis_from_unicode_tree, + NULL, 0, + NULL, + PG_SJIS, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c index 4bcc886d674..1fffdc5930c 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis2004/utf8_and_sjis2004.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_shift_jis_2004); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ shift_jis_2004_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_SHIFT_JIS_2004, PG_UTF8); - LocalToUtf(src, len, dest, - &shift_jis_2004_to_unicode_tree, - LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = LocalToUtf(src, len, dest, + &shift_jis_2004_to_unicode_tree, + LUmapSHIFT_JIS_2004_combined, lengthof(LUmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_shift_jis_2004(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_SHIFT_JIS_2004); - UtfToLocal(src, len, dest, - &shift_jis_2004_from_unicode_tree, - ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), - NULL, - PG_SHIFT_JIS_2004); + converted = UtfToLocal(src, len, dest, + &shift_jis_2004_from_unicode_tree, + ULmapSHIFT_JIS_2004_combined, lengthof(ULmapSHIFT_JIS_2004_combined), + NULL, + PG_SHIFT_JIS_2004, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c index c8e512994a1..d9471dad097 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c @@ -28,8 +28,11 @@ PG_FUNCTION_INFO_V1(utf8_to_uhc); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ Datum @@ -38,16 +41,19 @@ uhc_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UHC, PG_UTF8); - LocalToUtf(src, len, dest, - &uhc_to_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = LocalToUtf(src, len, dest, + &uhc_to_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } Datum @@ -56,14 +62,17 @@ utf8_to_uhc(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); + int converted; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, PG_UHC); - UtfToLocal(src, len, dest, - &uhc_from_unicode_tree, - NULL, 0, - NULL, - PG_UHC); + converted = UtfToLocal(src, len, dest, + &uhc_from_unicode_tree, + NULL, 0, + NULL, + PG_UHC, + noError); - PG_RETURN_VOID(); + PG_RETURN_INT32(converted); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c index 0c9493dee56..110ba5677d0 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c @@ -48,8 +48,11 @@ PG_FUNCTION_INFO_V1(utf8_to_win); * INTEGER, -- destination encoding id * CSTRING, -- source string (null terminated C string) * CSTRING, -- destination string (null terminated C string) - * INTEGER -- source string length - * ) returns VOID; + * INTEGER, -- source string length + * BOOL -- if true, don't throw an error if conversion fails + * ) returns INTEGER; + * + * Returns the number of bytes successfully converted. * ---------- */ @@ -81,6 +84,7 @@ win_to_utf8(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(-1, PG_UTF8); @@ -89,12 +93,15 @@ win_to_utf8(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - LocalToUtf(src, len, dest, - maps[i].map1, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = LocalToUtf(src, len, dest, + maps[i].map1, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -103,7 +110,7 @@ win_to_utf8(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } Datum @@ -113,6 +120,7 @@ utf8_to_win(PG_FUNCTION_ARGS) unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2); unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); + bool noError = PG_GETARG_BOOL(5); int i; CHECK_ENCODING_CONVERSION_ARGS(PG_UTF8, -1); @@ -121,12 +129,15 @@ utf8_to_win(PG_FUNCTION_ARGS) { if (encoding == maps[i].encoding) { - UtfToLocal(src, len, dest, - maps[i].map2, - NULL, 0, - NULL, - encoding); - PG_RETURN_VOID(); + int converted; + + converted = UtfToLocal(src, len, dest, + maps[i].map2, + NULL, 0, + NULL, + encoding, + noError); + PG_RETURN_INT32(converted); } } @@ -135,5 +146,5 @@ utf8_to_win(PG_FUNCTION_ARGS) errmsg("unexpected encoding ID %d for WIN character sets", encoding))); - PG_RETURN_VOID(); + PG_RETURN_INT32(0); } diff --git a/src/backend/utils/mb/mbutils.c b/src/backend/utils/mb/mbutils.c index 2578573b0ab..b41d3e0bb9a 100644 --- a/src/backend/utils/mb/mbutils.c +++ b/src/backend/utils/mb/mbutils.c @@ -406,12 +406,13 @@ pg_do_encoding_conversion(unsigned char *src, int len, MemoryContextAllocHuge(CurrentMemoryContext, (Size) len * MAX_CONVERSION_GROWTH + 1); - OidFunctionCall5(proc, - Int32GetDatum(src_encoding), - Int32GetDatum(dest_encoding), - CStringGetDatum(src), - CStringGetDatum(result), - Int32GetDatum(len)); + (void) OidFunctionCall6(proc, + Int32GetDatum(src_encoding), + Int32GetDatum(dest_encoding), + CStringGetDatum(src), + CStringGetDatum(result), + Int32GetDatum(len), + BoolGetDatum(false)); /* * If the result is large, it's worth repalloc'ing to release any extra diff --git a/src/bin/pg_upgrade/check.c b/src/bin/pg_upgrade/check.c index 43fc297eb69..ee6be95b08d 100644 --- a/src/bin/pg_upgrade/check.c +++ b/src/bin/pg_upgrade/check.c @@ -28,6 +28,7 @@ static void check_for_reg_data_type_usage(ClusterInfo *cluster); static void check_for_jsonb_9_4_usage(ClusterInfo *cluster); static void check_for_pg_role_prefix(ClusterInfo *cluster); static void check_for_new_tablespace_dir(ClusterInfo *new_cluster); +static void check_for_user_defined_encoding_conversions(ClusterInfo *cluster); static char *get_canonical_locale_name(int category, const char *locale); @@ -102,6 +103,15 @@ check_and_dump_old_cluster(bool live_check) check_for_reg_data_type_usage(&old_cluster); check_for_isn_and_int8_passing_mismatch(&old_cluster); + /* + * PG 14 changed the function signature of encoding conversion functions. + * Conversions from older versions cannot be upgraded automatically + * because the user-defined functions used by the encoding conversions + * need to changed to match the new signature. + */ + if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1300) + check_for_user_defined_encoding_conversions(&old_cluster); + /* * Pre-PG 14 allowed user defined postfix operators, which are not * supported anymore. Verify there are none, iff applicable. @@ -1268,6 +1278,91 @@ check_for_pg_role_prefix(ClusterInfo *cluster) check_ok(); } +/* + * Verify that no user-defined encoding conversions exist. + */ +static void +check_for_user_defined_encoding_conversions(ClusterInfo *cluster) +{ + int dbnum; + FILE *script = NULL; + bool found = false; + char output_path[MAXPGPATH]; + + prep_status("Checking for user-defined encoding conversions"); + + snprintf(output_path, sizeof(output_path), + "encoding_conversions.txt"); + + /* Find any user defined encoding conversions */ + for (dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++) + { + PGresult *res; + bool db_used = false; + int ntups; + int rowno; + int i_conoid, + i_conname, + i_nspname; + DbInfo *active_db = &cluster->dbarr.dbs[dbnum]; + PGconn *conn = connectToServer(cluster, active_db->db_name); + + /* + * The query below hardcodes FirstNormalObjectId as 16384 rather than + * interpolating that C #define into the query because, if that + * #define is ever changed, the cutoff we want to use is the value + * used by pre-version 14 servers, not that of some future version. + */ + res = executeQueryOrDie(conn, + "SELECT c.oid as conoid, c.conname, n.nspname " + "FROM pg_catalog.pg_conversion c, " + " pg_catalog.pg_namespace n " + "WHERE c.connamespace = n.oid AND " + " c.oid >= 16384"); + ntups = PQntuples(res); + i_conoid = PQfnumber(res, "conoid"); + i_conname = PQfnumber(res, "conname"); + i_nspname = PQfnumber(res, "nspname"); + for (rowno = 0; rowno < ntups; rowno++) + { + found = true; + if (script == NULL && + (script = fopen_priv(output_path, "w")) == NULL) + pg_fatal("could not open file \"%s\": %s\n", + output_path, strerror(errno)); + if (!db_used) + { + fprintf(script, "In database: %s\n", active_db->db_name); + db_used = true; + } + fprintf(script, " (oid=%s) %s.%s\n", + PQgetvalue(res, rowno, i_conoid), + PQgetvalue(res, rowno, i_nspname), + PQgetvalue(res, rowno, i_conname)); + } + + PQclear(res); + + PQfinish(conn); + } + + if (script) + fclose(script); + + if (found) + { + pg_log(PG_REPORT, "fatal\n"); + pg_fatal("Your installation contains user-defined encoding conversions.\n" + "The conversion function parameters changed in PostgreSQL version 14\n" + "so this cluster cannot currently be upgraded. You can remove the\n" + "encoding conversions in the old cluster and restart the upgrade.\n" + "A list of user-defined encoding conversions is in the file:\n" + " %s\n\n", output_path); + } + else + check_ok(); +} + /* * get_canonical_locale_name diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index b5f52d4e4a3..f97a911a716 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10766,388 +10766,388 @@ # conversion functions { oid => '4302', descr => 'internal conversion function for KOI8R to MULE_INTERNAL', - proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_mic', + proname => 'koi8r_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4303', descr => 'internal conversion function for MULE_INTERNAL to KOI8R', - proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_koi8r', + proname => 'mic_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4304', descr => 'internal conversion function for ISO-8859-5 to MULE_INTERNAL', - proname => 'iso_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_mic', + proname => 'iso_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4305', descr => 'internal conversion function for MULE_INTERNAL to ISO-8859-5', - proname => 'mic_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_iso', + proname => 'mic_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4306', descr => 'internal conversion function for WIN1251 to MULE_INTERNAL', - proname => 'win1251_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_mic', + proname => 'win1251_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4307', descr => 'internal conversion function for MULE_INTERNAL to WIN1251', - proname => 'mic_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1251', + proname => 'mic_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4308', descr => 'internal conversion function for WIN866 to MULE_INTERNAL', - proname => 'win866_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_mic', + proname => 'win866_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_mic', probin => '$libdir/cyrillic_and_mic' }, { oid => '4309', descr => 'internal conversion function for MULE_INTERNAL to WIN866', - proname => 'mic_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win866', + proname => 'mic_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4310', descr => 'internal conversion function for KOI8R to WIN1251', - proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'koi8r_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4311', descr => 'internal conversion function for WIN1251 to KOI8R', - proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4312', descr => 'internal conversion function for KOI8R to WIN866', - proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_win866', + proname => 'koi8r_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4313', descr => 'internal conversion function for WIN866 to KOI8R', - proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_koi8r', + proname => 'win866_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4314', descr => 'internal conversion function for WIN866 to WIN1251', - proname => 'win866_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win866_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4315', descr => 'internal conversion function for WIN1251 to WIN866', - proname => 'win1251_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1251_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4316', descr => 'internal conversion function for ISO-8859-5 to KOI8R', - proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_koi8r', + proname => 'iso_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_koi8r', probin => '$libdir/cyrillic_and_mic' }, { oid => '4317', descr => 'internal conversion function for KOI8R to ISO-8859-5', - proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_iso', + proname => 'koi8r_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4318', descr => 'internal conversion function for ISO-8859-5 to WIN1251', - proname => 'iso_to_win1251', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win1251', + proname => 'iso_to_win1251', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win1251', probin => '$libdir/cyrillic_and_mic' }, { oid => '4319', descr => 'internal conversion function for WIN1251 to ISO-8859-5', - proname => 'win1251_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1251_to_iso', + proname => 'win1251_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1251_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4320', descr => 'internal conversion function for ISO-8859-5 to WIN866', - proname => 'iso_to_win866', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso_to_win866', + proname => 'iso_to_win866', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso_to_win866', probin => '$libdir/cyrillic_and_mic' }, { oid => '4321', descr => 'internal conversion function for WIN866 to ISO-8859-5', - proname => 'win866_to_iso', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win866_to_iso', + proname => 'win866_to_iso', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win866_to_iso', probin => '$libdir/cyrillic_and_mic' }, { oid => '4322', descr => 'internal conversion function for EUC_CN to MULE_INTERNAL', - proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_mic', + proname => 'euc_cn_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_mic', probin => '$libdir/euc_cn_and_mic' }, { oid => '4323', descr => 'internal conversion function for MULE_INTERNAL to EUC_CN', - proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_cn', + proname => 'mic_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_cn', probin => '$libdir/euc_cn_and_mic' }, { oid => '4324', descr => 'internal conversion function for EUC_JP to SJIS', - proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_sjis', + proname => 'euc_jp_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4325', descr => 'internal conversion function for SJIS to EUC_JP', - proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_euc_jp', + proname => 'sjis_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4326', descr => 'internal conversion function for EUC_JP to MULE_INTERNAL', - proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_mic', + proname => 'euc_jp_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4327', descr => 'internal conversion function for SJIS to MULE_INTERNAL', - proname => 'sjis_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_mic', + proname => 'sjis_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_mic', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4328', descr => 'internal conversion function for MULE_INTERNAL to EUC_JP', - proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_jp', + proname => 'mic_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_jp', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4329', descr => 'internal conversion function for MULE_INTERNAL to SJIS', - proname => 'mic_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_sjis', + proname => 'mic_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_sjis', probin => '$libdir/euc_jp_and_sjis' }, { oid => '4330', descr => 'internal conversion function for EUC_KR to MULE_INTERNAL', - proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_mic', + proname => 'euc_kr_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_mic', probin => '$libdir/euc_kr_and_mic' }, { oid => '4331', descr => 'internal conversion function for MULE_INTERNAL to EUC_KR', - proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_kr', + proname => 'mic_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_kr', probin => '$libdir/euc_kr_and_mic' }, { oid => '4332', descr => 'internal conversion function for EUC_TW to BIG5', - proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_big5', + proname => 'euc_tw_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4333', descr => 'internal conversion function for BIG5 to EUC_TW', - proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_euc_tw', + proname => 'big5_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4334', descr => 'internal conversion function for EUC_TW to MULE_INTERNAL', - proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_mic', + proname => 'euc_tw_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4335', descr => 'internal conversion function for BIG5 to MULE_INTERNAL', - proname => 'big5_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_mic', + proname => 'big5_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_mic', probin => '$libdir/euc_tw_and_big5' }, { oid => '4336', descr => 'internal conversion function for MULE_INTERNAL to EUC_TW', - proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_euc_tw', + proname => 'mic_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_euc_tw', probin => '$libdir/euc_tw_and_big5' }, { oid => '4337', descr => 'internal conversion function for MULE_INTERNAL to BIG5', - proname => 'mic_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_big5', + proname => 'mic_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_big5', probin => '$libdir/euc_tw_and_big5' }, { oid => '4338', descr => 'internal conversion function for LATIN2 to MULE_INTERNAL', - proname => 'latin2_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin2_to_mic', + proname => 'latin2_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4339', descr => 'internal conversion function for MULE_INTERNAL to LATIN2', - proname => 'mic_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin2', + proname => 'mic_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4340', descr => 'internal conversion function for WIN1250 to MULE_INTERNAL', - proname => 'win1250_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win1250_to_mic', + proname => 'win1250_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_mic', probin => '$libdir/latin2_and_win1250' }, { oid => '4341', descr => 'internal conversion function for MULE_INTERNAL to WIN1250', - proname => 'mic_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_win1250', + proname => 'mic_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4342', descr => 'internal conversion function for LATIN2 to WIN1250', - proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'latin2_to_win1250', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin2_to_win1250', probin => '$libdir/latin2_and_win1250' }, { oid => '4343', descr => 'internal conversion function for WIN1250 to LATIN2', - proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'win1250_to_latin2', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win1250_to_latin2', probin => '$libdir/latin2_and_win1250' }, { oid => '4344', descr => 'internal conversion function for LATIN1 to MULE_INTERNAL', - proname => 'latin1_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin1_to_mic', + proname => 'latin1_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin1_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4345', descr => 'internal conversion function for MULE_INTERNAL to LATIN1', - proname => 'mic_to_latin1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin1', + proname => 'mic_to_latin1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin1', probin => '$libdir/latin_and_mic' }, { oid => '4346', descr => 'internal conversion function for LATIN3 to MULE_INTERNAL', - proname => 'latin3_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin3_to_mic', + proname => 'latin3_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin3_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4347', descr => 'internal conversion function for MULE_INTERNAL to LATIN3', - proname => 'mic_to_latin3', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin3', + proname => 'mic_to_latin3', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin3', probin => '$libdir/latin_and_mic' }, { oid => '4348', descr => 'internal conversion function for LATIN4 to MULE_INTERNAL', - proname => 'latin4_to_mic', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'latin4_to_mic', + proname => 'latin4_to_mic', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'latin4_to_mic', probin => '$libdir/latin_and_mic' }, { oid => '4349', descr => 'internal conversion function for MULE_INTERNAL to LATIN4', - proname => 'mic_to_latin4', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'mic_to_latin4', + proname => 'mic_to_latin4', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'mic_to_latin4', probin => '$libdir/latin_and_mic' }, { oid => '4352', descr => 'internal conversion function for BIG5 to UTF8', - proname => 'big5_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'big5_to_utf8', + proname => 'big5_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'big5_to_utf8', probin => '$libdir/utf8_and_big5' }, { oid => '4353', descr => 'internal conversion function for UTF8 to BIG5', - proname => 'utf8_to_big5', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_big5', + proname => 'utf8_to_big5', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_big5', probin => '$libdir/utf8_and_big5' }, { oid => '4354', descr => 'internal conversion function for UTF8 to KOI8R', - proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8r', + proname => 'utf8_to_koi8r', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8r', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4355', descr => 'internal conversion function for KOI8R to UTF8', - proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8r_to_utf8', + proname => 'koi8r_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8r_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4356', descr => 'internal conversion function for UTF8 to KOI8U', - proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_koi8u', + proname => 'utf8_to_koi8u', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_koi8u', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4357', descr => 'internal conversion function for KOI8U to UTF8', - proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'koi8u_to_utf8', + proname => 'koi8u_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'koi8u_to_utf8', probin => '$libdir/utf8_and_cyrillic' }, { oid => '4358', descr => 'internal conversion function for UTF8 to WIN', - proname => 'utf8_to_win', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_win', + proname => 'utf8_to_win', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_win', probin => '$libdir/utf8_and_win' }, { oid => '4359', descr => 'internal conversion function for WIN to UTF8', - proname => 'win_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'win_to_utf8', + proname => 'win_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'win_to_utf8', probin => '$libdir/utf8_and_win' }, { oid => '4360', descr => 'internal conversion function for EUC_CN to UTF8', - proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_cn_to_utf8', + proname => 'euc_cn_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_cn_to_utf8', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4361', descr => 'internal conversion function for UTF8 to EUC_CN', - proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_cn', + proname => 'utf8_to_euc_cn', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_cn', probin => '$libdir/utf8_and_euc_cn' }, { oid => '4362', descr => 'internal conversion function for EUC_JP to UTF8', - proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_jp_to_utf8', + proname => 'euc_jp_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jp_to_utf8', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4363', descr => 'internal conversion function for UTF8 to EUC_JP', - proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_jp', + proname => 'utf8_to_euc_jp', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jp', probin => '$libdir/utf8_and_euc_jp' }, { oid => '4364', descr => 'internal conversion function for EUC_KR to UTF8', - proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_kr_to_utf8', + proname => 'euc_kr_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_kr_to_utf8', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4365', descr => 'internal conversion function for UTF8 to EUC_KR', - proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_kr', + proname => 'utf8_to_euc_kr', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_kr', probin => '$libdir/utf8_and_euc_kr' }, { oid => '4366', descr => 'internal conversion function for EUC_TW to UTF8', - proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'euc_tw_to_utf8', + proname => 'euc_tw_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_tw_to_utf8', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4367', descr => 'internal conversion function for UTF8 to EUC_TW', - proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_euc_tw', + proname => 'utf8_to_euc_tw', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_tw', probin => '$libdir/utf8_and_euc_tw' }, { oid => '4368', descr => 'internal conversion function for GB18030 to UTF8', - proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gb18030_to_utf8', + proname => 'gb18030_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gb18030_to_utf8', probin => '$libdir/utf8_and_gb18030' }, { oid => '4369', descr => 'internal conversion function for UTF8 to GB18030', - proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gb18030', + proname => 'utf8_to_gb18030', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gb18030', probin => '$libdir/utf8_and_gb18030' }, { oid => '4370', descr => 'internal conversion function for GBK to UTF8', - proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'gbk_to_utf8', + proname => 'gbk_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'gbk_to_utf8', probin => '$libdir/utf8_and_gbk' }, { oid => '4371', descr => 'internal conversion function for UTF8 to GBK', - proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_gbk', + proname => 'utf8_to_gbk', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_gbk', probin => '$libdir/utf8_and_gbk' }, { oid => '4372', descr => 'internal conversion function for UTF8 to ISO-8859 2-16', - proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_iso8859', + proname => 'utf8_to_iso8859', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859', probin => '$libdir/utf8_and_iso8859' }, { oid => '4373', descr => 'internal conversion function for ISO-8859 2-16 to UTF8', - proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'iso8859_to_utf8', + proname => 'iso8859_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_to_utf8', probin => '$libdir/utf8_and_iso8859' }, { oid => '4374', descr => 'internal conversion function for LATIN1 to UTF8', - proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'iso8859_1_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'iso8859_1_to_utf8', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4375', descr => 'internal conversion function for UTF8 to LATIN1', - proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_iso8859_1', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_iso8859_1', probin => '$libdir/utf8_and_iso8859_1' }, { oid => '4376', descr => 'internal conversion function for JOHAB to UTF8', - proname => 'johab_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'johab_to_utf8', + proname => 'johab_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'johab_to_utf8', probin => '$libdir/utf8_and_johab' }, { oid => '4377', descr => 'internal conversion function for UTF8 to JOHAB', - proname => 'utf8_to_johab', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_johab', + proname => 'utf8_to_johab', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_johab', probin => '$libdir/utf8_and_johab' }, { oid => '4378', descr => 'internal conversion function for SJIS to UTF8', - proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'sjis_to_utf8', + proname => 'sjis_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'sjis_to_utf8', probin => '$libdir/utf8_and_sjis' }, { oid => '4379', descr => 'internal conversion function for UTF8 to SJIS', - proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_sjis', + proname => 'utf8_to_sjis', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_sjis', probin => '$libdir/utf8_and_sjis' }, { oid => '4380', descr => 'internal conversion function for UHC to UTF8', - proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'uhc_to_utf8', + proname => 'uhc_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'uhc_to_utf8', probin => '$libdir/utf8_and_uhc' }, { oid => '4381', descr => 'internal conversion function for UTF8 to UHC', - proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', prosrc => 'utf8_to_uhc', + proname => 'utf8_to_uhc', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_uhc', probin => '$libdir/utf8_and_uhc' }, { oid => '4382', descr => 'internal conversion function for EUC_JIS_2004 to UTF8', - proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'euc_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_utf8', probin => '$libdir/utf8_and_euc2004' }, { oid => '4383', descr => 'internal conversion function for UTF8 to EUC_JIS_2004', - proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_euc_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_euc_jis_2004', probin => '$libdir/utf8_and_euc2004' }, { oid => '4384', descr => 'internal conversion function for SHIFT_JIS_2004 to UTF8', - proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'shift_jis_2004_to_utf8', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_utf8', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4385', descr => 'internal conversion function for UTF8 to SHIFT_JIS_2004', - proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'void', - proargtypes => 'int4 int4 cstring internal int4', + proname => 'utf8_to_shift_jis_2004', prolang => 'c', prorettype => 'int4', + proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'utf8_to_shift_jis_2004', probin => '$libdir/utf8_and_sjis2004' }, { oid => '4386', descr => 'internal conversion function for EUC_JIS_2004 to SHIFT_JIS_2004', proname => 'euc_jis_2004_to_shift_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'euc_jis_2004_to_shift_jis_2004', probin => '$libdir/euc2004_sjis2004' }, { oid => '4387', descr => 'internal conversion function for SHIFT_JIS_2004 to EUC_JIS_2004', proname => 'shift_jis_2004_to_euc_jis_2004', prolang => 'c', - prorettype => 'void', proargtypes => 'int4 int4 cstring internal int4', + prorettype => 'int4', proargtypes => 'int4 int4 cstring internal int4 bool', prosrc => 'shift_jis_2004_to_euc_jis_2004', probin => '$libdir/euc2004_sjis2004' }, diff --git a/src/include/mb/pg_wchar.h b/src/include/mb/pg_wchar.h index 64b22e4b0d4..346a41a1f3d 100644 --- a/src/include/mb/pg_wchar.h +++ b/src/include/mb/pg_wchar.h @@ -627,18 +627,18 @@ extern void pg_unicode_to_server(pg_wchar c, unsigned char *s); extern unsigned short BIG5toCNS(unsigned short big5, unsigned char *lc); extern unsigned short CNStoBIG5(unsigned short cns, unsigned char lc); -extern void UtfToLocal(const unsigned char *utf, int len, - unsigned char *iso, - const pg_mb_radix_tree *map, - const pg_utf_to_local_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); -extern void LocalToUtf(const unsigned char *iso, int len, - unsigned char *utf, - const pg_mb_radix_tree *map, - const pg_local_to_utf_combined *cmap, int cmapsize, - utf_local_conversion_func conv_func, - int encoding); +extern int UtfToLocal(const unsigned char *utf, int len, + unsigned char *iso, + const pg_mb_radix_tree *map, + const pg_utf_to_local_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); +extern int LocalToUtf(const unsigned char *iso, int len, + unsigned char *utf, + const pg_mb_radix_tree *map, + const pg_local_to_utf_combined *cmap, int cmapsize, + utf_local_conversion_func conv_func, + int encoding, bool noError); extern bool pg_verifymbstr(const char *mbstr, int len, bool noError); extern bool pg_verify_mbstr(int encoding, const char *mbstr, int len, @@ -656,18 +656,19 @@ extern void report_invalid_encoding(int encoding, const char *mbstr, int len) pg extern void report_untranslatable_char(int src_encoding, int dest_encoding, const char *mbstr, int len) pg_attribute_noreturn(); -extern void local2local(const unsigned char *l, unsigned char *p, int len, - int src_encoding, int dest_encoding, const unsigned char *tab); -extern void latin2mic(const unsigned char *l, unsigned char *p, int len, - int lc, int encoding); -extern void mic2latin(const unsigned char *mic, unsigned char *p, int len, - int lc, int encoding); -extern void latin2mic_with_table(const unsigned char *l, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); -extern void mic2latin_with_table(const unsigned char *mic, unsigned char *p, - int len, int lc, int encoding, - const unsigned char *tab); +extern int local2local(const unsigned char *l, unsigned char *p, int len, + int src_encoding, int dest_encoding, const unsigned char *tab, + bool noError); +extern int latin2mic(const unsigned char *l, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int mic2latin(const unsigned char *mic, unsigned char *p, int len, + int lc, int encoding, bool noError); +extern int latin2mic_with_table(const unsigned char *l, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); +extern int mic2latin_with_table(const unsigned char *mic, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab, bool noError); #ifdef WIN32 extern WCHAR *pgwin32_message_to_UTF16(const char *str, int len, int *utf16len); diff --git a/src/test/regress/expected/opr_sanity.out b/src/test/regress/expected/opr_sanity.out index 254ca06d3dd..23ba60e395f 100644 --- a/src/test/regress/expected/opr_sanity.out +++ b/src/test/regress/expected/opr_sanity.out @@ -1052,13 +1052,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); oid | proname | oid | conname -----+---------+-----+--------- (0 rows) diff --git a/src/test/regress/sql/opr_sanity.sql b/src/test/regress/sql/opr_sanity.sql index bbd3834b634..04691745981 100644 --- a/src/test/regress/sql/opr_sanity.sql +++ b/src/test/regress/sql/opr_sanity.sql @@ -556,13 +556,14 @@ WHERE p1.conproc = 0 OR SELECT p.oid, p.proname, c.oid, c.conname FROM pg_proc p, pg_conversion c WHERE p.oid = c.conproc AND - (p.prorettype != 'void'::regtype OR p.proretset OR - p.pronargs != 5 OR + (p.prorettype != 'int4'::regtype OR p.proretset OR + p.pronargs != 6 OR p.proargtypes[0] != 'int4'::regtype OR p.proargtypes[1] != 'int4'::regtype OR p.proargtypes[2] != 'cstring'::regtype OR p.proargtypes[3] != 'internal'::regtype OR - p.proargtypes[4] != 'int4'::regtype); + p.proargtypes[4] != 'int4'::regtype OR + p.proargtypes[5] != 'bool'::regtype); -- Check for conprocs that don't perform the specific conversion that -- pg_conversion alleges they do, by trying to invoke each conversion -- 2.29.2 --------------B7FB7AC96BFBBB314DDCCEF3 Content-Type: text/x-patch; charset=UTF-8; name="v2-0002-Do-COPY-FROM-encoding-conversion-verification-in-.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="v2-0002-Do-COPY-FROM-encoding-conversion-verification-in-.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 34+ messages in thread
* Allow database owners to CREATE EVENT TRIGGER @ 2025-03-05 01:16 Steve Chavez <[email protected]> 0 siblings, 2 replies; 34+ messages in thread From: Steve Chavez @ 2025-03-05 01:16 UTC (permalink / raw) To: pgsql-hackers Hello hackers, Currently PostgreSQL only allows creating event triggers for superusers, this prevents usage on PostgreSQL service providers, which do not grant superuser access. This patch allows database owners to create event triggers, while preventing privilege escalation. Unlike superuser event triggers, which execute functions for every role, database owner event triggers are only executed for non-superusers. This is necessary to prevent privesc. i.e. a superuser tripping on an event trigger containing an `ALTER ROLE dbowner SUPERUSER`. For skipping dbowner event triggers for superusers: - A restriction is added for superuser event triggers, the event trigger function must be owned by a superuser. + While this is a breaking change, I think it's minor as the usual flow is to "login as superuser" -> "create an evtrig function" -> "create the evtrig". This is also proved by the existing tests, which barely change. - A restriction is added for dbowner event triggers, the event trigger function must not be owned by a superuser. This way we can filter dbowner event trigger functions inside `EventTriggerInvoke`. Tests are included in the patch, I've added a dedicated regression file for easier review. Only a couple of error messages of the existing event trigger regression tests are changed. Any feedback is welcomed. I haven't added docs yet but I'll gladly add them if the community thinks this patch makes sense. (Previous thread that also discussed allowing event triggers for non-superusers: https://www.postgresql.org/message-id/flat/81C10FFB-5ADC-4956-9337-FA248A4CC20D%40enterprisedb.com#7... ) Best regards, Steve Chavez Attachments: [text/x-patch] 0001-Allow-database-owners-to-CREATE-EVENT-TRIGGER.patch (11.0K, ../../CAGRrpzbtYDkg7_xwfzrqByYgCJQbbL38tADyuN+6tAkbA-Pnkg@mail.gmail.com/3-0001-Allow-database-owners-to-CREATE-EVENT-TRIGGER.patch) download | inline diff: From 84965d3ad70c4794f93473b939f5437c0d154826 Mon Sep 17 00:00:00 2001 From: steve-chavez <[email protected]> Date: Wed, 26 Feb 2025 20:17:36 -0500 Subject: [PATCH] Allow database owners to CREATE EVENT TRIGGER --- src/backend/commands/dbcommands.c | 22 ++++ src/backend/commands/event_trigger.c | 38 ++++-- src/backend/utils/cache/lsyscache.c | 23 ++++ src/include/commands/dbcommands.h | 1 + src/include/utils/lsyscache.h | 1 + src/test/regress/expected/event_trigger.out | 2 +- src/test/regress/parallel_schedule | 2 +- .../regress/sql/event_trigger_dbowner.sql | 117 ++++++++++++++++++ 8 files changed, 197 insertions(+), 9 deletions(-) create mode 100644 src/test/regress/sql/event_trigger_dbowner.sql diff --git a/src/backend/commands/dbcommands.c b/src/backend/commands/dbcommands.c index 1753b289074..4cd31dc1d90 100644 --- a/src/backend/commands/dbcommands.c +++ b/src/backend/commands/dbcommands.c @@ -3201,6 +3201,28 @@ get_database_name(Oid dbid) return result; } +/* + * get_database_owner - given a database OID, look up the owner OID + * + * If the owner is not found, it will return InvalidOid + */ +Oid +get_database_owner(Oid dbid) +{ + HeapTuple dbtuple; + Oid dbowner; + + dbtuple = SearchSysCache1(DATABASEOID, ObjectIdGetDatum(dbid)); + if (HeapTupleIsValid(dbtuple)) + { + dbowner = ((Form_pg_database) GETSTRUCT(dbtuple))->datdba; + ReleaseSysCache(dbtuple); + } + else + dbowner = InvalidOid; + + return dbowner; +} /* * While dropping a database the pg_database row is marked invalid, but the diff --git a/src/backend/commands/event_trigger.c b/src/backend/commands/event_trigger.c index edc2c988e29..62e7c7326f4 100644 --- a/src/backend/commands/event_trigger.c +++ b/src/backend/commands/event_trigger.c @@ -34,6 +34,7 @@ #include "catalog/pg_trigger.h" #include "catalog/pg_ts_config.h" #include "catalog/pg_type.h" +#include "commands/dbcommands.h" #include "commands/event_trigger.h" #include "commands/extension.h" #include "commands/trigger.h" @@ -125,18 +126,17 @@ CreateEventTrigger(CreateEventTrigStmt *stmt) Oid evtowner = GetUserId(); ListCell *lc; List *tags = NULL; + bool is_database_owner = (evtowner == get_database_owner(MyDatabaseId)); + bool owner_is_super = superuser_arg(evtowner); + bool function_is_owned_by_super; - /* - * It would be nice to allow database owners or even regular users to do - * this, but there are obvious privilege escalation risks which would have - * to somehow be plugged first. - */ - if (!superuser()) + if (!owner_is_super && !is_database_owner){ ereport(ERROR, (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), errmsg("permission denied to create event trigger \"%s\"", stmt->trigname), - errhint("Must be superuser to create an event trigger."))); + errhint("Must be the database owner or superuser to create an event trigger."))); + } /* Validate event name. */ if (strcmp(stmt->eventname, "ddl_command_start") != 0 && @@ -200,6 +200,24 @@ CreateEventTrigger(CreateEventTrigStmt *stmt) errmsg("function %s must return type %s", NameListToString(stmt->funcname), "event_trigger"))); + function_is_owned_by_super = superuser_arg(get_func_owner(funcoid)); + + if(owner_is_super && !function_is_owned_by_super){ + ereport(ERROR, ( + errcode(ERRCODE_INVALID_OBJECT_DEFINITION) + , errmsg("A superuser event trigger must execute a superuser owned function") + , errdetail("The current user \"%s\" is a superuser and the function \"%s\" is owned by a non-superuser", GetUserNameFromId(evtowner, false), NameListToString(stmt->funcname)) + )); + } + + if(!owner_is_super && function_is_owned_by_super){ + ereport(ERROR, ( + errcode(ERRCODE_INVALID_OBJECT_DEFINITION) + , errmsg("A database owner event trigger must not execute a superuser owned function") + , errdetail("The function \"%s\" is owned by a superuser", NameListToString(stmt->funcname)) + )); + } + /* Insert catalog entries. */ return insert_event_trigger_tuple(stmt->trigname, stmt->eventname, evtowner, funcoid, tags); @@ -1087,9 +1105,15 @@ EventTriggerInvoke(List *fn_oid_list, EventTriggerData *trigdata) Oid fnoid = lfirst_oid(lc); FmgrInfo flinfo; PgStat_FunctionCallUsage fcusage; + bool function_is_owned_by_super = superuser_arg(get_func_owner(fnoid)); elog(DEBUG1, "EventTriggerInvoke %u", fnoid); + if (superuser() && !function_is_owned_by_super) { + elog(DEBUG1, "Non-superuser owned event trigger function \"%s\" is skipped for superuser \"%s\"", get_func_name(fnoid), GetUserNameFromId(GetUserId(), false)); + continue; + } + /* * We want each event trigger to be able to see the results of the * previous event trigger's action. Caller is responsible for any diff --git a/src/backend/utils/cache/lsyscache.c b/src/backend/utils/cache/lsyscache.c index 7bd476f3de7..3fc0eec9783 100644 --- a/src/backend/utils/cache/lsyscache.c +++ b/src/backend/utils/cache/lsyscache.c @@ -1650,6 +1650,29 @@ get_func_name(Oid funcid) return NULL; } +/* + * get_func_owner + * returns the name of the function owner the given funcid + */ +Oid +get_func_owner(Oid funcid) +{ + HeapTuple tp; + + tp = SearchSysCache1(PROCOID, ObjectIdGetDatum(funcid)); + if (HeapTupleIsValid(tp)) + { + Form_pg_proc functup = (Form_pg_proc) GETSTRUCT(tp); + Oid result; + + result = functup->proowner; + ReleaseSysCache(tp); + return result; + } + else + return InvalidOid; +} + /* * get_func_namespace * diff --git a/src/include/commands/dbcommands.h b/src/include/commands/dbcommands.h index 524ac6d97e8..4d572bb53ed 100644 --- a/src/include/commands/dbcommands.h +++ b/src/include/commands/dbcommands.h @@ -30,6 +30,7 @@ extern ObjectAddress AlterDatabaseOwner(const char *dbname, Oid newOwnerId); extern Oid get_database_oid(const char *dbname, bool missing_ok); extern char *get_database_name(Oid dbid); +extern Oid get_database_owner(Oid dbid); extern bool have_createdb_privilege(void); extern void check_encoding_locale_matches(int encoding, const char *collate, const char *ctype); diff --git a/src/include/utils/lsyscache.h b/src/include/utils/lsyscache.h index 6fab7aa6009..b9d560a6ef9 100644 --- a/src/include/utils/lsyscache.h +++ b/src/include/utils/lsyscache.h @@ -122,6 +122,7 @@ extern Oid get_negator(Oid opno); extern RegProcedure get_oprrest(Oid opno); extern RegProcedure get_oprjoin(Oid opno); extern char *get_func_name(Oid funcid); +extern Oid get_func_owner(Oid funcid); extern Oid get_func_namespace(Oid funcid); extern Oid get_func_rettype(Oid funcid); extern int get_func_nargs(Oid funcid); diff --git a/src/test/regress/expected/event_trigger.out b/src/test/regress/expected/event_trigger.out index 7b2198eac6f..f951031b4c8 100644 --- a/src/test/regress/expected/event_trigger.out +++ b/src/test/regress/expected/event_trigger.out @@ -90,7 +90,7 @@ set role regress_evt_user; create event trigger regress_event_trigger_noperms on ddl_command_start execute procedure test_event_trigger(); ERROR: permission denied to create event trigger "regress_event_trigger_noperms" -HINT: Must be superuser to create an event trigger. +HINT: Must be the database owner or superuser to create an event trigger. reset role; -- test enabling and disabling alter event trigger regress_event_trigger disable; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index 37b6d21e1f9..6b322c76b00 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -124,7 +124,7 @@ test: partition_join partition_prune reloptions hash_part indexing partition_agg # event_trigger depends on create_am and cannot run concurrently with # any test that runs DDL # oidjoins is read-only, though, and should run late for best coverage -test: oidjoins event_trigger +test: oidjoins event_trigger event_trigger_dbowner # event_trigger_login cannot run concurrently with any other tests because # on-login event handling could catch connection of a concurrent test. diff --git a/src/test/regress/sql/event_trigger_dbowner.sql b/src/test/regress/sql/event_trigger_dbowner.sql new file mode 100644 index 00000000000..00b62045e47 --- /dev/null +++ b/src/test/regress/sql/event_trigger_dbowner.sql @@ -0,0 +1,117 @@ +-- set up +create role regress_non_owner; +create role regress_owner login nosuperuser; +create database regress_owner owner regress_owner; +\connect regress_owner +grant create on schema public to regress_non_owner; +create function regress_super_show_cur_user() + returns event_trigger + language plpgsql as +$$ +begin + raise notice 'the superuser event trigger is executed'; +end; +$$; +\echo + +-- a database owner can create event triggers +set role regress_owner; +\echo + +create function regress_show_cur_user() + returns event_trigger + language plpgsql as +$$ +begin + raise notice 'the event trigger is executed for %', current_user; +end; +$$; +\echo + +create event trigger regress_evtrig_1 on ddl_command_end +execute procedure regress_show_cur_user(); +\echo + +reset role; +\echo + +-- a database owner cannot create event triggers when the function is superuser owned +set role regress_owner; +\echo + +create event trigger regress_evtrig_2 on ddl_command_end +execute procedure regress_super_show_cur_user(); +\echo + +reset role; +\echo + +-- a superuser cannot create event triggers when the function is not superuser owned +create event trigger regress_evtrig_3 on ddl_command_end +execute procedure regress_show_cur_user(); +\echo + +-- a non-database owner cannot create event triggers +set role regress_non_owner; +\echo + +create event trigger regress_evtrig_4 on ddl_command_end +execute procedure regress_show_cur_user(); +\echo + +reset role; +\echo + +-- database owner event trigger will fire for database owners +set role regress_owner; +create table regress_foo(); +reset role; +\echo + +-- database owner event trigger will fire for non-database owners +set role regress_non_owner; +create table regress_bar(); +reset role; +\echo + +-- database owner event trigger will not fire for superusers +create table regress_qux(); +\echo + +-- superuser event triggers will fire for all roles +create event trigger regress_evtrig_5 on ddl_command_end +execute procedure regress_super_show_cur_user(); +\echo + +-- will fire for superusers +create table regress_super_foo(); +\echo + +-- will fire for db owners +set role regress_owner; +create table regress_foo_2(); +reset role; +\echo + +-- will fire for non-db-owners +set role regress_owner; +create table regress_bar_2(); +reset role; +\echo + +-- clean up +drop event trigger regress_evtrig_5; +drop table regress_foo; +drop table regress_foo_2; +drop table regress_bar; +drop table regress_bar_2; +drop table regress_qux; +drop table regress_super_foo; +revoke create on schema public from regress_non_owner; +drop role regress_non_owner; +drop event trigger regress_evtrig_1; +drop function regress_show_cur_user(); +drop function regress_super_show_cur_user(); +\connect regression +drop database regress_owner; +drop role regress_owner; -- 2.40.1 ^ permalink raw reply [nested|flat] 34+ messages in thread
* Re: Allow database owners to CREATE EVENT TRIGGER @ 2025-03-05 13:46 Aleksander Alekseev <[email protected]> parent: Steve Chavez <[email protected]> 1 sibling, 1 reply; 34+ messages in thread From: Aleksander Alekseev @ 2025-03-05 13:46 UTC (permalink / raw) To: Steve Chavez <[email protected]>; +Cc: pgsql-hackers Hi, > Unlike superuser event triggers, which execute functions for every role, database owner event triggers are only executed for non-superusers. Even if we forget about the security aspect for a moment, personally I have mixed feelings about the idea of adding a new type of event trigger that looks like a regular one but works differently depending on who creates them. Also what will happen if I promote a user to a superuser or vice versa? All this doesn't strike me as a great UI. Maybe you could explain your particular use case? -- Best regards, Aleksander Alekseev ^ permalink raw reply [nested|flat] 34+ messages in thread
* Re: Allow database owners to CREATE EVENT TRIGGER @ 2025-03-05 13:54 David G. Johnston <[email protected]> parent: Aleksander Alekseev <[email protected]> 0 siblings, 1 reply; 34+ messages in thread From: David G. Johnston @ 2025-03-05 13:54 UTC (permalink / raw) To: Aleksander Alekseev <[email protected]>; +Cc: Steve Chavez <[email protected]>; pgsql-hackers On Wednesday, March 5, 2025, Aleksander Alekseev <[email protected]> wrote: > > > Unlike superuser event triggers, which execute functions for every role, > database owner event triggers are only executed for non-superusers. > All this doesn't strike me as a great UI. > Yeah. Seems better to make “execute_for” an attribute of the trigger and allow both superusers and non-superusers to create them. Then enforce that non-superusers must specify the more limited value. Though it would seem nice to be able to exclude the pseudo-admin roles these service providers create as well. David J. ^ permalink raw reply [nested|flat] 34+ messages in thread
* Re: Allow database owners to CREATE EVENT TRIGGER @ 2025-03-05 14:55 Steve Chavez <[email protected]> parent: David G. Johnston <[email protected]> 0 siblings, 2 replies; 34+ messages in thread From: Steve Chavez @ 2025-03-05 14:55 UTC (permalink / raw) To: David G. Johnston <[email protected]>; +Cc: Aleksander Alekseev <[email protected]>; pgsql-hackers Many thanks for the feedback. > an attribute of the trigger and allow both superusers and non-superusers to create them. The above is the crux of the issue. Superuser evtrigs can target every role but non-superusers evtrigs must apply only to a restricted set of roles to avoid privilege escalation. With an explicit attribute, I guess the SQL syntax should be like: > Seems better to make “execute_for” an attribute of the trigger CREATE EVENT TRIGGER name ... FOR role1, role2; Now say a new role is created and has usage/create on this database and we want the evtrig to apply to it. We would need to manually update the list of roles, it won't be done automatically. That is a problem if, for example, we need to enforce an audit trail through event triggers. This is why I thought the database owner is the right role to allow evtrig creation since it won't need an explicit list of roles. How about requiring explicit non-superuser execution for the database owner evtrig? It would be like: CREATE EVENT TRIGGER name ... FOR NOSUPERUSER; I welcome any alternative ideas. Best regards, Steve Chavez On Wed, 5 Mar 2025 at 08:54, David G. Johnston <[email protected]> wrote: > On Wednesday, March 5, 2025, Aleksander Alekseev <[email protected]> > wrote: >> >> > Unlike superuser event triggers, which execute functions for every >> role, database owner event triggers are only executed for non-superusers. >> > > All this doesn't strike me as a great UI. >> > > Yeah. Seems better to make “execute_for” an attribute of the trigger and > allow both superusers and non-superusers to create them. Then enforce that > non-superusers must specify the more limited value. > > Though it would seem nice to be able to exclude the pseudo-admin roles > these service providers create as well. > > David J. > > ^ permalink raw reply [nested|flat] 34+ messages in thread
* Re: Allow database owners to CREATE EVENT TRIGGER @ 2025-03-05 14:58 David G. Johnston <[email protected]> parent: Steve Chavez <[email protected]> 1 sibling, 0 replies; 34+ messages in thread From: David G. Johnston @ 2025-03-05 14:58 UTC (permalink / raw) To: Steve Chavez <[email protected]>; +Cc: Aleksander Alekseev <[email protected]>; pgsql-hackers On Wed, Mar 5, 2025 at 7:55 AM Steve Chavez <[email protected]> wrote: > How about requiring explicit non-superuser execution for the database > owner evtrig? It would be like: > > CREATE EVENT TRIGGER name ... FOR NOSUPERUSER; > This is more what I was thinking - which works for a boolean. The ability to have an exclusion list would make sense, or maybe just a predefined role pg_bypass_eventtriggers. David J. ^ permalink raw reply [nested|flat] 34+ messages in thread
* Re: Allow database owners to CREATE EVENT TRIGGER @ 2025-03-05 15:13 Tom Lane <[email protected]> parent: Steve Chavez <[email protected]> 1 sibling, 1 reply; 34+ messages in thread From: Tom Lane @ 2025-03-05 15:13 UTC (permalink / raw) To: Steve Chavez <[email protected]>; +Cc: pgsql-hackers Steve Chavez <[email protected]> writes: > Currently PostgreSQL only allows creating event triggers for superusers, > this prevents usage on PostgreSQL service providers, which do not grant > superuser access. > This patch allows database owners to create event triggers, while > preventing privilege escalation. I'm pretty down on this, at least in the form presented. While you may have managed to keep the DB owner from sabotaging superusers, the proposed feature still allows owning every other special role, for example pg_write_server_files (which is something that's pretty trivially exploitable to get superuser). Since we've generally been working towards not requiring superuser for most routine admin tasks, that problem is going to get worse not better over time. I don't want to see us add a feature that creates a security reason to avoid using those special roles in favor of using a superuser. Or in other words: not-superuser to superuser is far from the only type of privilege escalation that we need to prevent. regards, tom lane ^ permalink raw reply [nested|flat] 34+ messages in thread
* Re: Allow database owners to CREATE EVENT TRIGGER @ 2025-03-05 15:28 Tom Lane <[email protected]> parent: Tom Lane <[email protected]> 0 siblings, 1 reply; 34+ messages in thread From: Tom Lane @ 2025-03-05 15:28 UTC (permalink / raw) To: Steve Chavez <[email protected]>; +Cc: pgsql-hackers I wrote: > Or in other words: not-superuser to superuser is far from the only > type of privilege escalation that we need to prevent. After reflecting on that for a moment: maybe say that an event trigger fires for queries that are run by a role that the trigger's owning role is a member of? That changes nothing for superuser-owned triggers. regards, tom lane ^ permalink raw reply [nested|flat] 34+ messages in thread
* Re: Allow database owners to CREATE EVENT TRIGGER @ 2025-03-05 16:17 Isaac Morland <[email protected]> parent: Tom Lane <[email protected]> 0 siblings, 0 replies; 34+ messages in thread From: Isaac Morland @ 2025-03-05 16:17 UTC (permalink / raw) To: Tom Lane <[email protected]>; +Cc: Steve Chavez <[email protected]>; pgsql-hackers On Wed, 5 Mar 2025 at 10:28, Tom Lane <[email protected]> wrote: > I wrote: > > Or in other words: not-superuser to superuser is far from the only > > type of privilege escalation that we need to prevent. > > After reflecting on that for a moment: maybe say that an event trigger > fires for queries that are run by a role that the trigger's owning > role is a member of? That changes nothing for superuser-owned > triggers. > Can somebody remind me why triggers don't run as their owner in the first place? It would make triggers way more useful, and eliminate the whole issue of trigger owners escalating to whomever tries to access the object on which the trigger is defined. ^ permalink raw reply [nested|flat] 34+ messages in thread
* Re: Allow database owners to CREATE EVENT TRIGGER @ 2025-03-07 20:19 Tom Lane <[email protected]> parent: Steve Chavez <[email protected]> 1 sibling, 1 reply; 34+ messages in thread From: Tom Lane @ 2025-03-07 20:19 UTC (permalink / raw) To: Steve Chavez <[email protected]>; +Cc: David G. Johnston <[email protected]>; Aleksander Alekseev <[email protected]>; pgsql-hackers Steve Chavez <[email protected]> writes: > This is why I thought the database owner is the right role to allow evtrig > creation since it won't need an explicit list of roles. > How about requiring explicit non-superuser execution for the database owner > evtrig? It would be like: > CREATE EVENT TRIGGER name ... FOR NOSUPERUSER; Well, no. That still allows the database owner to commandeer any non-superuser role. Even if we tightened "nosuperuser" to mean "not superuser and not any built-in role", I don't think it will fly. Here is the real problem: database owners are not specially privileged in Postgres. Yeah, they can drop their DB, but they don't have automatic permissions to mess with other people's objects inside the DB. (Much the same can be said of schema owners.) So any proposal that effectively gives DB owners such privileges is going to fail. I realize that some other DBMSes assign more privileges to schema or DB owners, but we don't and I don't think we're open to changing that. I think you need to be thinking of this in terms of "what sort of feature can we add that can be allowed to any SQL user?" The notion I proposed earlier that an event trigger only fires on queries executed by roles the trigger's owner belongs to is (AFAICS) safe to allow to anyone. If that's not good enough for your notion of what a DB owner should be able to do, the answer is to grant the DB owner membership in every role that uses her database. That's effectively what the feature you're suggesting would do anyway. regards, tom lane ^ permalink raw reply [nested|flat] 34+ messages in thread
* Re: Allow database owners to CREATE EVENT TRIGGER @ 2025-03-08 05:03 Steve Chavez <[email protected]> parent: Tom Lane <[email protected]> 0 siblings, 0 replies; 34+ messages in thread From: Steve Chavez @ 2025-03-08 05:03 UTC (permalink / raw) To: Tom Lane <[email protected]>; +Cc: David G. Johnston <[email protected]>; Aleksander Alekseev <[email protected]>; pgsql-hackers --0000000000002ca6e4062fcdabf7 Content-Type: text/plain; charset="UTF-8" Hi Tom, > Well, no. That still allows the database owner to commandeer any > non-superuser role. Even if we tightened "nosuperuser" to mean > "not superuser and not any built-in role", I don't think it will fly. Why would the predefined roles be taken into consideration here? The docs on https://www.postgresql.org/docs/current/predefined-roles.html say: " pg_read_server_files, pg_write_server_files and pg_execute_server_program..." " ..they could be used to gain superuser-level access, therefore great care should be taken when granting these roles to users." If a dbowner event trigger does `GRANT pg_read_server_files TO current_user;` inside it will fail with `ERROR: permission denied to grant role "pg_read_server_files"`. The only way for that to succeed is for a superuser to explicitly grant access to `pg_read_server_files` before, and that would have to be a conscious operation. I would appreciate any clarification here. > maybe say that an event trigger fires for queries that are run by a role - that the trigger's owning role is a member of? The role membership approach would work but it seems insufficient. For example consider `pgaudit` which installs event triggers and requires superuser. Let's assume `pgaudit` would try to adopt this new feature. Then it would need to provide some special role like `pgaudit_admin`, create the event triggers under this role, and users of this extension would have to manually grant membership to `pgaudit_admin` for the audit event triggers to fire. That is a problem because that's easy to forget when creating new roles and the audit event triggers won't be "enforced". So in that case I guess `pgaudit` developers would keep requiring superuser and not bother to adopt this new feature. ^ permalink raw reply [nested|flat] 34+ messages in thread
end of thread, other threads:[~2025-03-08 05:03 UTC | newest] Thread overview: 34+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 2020-12-16 10:13 [PATCH 4/5] Change conversion function signature. Heikki Linnakangas <[email protected]> 2021-01-28 16:42 [PATCH v3 2/5] Change conversion function signature. Heikki Linnakangas <[email protected]> 2021-01-28 16:42 [PATCH v3 2/5] Change conversion function signature. Heikki Linnakangas <[email protected]> 2021-01-28 16:42 [PATCH v3 2/5] Change conversion function signature. Heikki Linnakangas <[email protected]> 2021-01-28 16:42 [PATCH v3 2/5] Change conversion function signature. Heikki Linnakangas <[email protected]> 2021-01-28 16:42 [PATCH v3 2/5] Change conversion function signature. Heikki Linnakangas <[email protected]> 2021-01-28 16:42 [PATCH v2 1/2] Change conversion function signature. Heikki Linnakangas <[email protected]> 2021-01-28 16:42 [PATCH v3 2/5] Change conversion function signature. Heikki Linnakangas <[email protected]> 2021-01-28 16:42 [PATCH v3 2/5] Change conversion function signature. Heikki Linnakangas <[email protected]> 2021-01-28 16:42 [PATCH v3 2/5] Change conversion function signature. Heikki Linnakangas <[email protected]> 2021-01-28 16:42 [PATCH v3 2/5] Change conversion function signature. Heikki Linnakangas <[email protected]> 2021-01-28 16:42 [PATCH v3 2/5] Change conversion function signature. Heikki Linnakangas <[email protected]> 2021-01-28 16:42 [PATCH v3 2/5] Change conversion function signature. Heikki Linnakangas <[email protected]> 2021-01-28 16:42 [PATCH v3 2/5] Change conversion function signature. Heikki Linnakangas <[email protected]> 2021-01-28 16:42 [PATCH v3 2/5] Change conversion function signature. Heikki Linnakangas <[email protected]> 2021-01-28 16:42 [PATCH v3 2/5] Change conversion function signature. Heikki Linnakangas <[email protected]> 2021-01-28 16:42 [PATCH v3 2/5] Change conversion function signature. Heikki Linnakangas <[email protected]> 2021-01-28 16:42 [PATCH v3 2/5] Change conversion function signature. Heikki Linnakangas <[email protected]> 2021-01-28 16:42 [PATCH v3 2/5] Change conversion function signature. Heikki Linnakangas <[email protected]> 2021-01-28 16:42 [PATCH v3 2/5] Change conversion function signature. Heikki Linnakangas <[email protected]> 2021-01-28 16:42 [PATCH v3 2/5] Change conversion function signature. Heikki Linnakangas <[email protected]> 2021-01-28 16:42 [PATCH v3 2/5] Change conversion function signature. Heikki Linnakangas <[email protected]> 2021-01-28 16:42 [PATCH v3 2/5] Change conversion function signature. Heikki Linnakangas <[email protected]> 2021-01-28 16:42 [PATCH v3 2/5] Change conversion function signature. Heikki Linnakangas <[email protected]> 2025-03-05 01:16 Allow database owners to CREATE EVENT TRIGGER Steve Chavez <[email protected]> 2025-03-05 13:46 ` Re: Allow database owners to CREATE EVENT TRIGGER Aleksander Alekseev <[email protected]> 2025-03-05 13:54 ` Re: Allow database owners to CREATE EVENT TRIGGER David G. Johnston <[email protected]> 2025-03-05 14:55 ` Re: Allow database owners to CREATE EVENT TRIGGER Steve Chavez <[email protected]> 2025-03-05 14:58 ` Re: Allow database owners to CREATE EVENT TRIGGER David G. Johnston <[email protected]> 2025-03-07 20:19 ` Re: Allow database owners to CREATE EVENT TRIGGER Tom Lane <[email protected]> 2025-03-08 05:03 ` Re: Allow database owners to CREATE EVENT TRIGGER Steve Chavez <[email protected]> 2025-03-05 15:13 ` Re: Allow database owners to CREATE EVENT TRIGGER Tom Lane <[email protected]> 2025-03-05 15:28 ` Re: Allow database owners to CREATE EVENT TRIGGER Tom Lane <[email protected]> 2025-03-05 16:17 ` Re: Allow database owners to CREATE EVENT TRIGGER Isaac Morland <[email protected]>
This inbox is served by agora; see mirroring instructions for how to clone and mirror all data and code used for this inbox