aboutsummaryrefslogtreecommitdiff
path: root/src/backend/utils/adt/like_support.c
diff options
context:
space:
mode:
authorTom Lane <tgl@sss.pgh.pa.us>2019-08-12 13:15:47 -0400
committerTom Lane <tgl@sss.pgh.pa.us>2019-08-12 13:15:47 -0400
commit03c811a483b243952874d8e2b3f0c2e3793bc952 (patch)
tree0b55bd3212a7e94cc2c3368846b7dc01528e9589 /src/backend/utils/adt/like_support.c
parent3c926587b5928795e54dfea65c712a604f63cdeb (diff)
downloadpostgresql-03c811a483b243952874d8e2b3f0c2e3793bc952.tar.gz
postgresql-03c811a483b243952874d8e2b3f0c2e3793bc952.zip
Fix planner's test for case-foldable characters in ILIKE with ICU.
As coded, the ICU-collation path in pattern_char_isalpha() failed to consider regular ASCII letters to be case-varying. This led to like_fixed_prefix treating too much of an ILIKE pattern as being a fixed prefix, so that indexscans derived from an ILIKE clause might miss entries that they should find. Per bug #15892 from James Inform. This is an oversight in the original ICU patch (commit eccfef81e), so back-patch to v10 where that came in. Discussion: https://postgr.es/m/15892-e5d2bea3e8a04a1b@postgresql.org
Diffstat (limited to 'src/backend/utils/adt/like_support.c')
-rw-r--r--src/backend/utils/adt/like_support.c8
1 files changed, 5 insertions, 3 deletions
diff --git a/src/backend/utils/adt/like_support.c b/src/backend/utils/adt/like_support.c
index 26e06348338..c8fec7863f4 100644
--- a/src/backend/utils/adt/like_support.c
+++ b/src/backend/utils/adt/like_support.c
@@ -1437,8 +1437,9 @@ regex_selectivity(const char *patt, int pattlen, bool case_insensitive,
* Check whether char is a letter (and, hence, subject to case-folding)
*
* In multibyte character sets or with ICU, we can't use isalpha, and it does
- * not seem worth trying to convert to wchar_t to use iswalpha. Instead, just
- * assume any multibyte char is potentially case-varying.
+ * not seem worth trying to convert to wchar_t to use iswalpha or u_isalpha.
+ * Instead, just assume any non-ASCII char is potentially case-varying, and
+ * hard-wire knowledge of which ASCII chars are letters.
*/
static int
pattern_char_isalpha(char c, bool is_multibyte,
@@ -1449,7 +1450,8 @@ pattern_char_isalpha(char c, bool is_multibyte,
else if (is_multibyte && IS_HIGHBIT_SET(c))
return true;
else if (locale && locale->provider == COLLPROVIDER_ICU)
- return IS_HIGHBIT_SET(c) ? true : false;
+ return IS_HIGHBIT_SET(c) ||
+ (c >= 'A' && c <= 'Z') || (c >= 'a' && c <= 'z');
#ifdef HAVE_LOCALE_T
else if (locale && locale->provider == COLLPROVIDER_LIBC)
return isalpha_l((unsigned char) c, locale->info.lt);