database/postgres
database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-05-18 17:41:14 +03:00
Code

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 02:45:24 +00:00
parent d237a12e49
commit 6ba32b24b2
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 * IDENTIFICATION
* $Header: /cvsroot/pgsql/src/backend/utils/adt/selfuncs.c,v 1.147.2.3 2004/02/27 21:44:44 tgl Exp $ * $Header: /cvsroot/pgsql/src/backend/utils/adt/selfuncs.c,v 1.147.2.4 2004/12/02 02:45:24 tgl Exp $
* *
*------------------------------------------------------------------------- *-------------------------------------------------------------------------
*/ */
@ -3218,6 +3218,8 @@ regex_fixed_prefix(Const *patt_const, bool case_insensitive,
char *match; char *match;
int pos, int pos,
match_pos, match_pos,
prev_pos,
prev_match_pos,
paren_depth; paren_depth;
char *patt; char *patt;
char *rest; char *rest;
@ -3278,11 +3280,13 @@ regex_fixed_prefix(Const *patt_const, bool case_insensitive,
/* OK, allocate space for pattern */ /* OK, allocate space for pattern */
match = palloc(strlen(patt) + 1); match = palloc(strlen(patt) + 1);
match_pos = 0; prev_match_pos = match_pos = 0;
/* note start at pos 1 to skip leading ^ */ /* 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 * Check for characters that indicate multiple possible matches
* here. XXX I suspect isalpha() is not an adequately * here. XXX I suspect isalpha() is not an adequately
@ -3296,6 +3300,14 @@ regex_fixed_prefix(Const *patt_const, bool case_insensitive,
(case_insensitive && isalpha((unsigned char) patt[pos]))) (case_insensitive && isalpha((unsigned char) patt[pos])))
break; 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 * Check for quantifiers. Except for +, this means the preceding
* character is optional, so we must remove it from the prefix * character is optional, so we must remove it from the prefix
@ -3305,14 +3317,13 @@ regex_fixed_prefix(Const *patt_const, bool case_insensitive,
patt[pos] == '?' || patt[pos] == '?' ||
patt[pos] == '{') patt[pos] == '{')
{ {
if (match_pos > 0) match_pos = prev_match_pos;
match_pos--; pos = prev_pos;
pos--;
break; break;
} }
if (patt[pos] == '+') if (patt[pos] == '+')
{ {
pos--; pos = prev_pos;
break; break;
} }
if (patt[pos] == '\\') if (patt[pos] == '\\')
@ -3322,7 +3333,14 @@ regex_fixed_prefix(Const *patt_const, bool case_insensitive,
if (patt[pos] == '\0') if (patt[pos] == '\0')
break; 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'; match[match_pos] = '\0';