From 05d249717d652f0b16960d8a58611e222f1f907b Mon Sep 17 00:00:00 2001 From: Tom Lane Date: Sat, 10 Oct 2009 03:50:15 +0000 Subject: Improve similar_escape() in two different ways: * Stop escaping ? and {. As of SQL:2008, SIMILAR TO is defined to have POSIX-compatible interpretation of ? as well as {m,n} and related constructs, so we should allow these things through to our regex engine. * Escape ^ and $. It appears that our regex engine will treat ^^ at the beginning of the string the same as ^, and similarly for $$ at the end of the string, which meant that SIMILAR TO was effectively ignoring ^ at the start of the pattern and $ at the end. Since these are not supposed to be metacharacters, this is a bug. The second part of this is arguably a back-patchable bug fix, but I'm hesitant to do that because it might break applications that are expecting something like "col SIMILAR TO '^foo$'" to work like a POSIX pattern. Seems safer to only change it at a major version boundary. Per discussion of an example from Doug Gorley. --- src/backend/utils/adt/regexp.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'src/backend/utils/adt/regexp.c') diff --git a/src/backend/utils/adt/regexp.c b/src/backend/utils/adt/regexp.c index e4e3c776658..118d42d2a0a 100644 --- a/src/backend/utils/adt/regexp.c +++ b/src/backend/utils/adt/regexp.c @@ -8,7 +8,7 @@ * * * 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 1.83 2009/10/10 03:50:15 tgl Exp $ * * Alistair Crooks added the code for the regex caching * agc - cached the regular expressions used - there's a good chance @@ -639,7 +639,7 @@ 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 @@ -740,8 +740,8 @@ similar_escape(PG_FUNCTION_ARGS) } else if (pchar == '_') *r++ = '.'; - else if (pchar == '\\' || pchar == '.' || pchar == '?' || - pchar == '{') + else if (pchar == '\\' || pchar == '.' || + pchar == '^' || pchar == '$') { *r++ = '\\'; *r++ = pchar; -- cgit v1.2.3