From c0c12ce391d89328640dd948b82466c308d85415 Mon Sep 17 00:00:00 2001 From: Tom Lane Date: Mon, 12 Aug 2019 13:15:47 -0400 Subject: 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 --- src/backend/utils/adt/like_support.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'src/backend/utils/adt/like_support.c') 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); -- cgit v1.2.3