diff options
| author | Jeff Davis | 2025-12-16 19:13:17 +0000 |
|---|---|---|
| committer | Jeff Davis | 2025-12-16 20:57:12 +0000 |
| commit | 806555e3000d0b0e0c536c1dc65548128d457d86 (patch) | |
| tree | 8b63be0550fb7d31cc82630f1e5545f9bb0a7d0b /contrib/ltree/crc32.c | |
| parent | f79e239e0bc6e4d5fe91e1a0e573ecf0715d6c8c (diff) | |
ltree: fix case-insensitive matching.REL_18_STABLE
Previously, ltree_prefix_eq_ci() used lowercasing with the default
collation; while ltree_crc32_sz() used tolower() directly. These were
equivalent only if the default collation provider was libc and the
encoding was single-byte.
Change both to use casefolding with the default collation.
Backpatch through 18, where the casefolding APIs were introduced. The
bug exists in earlier versions, but would require some adaptation.
A REINDEX is required for ltree indexes where the database default
collation is not libc.
Reviewed-by: Chao Li <li.evan.chao@gmail.com>
Reviewed-by: Peter Eisentraut <peter@eisentraut.org>
Backpatch-through: 18
Discussion: https://postgr.es/m/450ceb6260cad30d7afdf155d991a9caafee7c0d.camel@j-davis.com
Discussion: https://postgr.es/m/01fc00fd66f641b9693d4f9f1af0ccf44cbdfbdf.camel@j-davis.com
Diffstat (limited to 'contrib/ltree/crc32.c')
| -rw-r--r-- | contrib/ltree/crc32.c | 47 |
1 files changed, 39 insertions, 8 deletions
diff --git a/contrib/ltree/crc32.c b/contrib/ltree/crc32.c index 134f46a805e..ce1b0f28e21 100644 --- a/contrib/ltree/crc32.c +++ b/contrib/ltree/crc32.c @@ -10,31 +10,62 @@ #include "postgres.h" #include "ltree.h" +#include "crc32.h" +#include "utils/pg_crc.h" #ifdef LOWER_NODE -#include <ctype.h> -#define TOLOWER(x) tolower((unsigned char) (x)) -#else -#define TOLOWER(x) (x) +#include "catalog/pg_collation.h" +#include "utils/pg_locale.h" #endif -#include "crc32.h" -#include "utils/pg_crc.h" +#ifdef LOWER_NODE unsigned int ltree_crc32_sz(const char *buf, int size) { pg_crc32 crc; const char *p = buf; + static pg_locale_t locale = NULL; + + if (!locale) + locale = pg_newlocale_from_collation(DEFAULT_COLLATION_OID); INIT_TRADITIONAL_CRC32(crc); while (size > 0) { - char c = (char) TOLOWER(*p); + char foldstr[UNICODE_CASEMAP_BUFSZ]; + int srclen = pg_mblen(p); + size_t foldlen; + + /* fold one codepoint at a time */ + foldlen = pg_strfold(foldstr, UNICODE_CASEMAP_BUFSZ, p, srclen, + locale); + + COMP_TRADITIONAL_CRC32(crc, foldstr, foldlen); + + size -= srclen; + p += srclen; + } + FIN_TRADITIONAL_CRC32(crc); + return (unsigned int) crc; +} + +#else - COMP_TRADITIONAL_CRC32(crc, &c, 1); +unsigned int +ltree_crc32_sz(const char *buf, int size) +{ + pg_crc32 crc; + const char *p = buf; + + INIT_TRADITIONAL_CRC32(crc); + while (size > 0) + { + COMP_TRADITIONAL_CRC32(crc, p, 1); size--; p++; } FIN_TRADITIONAL_CRC32(crc); return (unsigned int) crc; } + +#endif /* !LOWER_NODE */ |