summaryrefslogtreecommitdiff
path: root/src/backend/utils/adt/regexp.c
diff options
context:
space:
mode:
Diffstat (limited to 'src/backend/utils/adt/regexp.c')
-rw-r--r--src/backend/utils/adt/regexp.c91
1 files changed, 46 insertions, 45 deletions
diff --git a/src/backend/utils/adt/regexp.c b/src/backend/utils/adt/regexp.c
index e4e3c77665..cbffcdb183 100644
--- a/src/backend/utils/adt/regexp.c
+++ b/src/backend/utils/adt/regexp.c
@@ -3,12 +3,12 @@
* regexp.c
* Postgres' interface to the regular expression package.
*
- * Portions Copyright (c) 1996-2009, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1996-2010, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
*
* IDENTIFICATION
- * $PostgreSQL: pgsql/src/backend/utils/adt/regexp.c,v 1.82 2009/06/11 14:49:04 momjian Exp $
+ * $PostgreSQL: pgsql/src/backend/utils/adt/regexp.c,v 1.86 2010/01/02 20:59:16 tgl Exp $
*
* Alistair Crooks added the code for the regex caching
* agc - cached the regular expressions used - there's a good chance
@@ -39,10 +39,6 @@
(PG_NARGS() > (_n) ? PG_GETARG_TEXT_PP(_n) : NULL)
-/* GUC-settable flavor parameter */
-int regex_flavor = REG_ADVANCED;
-
-
/* all the options of interest for regex functions */
typedef struct pg_re_flags
{
@@ -347,8 +343,8 @@ RE_compile_and_execute(text *text_re, char *dat, int dat_len,
static void
parse_re_flags(pg_re_flags *flags, text *opts)
{
- /* regex_flavor is always folded into the compile flags */
- flags->cflags = regex_flavor;
+ /* regex flavor is always folded into the compile flags */
+ flags->cflags = REG_ADVANCED;
flags->glob = false;
if (opts)
@@ -415,16 +411,6 @@ parse_re_flags(pg_re_flags *flags, text *opts)
/*
- * report whether regex_flavor is currently BASIC
- */
-bool
-regex_flavor_is_basic(void)
-{
- return (regex_flavor == REG_BASIC);
-}
-
-
-/*
* interface routines called by the function manager
*/
@@ -437,7 +423,7 @@ nameregexeq(PG_FUNCTION_ARGS)
PG_RETURN_BOOL(RE_compile_and_execute(p,
NameStr(*n),
strlen(NameStr(*n)),
- regex_flavor,
+ REG_ADVANCED,
0, NULL));
}
@@ -450,7 +436,7 @@ nameregexne(PG_FUNCTION_ARGS)
PG_RETURN_BOOL(!RE_compile_and_execute(p,
NameStr(*n),
strlen(NameStr(*n)),
- regex_flavor,
+ REG_ADVANCED,
0, NULL));
}
@@ -463,7 +449,7 @@ textregexeq(PG_FUNCTION_ARGS)
PG_RETURN_BOOL(RE_compile_and_execute(p,
VARDATA_ANY(s),
VARSIZE_ANY_EXHDR(s),
- regex_flavor,
+ REG_ADVANCED,
0, NULL));
}
@@ -476,7 +462,7 @@ textregexne(PG_FUNCTION_ARGS)
PG_RETURN_BOOL(!RE_compile_and_execute(p,
VARDATA_ANY(s),
VARSIZE_ANY_EXHDR(s),
- regex_flavor,
+ REG_ADVANCED,
0, NULL));
}
@@ -496,7 +482,7 @@ nameicregexeq(PG_FUNCTION_ARGS)
PG_RETURN_BOOL(RE_compile_and_execute(p,
NameStr(*n),
strlen(NameStr(*n)),
- regex_flavor | REG_ICASE,
+ REG_ADVANCED | REG_ICASE,
0, NULL));
}
@@ -509,7 +495,7 @@ nameicregexne(PG_FUNCTION_ARGS)
PG_RETURN_BOOL(!RE_compile_and_execute(p,
NameStr(*n),
strlen(NameStr(*n)),
- regex_flavor | REG_ICASE,
+ REG_ADVANCED | REG_ICASE,
0, NULL));
}
@@ -522,7 +508,7 @@ texticregexeq(PG_FUNCTION_ARGS)
PG_RETURN_BOOL(RE_compile_and_execute(p,
VARDATA_ANY(s),
VARSIZE_ANY_EXHDR(s),
- regex_flavor | REG_ICASE,
+ REG_ADVANCED | REG_ICASE,
0, NULL));
}
@@ -535,7 +521,7 @@ texticregexne(PG_FUNCTION_ARGS)
PG_RETURN_BOOL(!RE_compile_and_execute(p,
VARDATA_ANY(s),
VARSIZE_ANY_EXHDR(s),
- regex_flavor | REG_ICASE,
+ REG_ADVANCED | REG_ICASE,
0, NULL));
}
@@ -555,7 +541,7 @@ textregexsubstr(PG_FUNCTION_ARGS)
eo;
/* Compile RE */
- re = RE_compile_and_cache(p, regex_flavor);
+ re = RE_compile_and_cache(p, REG_ADVANCED);
/*
* We pass two regmatch_t structs to get info about the overall match and
@@ -611,7 +597,7 @@ textregexreplace_noopt(PG_FUNCTION_ARGS)
text *r = PG_GETARG_TEXT_PP(2);
regex_t *re;
- re = RE_compile_and_cache(p, regex_flavor);
+ re = RE_compile_and_cache(p, REG_ADVANCED);
PG_RETURN_TEXT_P(replace_text_regexp(s, (void *) re, r, false));
}
@@ -639,7 +625,7 @@ textregexreplace(PG_FUNCTION_ARGS)
/*
* similar_escape()
- * Convert a SQL99 regexp pattern to POSIX style, so it can be used by
+ * Convert a SQL:2008 regexp pattern to POSIX style, so it can be used by
* our regexp engine.
*/
Datum
@@ -654,6 +640,7 @@ similar_escape(PG_FUNCTION_ARGS)
int plen,
elen;
bool afterescape = false;
+ bool incharclass = false;
int nquotes = 0;
/* This function is not strict, so must test explicitly */
@@ -684,12 +671,10 @@ similar_escape(PG_FUNCTION_ARGS)
/*----------
* We surround the transformed input string with
- * ***:^(?: ... )$
- * which is bizarre enough to require some explanation. "***:" is a
- * director prefix to force the regex to be treated as an ARE regardless
- * of the current regex_flavor setting. We need "^" and "$" to force
- * the pattern to match the entire input string as per SQL99 spec. The
- * "(?:" and ")" are a non-capturing set of parens; we have to have
+ * ^(?: ... )$
+ * which requires some explanation. We need "^" and "$" to force
+ * the pattern to match the entire input string as per SQL99 spec.
+ * The "(?:" and ")" are a non-capturing set of parens; we have to have
* parens in case the string contains "|", else the "^" and "$" will
* be bound into the first and last alternatives which is not what we
* want, and the parens must be non capturing because we don't want them
@@ -698,16 +683,12 @@ similar_escape(PG_FUNCTION_ARGS)
*/
/*
- * We need room for the prefix/postfix plus as many as 2 output bytes per
- * input byte
+ * We need room for the prefix/postfix plus as many as 3 output bytes per
+ * input byte; since the input is at most 1GB this can't overflow
*/
- result = (text *) palloc(VARHDRSZ + 10 + 2 * plen);
+ result = (text *) palloc(VARHDRSZ + 6 + 3 * plen);
r = VARDATA(result);
- *r++ = '*';
- *r++ = '*';
- *r++ = '*';
- *r++ = ':';
*r++ = '^';
*r++ = '(';
*r++ = '?';
@@ -719,7 +700,7 @@ similar_escape(PG_FUNCTION_ARGS)
if (afterescape)
{
- if (pchar == '"') /* for SUBSTRING patterns */
+ if (pchar == '"' && !incharclass) /* for SUBSTRING patterns */
*r++ = ((nquotes++ % 2) == 0) ? '(' : ')';
else
{
@@ -733,6 +714,19 @@ similar_escape(PG_FUNCTION_ARGS)
/* SQL99 escape character; do not send to output */
afterescape = true;
}
+ else if (incharclass)
+ {
+ if (pchar == '\\')
+ *r++ = '\\';
+ *r++ = pchar;
+ if (pchar == ']')
+ incharclass = false;
+ }
+ else if (pchar == '[')
+ {
+ *r++ = pchar;
+ incharclass = true;
+ }
else if (pchar == '%')
{
*r++ = '.';
@@ -740,8 +734,15 @@ similar_escape(PG_FUNCTION_ARGS)
}
else if (pchar == '_')
*r++ = '.';
- else if (pchar == '\\' || pchar == '.' || pchar == '?' ||
- pchar == '{')
+ else if (pchar == '(')
+ {
+ /* convert to non-capturing parenthesis */
+ *r++ = '(';
+ *r++ = '?';
+ *r++ = ':';
+ }
+ else if (pchar == '\\' || pchar == '.' ||
+ pchar == '^' || pchar == '$')
{
*r++ = '\\';
*r++ = pchar;
generated by cgit v1.2.3 (git 2.39.1) at 2025-07-10 22:51:42 +0000