From 0862aeaeec46153337df89c9c0d4d25e6d5c7713 Mon Sep 17 00:00:00 2001 From: Tom Lane Date: Thu, 22 Dec 2005 22:50:22 +0000 Subject: Adjust string comparison so that only bitwise-equal strings are considered equal: if strcoll claims two strings are equal, check it with strcmp, and sort according to strcmp if not identical. This fixes inconsistent behavior under glibc's hu_HU locale, and probably under some other locales as well. Also, take advantage of the now-well-defined behavior to speed up texteq, textne, bpchareq, bpcharne: they may as well just do a bitwise comparison and not bother with strcoll at all. NOTE: affected databases may need to REINDEX indexes on text columns to be sure they are self-consistent. --- src/backend/utils/adt/varchar.c | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) (limited to 'src/backend/utils/adt/varchar.c') diff --git a/src/backend/utils/adt/varchar.c b/src/backend/utils/adt/varchar.c index 0982fb95d4f..0fe34439178 100644 --- a/src/backend/utils/adt/varchar.c +++ b/src/backend/utils/adt/varchar.c @@ -8,7 +8,7 @@ * * * IDENTIFICATION - * $Header: /cvsroot/pgsql/src/backend/utils/adt/varchar.c,v 1.102 2003/08/04 04:03:10 tgl Exp $ + * $Header: /cvsroot/pgsql/src/backend/utils/adt/varchar.c,v 1.102.4.1 2005/12/22 22:50:22 tgl Exp $ * *------------------------------------------------------------------------- */ @@ -549,11 +549,14 @@ bpchareq(PG_FUNCTION_ARGS) len1 = bcTruelen(arg1); len2 = bcTruelen(arg2); - /* fast path for different-length inputs */ + /* + * Since we only care about equality or not-equality, we can avoid all + * the expense of strcoll() here, and just do bitwise comparison. + */ if (len1 != len2) result = false; else - result = (varstr_cmp(VARDATA(arg1), len1, VARDATA(arg2), len2) == 0); + result = (strncmp(VARDATA(arg1), VARDATA(arg2), len1) == 0); PG_FREE_IF_COPY(arg1, 0); PG_FREE_IF_COPY(arg2, 1); @@ -573,11 +576,14 @@ bpcharne(PG_FUNCTION_ARGS) len1 = bcTruelen(arg1); len2 = bcTruelen(arg2); - /* fast path for different-length inputs */ + /* + * Since we only care about equality or not-equality, we can avoid all + * the expense of strcoll() here, and just do bitwise comparison. + */ if (len1 != len2) result = true; else - result = (varstr_cmp(VARDATA(arg1), len1, VARDATA(arg2), len2) != 0); + result = (strncmp(VARDATA(arg1), VARDATA(arg2), len1) != 0); PG_FREE_IF_COPY(arg1, 0); PG_FREE_IF_COPY(arg2, 1); @@ -690,7 +696,9 @@ bpcharcmp(PG_FUNCTION_ARGS) * bpchar needs a specialized hash function because we want to ignore * trailing blanks in comparisons. * - * XXX is there any need for locale-specific behavior here? + * Note: currently there is no need for locale-specific behavior here, + * but if we ever change the semantics of bpchar comparison to trust + * strcoll() completely, we'd need to do something different in non-C locales. */ Datum hashbpchar(PG_FUNCTION_ARGS) -- cgit v1.2.3