From 8526ae1884e7d36ab9d0da06a1fd16b9ea0f7206 Mon Sep 17 00:00:00 2001 From: Jeff Davis Date: Mon, 12 Jan 2026 09:04:03 -0800 Subject: [PATCH v1 2/4] citext: use CASEFOLD() rather than LOWER(). CASEFOLD() is better for case-insensitive matching in edge cases. Existing citext indexes require REINDEX. --- contrib/citext/citext.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) diff --git a/contrib/citext/citext.c b/contrib/citext/citext.c index a15ce5db829..02cad8c4ac3 100644 --- a/contrib/citext/citext.c +++ b/contrib/citext/citext.c @@ -43,15 +43,15 @@ citextcmp(text *left, text *right, Oid collid) int32 result; /* - * We must do our str_tolower calls with DEFAULT_COLLATION_OID, not the + * We must do our str_casefold calls with DEFAULT_COLLATION_OID, not the * input collation as you might expect. This is so that the behavior of * citext's equality and hashing functions is not collation-dependent. We * should change this once the core infrastructure is able to cope with * collation-dependent equality and hashing functions. */ - lcstr = str_tolower(VARDATA_ANY(left), VARSIZE_ANY_EXHDR(left), DEFAULT_COLLATION_OID); - rcstr = str_tolower(VARDATA_ANY(right), VARSIZE_ANY_EXHDR(right), DEFAULT_COLLATION_OID); + lcstr = str_casefold(VARDATA_ANY(left), VARSIZE_ANY_EXHDR(left), DEFAULT_COLLATION_OID); + rcstr = str_casefold(VARDATA_ANY(right), VARSIZE_ANY_EXHDR(right), DEFAULT_COLLATION_OID); result = varstr_cmp(lcstr, strlen(lcstr), rcstr, strlen(rcstr), @@ -77,8 +77,8 @@ internal_citext_pattern_cmp(text *left, text *right, Oid collid) rlen; int32 result; - lcstr = str_tolower(VARDATA_ANY(left), VARSIZE_ANY_EXHDR(left), DEFAULT_COLLATION_OID); - rcstr = str_tolower(VARDATA_ANY(right), VARSIZE_ANY_EXHDR(right), DEFAULT_COLLATION_OID); + lcstr = str_casefold(VARDATA_ANY(left), VARSIZE_ANY_EXHDR(left), DEFAULT_COLLATION_OID); + rcstr = str_casefold(VARDATA_ANY(right), VARSIZE_ANY_EXHDR(right), DEFAULT_COLLATION_OID); llen = strlen(lcstr); rlen = strlen(rcstr); @@ -147,7 +147,7 @@ citext_hash(PG_FUNCTION_ARGS) char *str; Datum result; - str = str_tolower(VARDATA_ANY(txt), VARSIZE_ANY_EXHDR(txt), DEFAULT_COLLATION_OID); + str = str_casefold(VARDATA_ANY(txt), VARSIZE_ANY_EXHDR(txt), DEFAULT_COLLATION_OID); result = hash_any((unsigned char *) str, strlen(str)); pfree(str); @@ -167,7 +167,7 @@ citext_hash_extended(PG_FUNCTION_ARGS) char *str; Datum result; - str = str_tolower(VARDATA_ANY(txt), VARSIZE_ANY_EXHDR(txt), DEFAULT_COLLATION_OID); + str = str_casefold(VARDATA_ANY(txt), VARSIZE_ANY_EXHDR(txt), DEFAULT_COLLATION_OID); result = hash_any_extended((unsigned char *) str, strlen(str), seed); pfree(str); @@ -196,8 +196,8 @@ citext_eq(PG_FUNCTION_ARGS) /* We can't compare lengths in advance of downcasing ... */ - lcstr = str_tolower(VARDATA_ANY(left), VARSIZE_ANY_EXHDR(left), DEFAULT_COLLATION_OID); - rcstr = str_tolower(VARDATA_ANY(right), VARSIZE_ANY_EXHDR(right), DEFAULT_COLLATION_OID); + lcstr = str_casefold(VARDATA_ANY(left), VARSIZE_ANY_EXHDR(left), DEFAULT_COLLATION_OID); + rcstr = str_casefold(VARDATA_ANY(right), VARSIZE_ANY_EXHDR(right), DEFAULT_COLLATION_OID); /* * Since we only care about equality or not-equality, we can avoid all the @@ -226,8 +226,8 @@ citext_ne(PG_FUNCTION_ARGS) /* We can't compare lengths in advance of downcasing ... */ - lcstr = str_tolower(VARDATA_ANY(left), VARSIZE_ANY_EXHDR(left), DEFAULT_COLLATION_OID); - rcstr = str_tolower(VARDATA_ANY(right), VARSIZE_ANY_EXHDR(right), DEFAULT_COLLATION_OID); + lcstr = str_casefold(VARDATA_ANY(left), VARSIZE_ANY_EXHDR(left), DEFAULT_COLLATION_OID); + rcstr = str_casefold(VARDATA_ANY(right), VARSIZE_ANY_EXHDR(right), DEFAULT_COLLATION_OID); /* * Since we only care about equality or not-equality, we can avoid all the -- 2.43.0