mirror/postgresql
2
0
Fork 0
mirror of https://git.postgresql.org/git/postgresql.git synced 2025-01-18 18:44:06 +08:00
Code Issues Packages Projects Releases Wiki Activity

Teach regex_fixed_prefix() the correct handling of advanced regex

Browse Source 
escapes --- they aren't simply quoted characters.  Problem noted by
Antti Salmela.  Also fix problem with incorrect handling of multibyte
characters when followed by a quantifier.
This commit is contained in:
Tom Lane 2004-12-02 02:45:07 +00:00
parent 4e91824b94
commit 76e8a87f15
1 changed files with 26 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
src/backend/utils/adt/selfuncs.c
View File

@ -15,7 +15,7 @@
*
*
* IDENTIFICATION
* $PostgreSQL: pgsql/src/backend/utils/adt/selfuncs.c,v 1.167 2004/11/09 00:34:42 tgl Exp $
* $PostgreSQL: pgsql/src/backend/utils/adt/selfuncs.c,v 1.168 2004/12/02 02:45:07 tgl Exp $
*
*-------------------------------------------------------------------------
*/
@ -3459,6 +3459,8 @@ regex_fixed_prefix(Const *patt_const, bool case_insensitive,
char *match;
int pos,
match_pos,
prev_pos,
prev_match_pos,
paren_depth;
char *patt;
char *rest;
@ -3519,11 +3521,13 @@ regex_fixed_prefix(Const *patt_const, bool case_insensitive,
/* OK, allocate space for pattern */
match = palloc(strlen(patt) + 1);
match_pos = 0;
prev_match_pos = match_pos = 0;
/* note start at pos 1 to skip leading ^ */
for (pos = 1; patt[pos]; pos++)
for (prev_pos = pos = 1; patt[pos]; )
{
int len;
/*
* Check for characters that indicate multiple possible matches
* here. XXX I suspect isalpha() is not an adequately
@ -3537,6 +3541,14 @@ regex_fixed_prefix(Const *patt_const, bool case_insensitive,
(case_insensitive && isalpha((unsigned char) patt[pos])))
break;
/*
* In AREs, backslash followed by alphanumeric is an escape, not
* a quoted character. Must treat it as having multiple possible
* matches.
*/
if (patt[pos] == '\\' && isalnum((unsigned char) patt[pos + 1]))
break;
/*
* Check for quantifiers. Except for +, this means the preceding
* character is optional, so we must remove it from the prefix
@ -3546,14 +3558,13 @@ regex_fixed_prefix(Const *patt_const, bool case_insensitive,
patt[pos] == '?' ||
patt[pos] == '{')
{
if (match_pos > 0)
match_pos--;
pos--;
match_pos = prev_match_pos;
pos = prev_pos;
break;
}
if (patt[pos] == '+')
{
pos--;
pos = prev_pos;
break;
}
if (patt[pos] == '\\')
@ -3563,7 +3574,14 @@ regex_fixed_prefix(Const *patt_const, bool case_insensitive,
if (patt[pos] == '\0')
break;
}
match[match_pos++] = patt[pos];
/* save position in case we need to back up on next loop cycle */
prev_match_pos = match_pos;
prev_pos = pos;
/* must use encoding-aware processing here */
len = pg_mblen(&patt[pos]);
memcpy(&match[match_pos], &patt[pos], len);
match_pos += len;
pos += len;
}
match[match_pos] = '\0';