From 1b30cb9b34b770cebc0bb20af867baec2f72aedb Mon Sep 17 00:00:00 2001 From: jian he Date: Wed, 30 Jul 2025 16:48:56 +0800 Subject: [PATCH v18 1/3] introduce CopyFormat refactor CopyFormatOptions Currently, COPY command format is determined by two booleans, binary and csv_mode, within CopyFormatOptions. This approach, while functional, isn't ideal for future expansion. To simplify adding new formats, we've introduced an enum CopyFormat. This makes the code cleaner and more maintainable, allowing for easier integration of additional formats down the line. The CopyFormat enum was originally contributed by Joel Jacobson joel@compiler.org, later refactored by Jian He to address various issues. discussion: https://postgr.es/m/CALvfUkBxTYy5uWPFVwpk_7ii2zgT07t3d-yR_cy4sfrrLU%3Dkcg%40mail.gmail.com discussion: https://postgr.es/m/6a04628d-0d53-41d9-9e35-5a8dc302c34c@joeconway.com --- src/backend/commands/copy.c | 50 +++++++++++++++------------- src/backend/commands/copyfrom.c | 6 ++-- src/backend/commands/copyfromparse.c | 7 ++-- src/backend/commands/copyto.c | 8 ++--- src/include/commands/copy.h | 13 ++++++-- 5 files changed, 48 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/copy.c b/src/backend/commands/copy.c index fae9c41db65..68f69cfb9df 100644 --- a/src/backend/commands/copy.c +++ b/src/backend/commands/copy.c @@ -521,6 +521,8 @@ ProcessCopyOptions(ParseState *pstate, opts_out = (CopyFormatOptions *) palloc0(sizeof(CopyFormatOptions)); opts_out->file_encoding = -1; + /* default format */ + opts_out->format = COPY_FORMAT_TEXT; /* Extract options from the statement node tree */ foreach(option, options) @@ -535,11 +537,11 @@ ProcessCopyOptions(ParseState *pstate, errorConflictingDefElem(defel, pstate); format_specified = true; if (strcmp(fmt, "text") == 0) - /* default format */ ; + opts_out->format = COPY_FORMAT_TEXT; else if (strcmp(fmt, "csv") == 0) - opts_out->csv_mode = true; + opts_out->format = COPY_FORMAT_CSV; else if (strcmp(fmt, "binary") == 0) - opts_out->binary = true; + opts_out->format = COPY_FORMAT_BINARY; else ereport(ERROR, (errcode(ERRCODE_INVALID_PARAMETER_VALUE), @@ -699,31 +701,31 @@ ProcessCopyOptions(ParseState *pstate, * Check for incompatible options (must do these three before inserting * defaults) */ - if (opts_out->binary && opts_out->delim) + if (opts_out->format == COPY_FORMAT_BINARY && opts_out->delim) ereport(ERROR, (errcode(ERRCODE_SYNTAX_ERROR), /*- translator: %s is the name of a COPY option, e.g. ON_ERROR */ errmsg("cannot specify %s in BINARY mode", "DELIMITER"))); - if (opts_out->binary && opts_out->null_print) + if (opts_out->format == COPY_FORMAT_BINARY && opts_out->null_print) ereport(ERROR, (errcode(ERRCODE_SYNTAX_ERROR), errmsg("cannot specify %s in BINARY mode", "NULL"))); - if (opts_out->binary && opts_out->default_print) + if (opts_out->format == COPY_FORMAT_BINARY && opts_out->default_print) ereport(ERROR, (errcode(ERRCODE_SYNTAX_ERROR), errmsg("cannot specify %s in BINARY mode", "DEFAULT"))); /* Set defaults for omitted options */ if (!opts_out->delim) - opts_out->delim = opts_out->csv_mode ? "," : "\t"; + opts_out->delim = (opts_out->format == COPY_FORMAT_CSV) ? "," : "\t"; if (!opts_out->null_print) - opts_out->null_print = opts_out->csv_mode ? "" : "\\N"; + opts_out->null_print = (opts_out->format == COPY_FORMAT_CSV) ? "" : "\\N"; opts_out->null_print_len = strlen(opts_out->null_print); - if (opts_out->csv_mode) + if (opts_out->format == COPY_FORMAT_CSV) { if (!opts_out->quote) opts_out->quote = "\""; @@ -771,7 +773,7 @@ ProcessCopyOptions(ParseState *pstate, * future-proofing. Likewise we disallow all digits though only octal * digits are actually dangerous. */ - if (!opts_out->csv_mode && + if (opts_out->format != COPY_FORMAT_CSV && strchr("\\.abcdefghijklmnopqrstuvwxyz0123456789", opts_out->delim[0]) != NULL) ereport(ERROR, @@ -779,43 +781,43 @@ ProcessCopyOptions(ParseState *pstate, errmsg("COPY delimiter cannot be \"%s\"", opts_out->delim))); /* Check header */ - if (opts_out->binary && opts_out->header_line != COPY_HEADER_FALSE) + if (opts_out->format == COPY_FORMAT_BINARY && opts_out->header_line != COPY_HEADER_FALSE) ereport(ERROR, (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), /*- translator: %s is the name of a COPY option, e.g. ON_ERROR */ errmsg("cannot specify %s in BINARY mode", "HEADER"))); /* Check quote */ - if (!opts_out->csv_mode && opts_out->quote != NULL) + if (opts_out->format != COPY_FORMAT_CSV && opts_out->quote != NULL) ereport(ERROR, (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), /*- translator: %s is the name of a COPY option, e.g. ON_ERROR */ errmsg("COPY %s requires CSV mode", "QUOTE"))); - if (opts_out->csv_mode && strlen(opts_out->quote) != 1) + if (opts_out->format == COPY_FORMAT_CSV && strlen(opts_out->quote) != 1) ereport(ERROR, (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), errmsg("COPY quote must be a single one-byte character"))); - if (opts_out->csv_mode && opts_out->delim[0] == opts_out->quote[0]) + if (opts_out->format == COPY_FORMAT_CSV && opts_out->delim[0] == opts_out->quote[0]) ereport(ERROR, (errcode(ERRCODE_INVALID_PARAMETER_VALUE), errmsg("COPY delimiter and quote must be different"))); /* Check escape */ - if (!opts_out->csv_mode && opts_out->escape != NULL) + if (opts_out->format != COPY_FORMAT_CSV && opts_out->escape != NULL) ereport(ERROR, (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), /*- translator: %s is the name of a COPY option, e.g. ON_ERROR */ errmsg("COPY %s requires CSV mode", "ESCAPE"))); - if (opts_out->csv_mode && strlen(opts_out->escape) != 1) + if (opts_out->format == COPY_FORMAT_CSV && strlen(opts_out->escape) != 1) ereport(ERROR, (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), errmsg("COPY escape must be a single one-byte character"))); /* Check force_quote */ - if (!opts_out->csv_mode && (opts_out->force_quote || opts_out->force_quote_all)) + if (opts_out->format != COPY_FORMAT_CSV && (opts_out->force_quote || opts_out->force_quote_all)) ereport(ERROR, (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), /*- translator: %s is the name of a COPY option, e.g. ON_ERROR */ @@ -829,8 +831,8 @@ ProcessCopyOptions(ParseState *pstate, "COPY FROM"))); /* Check force_notnull */ - if (!opts_out->csv_mode && (opts_out->force_notnull != NIL || - opts_out->force_notnull_all)) + if (opts_out->format != COPY_FORMAT_CSV && (opts_out->force_notnull != NIL || + opts_out->force_notnull_all)) ereport(ERROR, (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), /*- translator: %s is the name of a COPY option, e.g. ON_ERROR */ @@ -845,8 +847,8 @@ ProcessCopyOptions(ParseState *pstate, "COPY TO"))); /* Check force_null */ - if (!opts_out->csv_mode && (opts_out->force_null != NIL || - opts_out->force_null_all)) + if (opts_out->format != COPY_FORMAT_CSV && (opts_out->force_null != NIL || + opts_out->force_null_all)) ereport(ERROR, (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), /*- translator: %s is the name of a COPY option, e.g. ON_ERROR */ @@ -870,7 +872,7 @@ ProcessCopyOptions(ParseState *pstate, "NULL"))); /* Don't allow the CSV quote char to appear in the null string. */ - if (opts_out->csv_mode && + if (opts_out->format == COPY_FORMAT_CSV && strchr(opts_out->null_print, opts_out->quote[0]) != NULL) ereport(ERROR, (errcode(ERRCODE_INVALID_PARAMETER_VALUE), @@ -906,7 +908,7 @@ ProcessCopyOptions(ParseState *pstate, "DEFAULT"))); /* Don't allow the CSV quote char to appear in the default string. */ - if (opts_out->csv_mode && + if (opts_out->format == COPY_FORMAT_CSV && strchr(opts_out->default_print, opts_out->quote[0]) != NULL) ereport(ERROR, (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), @@ -923,7 +925,7 @@ ProcessCopyOptions(ParseState *pstate, errmsg("NULL specification and DEFAULT specification cannot be the same"))); } /* Check on_error */ - if (opts_out->binary && opts_out->on_error != COPY_ON_ERROR_STOP) + if (opts_out->format == COPY_FORMAT_BINARY && opts_out->on_error != COPY_ON_ERROR_STOP) ereport(ERROR, (errcode(ERRCODE_SYNTAX_ERROR), errmsg("only ON_ERROR STOP is allowed in BINARY mode"))); diff --git a/src/backend/commands/copyfrom.c b/src/backend/commands/copyfrom.c index fbbbc09a97b..6c4bd303841 100644 --- a/src/backend/commands/copyfrom.c +++ b/src/backend/commands/copyfrom.c @@ -155,9 +155,9 @@ static const CopyFromRoutine CopyFromRoutineBinary = { static const CopyFromRoutine * CopyFromGetRoutine(const CopyFormatOptions *opts) { - if (opts->csv_mode) + if (opts->format == COPY_FORMAT_CSV) return &CopyFromRoutineCSV; - else if (opts->binary) + else if (opts->format == COPY_FORMAT_BINARY) return &CopyFromRoutineBinary; /* default is text */ @@ -261,7 +261,7 @@ CopyFromErrorCallback(void *arg) cstate->cur_relname); return; } - if (cstate->opts.binary) + if (cstate->opts.format == COPY_FORMAT_BINARY) { /* can't usefully display the data */ if (cstate->cur_attname) diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c index b1ae97b833d..578e6c0c9a2 100644 --- a/src/backend/commands/copyfromparse.c +++ b/src/backend/commands/copyfromparse.c @@ -171,7 +171,7 @@ ReceiveCopyBegin(CopyFromState cstate) { StringInfoData buf; int natts = list_length(cstate->attnumlist); - int16 format = (cstate->opts.binary ? 1 : 0); + int16 format = (cstate->opts.format == COPY_FORMAT_BINARY ? 1 : 0); int i; pq_beginmessage(&buf, PqMsg_CopyInResponse); @@ -747,7 +747,7 @@ bool NextCopyFromRawFields(CopyFromState cstate, char ***fields, int *nfields) { return NextCopyFromRawFieldsInternal(cstate, fields, nfields, - cstate->opts.csv_mode); + cstate->opts.format == COPY_FORMAT_CSV); } /* @@ -774,7 +774,8 @@ NextCopyFromRawFieldsInternal(CopyFromState cstate, char ***fields, int *nfields bool done = false; /* only available for text or csv input */ - Assert(!cstate->opts.binary); + Assert(cstate->opts.format == COPY_FORMAT_TEXT || + cstate->opts.format == COPY_FORMAT_CSV); /* on input check that the header line is correct if needed */ if (cstate->cur_lineno == 0 && cstate->opts.header_line != COPY_HEADER_FALSE) diff --git a/src/backend/commands/copyto.c b/src/backend/commands/copyto.c index 67b94b91cae..e990343bab0 100644 --- a/src/backend/commands/copyto.c +++ b/src/backend/commands/copyto.c @@ -176,9 +176,9 @@ static const CopyToRoutine CopyToRoutineBinary = { static const CopyToRoutine * CopyToGetRoutine(const CopyFormatOptions *opts) { - if (opts->csv_mode) + if (opts->format == COPY_FORMAT_CSV) return &CopyToRoutineCSV; - else if (opts->binary) + else if (opts->format == COPY_FORMAT_BINARY) return &CopyToRoutineBinary; /* default is text */ @@ -215,7 +215,7 @@ CopyToTextLikeStart(CopyToState cstate, TupleDesc tupDesc) colname = NameStr(TupleDescAttr(tupDesc, attnum - 1)->attname); - if (cstate->opts.csv_mode) + if (cstate->opts.format == COPY_FORMAT_CSV) CopyAttributeOutCSV(cstate, colname, false); else CopyAttributeOutText(cstate, colname); @@ -392,7 +392,7 @@ SendCopyBegin(CopyToState cstate) { StringInfoData buf; int natts = list_length(cstate->attnumlist); - int16 format = (cstate->opts.binary ? 1 : 0); + int16 format = (cstate->opts.format == COPY_FORMAT_BINARY ? 1 : 0); int i; pq_beginmessage(&buf, PqMsg_CopyOutResponse); diff --git a/src/include/commands/copy.h b/src/include/commands/copy.h index 541176e1980..686653233b2 100644 --- a/src/include/commands/copy.h +++ b/src/include/commands/copy.h @@ -48,6 +48,16 @@ typedef enum CopyLogVerbosityChoice COPY_LOG_VERBOSITY_VERBOSE, /* logs additional messages */ } CopyLogVerbosityChoice; +/* + * Represents the format of the COPY operation. + */ +typedef enum CopyFormat +{ + COPY_FORMAT_TEXT = 0, + COPY_FORMAT_BINARY, + COPY_FORMAT_CSV, +} CopyFormat; + /* * A struct to hold COPY options, in a parsed form. All of these are related * to formatting, except for 'freeze', which doesn't really belong here, but @@ -58,9 +68,8 @@ typedef struct CopyFormatOptions /* parameters from the COPY command */ int file_encoding; /* file or remote side's character encoding, * -1 if not specified */ - bool binary; /* binary format? */ + CopyFormat format; /* format of the COPY operation */ bool freeze; /* freeze rows on loading? */ - bool csv_mode; /* Comma Separated Value format? */ int header_line; /* number of lines to skip or COPY_HEADER_XXX * value (see the above) */ char *null_print; /* NULL marker string (server encoding!) */ -- 2.34.1