public inbox for [email protected]
help / color / mirror / Atom feedFrom: Jeff Davis <[email protected]>
To: Peter Geoghegan <[email protected]>
Cc: [email protected]
Subject: Re: Rework of collation code, extensibility
Date: Fri, 20 Jan 2023 12:54:25 -0800
Message-ID: <[email protected]> (raw)
In-Reply-To: <CAH2-WzmDEYEobEjWYpnHPx3F92pxaG1W4TVFdhCMjjHK+voq9g@mail.gmail.com>
References: <[email protected]>
<[email protected]>
<[email protected]>
<CAH2-WzmQ+qe_bemX=S6T_xvZ-cpfDOV06imo3kpmx4m7b6b7jg@mail.gmail.com>
<[email protected]>
<CAH2-WzmDEYEobEjWYpnHPx3F92pxaG1W4TVFdhCMjjHK+voq9g@mail.gmail.com>
On Tue, 2023-01-17 at 14:18 -0800, Peter Geoghegan wrote:
> The second goal is a perfectly good enough goal on its own, and one
> that I am totally supportive of. Making the code clearer is icing on
> the cake.
Attached v8, which is just a rebase.
To reiterate: commitfest entry
https://commitfest.postgresql.org/41/3956/ is dependent on these
patches and is a big part of the motivation for refactoring.
>
> I don't know. Quite possibly not. It would be nice to have some data
> on that, though.
I tested with hash aggregation, which might be more dependent on
pg_locale_deterministic() than sorting. I didn't see any significant
difference between master and the refactoring branch, so I don't see a
need to make that function "inline".
I also re-tested sorting and found some interesting results for en-US-
x-icu on a UTF-8 database (which is I suspect one of the most common
configurations for ICU):
* the refactoring branch is now more than 5% faster, whether using
abbreviated keys or not
* disabling abbreviated keys makes sorting 8-10% faster on both
master and the refactoring branch
Both of these are surprising, and I haven't investigated deeply yet.
Maybe something about LTO, some intervening patch, or I just made some
mistakes somewhere (I did this fairly quickly). But as of now, it
doesn't look like the refactoring patch hurts anything.
--
Jeff Davis
PostgreSQL Contributor Team - AWS
Attachments:
[text/x-patch] v8-0002-Refactor-pg_locale_t-routines.patch (43.5K, ../[email protected]/2-v8-0002-Refactor-pg_locale_t-routines.patch)
download | inline diff:
From d1e2e1757b043c876695b8fa8c304b5126efb3aa Mon Sep 17 00:00:00 2001
From: Jeff Davis <[email protected]>
Date: Mon, 5 Dec 2022 10:43:52 -0800
Subject: [PATCH v8 2/2] Refactor pg_locale_t routines.
* add pg_locale_internal.h to hide pg_locale_struct
* move info.lt into info.libc.lt to match icu
* introduce init_default_locale()
* introduce pg_locale_deterministic() accessor
* make default_locale a static global in pg_locale.c
* refactor pg_newlocale_from_collation()
---
src/backend/access/hash/hashfunc.c | 82 +++---
src/backend/commands/collationcmds.c | 1 +
src/backend/regex/regc_pg_locale.c | 45 ++--
src/backend/utils/adt/formatting.c | 25 +-
src/backend/utils/adt/like.c | 3 +-
src/backend/utils/adt/like_support.c | 3 +-
src/backend/utils/adt/pg_locale.c | 342 +++++++++++++++----------
src/backend/utils/adt/varchar.c | 62 ++---
src/backend/utils/adt/varlena.c | 14 +-
src/backend/utils/init/postinit.c | 29 ++-
src/include/utils/pg_locale.h | 55 +---
src/include/utils/pg_locale_internal.h | 68 +++++
12 files changed, 402 insertions(+), 327 deletions(-)
create mode 100644 src/include/utils/pg_locale_internal.h
diff --git a/src/backend/access/hash/hashfunc.c b/src/backend/access/hash/hashfunc.c
index c0ed995919..7cbd39f466 100644
--- a/src/backend/access/hash/hashfunc.c
+++ b/src/backend/access/hash/hashfunc.c
@@ -282,36 +282,28 @@ hashtext(PG_FUNCTION_ARGS)
if (!lc_collate_is_c(collid))
mylocale = pg_newlocale_from_collation(collid);
- if (!mylocale || mylocale->deterministic)
+ if (pg_locale_deterministic(mylocale))
{
result = hash_any((unsigned char *) VARDATA_ANY(key),
VARSIZE_ANY_EXHDR(key));
}
else
{
-#ifdef USE_ICU
- if (mylocale->provider == COLLPROVIDER_ICU)
- {
- Size bsize, rsize;
- char *buf;
- const char *keydata = VARDATA_ANY(key);
- size_t keylen = VARSIZE_ANY_EXHDR(key);
-
- bsize = pg_strnxfrm(NULL, 0, keydata, keylen, mylocale);
- buf = palloc(bsize);
-
- rsize = pg_strnxfrm(buf, bsize, keydata, keylen, mylocale);
- if (rsize != bsize)
- elog(ERROR, "pg_strnxfrm() returned unexpected result");
-
- result = hash_any((uint8_t *) buf, bsize);
-
- pfree(buf);
- }
- else
-#endif
- /* shouldn't happen */
- elog(ERROR, "unsupported collprovider: %c", mylocale->provider);
+ Size bsize, rsize;
+ char *buf;
+ const char *keydata = VARDATA_ANY(key);
+ size_t keylen = VARSIZE_ANY_EXHDR(key);
+
+ bsize = pg_strnxfrm(NULL, 0, keydata, keylen, mylocale);
+ buf = palloc(bsize);
+
+ rsize = pg_strnxfrm(buf, bsize, keydata, keylen, mylocale);
+ if (rsize != bsize)
+ elog(ERROR, "pg_strnxfrm() returned unexpected result");
+
+ result = hash_any((uint8_t *) buf, bsize);
+
+ pfree(buf);
}
/* Avoid leaking memory for toasted inputs */
@@ -337,7 +329,7 @@ hashtextextended(PG_FUNCTION_ARGS)
if (!lc_collate_is_c(collid))
mylocale = pg_newlocale_from_collation(collid);
- if (!mylocale || mylocale->deterministic)
+ if (pg_locale_deterministic(mylocale))
{
result = hash_any_extended((unsigned char *) VARDATA_ANY(key),
VARSIZE_ANY_EXHDR(key),
@@ -345,30 +337,22 @@ hashtextextended(PG_FUNCTION_ARGS)
}
else
{
-#ifdef USE_ICU
- if (mylocale->provider == COLLPROVIDER_ICU)
- {
- Size bsize, rsize;
- char *buf;
- const char *keydata = VARDATA_ANY(key);
- size_t keylen = VARSIZE_ANY_EXHDR(key);
-
- bsize = pg_strnxfrm(NULL, 0, keydata, keylen, mylocale);
- buf = palloc(bsize);
-
- rsize = pg_strnxfrm(buf, bsize, keydata, keylen, mylocale);
- if (rsize != bsize)
- elog(ERROR, "pg_strnxfrm() returned unexpected result");
-
- result = hash_any_extended((uint8_t *) buf, bsize,
- PG_GETARG_INT64(1));
-
- pfree(buf);
- }
- else
-#endif
- /* shouldn't happen */
- elog(ERROR, "unsupported collprovider: %c", mylocale->provider);
+ Size bsize, rsize;
+ char *buf;
+ const char *keydata = VARDATA_ANY(key);
+ size_t keylen = VARSIZE_ANY_EXHDR(key);
+
+ bsize = pg_strnxfrm(NULL, 0, keydata, keylen, mylocale);
+ buf = palloc(bsize);
+
+ rsize = pg_strnxfrm(buf, bsize, keydata, keylen, mylocale);
+ if (rsize != bsize)
+ elog(ERROR, "pg_strnxfrm() returned unexpected result");
+
+ result = hash_any_extended((uint8_t *) buf, bsize,
+ PG_GETARG_INT64(1));
+
+ pfree(buf);
}
PG_FREE_IF_COPY(key, 0);
diff --git a/src/backend/commands/collationcmds.c b/src/backend/commands/collationcmds.c
index 6a4311cc63..d878be2fb8 100644
--- a/src/backend/commands/collationcmds.c
+++ b/src/backend/commands/collationcmds.c
@@ -36,6 +36,7 @@
#include "utils/builtins.h"
#include "utils/lsyscache.h"
#include "utils/pg_locale.h"
+#include "utils/pg_locale_internal.h"
#include "utils/rel.h"
#include "utils/syscache.h"
diff --git a/src/backend/regex/regc_pg_locale.c b/src/backend/regex/regc_pg_locale.c
index 323f00516d..3dc89b0336 100644
--- a/src/backend/regex/regc_pg_locale.c
+++ b/src/backend/regex/regc_pg_locale.c
@@ -17,6 +17,7 @@
#include "catalog/pg_collation.h"
#include "utils/pg_locale.h"
+#include "utils/pg_locale_internal.h"
/*
* To provide as much functionality as possible on a variety of platforms,
@@ -306,13 +307,13 @@ pg_wc_isdigit(pg_wchar c)
case PG_REGEX_LOCALE_WIDE_L:
#ifdef HAVE_LOCALE_T
if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF)
- return iswdigit_l((wint_t) c, pg_regex_locale->info.lt);
+ return iswdigit_l((wint_t) c, pg_regex_locale->info.libc.lt);
#endif
/* FALL THRU */
case PG_REGEX_LOCALE_1BYTE_L:
#ifdef HAVE_LOCALE_T
return (c <= (pg_wchar) UCHAR_MAX &&
- isdigit_l((unsigned char) c, pg_regex_locale->info.lt));
+ isdigit_l((unsigned char) c, pg_regex_locale->info.libc.lt));
#endif
break;
case PG_REGEX_LOCALE_ICU:
@@ -342,13 +343,13 @@ pg_wc_isalpha(pg_wchar c)
case PG_REGEX_LOCALE_WIDE_L:
#ifdef HAVE_LOCALE_T
if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF)
- return iswalpha_l((wint_t) c, pg_regex_locale->info.lt);
+ return iswalpha_l((wint_t) c, pg_regex_locale->info.libc.lt);
#endif
/* FALL THRU */
case PG_REGEX_LOCALE_1BYTE_L:
#ifdef HAVE_LOCALE_T
return (c <= (pg_wchar) UCHAR_MAX &&
- isalpha_l((unsigned char) c, pg_regex_locale->info.lt));
+ isalpha_l((unsigned char) c, pg_regex_locale->info.libc.lt));
#endif
break;
case PG_REGEX_LOCALE_ICU:
@@ -378,13 +379,13 @@ pg_wc_isalnum(pg_wchar c)
case PG_REGEX_LOCALE_WIDE_L:
#ifdef HAVE_LOCALE_T
if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF)
- return iswalnum_l((wint_t) c, pg_regex_locale->info.lt);
+ return iswalnum_l((wint_t) c, pg_regex_locale->info.libc.lt);
#endif
/* FALL THRU */
case PG_REGEX_LOCALE_1BYTE_L:
#ifdef HAVE_LOCALE_T
return (c <= (pg_wchar) UCHAR_MAX &&
- isalnum_l((unsigned char) c, pg_regex_locale->info.lt));
+ isalnum_l((unsigned char) c, pg_regex_locale->info.libc.lt));
#endif
break;
case PG_REGEX_LOCALE_ICU:
@@ -423,13 +424,13 @@ pg_wc_isupper(pg_wchar c)
case PG_REGEX_LOCALE_WIDE_L:
#ifdef HAVE_LOCALE_T
if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF)
- return iswupper_l((wint_t) c, pg_regex_locale->info.lt);
+ return iswupper_l((wint_t) c, pg_regex_locale->info.libc.lt);
#endif
/* FALL THRU */
case PG_REGEX_LOCALE_1BYTE_L:
#ifdef HAVE_LOCALE_T
return (c <= (pg_wchar) UCHAR_MAX &&
- isupper_l((unsigned char) c, pg_regex_locale->info.lt));
+ isupper_l((unsigned char) c, pg_regex_locale->info.libc.lt));
#endif
break;
case PG_REGEX_LOCALE_ICU:
@@ -459,13 +460,13 @@ pg_wc_islower(pg_wchar c)
case PG_REGEX_LOCALE_WIDE_L:
#ifdef HAVE_LOCALE_T
if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF)
- return iswlower_l((wint_t) c, pg_regex_locale->info.lt);
+ return iswlower_l((wint_t) c, pg_regex_locale->info.libc.lt);
#endif
/* FALL THRU */
case PG_REGEX_LOCALE_1BYTE_L:
#ifdef HAVE_LOCALE_T
return (c <= (pg_wchar) UCHAR_MAX &&
- islower_l((unsigned char) c, pg_regex_locale->info.lt));
+ islower_l((unsigned char) c, pg_regex_locale->info.libc.lt));
#endif
break;
case PG_REGEX_LOCALE_ICU:
@@ -495,13 +496,13 @@ pg_wc_isgraph(pg_wchar c)
case PG_REGEX_LOCALE_WIDE_L:
#ifdef HAVE_LOCALE_T
if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF)
- return iswgraph_l((wint_t) c, pg_regex_locale->info.lt);
+ return iswgraph_l((wint_t) c, pg_regex_locale->info.libc.lt);
#endif
/* FALL THRU */
case PG_REGEX_LOCALE_1BYTE_L:
#ifdef HAVE_LOCALE_T
return (c <= (pg_wchar) UCHAR_MAX &&
- isgraph_l((unsigned char) c, pg_regex_locale->info.lt));
+ isgraph_l((unsigned char) c, pg_regex_locale->info.libc.lt));
#endif
break;
case PG_REGEX_LOCALE_ICU:
@@ -531,13 +532,13 @@ pg_wc_isprint(pg_wchar c)
case PG_REGEX_LOCALE_WIDE_L:
#ifdef HAVE_LOCALE_T
if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF)
- return iswprint_l((wint_t) c, pg_regex_locale->info.lt);
+ return iswprint_l((wint_t) c, pg_regex_locale->info.libc.lt);
#endif
/* FALL THRU */
case PG_REGEX_LOCALE_1BYTE_L:
#ifdef HAVE_LOCALE_T
return (c <= (pg_wchar) UCHAR_MAX &&
- isprint_l((unsigned char) c, pg_regex_locale->info.lt));
+ isprint_l((unsigned char) c, pg_regex_locale->info.libc.lt));
#endif
break;
case PG_REGEX_LOCALE_ICU:
@@ -567,13 +568,13 @@ pg_wc_ispunct(pg_wchar c)
case PG_REGEX_LOCALE_WIDE_L:
#ifdef HAVE_LOCALE_T
if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF)
- return iswpunct_l((wint_t) c, pg_regex_locale->info.lt);
+ return iswpunct_l((wint_t) c, pg_regex_locale->info.libc.lt);
#endif
/* FALL THRU */
case PG_REGEX_LOCALE_1BYTE_L:
#ifdef HAVE_LOCALE_T
return (c <= (pg_wchar) UCHAR_MAX &&
- ispunct_l((unsigned char) c, pg_regex_locale->info.lt));
+ ispunct_l((unsigned char) c, pg_regex_locale->info.libc.lt));
#endif
break;
case PG_REGEX_LOCALE_ICU:
@@ -603,13 +604,13 @@ pg_wc_isspace(pg_wchar c)
case PG_REGEX_LOCALE_WIDE_L:
#ifdef HAVE_LOCALE_T
if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF)
- return iswspace_l((wint_t) c, pg_regex_locale->info.lt);
+ return iswspace_l((wint_t) c, pg_regex_locale->info.libc.lt);
#endif
/* FALL THRU */
case PG_REGEX_LOCALE_1BYTE_L:
#ifdef HAVE_LOCALE_T
return (c <= (pg_wchar) UCHAR_MAX &&
- isspace_l((unsigned char) c, pg_regex_locale->info.lt));
+ isspace_l((unsigned char) c, pg_regex_locale->info.libc.lt));
#endif
break;
case PG_REGEX_LOCALE_ICU:
@@ -647,13 +648,13 @@ pg_wc_toupper(pg_wchar c)
case PG_REGEX_LOCALE_WIDE_L:
#ifdef HAVE_LOCALE_T
if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF)
- return towupper_l((wint_t) c, pg_regex_locale->info.lt);
+ return towupper_l((wint_t) c, pg_regex_locale->info.libc.lt);
#endif
/* FALL THRU */
case PG_REGEX_LOCALE_1BYTE_L:
#ifdef HAVE_LOCALE_T
if (c <= (pg_wchar) UCHAR_MAX)
- return toupper_l((unsigned char) c, pg_regex_locale->info.lt);
+ return toupper_l((unsigned char) c, pg_regex_locale->info.libc.lt);
#endif
return c;
case PG_REGEX_LOCALE_ICU:
@@ -691,13 +692,13 @@ pg_wc_tolower(pg_wchar c)
case PG_REGEX_LOCALE_WIDE_L:
#ifdef HAVE_LOCALE_T
if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF)
- return towlower_l((wint_t) c, pg_regex_locale->info.lt);
+ return towlower_l((wint_t) c, pg_regex_locale->info.libc.lt);
#endif
/* FALL THRU */
case PG_REGEX_LOCALE_1BYTE_L:
#ifdef HAVE_LOCALE_T
if (c <= (pg_wchar) UCHAR_MAX)
- return tolower_l((unsigned char) c, pg_regex_locale->info.lt);
+ return tolower_l((unsigned char) c, pg_regex_locale->info.libc.lt);
#endif
return c;
case PG_REGEX_LOCALE_ICU:
diff --git a/src/backend/utils/adt/formatting.c b/src/backend/utils/adt/formatting.c
index f3f4db5ef6..f45e2043a1 100644
--- a/src/backend/utils/adt/formatting.c
+++ b/src/backend/utils/adt/formatting.c
@@ -88,6 +88,7 @@
#include "utils/memutils.h"
#include "utils/numeric.h"
#include "utils/pg_locale.h"
+#include "utils/pg_locale_internal.h"
#include "varatt.h"
@@ -1577,7 +1578,7 @@ icu_convert_case(ICU_Convert_Func func, pg_locale_t mylocale,
*buff_dest = palloc(len_dest * sizeof(**buff_dest));
status = U_ZERO_ERROR;
len_dest = func(*buff_dest, len_dest, buff_source, len_source,
- mylocale->info.icu.locale, &status);
+ mylocale->ctype, &status);
if (status == U_BUFFER_OVERFLOW_ERROR)
{
/* try again with adjusted length */
@@ -1585,7 +1586,7 @@ icu_convert_case(ICU_Convert_Func func, pg_locale_t mylocale,
*buff_dest = palloc(len_dest * sizeof(**buff_dest));
status = U_ZERO_ERROR;
len_dest = func(*buff_dest, len_dest, buff_source, len_source,
- mylocale->info.icu.locale, &status);
+ mylocale->ctype, &status);
}
if (U_FAILURE(status))
ereport(ERROR,
@@ -1698,7 +1699,7 @@ str_tolower(const char *buff, size_t nbytes, Oid collid)
{
#ifdef HAVE_LOCALE_T
if (mylocale)
- workspace[curr_char] = towlower_l(workspace[curr_char], mylocale->info.lt);
+ workspace[curr_char] = towlower_l(workspace[curr_char], mylocale->info.libc.lt);
else
#endif
workspace[curr_char] = towlower(workspace[curr_char]);
@@ -1731,7 +1732,7 @@ str_tolower(const char *buff, size_t nbytes, Oid collid)
{
#ifdef HAVE_LOCALE_T
if (mylocale)
- *p = tolower_l((unsigned char) *p, mylocale->info.lt);
+ *p = tolower_l((unsigned char) *p, mylocale->info.libc.lt);
else
#endif
*p = pg_tolower((unsigned char) *p);
@@ -1820,7 +1821,7 @@ str_toupper(const char *buff, size_t nbytes, Oid collid)
{
#ifdef HAVE_LOCALE_T
if (mylocale)
- workspace[curr_char] = towupper_l(workspace[curr_char], mylocale->info.lt);
+ workspace[curr_char] = towupper_l(workspace[curr_char], mylocale->info.libc.lt);
else
#endif
workspace[curr_char] = towupper(workspace[curr_char]);
@@ -1853,7 +1854,7 @@ str_toupper(const char *buff, size_t nbytes, Oid collid)
{
#ifdef HAVE_LOCALE_T
if (mylocale)
- *p = toupper_l((unsigned char) *p, mylocale->info.lt);
+ *p = toupper_l((unsigned char) *p, mylocale->info.libc.lt);
else
#endif
*p = pg_toupper((unsigned char) *p);
@@ -1945,10 +1946,10 @@ str_initcap(const char *buff, size_t nbytes, Oid collid)
if (mylocale)
{
if (wasalnum)
- workspace[curr_char] = towlower_l(workspace[curr_char], mylocale->info.lt);
+ workspace[curr_char] = towlower_l(workspace[curr_char], mylocale->info.libc.lt);
else
- workspace[curr_char] = towupper_l(workspace[curr_char], mylocale->info.lt);
- wasalnum = iswalnum_l(workspace[curr_char], mylocale->info.lt);
+ workspace[curr_char] = towupper_l(workspace[curr_char], mylocale->info.libc.lt);
+ wasalnum = iswalnum_l(workspace[curr_char], mylocale->info.libc.lt);
}
else
#endif
@@ -1990,10 +1991,10 @@ str_initcap(const char *buff, size_t nbytes, Oid collid)
if (mylocale)
{
if (wasalnum)
- *p = tolower_l((unsigned char) *p, mylocale->info.lt);
+ *p = tolower_l((unsigned char) *p, mylocale->info.libc.lt);
else
- *p = toupper_l((unsigned char) *p, mylocale->info.lt);
- wasalnum = isalnum_l((unsigned char) *p, mylocale->info.lt);
+ *p = toupper_l((unsigned char) *p, mylocale->info.libc.lt);
+ wasalnum = isalnum_l((unsigned char) *p, mylocale->info.libc.lt);
}
else
#endif
diff --git a/src/backend/utils/adt/like.c b/src/backend/utils/adt/like.c
index fc6cb7f5b7..6fdfa2cebd 100644
--- a/src/backend/utils/adt/like.c
+++ b/src/backend/utils/adt/like.c
@@ -24,6 +24,7 @@
#include "miscadmin.h"
#include "utils/builtins.h"
#include "utils/pg_locale.h"
+#include "utils/pg_locale_internal.h"
#include "varatt.h"
@@ -97,7 +98,7 @@ SB_lower_char(unsigned char c, pg_locale_t locale, bool locale_is_c)
return pg_ascii_tolower(c);
#ifdef HAVE_LOCALE_T
else if (locale)
- return tolower_l(c, locale->info.lt);
+ return tolower_l(c, locale->info.libc.lt);
#endif
else
return pg_tolower(c);
diff --git a/src/backend/utils/adt/like_support.c b/src/backend/utils/adt/like_support.c
index 9b603d42f3..43150741c8 100644
--- a/src/backend/utils/adt/like_support.c
+++ b/src/backend/utils/adt/like_support.c
@@ -52,6 +52,7 @@
#include "utils/datum.h"
#include "utils/lsyscache.h"
#include "utils/pg_locale.h"
+#include "utils/pg_locale_internal.h"
#include "utils/selfuncs.h"
#include "utils/varlena.h"
@@ -1511,7 +1512,7 @@ pattern_char_isalpha(char c, bool is_multibyte,
(c >= 'A' && c <= 'Z') || (c >= 'a' && c <= 'z');
#ifdef HAVE_LOCALE_T
else if (locale && locale->provider == COLLPROVIDER_LIBC)
- return isalpha_l((unsigned char) c, locale->info.lt);
+ return isalpha_l((unsigned char) c, locale->info.libc.lt);
#endif
else
return isalpha((unsigned char) c);
diff --git a/src/backend/utils/adt/pg_locale.c b/src/backend/utils/adt/pg_locale.c
index 509ef0784e..d3ca3c5011 100644
--- a/src/backend/utils/adt/pg_locale.c
+++ b/src/backend/utils/adt/pg_locale.c
@@ -65,6 +65,7 @@
#include "utils/lsyscache.h"
#include "utils/memutils.h"
#include "utils/pg_locale.h"
+#include "utils/pg_locale_internal.h"
#include "utils/syscache.h"
#ifdef USE_ICU
@@ -131,6 +132,11 @@ static HTAB *collation_cache = NULL;
static char *IsoLocaleName(const char *);
#endif
+/*
+ * Database default locale.
+ */
+static pg_locale_t default_locale = NULL;
+
#ifdef USE_ICU
/*
* Converter object for converting between ICU's UChar strings and C strings
@@ -1336,7 +1342,7 @@ lc_collate_is_c(Oid collation)
static int result = -1;
char *localeptr;
- if (default_locale.provider == COLLPROVIDER_ICU)
+ if (default_locale->provider == COLLPROVIDER_ICU)
return false;
if (result >= 0)
@@ -1389,7 +1395,7 @@ lc_ctype_is_c(Oid collation)
static int result = -1;
char *localeptr;
- if (default_locale.provider == COLLPROVIDER_ICU)
+ if (default_locale->provider == COLLPROVIDER_ICU)
return false;
if (result >= 0)
@@ -1420,38 +1426,6 @@ lc_ctype_is_c(Oid collation)
return (lookup_collation_cache(collation, true))->ctype_is_c;
}
-struct pg_locale_struct default_locale;
-
-void
-make_icu_collator(const char *iculocstr,
- struct pg_locale_struct *resultp)
-{
-#ifdef USE_ICU
- UCollator *collator;
- UErrorCode status;
-
- status = U_ZERO_ERROR;
- collator = ucol_open(iculocstr, &status);
- if (U_FAILURE(status))
- ereport(ERROR,
- (errmsg("could not open collator for locale \"%s\": %s",
- iculocstr, u_errorName(status))));
-
- if (U_ICU_VERSION_MAJOR_NUM < 54)
- icu_set_collation_attributes(collator, iculocstr);
-
- /* We will leak this string if the caller errors later :-( */
- resultp->info.icu.locale = MemoryContextStrdup(TopMemoryContext, iculocstr);
- resultp->info.icu.ucol = collator;
-#else /* not USE_ICU */
- /* could get here if a collation was created by a build with ICU */
- ereport(ERROR,
- (errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
- errmsg("ICU is not supported in this build")));
-#endif /* not USE_ICU */
-}
-
-
/* simple subroutine for reporting errors from newlocale() */
#ifdef HAVE_LOCALE_T
static void
@@ -1485,6 +1459,163 @@ report_newlocale_failure(const char *localename)
#endif /* HAVE_LOCALE_T */
+/*
+ * Construct a new pg_locale_t object.
+ *
+ * Passing NULL for the version is allowed; and even if it is specified, the
+ * result may or may not have an exactly matching version. Other parameters
+ * are required.
+ *
+ * Ordinarily, collate and ctype should be the same. If the provider is ICU,
+ * this is a requirement, and the 'collate' and 'ctype' arguments should both
+ * come from colliculocale (or daticulocale). If the provider is libc, the
+ * arguments should come from collcollate and collctype (or datcollate and
+ * datctype), respectively.
+ *
+ * Structures are allocated in TopMemoryContext, and the libc locale_t or
+ * UCollator is not allocated in any memory context, so the result is
+ * effectively permanent.
+ */
+static pg_locale_t
+pg_newlocale(char provider, bool deterministic, const char *collate,
+ const char *ctype, const char *version)
+{
+ pg_locale_t result = MemoryContextAlloc(TopMemoryContext,
+ sizeof(struct pg_locale_struct));
+
+ /*
+ * If COLLPROVIDER_DEFAULT, caller should use default_locale or NULL
+ * instead.
+ */
+ Assert(provider != COLLPROVIDER_DEFAULT);
+
+ result->provider = provider;
+ result->deterministic = deterministic;
+ result->collate = MemoryContextStrdup(TopMemoryContext, collate);
+ result->ctype = MemoryContextStrdup(TopMemoryContext, ctype);
+
+ if (provider == COLLPROVIDER_LIBC)
+ {
+#ifdef HAVE_LOCALE_T
+ locale_t loc;
+
+ /* newlocale's result may be leaked if we encounter an error */
+
+ if (strcmp(collate, ctype) == 0)
+ {
+ /* Normal case where they're the same */
+ errno = 0;
+#ifndef WIN32
+ loc = newlocale(LC_COLLATE_MASK | LC_CTYPE_MASK, collate,
+ NULL);
+#else
+ loc = _create_locale(LC_ALL, collate);
+#endif
+ if (!loc)
+ report_newlocale_failure(collate);
+ }
+ else
+ {
+#ifndef WIN32
+ /* We need two newlocale() steps */
+ locale_t loc1;
+
+ errno = 0;
+ loc1 = newlocale(LC_COLLATE_MASK, collate, NULL);
+ if (!loc1)
+ report_newlocale_failure(collate);
+ errno = 0;
+ loc = newlocale(LC_CTYPE_MASK, ctype, loc1);
+ if (!loc)
+ report_newlocale_failure(ctype);
+#else
+
+ /*
+ * XXX The _create_locale() API doesn't appear to support
+ * this. Could perhaps be worked around by changing
+ * pg_locale_t to contain two separate fields.
+ */
+ ereport(ERROR,
+ (errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+ errmsg("collations with different collate and ctype values are not supported on this platform")));
+#endif
+ }
+
+ result->info.libc.lt = loc;
+#else /* not HAVE_LOCALE_T */
+ /* platform that doesn't support locale_t */
+ ereport(ERROR,
+ (errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+ errmsg("collation provider LIBC is not supported on this platform")));
+#endif /* not HAVE_LOCALE_T */
+ }
+#ifdef USE_ICU
+ else if (provider == COLLPROVIDER_ICU)
+ {
+ UCollator *collator;
+ UErrorCode status;
+
+ /* collator may be leaked if we encounter an error */
+
+ status = U_ZERO_ERROR;
+ collator = ucol_open(collate, &status);
+ if (U_FAILURE(status))
+ ereport(ERROR,
+ (errmsg("could not open collator for locale \"%s\": %s",
+ collate, u_errorName(status))));
+
+ if (U_ICU_VERSION_MAJOR_NUM < 54)
+ icu_set_collation_attributes(collator, collate);
+
+ result->info.icu.ucol = collator;
+ }
+#endif
+ else
+ /* shouldn't happen */
+ elog(ERROR, "unsupported collprovider: %c", provider);
+
+ return result;
+}
+
+/*
+ * Accessor so that callers don't need to include pg_locale_internal.h.
+ */
+bool
+pg_locale_deterministic(pg_locale_t locale)
+{
+ if (locale == NULL)
+ return true;
+ else
+ return locale->deterministic;
+}
+
+/*
+ * Initialize default database locale.
+ */
+void
+init_default_locale(char provider, const char *collate, const char *ctype,
+ const char *iculocale, const char *version)
+{
+ /*
+ * For the purposes of pg_locale_t, if the provider is ICU, we use
+ * iculocale for both collate and ctype.
+ */
+ if (provider == COLLPROVIDER_ICU)
+ {
+ collate = iculocale;
+ ctype = iculocale;
+ }
+ else
+ Assert(iculocale == NULL);
+
+ /*
+ * Default locale is currently always deterministic. Nondeterministic
+ * locales currently don't support pattern matching, which would break a
+ * lot of things if applied globally.
+ */
+ default_locale = pg_newlocale(provider, true, collate, ctype, version);
+}
+
/*
* Create a locale_t from a collation OID. Results are cached for the
* lifetime of the backend. Thus, do not free the result with freelocale().
@@ -1509,8 +1640,8 @@ pg_newlocale_from_collation(Oid collid)
if (collid == DEFAULT_COLLATION_OID)
{
- if (default_locale.provider == COLLPROVIDER_ICU)
- return &default_locale;
+ if (default_locale->provider == COLLPROVIDER_ICU)
+ return default_locale;
else
return (pg_locale_t) 0;
}
@@ -1522,107 +1653,64 @@ pg_newlocale_from_collation(Oid collid)
/* We haven't computed this yet in this session, so do it */
HeapTuple tp;
Form_pg_collation collform;
- struct pg_locale_struct result;
- pg_locale_t resultp;
+ pg_locale_t locale;
Datum datum;
bool isnull;
+ char *collate;
+ char *ctype;
+ char *collversionstr;
tp = SearchSysCache1(COLLOID, ObjectIdGetDatum(collid));
if (!HeapTupleIsValid(tp))
elog(ERROR, "cache lookup failed for collation %u", collid);
collform = (Form_pg_collation) GETSTRUCT(tp);
- /* We'll fill in the result struct locally before allocating memory */
- memset(&result, 0, sizeof(result));
- result.provider = collform->collprovider;
- result.deterministic = collform->collisdeterministic;
+ datum = SysCacheGetAttr(COLLOID, tp, Anum_pg_collation_collversion,
+ &isnull);
+ if (!isnull)
+ collversionstr = TextDatumGetCString(datum);
+ else
+ collversionstr = NULL;
if (collform->collprovider == COLLPROVIDER_LIBC)
{
-#ifdef HAVE_LOCALE_T
- const char *collcollate;
- const char *collctype pg_attribute_unused();
- locale_t loc;
-
- datum = SysCacheGetAttr(COLLOID, tp, Anum_pg_collation_collcollate, &isnull);
+ datum = SysCacheGetAttr(COLLOID, tp, Anum_pg_collation_collcollate,
+ &isnull);
Assert(!isnull);
- collcollate = TextDatumGetCString(datum);
- datum = SysCacheGetAttr(COLLOID, tp, Anum_pg_collation_collctype, &isnull);
+ collate = TextDatumGetCString(datum);
+ datum = SysCacheGetAttr(COLLOID, tp, Anum_pg_collation_collctype,
+ &isnull);
Assert(!isnull);
- collctype = TextDatumGetCString(datum);
-
- if (strcmp(collcollate, collctype) == 0)
- {
- /* Normal case where they're the same */
- errno = 0;
-#ifndef WIN32
- loc = newlocale(LC_COLLATE_MASK | LC_CTYPE_MASK, collcollate,
- NULL);
-#else
- loc = _create_locale(LC_ALL, collcollate);
-#endif
- if (!loc)
- report_newlocale_failure(collcollate);
- }
- else
- {
-#ifndef WIN32
- /* We need two newlocale() steps */
- locale_t loc1;
-
- errno = 0;
- loc1 = newlocale(LC_COLLATE_MASK, collcollate, NULL);
- if (!loc1)
- report_newlocale_failure(collcollate);
- errno = 0;
- loc = newlocale(LC_CTYPE_MASK, collctype, loc1);
- if (!loc)
- report_newlocale_failure(collctype);
-#else
-
- /*
- * XXX The _create_locale() API doesn't appear to support
- * this. Could perhaps be worked around by changing
- * pg_locale_t to contain two separate fields.
- */
- ereport(ERROR,
- (errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
- errmsg("collations with different collate and ctype values are not supported on this platform")));
-#endif
- }
-
- result.info.lt = loc;
-#else /* not HAVE_LOCALE_T */
- /* platform that doesn't support locale_t */
- ereport(ERROR,
- (errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
- errmsg("collation provider LIBC is not supported on this platform")));
-#endif /* not HAVE_LOCALE_T */
+ ctype = TextDatumGetCString(datum);
}
+#ifdef USE_ICU
else if (collform->collprovider == COLLPROVIDER_ICU)
{
- const char *iculocstr;
-
- datum = SysCacheGetAttr(COLLOID, tp, Anum_pg_collation_colliculocale, &isnull);
+ datum = SysCacheGetAttr(COLLOID, tp, Anum_pg_collation_colliculocale,
+ &isnull);
Assert(!isnull);
- iculocstr = TextDatumGetCString(datum);
- make_icu_collator(iculocstr, &result);
+ collate = TextDatumGetCString(datum);
+
+ /* for ICU, collate and ctype are both set from iculocale */
+ ctype = collate;
}
+#endif
+ else
+ /* shouldn't happen */
+ elog(ERROR, "unsupported collprovider: %c", collform->collprovider);
- datum = SysCacheGetAttr(COLLOID, tp, Anum_pg_collation_collversion,
- &isnull);
- if (!isnull)
+ locale = pg_newlocale(collform->collprovider,
+ collform->collisdeterministic,
+ collate, ctype, collversionstr);
+
+ ReleaseSysCache(tp);
+
+ if (collversionstr != NULL)
{
char *actual_versionstr;
- char *collversionstr;
- collversionstr = TextDatumGetCString(datum);
-
- datum = SysCacheGetAttr(COLLOID, tp, collform->collprovider == COLLPROVIDER_ICU ? Anum_pg_collation_colliculocale : Anum_pg_collation_collcollate, &isnull);
- Assert(!isnull);
+ actual_versionstr = get_collation_actual_version(collform->collprovider, collate);
- actual_versionstr = get_collation_actual_version(collform->collprovider,
- TextDatumGetCString(datum));
if (!actual_versionstr)
{
/*
@@ -1649,13 +1737,7 @@ pg_newlocale_from_collation(Oid collid)
NameStr(collform->collname)))));
}
- ReleaseSysCache(tp);
-
- /* We'll keep the pg_locale_t structures in TopMemoryContext */
- resultp = MemoryContextAlloc(TopMemoryContext, sizeof(*resultp));
- *resultp = result;
-
- cache_entry->locale = resultp;
+ cache_entry->locale = locale;
}
return cache_entry->locale;
@@ -1815,7 +1897,7 @@ pg_strncoll_libc_win32_utf8(const char *arg1, size_t len1, const char *arg2,
errno = 0;
#ifdef HAVE_LOCALE_T
if (locale)
- result = wcscoll_l((LPWSTR) a1p, (LPWSTR) a2p, locale->info.lt);
+ result = wcscoll_l((LPWSTR) a1p, (LPWSTR) a2p, locale->info.libc.lt);
else
#endif
result = wcscoll((LPWSTR) a1p, (LPWSTR) a2p);
@@ -1858,7 +1940,7 @@ pg_strcoll_libc(const char *arg1, const char *arg2, pg_locale_t locale)
if (locale)
{
#ifdef HAVE_LOCALE_T
- result = strcoll_l(arg1, arg2, locale->info.lt);
+ result = strcoll_l(arg1, arg2, locale->info.libc.lt);
#else
/* shouldn't happen */
elog(ERROR, "unsupported collprovider: %c", locale->provider);
@@ -2102,7 +2184,7 @@ pg_strxfrm_libc(char *dest, const char *src, size_t destsize,
#ifdef TRUST_STXFRM
#ifdef HAVE_LOCALE_T
if (locale)
- return strxfrm_l(dest, src, destsize, locale->info.lt);
+ return strxfrm_l(dest, src, destsize, locale->info.libc.lt);
else
#endif
return strxfrm(dest, src, destsize);
@@ -2699,8 +2781,8 @@ void
check_icu_locale(const char *icu_locale)
{
#ifdef USE_ICU
- UCollator *collator;
- UErrorCode status;
+ UCollator *collator;
+ UErrorCode status;
status = U_ZERO_ERROR;
collator = ucol_open(icu_locale, &status);
@@ -2774,10 +2856,10 @@ wchar2char(char *to, const wchar_t *from, size_t tolen, pg_locale_t locale)
#ifdef HAVE_LOCALE_T
#ifdef HAVE_WCSTOMBS_L
/* Use wcstombs_l for nondefault locales */
- result = wcstombs_l(to, from, tolen, locale->info.lt);
+ result = wcstombs_l(to, from, tolen, locale->info.libc.lt);
#else /* !HAVE_WCSTOMBS_L */
/* We have to temporarily set the locale as current ... ugh */
- locale_t save_locale = uselocale(locale->info.lt);
+ locale_t save_locale = uselocale(locale->info.libc.lt);
result = wcstombs(to, from, tolen);
@@ -2851,10 +2933,10 @@ char2wchar(wchar_t *to, size_t tolen, const char *from, size_t fromlen,
#ifdef HAVE_LOCALE_T
#ifdef HAVE_MBSTOWCS_L
/* Use mbstowcs_l for nondefault locales */
- result = mbstowcs_l(to, str, tolen, locale->info.lt);
+ result = mbstowcs_l(to, str, tolen, locale->info.libc.lt);
#else /* !HAVE_MBSTOWCS_L */
/* We have to temporarily set the locale as current ... ugh */
- locale_t save_locale = uselocale(locale->info.lt);
+ locale_t save_locale = uselocale(locale->info.libc.lt);
result = mbstowcs(to, str, tolen);
diff --git a/src/backend/utils/adt/varchar.c b/src/backend/utils/adt/varchar.c
index 5bbba94687..8dc1faaaf2 100644
--- a/src/backend/utils/adt/varchar.c
+++ b/src/backend/utils/adt/varchar.c
@@ -762,7 +762,7 @@ bpchareq(PG_FUNCTION_ARGS)
else
mylocale = pg_newlocale_from_collation(collid);
- if (locale_is_c || !mylocale || mylocale->deterministic)
+ if (locale_is_c || pg_locale_deterministic(mylocale))
{
/*
* Since we only care about equality or not-equality, we can avoid all
@@ -807,7 +807,7 @@ bpcharne(PG_FUNCTION_ARGS)
else
mylocale = pg_newlocale_from_collation(collid);
- if (locale_is_c || !mylocale || mylocale->deterministic)
+ if (locale_is_c || pg_locale_deterministic(mylocale))
{
/*
* Since we only care about equality or not-equality, we can avoid all
@@ -1015,33 +1015,25 @@ hashbpchar(PG_FUNCTION_ARGS)
if (!lc_collate_is_c(collid))
mylocale = pg_newlocale_from_collation(collid);
- if (!mylocale || mylocale->deterministic)
+ if (pg_locale_deterministic(mylocale))
{
result = hash_any((unsigned char *) keydata, keylen);
}
else
{
-#ifdef USE_ICU
- if (mylocale->provider == COLLPROVIDER_ICU)
- {
- Size bsize, rsize;
- char *buf;
+ Size bsize, rsize;
+ char *buf;
- bsize = pg_strnxfrm(NULL, 0, keydata, keylen, mylocale);
- buf = palloc(bsize);
+ bsize = pg_strnxfrm(NULL, 0, keydata, keylen, mylocale);
+ buf = palloc(bsize);
- rsize = pg_strnxfrm(buf, bsize, keydata, keylen, mylocale);
- if (rsize != bsize)
- elog(ERROR, "pg_strnxfrm() returned unexpected result");
+ rsize = pg_strnxfrm(buf, bsize, keydata, keylen, mylocale);
+ if (rsize != bsize)
+ elog(ERROR, "pg_strnxfrm() returned unexpected result");
- result = hash_any((uint8_t *) buf, bsize);
+ result = hash_any((uint8_t *) buf, bsize);
- pfree(buf);
- }
- else
-#endif
- /* shouldn't happen */
- elog(ERROR, "unsupported collprovider: %c", mylocale->provider);
+ pfree(buf);
}
/* Avoid leaking memory for toasted inputs */
@@ -1072,35 +1064,27 @@ hashbpcharextended(PG_FUNCTION_ARGS)
if (!lc_collate_is_c(collid))
mylocale = pg_newlocale_from_collation(collid);
- if (!mylocale || mylocale->deterministic)
+ if (pg_locale_deterministic(mylocale))
{
result = hash_any_extended((unsigned char *) keydata, keylen,
PG_GETARG_INT64(1));
}
else
{
-#ifdef USE_ICU
- if (mylocale->provider == COLLPROVIDER_ICU)
- {
- Size bsize, rsize;
- char *buf;
+ Size bsize, rsize;
+ char *buf;
- bsize = pg_strnxfrm(NULL, 0, keydata, keylen, mylocale);
- buf = palloc(bsize);
+ bsize = pg_strnxfrm(NULL, 0, keydata, keylen, mylocale);
+ buf = palloc(bsize);
- rsize = pg_strnxfrm(buf, bsize, keydata, keylen, mylocale);
- if (rsize != bsize)
- elog(ERROR, "pg_strnxfrm() returned unexpected result");
+ rsize = pg_strnxfrm(buf, bsize, keydata, keylen, mylocale);
+ if (rsize != bsize)
+ elog(ERROR, "pg_strnxfrm() returned unexpected result");
- result = hash_any_extended((uint8_t *) buf, bsize,
- PG_GETARG_INT64(1));
+ result = hash_any_extended((uint8_t *) buf, bsize,
+ PG_GETARG_INT64(1));
- pfree(buf);
- }
- else
-#endif
- /* shouldn't happen */
- elog(ERROR, "unsupported collprovider: %c", mylocale->provider);
+ pfree(buf);
}
PG_FREE_IF_COPY(key, 0);
diff --git a/src/backend/utils/adt/varlena.c b/src/backend/utils/adt/varlena.c
index 5030328f31..3c4e7be687 100644
--- a/src/backend/utils/adt/varlena.c
+++ b/src/backend/utils/adt/varlena.c
@@ -1205,7 +1205,7 @@ text_position_setup(text *t1, text *t2, Oid collid, TextPositionState *state)
if (!lc_collate_is_c(collid))
mylocale = pg_newlocale_from_collation(collid);
- if (mylocale && !mylocale->deterministic)
+ if (!pg_locale_deterministic(mylocale))
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("nondeterministic collations are not supported for substring searches")));
@@ -1556,8 +1556,7 @@ varstr_cmp(const char *arg1, int len1, const char *arg2, int len2, Oid collid)
result = pg_strncoll(arg1, len1, arg2, len2, mylocale);
/* Break tie if necessary. */
- if (result == 0 &&
- (!mylocale || mylocale->deterministic))
+ if (result == 0 && pg_locale_deterministic(mylocale))
{
result = memcmp(arg1, arg2, Min(len1, len2));
if ((result == 0) && (len1 != len2))
@@ -1612,7 +1611,7 @@ texteq(PG_FUNCTION_ARGS)
else
mylocale = pg_newlocale_from_collation(collid);
- if (locale_is_c || !mylocale || mylocale->deterministic)
+ if (locale_is_c || pg_locale_deterministic(mylocale))
{
Datum arg1 = PG_GETARG_DATUM(0);
Datum arg2 = PG_GETARG_DATUM(1);
@@ -1671,7 +1670,7 @@ textne(PG_FUNCTION_ARGS)
else
mylocale = pg_newlocale_from_collation(collid);
- if (locale_is_c || !mylocale || mylocale->deterministic)
+ if (locale_is_c || pg_locale_deterministic(mylocale))
{
Datum arg1 = PG_GETARG_DATUM(0);
Datum arg2 = PG_GETARG_DATUM(1);
@@ -1785,7 +1784,7 @@ text_starts_with(PG_FUNCTION_ARGS)
if (!lc_collate_is_c(collid))
mylocale = pg_newlocale_from_collation(collid);
- if (mylocale && !mylocale->deterministic)
+ if (!pg_locale_deterministic(mylocale))
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("nondeterministic collations are not supported for substring searches")));
@@ -2201,8 +2200,7 @@ varstrfastcmp_locale(char *a1p, int len1, char *a2p, int len2, SortSupport ssup)
result = pg_strcoll(sss->buf1, sss->buf2, sss->locale);
/* Break tie if necessary. */
- if (result == 0 &&
- (!sss->locale || sss->locale->deterministic))
+ if (result == 0 && pg_locale_deterministic(sss->locale))
result = strcmp(sss->buf1, sss->buf2);
/* Cache result, perhaps saving an expensive strcoll() call next time */
diff --git a/src/backend/utils/init/postinit.c b/src/backend/utils/init/postinit.c
index ae5a85ed65..c26dfb6104 100644
--- a/src/backend/utils/init/postinit.c
+++ b/src/backend/utils/init/postinit.c
@@ -317,6 +317,7 @@ CheckMyDatabase(const char *name, bool am_superuser, bool override_allow_connect
char *collate;
char *ctype;
char *iculocale;
+ char *collversionstr;
/* Fetch our pg_database row normally, via syscache */
tup = SearchSysCache1(DATABASEOID, ObjectIdGetDatum(MyDatabaseId));
@@ -424,35 +425,33 @@ CheckMyDatabase(const char *name, bool am_superuser, bool override_allow_connect
datum = SysCacheGetAttr(DATABASEOID, tup, Anum_pg_database_daticulocale, &isnull);
Assert(!isnull);
iculocale = TextDatumGetCString(datum);
- make_icu_collator(iculocale, &default_locale);
}
else
iculocale = NULL;
- default_locale.provider = dbform->datlocprovider;
+ datum = SysCacheGetAttr(DATABASEOID, tup, Anum_pg_database_datcollversion,
+ &isnull);
+ if (!isnull)
+ collversionstr = TextDatumGetCString(datum);
+ else
+ collversionstr = NULL;
- /*
- * Default locale is currently always deterministic. Nondeterministic
- * locales currently don't support pattern matching, which would break a
- * lot of things if applied globally.
- */
- default_locale.deterministic = true;
+ init_default_locale(dbform->datlocprovider, collate, ctype, iculocale,
+ collversionstr);
/*
* Check collation version. See similar code in
* pg_newlocale_from_collation(). Note that here we warn instead of error
* in any case, so that we don't prevent connecting.
*/
- datum = SysCacheGetAttr(DATABASEOID, tup, Anum_pg_database_datcollversion,
- &isnull);
- if (!isnull)
+ if (collversionstr != NULL)
{
char *actual_versionstr;
- char *collversionstr;
- collversionstr = TextDatumGetCString(datum);
+ actual_versionstr = get_collation_actual_version(
+ dbform->datlocprovider,
+ dbform->datlocprovider == COLLPROVIDER_ICU ? iculocale : collate);
- actual_versionstr = get_collation_actual_version(dbform->datlocprovider, dbform->datlocprovider == COLLPROVIDER_ICU ? iculocale : collate);
if (!actual_versionstr)
/* should not happen */
elog(WARNING,
@@ -470,6 +469,8 @@ CheckMyDatabase(const char *name, bool am_superuser, bool override_allow_connect
"or build PostgreSQL with the right library version.",
quote_identifier(name))));
}
+ else
+ collversionstr = NULL;
/* Make the locale settings visible as GUC variables, too */
SetConfigOption("lc_collate", collate, PGC_INTERNAL, PGC_S_DYNAMIC_DEFAULT);
diff --git a/src/include/utils/pg_locale.h b/src/include/utils/pg_locale.h
index c08e6ce07f..7be42fc21e 100644
--- a/src/include/utils/pg_locale.h
+++ b/src/include/utils/pg_locale.h
@@ -15,22 +15,6 @@
#if defined(LOCALE_T_IN_XLOCALE) || defined(WCSTOMBS_L_IN_XLOCALE)
#include <xlocale.h>
#endif
-#ifdef USE_ICU
-#include <unicode/ucol.h>
-#endif
-
-#ifdef USE_ICU
-/*
- * ucol_strcollUTF8() was introduced in ICU 50, but it is buggy before ICU 53.
- * (see
- * <https://www.postgresql.org/message-id/flat/f1438ec6-22aa-4029-9a3b-26f79d330e72%40manitou-mail.org>)
- */
-#if U_ICU_VERSION_MAJOR_NUM >= 53
-#define HAVE_UCOL_STRCOLLUTF8 1
-#else
-#undef HAVE_UCOL_STRCOLLUTF8
-#endif
-#endif
/* use for libc locale names */
#define LOCALE_NAME_BUFLEN 128
@@ -65,39 +49,12 @@ extern struct lconv *PGLC_localeconv(void);
extern void cache_locale_time(void);
-/*
- * We define our own wrapper around locale_t so we can keep the same
- * function signatures for all builds, while not having to create a
- * fake version of the standard type locale_t in the global namespace.
- * pg_locale_t is occasionally checked for truth, so make it a pointer.
- */
-struct pg_locale_struct
-{
- char provider;
- bool deterministic;
- union
- {
-#ifdef HAVE_LOCALE_T
- locale_t lt;
-#endif
-#ifdef USE_ICU
- struct
- {
- const char *locale;
- UCollator *ucol;
- } icu;
-#endif
- int dummy; /* in case we have neither LOCALE_T nor ICU */
- } info;
-};
-
typedef struct pg_locale_struct *pg_locale_t;
-extern PGDLLIMPORT struct pg_locale_struct default_locale;
-
-extern void make_icu_collator(const char *iculocstr,
- struct pg_locale_struct *resultp);
-
+extern void init_default_locale(char provider, const char *collate,
+ const char *ctype, const char *iculocale,
+ const char *version);
+extern bool pg_locale_deterministic(pg_locale_t locale);
extern pg_locale_t pg_newlocale_from_collation(Oid collid);
extern char *get_collation_actual_version(char collprovider, const char *collcollate);
@@ -115,10 +72,6 @@ extern size_t pg_strxfrm_prefix(char *dest, const char *src, size_t destsize,
extern size_t pg_strnxfrm_prefix(char *dest, size_t destsize, const char *src,
size_t srclen, pg_locale_t locale);
-#ifdef USE_ICU
-extern int32_t icu_to_uchar(UChar **buff_uchar, const char *buff, size_t nbytes);
-extern int32_t icu_from_uchar(char **result, const UChar *buff_uchar, int32_t len_uchar);
-#endif
extern void check_icu_locale(const char *icu_locale);
/* These functions convert from/to libc's wchar_t, *not* pg_wchar_t */
diff --git a/src/include/utils/pg_locale_internal.h b/src/include/utils/pg_locale_internal.h
new file mode 100644
index 0000000000..33465ad92d
--- /dev/null
+++ b/src/include/utils/pg_locale_internal.h
@@ -0,0 +1,68 @@
+/*-----------------------------------------------------------------------
+ *
+ * PostgreSQL locale utilities
+ *
+ * src/include/utils/pg_locale_internal.h
+ *
+ * Copyright (c) 2002-2022, PostgreSQL Global Development Group
+ *
+ *-----------------------------------------------------------------------
+ */
+
+
+#ifndef _PG_LOCALE_INTERNAL_
+#define _PG_LOCALE_INTERNAL_
+
+#ifdef USE_ICU
+#include <unicode/ucol.h>
+#endif
+
+#ifdef USE_ICU
+/*
+ * ucol_strcollUTF8() was introduced in ICU 50, but it is buggy before ICU 53.
+ * (see
+ * <https://www.postgresql.org/message-id/flat/f1438ec6-22aa-4029-9a3b-26f79d330e72%40manitou-mail.org>)
+ */
+#if U_ICU_VERSION_MAJOR_NUM >= 53
+#define HAVE_UCOL_STRCOLLUTF8 1
+#else
+#undef HAVE_UCOL_STRCOLLUTF8
+#endif
+#endif
+
+/*
+ * We define our own wrapper around locale_t so we can keep the same
+ * function signatures for all builds, while not having to create a
+ * fake version of the standard type locale_t in the global namespace.
+ * pg_locale_t is occasionally checked for truth, so make it a pointer.
+ */
+struct pg_locale_struct
+{
+ char provider;
+ bool deterministic;
+ char *collate;
+ char *ctype;
+ union
+ {
+#ifdef HAVE_LOCALE_T
+ struct
+ {
+ locale_t lt;
+ } libc;
+#endif
+#ifdef USE_ICU
+ struct
+ {
+ UCollator *ucol;
+ } icu;
+#endif
+ int dummy; /* in case we have neither LOCALE_T nor ICU */
+ } info;
+};
+
+#ifdef USE_ICU
+extern int32_t icu_to_uchar(UChar **buff_uchar, const char *buff, size_t nbytes);
+extern int32_t icu_from_uchar(char **result, const UChar *buff_uchar, int32_t len_uchar);
+#endif
+
+#endif /* _PG_LOCALE_INTERNAL_ */
--
2.34.1
[text/x-patch] v8-0001-Add-pg_strcoll-pg_strxfrm-and-variants.patch (43.0K, ../[email protected]/3-v8-0001-Add-pg_strcoll-pg_strxfrm-and-variants.patch)
download | inline diff:
From 954ddd0f8b3adb3d66e9b12adc6fc021393e2039 Mon Sep 17 00:00:00 2001
From: Jeff Davis <[email protected]>
Date: Thu, 1 Dec 2022 14:45:15 -0800
Subject: [PATCH v8 1/2] Add pg_strcoll(), pg_strxfrm(), and variants.
In preparation for multi-lib ICU, which should be based on a clean
separation of the routines required for collation providers. Also
offers a generally better separation of responsibilities.
Callers with NUL-terminated strings should call pg_strcoll() or
pg_strxfrm(); callers with strings and their length should call the
variants pg_strncoll() or pg_strnxfrm().
Also remove the TRUST_STRXFRM define, and replace with a developer GUC
for easier testing.
---
src/backend/access/hash/hashfunc.c | 45 +-
src/backend/utils/adt/pg_locale.c | 783 +++++++++++++++++++++++++++-
src/backend/utils/adt/varchar.c | 41 +-
src/backend/utils/adt/varlena.c | 368 ++-----------
src/backend/utils/misc/guc_tables.c | 11 +
src/include/utils/pg_locale.h | 14 +
6 files changed, 874 insertions(+), 388 deletions(-)
diff --git a/src/backend/access/hash/hashfunc.c b/src/backend/access/hash/hashfunc.c
index e3e40d6c21..c0ed995919 100644
--- a/src/backend/access/hash/hashfunc.c
+++ b/src/backend/access/hash/hashfunc.c
@@ -292,21 +292,19 @@ hashtext(PG_FUNCTION_ARGS)
#ifdef USE_ICU
if (mylocale->provider == COLLPROVIDER_ICU)
{
- int32_t ulen = -1;
- UChar *uchar = NULL;
- Size bsize;
- uint8_t *buf;
+ Size bsize, rsize;
+ char *buf;
+ const char *keydata = VARDATA_ANY(key);
+ size_t keylen = VARSIZE_ANY_EXHDR(key);
- ulen = icu_to_uchar(&uchar, VARDATA_ANY(key), VARSIZE_ANY_EXHDR(key));
-
- bsize = ucol_getSortKey(mylocale->info.icu.ucol,
- uchar, ulen, NULL, 0);
+ bsize = pg_strnxfrm(NULL, 0, keydata, keylen, mylocale);
buf = palloc(bsize);
- ucol_getSortKey(mylocale->info.icu.ucol,
- uchar, ulen, buf, bsize);
- pfree(uchar);
- result = hash_any(buf, bsize);
+ rsize = pg_strnxfrm(buf, bsize, keydata, keylen, mylocale);
+ if (rsize != bsize)
+ elog(ERROR, "pg_strnxfrm() returned unexpected result");
+
+ result = hash_any((uint8_t *) buf, bsize);
pfree(buf);
}
@@ -350,21 +348,20 @@ hashtextextended(PG_FUNCTION_ARGS)
#ifdef USE_ICU
if (mylocale->provider == COLLPROVIDER_ICU)
{
- int32_t ulen = -1;
- UChar *uchar = NULL;
- Size bsize;
- uint8_t *buf;
+ Size bsize, rsize;
+ char *buf;
+ const char *keydata = VARDATA_ANY(key);
+ size_t keylen = VARSIZE_ANY_EXHDR(key);
- ulen = icu_to_uchar(&uchar, VARDATA_ANY(key), VARSIZE_ANY_EXHDR(key));
-
- bsize = ucol_getSortKey(mylocale->info.icu.ucol,
- uchar, ulen, NULL, 0);
+ bsize = pg_strnxfrm(NULL, 0, keydata, keylen, mylocale);
buf = palloc(bsize);
- ucol_getSortKey(mylocale->info.icu.ucol,
- uchar, ulen, buf, bsize);
- pfree(uchar);
- result = hash_any_extended(buf, bsize, PG_GETARG_INT64(1));
+ rsize = pg_strnxfrm(buf, bsize, keydata, keylen, mylocale);
+ if (rsize != bsize)
+ elog(ERROR, "pg_strnxfrm() returned unexpected result");
+
+ result = hash_any_extended((uint8_t *) buf, bsize,
+ PG_GETARG_INT64(1));
pfree(buf);
}
diff --git a/src/backend/utils/adt/pg_locale.c b/src/backend/utils/adt/pg_locale.c
index 059e4fd79f..509ef0784e 100644
--- a/src/backend/utils/adt/pg_locale.c
+++ b/src/backend/utils/adt/pg_locale.c
@@ -79,6 +79,12 @@
#include <shlwapi.h>
#endif
+/*
+ * This should be large enough that most strings will fit, but small enough
+ * that we feel comfortable putting it on the stack
+ */
+#define TEXTBUFLEN 1024
+
#define MAX_L10N_DATA 80
@@ -88,6 +94,9 @@ char *locale_monetary;
char *locale_numeric;
char *locale_time;
+/* GUC to enable use of strxfrm() for abbreviated keys */
+bool trust_strxfrm = false;
+
/*
* lc_time localization cache.
*
@@ -123,6 +132,19 @@ static char *IsoLocaleName(const char *);
#endif
#ifdef USE_ICU
+/*
+ * Converter object for converting between ICU's UChar strings and C strings
+ * in database encoding. Since the database encoding doesn't change, we only
+ * need one of these per session.
+ */
+static UConverter *icu_converter = NULL;
+
+static void init_icu_converter(void);
+static size_t uchar_length(UConverter *converter,
+ const char *str, size_t len);
+static int32_t uchar_convert(UConverter *converter,
+ UChar *dest, int32_t destlen,
+ const char *str, size_t srclen);
static void icu_set_collation_attributes(UCollator *collator, const char *loc);
#endif
@@ -1731,15 +1753,716 @@ get_collation_actual_version(char collprovider, const char *collcollate)
return collversion;
}
+/*
+ * pg_strncoll_libc_win32_utf8
+ *
+ * Win32 does not have UTF-8. Convert UTF8 arguments to wide characters and
+ * invoke wcscoll() or wcscoll_l().
+ */
+#ifdef WIN32
+static int
+pg_strncoll_libc_win32_utf8(const char *arg1, size_t len1, const char *arg2,
+ size_t len2, pg_locale_t locale)
+{
+ char sbuf[TEXTBUFLEN];
+ char *buf = sbuf;
+ char *a1p,
+ *a2p;
+ int a1len = len1 * 2 + 2;
+ int a2len = len2 * 2 + 2;
+ int r;
+ int result;
+
+ Assert(!locale || locale->provider == COLLPROVIDER_LIBC);
+ Assert(GetDatabaseEncoding() == PG_UTF8);
+#ifndef WIN32
+ Assert(false);
+#endif
+
+ if (a1len + a2len > TEXTBUFLEN)
+ buf = palloc(a1len + a2len);
+
+ a1p = buf;
+ a2p = buf + a1len;
+
+ /* API does not work for zero-length input */
+ if (len1 == 0)
+ r = 0;
+ else
+ {
+ r = MultiByteToWideChar(CP_UTF8, 0, arg1, len1,
+ (LPWSTR) a1p, a1len / 2);
+ if (!r)
+ ereport(ERROR,
+ (errmsg("could not convert string to UTF-16: error code %lu",
+ GetLastError())));
+ }
+ ((LPWSTR) a1p)[r] = 0;
+
+ if (len2 == 0)
+ r = 0;
+ else
+ {
+ r = MultiByteToWideChar(CP_UTF8, 0, arg2, len2,
+ (LPWSTR) a2p, a2len / 2);
+ if (!r)
+ ereport(ERROR,
+ (errmsg("could not convert string to UTF-16: error code %lu",
+ GetLastError())));
+ }
+ ((LPWSTR) a2p)[r] = 0;
+
+ errno = 0;
+#ifdef HAVE_LOCALE_T
+ if (locale)
+ result = wcscoll_l((LPWSTR) a1p, (LPWSTR) a2p, locale->info.lt);
+ else
+#endif
+ result = wcscoll((LPWSTR) a1p, (LPWSTR) a2p);
+ if (result == 2147483647) /* _NLSCMPERROR; missing from mingw
+ * headers */
+ ereport(ERROR,
+ (errmsg("could not compare Unicode strings: %m")));
+
+ if (buf != sbuf)
+ pfree(buf);
+
+ return result;
+}
+#endif /* WIN32 */
+
+/*
+ * pg_strcoll_libc
+ *
+ * Call strcoll(), strcoll_l(), wcscoll(), or wcscoll_l() as appropriate for
+ * the given locale, platform, and database encoding. If the locale is NULL,
+ * use the database collation.
+ *
+ * Arguments must be encoded in the database encoding and nul-terminated.
+ */
+static int
+pg_strcoll_libc(const char *arg1, const char *arg2, pg_locale_t locale)
+{
+ int result;
+
+ Assert(!locale || locale->provider == COLLPROVIDER_LIBC);
+#ifdef WIN32
+ if (GetDatabaseEncoding() == PG_UTF8)
+ {
+ size_t len1 = strlen(arg1);
+ size_t len2 = strlen(arg2);
+ result = pg_strncoll_libc_win32_utf8(arg1, len1, arg2, len2, locale);
+ }
+ else
+#endif /* WIN32 */
+ if (locale)
+ {
+#ifdef HAVE_LOCALE_T
+ result = strcoll_l(arg1, arg2, locale->info.lt);
+#else
+ /* shouldn't happen */
+ elog(ERROR, "unsupported collprovider: %c", locale->provider);
+#endif
+ }
+ else
+ result = strcoll(arg1, arg2);
+
+ return result;
+}
+
+/*
+ * pg_strncoll_libc
+ *
+ * Null-terminate the arguments and call pg_strcoll_libc().
+ */
+static int
+pg_strncoll_libc(const char *arg1, size_t len1, const char *arg2, size_t len2,
+ pg_locale_t locale)
+{
+ char sbuf[TEXTBUFLEN];
+ char *buf = sbuf;
+ size_t bufsize1 = len1 + 1;
+ size_t bufsize2 = len2 + 1;
+ char *arg1n;
+ char *arg2n;
+ int result;
+
+ Assert(!locale || locale->provider == COLLPROVIDER_LIBC);
+
+#ifdef WIN32
+ /* check for this case before doing the work for nul-termination */
+ if (GetDatabaseEncoding() == PG_UTF8)
+ return pg_strncoll_libc_win32_utf8(arg1, len1, arg2, len2, locale);
+#endif /* WIN32 */
+
+ if (bufsize1 + bufsize2 > TEXTBUFLEN)
+ buf = palloc(bufsize1 + bufsize2);
+
+ arg1n = buf;
+ arg2n = buf + bufsize1;
+
+ /* nul-terminate arguments */
+ memcpy(arg1n, arg1, len1);
+ arg1n[len1] = '\0';
+ memcpy(arg2n, arg2, len2);
+ arg2n[len2] = '\0';
+
+ result = pg_strcoll_libc(arg1n, arg2n, locale);
+
+ if (buf != sbuf)
+ pfree(buf);
+
+ return result;
+}
#ifdef USE_ICU
+
/*
- * Converter object for converting between ICU's UChar strings and C strings
- * in database encoding. Since the database encoding doesn't change, we only
- * need one of these per session.
+ * pg_strncoll_icu_no_utf8
+ *
+ * Convert the arguments from the database encoding to UChar strings, then
+ * call ucol_strcoll().
+ *
+ * When the database encoding is UTF-8, and ICU supports ucol_strcollUTF8(),
+ * caller should call that instead.
*/
-static UConverter *icu_converter = NULL;
+static int
+pg_strncoll_icu_no_utf8(const char *arg1, size_t len1,
+ const char *arg2, size_t len2, pg_locale_t locale)
+{
+ char sbuf[TEXTBUFLEN];
+ char *buf = sbuf;
+ int32_t ulen1;
+ int32_t ulen2;
+ size_t bufsize1;
+ size_t bufsize2;
+ UChar *uchar1,
+ *uchar2;
+ int result;
+
+ Assert(locale->provider == COLLPROVIDER_ICU);
+#ifdef HAVE_UCOL_STRCOLLUTF8
+ Assert(GetDatabaseEncoding() != PG_UTF8);
+#endif
+
+ init_icu_converter();
+
+ ulen1 = uchar_length(icu_converter, arg1, len1);
+ ulen2 = uchar_length(icu_converter, arg2, len2);
+
+ bufsize1 = (ulen1 + 1) * sizeof(UChar);
+ bufsize2 = (ulen2 + 1) * sizeof(UChar);
+
+ if (bufsize1 + bufsize2 > TEXTBUFLEN)
+ buf = palloc(bufsize1 + bufsize2);
+
+ uchar1 = (UChar *) buf;
+ uchar2 = (UChar *) (buf + bufsize1);
+
+ ulen1 = uchar_convert(icu_converter, uchar1, ulen1 + 1, arg1, len1);
+ ulen2 = uchar_convert(icu_converter, uchar2, ulen2 + 1, arg2, len2);
+
+ result = ucol_strcoll(locale->info.icu.ucol,
+ uchar1, ulen1,
+ uchar2, ulen2);
+
+ if (buf != sbuf)
+ pfree(buf);
+
+ return result;
+}
+
+/*
+ * pg_strncoll_icu
+ *
+ * Call ucol_strcollUTF8() or ucol_strcoll() as appropriate for the given
+ * database encoding.
+ *
+ * Arguments must be encoded in the database encoding.
+ */
+static int
+pg_strncoll_icu(const char *arg1, size_t len1, const char *arg2, size_t len2,
+ pg_locale_t locale)
+{
+ int result;
+
+ Assert(locale->provider == COLLPROVIDER_ICU);
+
+#ifdef HAVE_UCOL_STRCOLLUTF8
+ if (GetDatabaseEncoding() == PG_UTF8)
+ {
+ UErrorCode status;
+
+ status = U_ZERO_ERROR;
+ result = ucol_strcollUTF8(locale->info.icu.ucol,
+ arg1, len1,
+ arg2, len2,
+ &status);
+ if (U_FAILURE(status))
+ ereport(ERROR,
+ (errmsg("collation failed: %s", u_errorName(status))));
+ }
+ else
+#endif
+ {
+ result = pg_strncoll_icu_no_utf8(arg1, len1, arg2, len2, locale);
+ }
+
+ return result;
+}
+
+/*
+ * pg_strcoll_icu
+ *
+ * Calculate the string lengths and call pg_strncoll_icu().
+ */
+static int
+pg_strcoll_icu(const char *arg1, const char *arg2, pg_locale_t locale)
+{
+ Assert(locale->provider == COLLPROVIDER_ICU);
+ return pg_strncoll_icu(arg1, -1, arg2, -1, locale);
+}
+
+#endif /* USE_ICU */
+
+/*
+ * pg_strcoll
+ *
+ * Call ucol_strcollUTF8(), ucol_strcoll(), strcoll(), strcoll_l(), wcscoll(),
+ * or wcscoll_l() as appropriate for the given locale, platform, and database
+ * encoding. If the locale is not specified, use the database collation.
+ *
+ * Arguments must be encoded in the database encoding and nul-terminated.
+ *
+ * The caller is responsible for breaking ties if the collation is
+ * deterministic; this maintains consistency with pg_strxfrm(), which cannot
+ * easily account for deterministic collations.
+ */
+int
+pg_strcoll(const char *arg1, const char *arg2, pg_locale_t locale)
+{
+ int result;
+
+ if (!locale || locale->provider == COLLPROVIDER_LIBC)
+ result = pg_strcoll_libc(arg1, arg2, locale);
+#ifdef USE_ICU
+ else if (locale->provider == COLLPROVIDER_ICU)
+ result = pg_strcoll_icu(arg1, arg2, locale);
+#endif
+ else
+ /* shouldn't happen */
+ elog(ERROR, "unsupported collprovider: %c", locale->provider);
+
+ return result;
+}
+
+/*
+ * pg_strncoll
+ *
+ * Call ucol_strcollUTF8(), ucol_strcoll(), strcoll(), strcoll_l(), wcscoll(),
+ * or wcscoll_l() as appropriate for the given locale, platform, and database
+ * encoding. If the locale is not specified, use the database collation.
+ *
+ * Arguments must be encoded in the database encoding.
+ *
+ * This function may need to nul-terminate the arguments for libc functions;
+ * so if the caller already has nul-terminated strings, it should call
+ * pg_strcoll() instead.
+ *
+ * The caller is responsible for breaking ties if the collation is
+ * deterministic; this maintains consistency with pg_strnxfrm(), which cannot
+ * easily account for deterministic collations.
+ */
+int
+pg_strncoll(const char *arg1, size_t len1, const char *arg2, size_t len2,
+ pg_locale_t locale)
+{
+ int result;
+
+ if (!locale || locale->provider == COLLPROVIDER_LIBC)
+ result = pg_strncoll_libc(arg1, len1, arg2, len2, locale);
+#ifdef USE_ICU
+ else if (locale->provider == COLLPROVIDER_ICU)
+ result = pg_strncoll_icu(arg1, len1, arg2, len2, locale);
+#endif
+ else
+ /* shouldn't happen */
+ elog(ERROR, "unsupported collprovider: %c", locale->provider);
+
+ return result;
+}
+
+
+static size_t
+pg_strxfrm_libc(char *dest, const char *src, size_t destsize,
+ pg_locale_t locale)
+{
+ Assert(!locale || locale->provider == COLLPROVIDER_LIBC);
+
+#ifdef TRUST_STXFRM
+#ifdef HAVE_LOCALE_T
+ if (locale)
+ return strxfrm_l(dest, src, destsize, locale->info.lt);
+ else
+#endif
+ return strxfrm(dest, src, destsize);
+#else
+ /* shouldn't happen */
+ elog(ERROR, "unsupported collprovider: %c", locale->provider);
+#endif
+}
+
+static size_t
+pg_strnxfrm_libc(char *dest, const char *src, size_t srclen, size_t destsize,
+ pg_locale_t locale)
+{
+ char sbuf[TEXTBUFLEN];
+ char *buf = sbuf;
+ size_t bufsize = srclen + 1;
+ size_t result;
+ Assert(!locale || locale->provider == COLLPROVIDER_LIBC);
+
+ if (bufsize > TEXTBUFLEN)
+ buf = palloc(bufsize);
+
+ /* nul-terminate arguments */
+ memcpy(buf, src, srclen);
+ buf[srclen] = '\0';
+
+ result = pg_strxfrm_libc(dest, buf, destsize, locale);
+
+ if (buf != sbuf)
+ pfree(buf);
+
+ return result;
+}
+
+static size_t
+pg_strnxfrm_prefix_libc(char *dest, const char *src, size_t srclen,
+ size_t destsize, pg_locale_t locale)
+{
+ Assert(!locale || locale->provider == COLLPROVIDER_LIBC);
+ /* unsupported; shouldn't happen */
+ elog(ERROR, "collprovider '%c' does not support pg_strnxfrm_prefix()",
+ locale->provider);
+}
+
+#ifdef USE_ICU
+
+static size_t
+pg_strnxfrm_icu(char *dest, const char *src, size_t srclen, size_t destsize,
+ pg_locale_t locale)
+{
+ char sbuf[TEXTBUFLEN];
+ char *buf = sbuf;
+ UChar *uchar;
+ int32_t ulen;
+ size_t uchar_bsize;
+ Size result_bsize;
+
+ Assert(locale->provider == COLLPROVIDER_ICU);
+
+ init_icu_converter();
+
+ ulen = uchar_length(icu_converter, src, srclen);
+
+ uchar_bsize = (ulen + 1) * sizeof(UChar);
+
+ if (uchar_bsize > TEXTBUFLEN)
+ buf = palloc(uchar_bsize);
+
+ uchar = (UChar *) buf;
+
+ ulen = uchar_convert(icu_converter, uchar, ulen + 1, src, srclen);
+
+ result_bsize = ucol_getSortKey(locale->info.icu.ucol,
+ uchar, ulen,
+ (uint8_t *) dest, destsize);
+
+ if (buf != sbuf)
+ pfree(buf);
+
+ return result_bsize;
+}
+
+static size_t
+pg_strxfrm_icu(char *dest, const char *src, size_t destsize,
+ pg_locale_t locale)
+{
+ Assert(locale->provider == COLLPROVIDER_ICU);
+ return pg_strnxfrm_icu(dest, src, -1, destsize, locale);
+}
+
+static size_t
+pg_strnxfrm_prefix_icu_no_utf8(char *dest, const char *src, size_t srclen,
+ size_t destsize, pg_locale_t locale)
+{
+ char sbuf[TEXTBUFLEN];
+ char *buf = sbuf;
+ UCharIterator iter;
+ uint32_t state[2];
+ UErrorCode status;
+ int32_t ulen = -1;
+ UChar *uchar = NULL;
+ size_t uchar_bsize;
+ Size result_bsize;
+
+ Assert(locale->provider == COLLPROVIDER_ICU);
+ Assert(GetDatabaseEncoding() != PG_UTF8);
+
+ init_icu_converter();
+
+ ulen = uchar_length(icu_converter, src, srclen);
+
+ uchar_bsize = (ulen + 1) * sizeof(UChar);
+
+ if (uchar_bsize > TEXTBUFLEN)
+ buf = palloc(uchar_bsize);
+
+ uchar = (UChar *) buf;
+
+ ulen = uchar_convert(icu_converter, uchar, ulen + 1, src, srclen);
+
+ uiter_setString(&iter, uchar, ulen);
+ state[0] = state[1] = 0; /* won't need that again */
+ status = U_ZERO_ERROR;
+ result_bsize = ucol_nextSortKeyPart(locale->info.icu.ucol,
+ &iter,
+ state,
+ (uint8_t *) dest,
+ destsize,
+ &status);
+ if (U_FAILURE(status))
+ ereport(ERROR,
+ (errmsg("sort key generation failed: %s",
+ u_errorName(status))));
+
+ return result_bsize;
+}
+
+static size_t
+pg_strnxfrm_prefix_icu(char *dest, const char *src, size_t srclen,
+ size_t destsize, pg_locale_t locale)
+{
+ size_t result;
+
+ Assert(locale->provider == COLLPROVIDER_ICU);
+
+ if (GetDatabaseEncoding() == PG_UTF8)
+ {
+ UCharIterator iter;
+ uint32_t state[2];
+ UErrorCode status;
+
+ uiter_setUTF8(&iter, src, srclen);
+ state[0] = state[1] = 0; /* won't need that again */
+ status = U_ZERO_ERROR;
+ result = ucol_nextSortKeyPart(locale->info.icu.ucol,
+ &iter,
+ state,
+ (uint8_t *) dest,
+ destsize,
+ &status);
+ if (U_FAILURE(status))
+ ereport(ERROR,
+ (errmsg("sort key generation failed: %s",
+ u_errorName(status))));
+ }
+ else
+ result = pg_strnxfrm_prefix_icu_no_utf8(dest, src, srclen, destsize,
+ locale);
+
+ return result;
+}
+
+static size_t
+pg_strxfrm_prefix_icu(char *dest, const char *src, size_t destsize,
+ pg_locale_t locale)
+{
+ Assert(locale->provider == COLLPROVIDER_ICU);
+ return pg_strnxfrm_prefix_icu(dest, src, -1, destsize, locale);
+}
+
+#endif
+
+/*
+ * Return true if the collation provider supports pg_strxfrm() and
+ * pg_strnxfrm(); otherwise false.
+ *
+ * Unfortunately, it seems that strxfrm() for non-C collations is broken on
+ * many common platforms; testing of multiple versions of glibc reveals that,
+ * for many locales, strcoll() and strxfrm() do not return consistent
+ * results. While no other libc other than Cygwin has so far been shown to
+ * have a problem, we take the conservative course of action for right now and
+ * disable this categorically. (Users who are certain this isn't a problem on
+ * their system can set the developer GUC "trust_strxfrm".)
+ *
+ * No similar problem is known for the ICU provider.
+ */
+bool
+pg_strxfrm_enabled(pg_locale_t locale)
+{
+ if (!locale || locale->provider == COLLPROVIDER_LIBC)
+ return trust_strxfrm;
+ else if (locale->provider == COLLPROVIDER_ICU)
+ return true;
+ else
+ /* shouldn't happen */
+ elog(ERROR, "unsupported collprovider: %c", locale->provider);
+}
+
+/*
+ * pg_strxfrm
+ *
+ * Transforms 'src' to a nul-terminated string stored in 'dest' such that
+ * ordinary strcmp() on transformed strings is equivalent to pg_strcoll() on
+ * untransformed strings.
+ *
+ * The provided 'src' must be nul-terminated.
+ *
+ * If destsize is large enough to hold the result, returns the number of bytes
+ * copied to 'dest'; otherwise, returns the number of bytes needed to hold the
+ * result and leaves the contents of 'dest' undefined. If destsize is zero,
+ * 'dest' may be NULL.
+ */
+size_t
+pg_strxfrm(char *dest, const char *src, size_t destsize, pg_locale_t locale)
+{
+ size_t result;
+
+ if (!locale || locale->provider == COLLPROVIDER_LIBC)
+ result = pg_strxfrm_libc(dest, src, destsize, locale);
+#ifdef USE_ICU
+ else if (locale->provider == COLLPROVIDER_ICU)
+ result = pg_strxfrm_icu(dest, src, destsize, locale);
+#endif
+ else
+ /* shouldn't happen */
+ elog(ERROR, "unsupported collprovider: %c", locale->provider);
+
+ return result;
+}
+
+/*
+ * pg_strnxfrm
+ *
+ * Transforms 'src' to a nul-terminated string stored in 'dest' such that
+ * ordinary strcmp() on transformed strings is equivalent to pg_strcoll() on
+ * untransformed strings.
+ *
+ * If destsize is large enough to hold the result, returns the number of bytes
+ * copied to 'dest'; otherwise, returns the number of bytes needed to hold the
+ * result and leaves the contents of 'dest' undefined. If destsize is zero,
+ * 'dest' may be NULL.
+ *
+ * This function may need to nul-terminate the argument for libc functions;
+ * so if the caller already has a nul-terminated string, it should call
+ * pg_strxfrm() instead.
+ */
+size_t
+pg_strnxfrm(char *dest, size_t destsize, const char *src, size_t srclen,
+ pg_locale_t locale)
+{
+ size_t result;
+
+ if (!locale || locale->provider == COLLPROVIDER_LIBC)
+ result = pg_strnxfrm_libc(dest, src, srclen, destsize, locale);
+#ifdef USE_ICU
+ else if (locale->provider == COLLPROVIDER_ICU)
+ result = pg_strnxfrm_icu(dest, src, srclen, destsize, locale);
+#endif
+ else
+ /* shouldn't happen */
+ elog(ERROR, "unsupported collprovider: %c", locale->provider);
+
+ return result;
+}
+
+/*
+ * Return true if the collation provider supports pg_strxfrm_prefix() and
+ * pg_strnxfrm_prefix(); otherwise false.
+ */
+bool
+pg_strxfrm_prefix_enabled(pg_locale_t locale)
+{
+ if (!locale || locale->provider == COLLPROVIDER_LIBC)
+ return false;
+ else if (locale->provider == COLLPROVIDER_ICU)
+ return true;
+ else
+ /* shouldn't happen */
+ elog(ERROR, "unsupported collprovider: %c", locale->provider);
+}
+
+/*
+ * pg_strxfrm_prefix
+ *
+ * Transforms 'src' to a byte sequence stored in 'dest' such that ordinary
+ * memcmp() on the byte sequence is equivalent to pg_strcoll() on
+ * untransformed strings. The result is not nul-terminated.
+ *
+ * The provided 'src' must be nul-terminated.
+ *
+ * If destsize is not large enough to hold the entire result, stores just the
+ * prefix in 'dest'. Returns the number of bytes actually copied to 'dest'.
+ */
+size_t
+pg_strxfrm_prefix(char *dest, const char *src, size_t destsize,
+ pg_locale_t locale)
+{
+ size_t result;
+
+ if (!locale || locale->provider == COLLPROVIDER_LIBC)
+ elog(ERROR, "collprovider '%c' does not support pg_strxfrm_prefix()",
+ locale->provider);
+#ifdef USE_ICU
+ else if (locale->provider == COLLPROVIDER_ICU)
+ result = pg_strxfrm_prefix_icu(dest, src, destsize, locale);
+#endif
+ else
+ /* shouldn't happen */
+ elog(ERROR, "unsupported collprovider: %c", locale->provider);
+
+ return result;
+}
+
+/*
+ * pg_strnxfrm_prefix
+ *
+ * Transforms 'src' to a byte sequence stored in 'dest' such that ordinary
+ * memcmp() on the byte sequence is equivalent to pg_strcoll() on
+ * untransformed strings. The result is not nul-terminated.
+ *
+ * The provided 'src' must be nul-terminated.
+ *
+ * If destsize is not large enough to hold the entire result, stores just the
+ * prefix in 'dest'. Returns the number of bytes actually copied to 'dest'.
+ *
+ * This function may need to nul-terminate the argument for libc functions;
+ * so if the caller already has a nul-terminated string, it should call
+ * pg_strxfrm_prefix() instead.
+ */
+size_t
+pg_strnxfrm_prefix(char *dest, size_t destsize, const char *src,
+ size_t srclen, pg_locale_t locale)
+{
+ size_t result;
+
+ if (!locale || locale->provider == COLLPROVIDER_LIBC)
+ result = pg_strnxfrm_prefix_libc(dest, src, srclen, destsize, locale);
+#ifdef USE_ICU
+ else if (locale->provider == COLLPROVIDER_ICU)
+ result = pg_strnxfrm_prefix_icu(dest, src, srclen, destsize, locale);
+#endif
+ else
+ /* shouldn't happen */
+ elog(ERROR, "unsupported collprovider: %c", locale->provider);
+
+ return result;
+}
+
+#ifdef USE_ICU
static void
init_icu_converter(void)
{
@@ -1767,6 +2490,39 @@ init_icu_converter(void)
icu_converter = conv;
}
+/*
+ * Find length, in UChars, of given string if converted to UChar string.
+ */
+static size_t
+uchar_length(UConverter *converter, const char *str, size_t len)
+{
+ UErrorCode status = U_ZERO_ERROR;
+ int32_t ulen;
+ ulen = ucnv_toUChars(converter, NULL, 0, str, len, &status);
+ if (U_FAILURE(status) && status != U_BUFFER_OVERFLOW_ERROR)
+ ereport(ERROR,
+ (errmsg("%s failed: %s", "ucnv_toUChars", u_errorName(status))));
+ return ulen;
+}
+
+/*
+ * Convert the given source string into a UChar string, stored in dest, and
+ * return the length (in UChars).
+ */
+static int32_t
+uchar_convert(UConverter *converter, UChar *dest, int32_t destlen,
+ const char *src, size_t srclen)
+{
+ UErrorCode status = U_ZERO_ERROR;
+ int32_t ulen;
+ status = U_ZERO_ERROR;
+ ulen = ucnv_toUChars(converter, dest, destlen, src, srclen, &status);
+ if (U_FAILURE(status))
+ ereport(ERROR,
+ (errmsg("%s failed: %s", "ucnv_toUChars", u_errorName(status))));
+ return ulen;
+}
+
/*
* Convert a string in the database encoding into a string of UChars.
*
@@ -1782,26 +2538,15 @@ init_icu_converter(void)
int32_t
icu_to_uchar(UChar **buff_uchar, const char *buff, size_t nbytes)
{
- UErrorCode status;
- int32_t len_uchar;
+ int32_t len_uchar;
init_icu_converter();
- status = U_ZERO_ERROR;
- len_uchar = ucnv_toUChars(icu_converter, NULL, 0,
- buff, nbytes, &status);
- if (U_FAILURE(status) && status != U_BUFFER_OVERFLOW_ERROR)
- ereport(ERROR,
- (errmsg("%s failed: %s", "ucnv_toUChars", u_errorName(status))));
+ len_uchar = uchar_length(icu_converter, buff, nbytes);
*buff_uchar = palloc((len_uchar + 1) * sizeof(**buff_uchar));
-
- status = U_ZERO_ERROR;
- len_uchar = ucnv_toUChars(icu_converter, *buff_uchar, len_uchar + 1,
- buff, nbytes, &status);
- if (U_FAILURE(status))
- ereport(ERROR,
- (errmsg("%s failed: %s", "ucnv_toUChars", u_errorName(status))));
+ len_uchar = uchar_convert(icu_converter,
+ *buff_uchar, len_uchar + 1, buff, nbytes);
return len_uchar;
}
diff --git a/src/backend/utils/adt/varchar.c b/src/backend/utils/adt/varchar.c
index 8ddbae8f51..5bbba94687 100644
--- a/src/backend/utils/adt/varchar.c
+++ b/src/backend/utils/adt/varchar.c
@@ -1024,21 +1024,17 @@ hashbpchar(PG_FUNCTION_ARGS)
#ifdef USE_ICU
if (mylocale->provider == COLLPROVIDER_ICU)
{
- int32_t ulen = -1;
- UChar *uchar = NULL;
- Size bsize;
- uint8_t *buf;
+ Size bsize, rsize;
+ char *buf;
- ulen = icu_to_uchar(&uchar, keydata, keylen);
-
- bsize = ucol_getSortKey(mylocale->info.icu.ucol,
- uchar, ulen, NULL, 0);
+ bsize = pg_strnxfrm(NULL, 0, keydata, keylen, mylocale);
buf = palloc(bsize);
- ucol_getSortKey(mylocale->info.icu.ucol,
- uchar, ulen, buf, bsize);
- pfree(uchar);
- result = hash_any(buf, bsize);
+ rsize = pg_strnxfrm(buf, bsize, keydata, keylen, mylocale);
+ if (rsize != bsize)
+ elog(ERROR, "pg_strnxfrm() returned unexpected result");
+
+ result = hash_any((uint8_t *) buf, bsize);
pfree(buf);
}
@@ -1086,21 +1082,18 @@ hashbpcharextended(PG_FUNCTION_ARGS)
#ifdef USE_ICU
if (mylocale->provider == COLLPROVIDER_ICU)
{
- int32_t ulen = -1;
- UChar *uchar = NULL;
- Size bsize;
- uint8_t *buf;
+ Size bsize, rsize;
+ char *buf;
- ulen = icu_to_uchar(&uchar, keydata, keylen);
-
- bsize = ucol_getSortKey(mylocale->info.icu.ucol,
- uchar, ulen, NULL, 0);
+ bsize = pg_strnxfrm(NULL, 0, keydata, keylen, mylocale);
buf = palloc(bsize);
- ucol_getSortKey(mylocale->info.icu.ucol,
- uchar, ulen, buf, bsize);
- pfree(uchar);
- result = hash_any_extended(buf, bsize, PG_GETARG_INT64(1));
+ rsize = pg_strnxfrm(buf, bsize, keydata, keylen, mylocale);
+ if (rsize != bsize)
+ elog(ERROR, "pg_strnxfrm() returned unexpected result");
+
+ result = hash_any_extended((uint8_t *) buf, bsize,
+ PG_GETARG_INT64(1));
pfree(buf);
}
diff --git a/src/backend/utils/adt/varlena.c b/src/backend/utils/adt/varlena.c
index 33ffdb013a..5030328f31 100644
--- a/src/backend/utils/adt/varlena.c
+++ b/src/backend/utils/adt/varlena.c
@@ -1537,10 +1537,6 @@ varstr_cmp(const char *arg1, int len1, const char *arg2, int len2, Oid collid)
}
else
{
- char a1buf[TEXTBUFLEN];
- char a2buf[TEXTBUFLEN];
- char *a1p,
- *a2p;
pg_locale_t mylocale;
mylocale = pg_newlocale_from_collation(collid);
@@ -1557,171 +1553,16 @@ varstr_cmp(const char *arg1, int len1, const char *arg2, int len2, Oid collid)
if (len1 == len2 && memcmp(arg1, arg2, len1) == 0)
return 0;
-#ifdef WIN32
- /* Win32 does not have UTF-8, so we need to map to UTF-16 */
- if (GetDatabaseEncoding() == PG_UTF8
- && (!mylocale || mylocale->provider == COLLPROVIDER_LIBC))
- {
- int a1len;
- int a2len;
- int r;
-
- if (len1 >= TEXTBUFLEN / 2)
- {
- a1len = len1 * 2 + 2;
- a1p = palloc(a1len);
- }
- else
- {
- a1len = TEXTBUFLEN;
- a1p = a1buf;
- }
- if (len2 >= TEXTBUFLEN / 2)
- {
- a2len = len2 * 2 + 2;
- a2p = palloc(a2len);
- }
- else
- {
- a2len = TEXTBUFLEN;
- a2p = a2buf;
- }
-
- /* stupid Microsloth API does not work for zero-length input */
- if (len1 == 0)
- r = 0;
- else
- {
- r = MultiByteToWideChar(CP_UTF8, 0, arg1, len1,
- (LPWSTR) a1p, a1len / 2);
- if (!r)
- ereport(ERROR,
- (errmsg("could not convert string to UTF-16: error code %lu",
- GetLastError())));
- }
- ((LPWSTR) a1p)[r] = 0;
-
- if (len2 == 0)
- r = 0;
- else
- {
- r = MultiByteToWideChar(CP_UTF8, 0, arg2, len2,
- (LPWSTR) a2p, a2len / 2);
- if (!r)
- ereport(ERROR,
- (errmsg("could not convert string to UTF-16: error code %lu",
- GetLastError())));
- }
- ((LPWSTR) a2p)[r] = 0;
-
- errno = 0;
-#ifdef HAVE_LOCALE_T
- if (mylocale)
- result = wcscoll_l((LPWSTR) a1p, (LPWSTR) a2p, mylocale->info.lt);
- else
-#endif
- result = wcscoll((LPWSTR) a1p, (LPWSTR) a2p);
- if (result == 2147483647) /* _NLSCMPERROR; missing from mingw
- * headers */
- ereport(ERROR,
- (errmsg("could not compare Unicode strings: %m")));
-
- /* Break tie if necessary. */
- if (result == 0 &&
- (!mylocale || mylocale->deterministic))
- {
- result = memcmp(arg1, arg2, Min(len1, len2));
- if ((result == 0) && (len1 != len2))
- result = (len1 < len2) ? -1 : 1;
- }
-
- if (a1p != a1buf)
- pfree(a1p);
- if (a2p != a2buf)
- pfree(a2p);
-
- return result;
- }
-#endif /* WIN32 */
-
- if (len1 >= TEXTBUFLEN)
- a1p = (char *) palloc(len1 + 1);
- else
- a1p = a1buf;
- if (len2 >= TEXTBUFLEN)
- a2p = (char *) palloc(len2 + 1);
- else
- a2p = a2buf;
-
- memcpy(a1p, arg1, len1);
- a1p[len1] = '\0';
- memcpy(a2p, arg2, len2);
- a2p[len2] = '\0';
-
- if (mylocale)
- {
- if (mylocale->provider == COLLPROVIDER_ICU)
- {
-#ifdef USE_ICU
-#ifdef HAVE_UCOL_STRCOLLUTF8
- if (GetDatabaseEncoding() == PG_UTF8)
- {
- UErrorCode status;
-
- status = U_ZERO_ERROR;
- result = ucol_strcollUTF8(mylocale->info.icu.ucol,
- arg1, len1,
- arg2, len2,
- &status);
- if (U_FAILURE(status))
- ereport(ERROR,
- (errmsg("collation failed: %s", u_errorName(status))));
- }
- else
-#endif
- {
- int32_t ulen1,
- ulen2;
- UChar *uchar1,
- *uchar2;
-
- ulen1 = icu_to_uchar(&uchar1, arg1, len1);
- ulen2 = icu_to_uchar(&uchar2, arg2, len2);
-
- result = ucol_strcoll(mylocale->info.icu.ucol,
- uchar1, ulen1,
- uchar2, ulen2);
-
- pfree(uchar1);
- pfree(uchar2);
- }
-#else /* not USE_ICU */
- /* shouldn't happen */
- elog(ERROR, "unsupported collprovider: %c", mylocale->provider);
-#endif /* not USE_ICU */
- }
- else
- {
-#ifdef HAVE_LOCALE_T
- result = strcoll_l(a1p, a2p, mylocale->info.lt);
-#else
- /* shouldn't happen */
- elog(ERROR, "unsupported collprovider: %c", mylocale->provider);
-#endif
- }
- }
- else
- result = strcoll(a1p, a2p);
+ result = pg_strncoll(arg1, len1, arg2, len2, mylocale);
/* Break tie if necessary. */
if (result == 0 &&
(!mylocale || mylocale->deterministic))
- result = strcmp(a1p, a2p);
-
- if (a1p != a1buf)
- pfree(a1p);
- if (a2p != a2buf)
- pfree(a2p);
+ {
+ result = memcmp(arg1, arg2, Min(len1, len2));
+ if ((result == 0) && (len1 != len2))
+ result = (len1 < len2) ? -1 : 1;
+ }
}
return result;
@@ -2057,20 +1898,6 @@ varstr_sortsupport(SortSupport ssup, Oid typid, Oid collid)
*/
locale = pg_newlocale_from_collation(collid);
- /*
- * There is a further exception on Windows. When the database
- * encoding is UTF-8 and we are not using the C collation, complex
- * hacks are required. We don't currently have a comparator that
- * handles that case, so we fall back on the slow method of having the
- * sort code invoke bttextcmp() (in the case of text) via the fmgr
- * trampoline. ICU locales work just the same on Windows, however.
- */
-#ifdef WIN32
- if (GetDatabaseEncoding() == PG_UTF8 &&
- !(locale && locale->provider == COLLPROVIDER_ICU))
- return;
-#endif
-
/*
* We use varlenafastcmp_locale except for type NAME.
*/
@@ -2086,13 +1913,7 @@ varstr_sortsupport(SortSupport ssup, Oid typid, Oid collid)
/*
* Unfortunately, it seems that abbreviation for non-C collations is
- * broken on many common platforms; testing of multiple versions of glibc
- * reveals that, for many locales, strcoll() and strxfrm() do not return
- * consistent results, which is fatal to this optimization. While no
- * other libc other than Cygwin has so far been shown to have a problem,
- * we take the conservative course of action for right now and disable
- * this categorically. (Users who are certain this isn't a problem on
- * their system can define TRUST_STRXFRM.)
+ * broken on many common platforms; see pg_strxfrm_enabled().
*
* Even apart from the risk of broken locales, it's possible that there
* are platforms where the use of abbreviated keys should be disabled at
@@ -2105,10 +1926,8 @@ varstr_sortsupport(SortSupport ssup, Oid typid, Oid collid)
* categorically, we may still want or need to disable it for particular
* platforms.
*/
-#ifndef TRUST_STRXFRM
- if (!collate_c && !(locale && locale->provider == COLLPROVIDER_ICU))
+ if (!collate_c && !pg_strxfrm_enabled(locale))
abbreviate = false;
-#endif
/*
* If we're using abbreviated keys, or if we're using a locale-aware
@@ -2379,60 +2198,7 @@ varstrfastcmp_locale(char *a1p, int len1, char *a2p, int len2, SortSupport ssup)
return sss->last_returned;
}
- if (sss->locale)
- {
- if (sss->locale->provider == COLLPROVIDER_ICU)
- {
-#ifdef USE_ICU
-#ifdef HAVE_UCOL_STRCOLLUTF8
- if (GetDatabaseEncoding() == PG_UTF8)
- {
- UErrorCode status;
-
- status = U_ZERO_ERROR;
- result = ucol_strcollUTF8(sss->locale->info.icu.ucol,
- a1p, len1,
- a2p, len2,
- &status);
- if (U_FAILURE(status))
- ereport(ERROR,
- (errmsg("collation failed: %s", u_errorName(status))));
- }
- else
-#endif
- {
- int32_t ulen1,
- ulen2;
- UChar *uchar1,
- *uchar2;
-
- ulen1 = icu_to_uchar(&uchar1, a1p, len1);
- ulen2 = icu_to_uchar(&uchar2, a2p, len2);
-
- result = ucol_strcoll(sss->locale->info.icu.ucol,
- uchar1, ulen1,
- uchar2, ulen2);
-
- pfree(uchar1);
- pfree(uchar2);
- }
-#else /* not USE_ICU */
- /* shouldn't happen */
- elog(ERROR, "unsupported collprovider: %c", sss->locale->provider);
-#endif /* not USE_ICU */
- }
- else
- {
-#ifdef HAVE_LOCALE_T
- result = strcoll_l(sss->buf1, sss->buf2, sss->locale->info.lt);
-#else
- /* shouldn't happen */
- elog(ERROR, "unsupported collprovider: %c", sss->locale->provider);
-#endif
- }
- }
- else
- result = strcoll(sss->buf1, sss->buf2);
+ result = pg_strcoll(sss->buf1, sss->buf2, sss->locale);
/* Break tie if necessary. */
if (result == 0 &&
@@ -2455,6 +2221,7 @@ varstrfastcmp_locale(char *a1p, int len1, char *a2p, int len2, SortSupport ssup)
static Datum
varstr_abbrev_convert(Datum original, SortSupport ssup)
{
+ const size_t max_prefix_bytes = sizeof(Datum);
VarStringSortSupport *sss = (VarStringSortSupport *) ssup->ssup_extra;
VarString *authoritative = DatumGetVarStringPP(original);
char *authoritative_data = VARDATA_ANY(authoritative);
@@ -2467,7 +2234,7 @@ varstr_abbrev_convert(Datum original, SortSupport ssup)
pres = (char *) &res;
/* memset(), so any non-overwritten bytes are NUL */
- memset(pres, 0, sizeof(Datum));
+ memset(pres, 0, max_prefix_bytes);
len = VARSIZE_ANY_EXHDR(authoritative);
/* Get number of bytes, ignoring trailing spaces */
@@ -2502,14 +2269,10 @@ varstr_abbrev_convert(Datum original, SortSupport ssup)
* thing: explicitly consider string length.
*/
if (sss->collate_c)
- memcpy(pres, authoritative_data, Min(len, sizeof(Datum)));
+ memcpy(pres, authoritative_data, Min(len, max_prefix_bytes));
else
{
Size bsize;
-#ifdef USE_ICU
- int32_t ulen = -1;
- UChar *uchar = NULL;
-#endif
/*
* We're not using the C collation, so fall back on strxfrm or ICU
@@ -2527,7 +2290,7 @@ varstr_abbrev_convert(Datum original, SortSupport ssup)
if (sss->last_len1 == len && sss->cache_blob &&
memcmp(sss->buf1, authoritative_data, len) == 0)
{
- memcpy(pres, sss->buf2, Min(sizeof(Datum), sss->last_len2));
+ memcpy(pres, sss->buf2, Min(max_prefix_bytes, sss->last_len2));
/* No change affecting cardinality, so no hashing required */
goto done;
}
@@ -2535,81 +2298,49 @@ varstr_abbrev_convert(Datum original, SortSupport ssup)
memcpy(sss->buf1, authoritative_data, len);
/*
- * Just like strcoll(), strxfrm() expects a NUL-terminated string. Not
- * necessary for ICU, but doesn't hurt.
+ * pg_strxfrm() and pg_strxfrm_prefix expect NUL-terminated
+ * strings.
*/
sss->buf1[len] = '\0';
sss->last_len1 = len;
-#ifdef USE_ICU
- /* When using ICU and not UTF8, convert string to UChar. */
- if (sss->locale && sss->locale->provider == COLLPROVIDER_ICU &&
- GetDatabaseEncoding() != PG_UTF8)
- ulen = icu_to_uchar(&uchar, sss->buf1, len);
-#endif
-
- /*
- * Loop: Call strxfrm() or ucol_getSortKey(), possibly enlarge buffer,
- * and try again. Both of these functions have the result buffer
- * content undefined if the result did not fit, so we need to retry
- * until everything fits, even though we only need the first few bytes
- * in the end. When using ucol_nextSortKeyPart(), however, we only
- * ask for as many bytes as we actually need.
- */
- for (;;)
+ if (pg_strxfrm_prefix_enabled(sss->locale))
{
-#ifdef USE_ICU
- if (sss->locale && sss->locale->provider == COLLPROVIDER_ICU)
+ if (sss->buflen2 < max_prefix_bytes)
{
- /*
- * When using UTF8, use the iteration interface so we only
- * need to produce as many bytes as we actually need.
- */
- if (GetDatabaseEncoding() == PG_UTF8)
- {
- UCharIterator iter;
- uint32_t state[2];
- UErrorCode status;
-
- uiter_setUTF8(&iter, sss->buf1, len);
- state[0] = state[1] = 0; /* won't need that again */
- status = U_ZERO_ERROR;
- bsize = ucol_nextSortKeyPart(sss->locale->info.icu.ucol,
- &iter,
- state,
- (uint8_t *) sss->buf2,
- Min(sizeof(Datum), sss->buflen2),
- &status);
- if (U_FAILURE(status))
- ereport(ERROR,
- (errmsg("sort key generation failed: %s",
- u_errorName(status))));
- }
- else
- bsize = ucol_getSortKey(sss->locale->info.icu.ucol,
- uchar, ulen,
- (uint8_t *) sss->buf2, sss->buflen2);
+ sss->buflen2 = Max(max_prefix_bytes,
+ Min(sss->buflen2 * 2, MaxAllocSize));
+ sss->buf2 = repalloc(sss->buf2, sss->buflen2);
}
- else
-#endif
-#ifdef HAVE_LOCALE_T
- if (sss->locale && sss->locale->provider == COLLPROVIDER_LIBC)
- bsize = strxfrm_l(sss->buf2, sss->buf1,
- sss->buflen2, sss->locale->info.lt);
- else
-#endif
- bsize = strxfrm(sss->buf2, sss->buf1, sss->buflen2);
-
- sss->last_len2 = bsize;
- if (bsize < sss->buflen2)
- break;
+ bsize = pg_strxfrm_prefix(sss->buf2, sss->buf1,
+ max_prefix_bytes, sss->locale);
+ }
+ else
+ {
/*
- * Grow buffer and retry.
+ * Loop: Call pg_strxfrm(), possibly enlarge buffer, and try
+ * again. The pg_strxfrm() function leaves the result buffer
+ * content undefined if the result did not fit, so we need to
+ * retry until everything fits, even though we only need the first
+ * few bytes in the end.
*/
- sss->buflen2 = Max(bsize + 1,
- Min(sss->buflen2 * 2, MaxAllocSize));
- sss->buf2 = repalloc(sss->buf2, sss->buflen2);
+ for (;;)
+ {
+ bsize = pg_strxfrm(sss->buf2, sss->buf1, sss->buflen2,
+ sss->locale);
+
+ sss->last_len2 = bsize;
+ if (bsize < sss->buflen2)
+ break;
+
+ /*
+ * Grow buffer and retry.
+ */
+ sss->buflen2 = Max(bsize + 1,
+ Min(sss->buflen2 * 2, MaxAllocSize));
+ sss->buf2 = repalloc(sss->buf2, sss->buflen2);
+ }
}
/*
@@ -2621,12 +2352,7 @@ varstr_abbrev_convert(Datum original, SortSupport ssup)
* (Actually, even if there were NUL bytes in the blob it would be
* okay. See remarks on bytea case above.)
*/
- memcpy(pres, sss->buf2, Min(sizeof(Datum), bsize));
-
-#ifdef USE_ICU
- if (uchar)
- pfree(uchar);
-#endif
+ memcpy(pres, sss->buf2, Min(max_prefix_bytes, bsize));
}
/*
diff --git a/src/backend/utils/misc/guc_tables.c b/src/backend/utils/misc/guc_tables.c
index cd0fc2cb8f..4562b028c7 100644
--- a/src/backend/utils/misc/guc_tables.c
+++ b/src/backend/utils/misc/guc_tables.c
@@ -1954,6 +1954,17 @@ struct config_bool ConfigureNamesBool[] =
NULL, NULL, NULL
},
+ {
+ {"trust_strxfrm", PGC_USERSET, DEVELOPER_OPTIONS,
+ gettext_noop("Allow use of strxfrm() for abbreviated keys optimization for libc provider."),
+ NULL,
+ GUC_NOT_IN_SAMPLE
+ },
+ &trust_strxfrm,
+ false,
+ NULL, NULL, NULL
+ },
+
{
{"data_sync_retry", PGC_POSTMASTER, ERROR_HANDLING_OPTIONS,
gettext_noop("Whether to continue running after a failure to sync data files."),
diff --git a/src/include/utils/pg_locale.h b/src/include/utils/pg_locale.h
index cede43440b..c08e6ce07f 100644
--- a/src/include/utils/pg_locale.h
+++ b/src/include/utils/pg_locale.h
@@ -40,6 +40,7 @@ extern PGDLLIMPORT char *locale_messages;
extern PGDLLIMPORT char *locale_monetary;
extern PGDLLIMPORT char *locale_numeric;
extern PGDLLIMPORT char *locale_time;
+extern PGDLLIMPORT bool trust_strxfrm;
/* lc_time localization cache */
extern PGDLLIMPORT char *localized_abbrev_days[];
@@ -100,6 +101,19 @@ extern void make_icu_collator(const char *iculocstr,
extern pg_locale_t pg_newlocale_from_collation(Oid collid);
extern char *get_collation_actual_version(char collprovider, const char *collcollate);
+extern int pg_strcoll(const char *arg1, const char *arg2, pg_locale_t locale);
+extern int pg_strncoll(const char *arg1, size_t len1,
+ const char *arg2, size_t len2, pg_locale_t locale);
+extern bool pg_strxfrm_enabled(pg_locale_t locale);
+extern size_t pg_strxfrm(char *dest, const char *src, size_t destsize,
+ pg_locale_t locale);
+extern size_t pg_strnxfrm(char *dest, size_t destsize, const char *src,
+ size_t srclen, pg_locale_t locale);
+extern bool pg_strxfrm_prefix_enabled(pg_locale_t locale);
+extern size_t pg_strxfrm_prefix(char *dest, const char *src, size_t destsize,
+ pg_locale_t locale);
+extern size_t pg_strnxfrm_prefix(char *dest, size_t destsize, const char *src,
+ size_t srclen, pg_locale_t locale);
#ifdef USE_ICU
extern int32_t icu_to_uchar(UChar **buff_uchar, const char *buff, size_t nbytes);
--
2.34.1
view thread (7+ messages) latest in thread
reply
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Reply to all the recipients using the --to and --cc options:
reply via email
To: [email protected]
Cc: [email protected], [email protected]
Subject: Re: Rework of collation code, extensibility
In-Reply-To: <[email protected]>
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
This inbox is served by agora; see mirroring instructions
for how to clone and mirror all data and code used for this inbox