From: Tom Lane <tgl@sss.pgh.pa.us>
Date: Thu, 22 Dec 2005 22:50:14 +0000 (+0000)
Subject: Adjust string comparison so that only bitwise-equal strings are considered
X-Git-Tag: REL8_0_6~19
X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=faefc812f8aa41c4875520640db0c4e6d5c2edca;p=thirdparty%2Fpostgresql.git

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.
---

diff --git a/src/backend/utils/adt/varchar.c b/src/backend/utils/adt/varchar.c
index eeb218bf57a..40e771ffab5 100644
--- a/src/backend/utils/adt/varchar.c
+++ b/src/backend/utils/adt/varchar.c
@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/utils/adt/varchar.c,v 1.108 2004/12/31 22:01:22 pgsql Exp $
+ *	  $PostgreSQL: pgsql/src/backend/utils/adt/varchar.c,v 1.108.4.1 2005/12/22 22:50:14 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -551,11 +551,14 @@ 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);
@@ -575,11 +578,14 @@ 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);
@@ -692,7 +698,9 @@ 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)
diff --git a/src/backend/utils/adt/varlena.c b/src/backend/utils/adt/varlena.c
index a2570a66bbe..f7f64add239 100644
--- a/src/backend/utils/adt/varlena.c
+++ b/src/backend/utils/adt/varlena.c
@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/utils/adt/varlena.c,v 1.118 2004/12/31 22:01:22 pgsql Exp $
+ *	  $PostgreSQL: pgsql/src/backend/utils/adt/varlena.c,v 1.118.4.1 2005/12/22 22:50:14 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -879,6 +879,15 @@ varstr_cmp(char *arg1, int len1, char *arg2, int len2)
 
 		result = strcoll(a1p, a2p);
 
+		/*
+		 * In some locales strcoll() can claim that nonidentical strings are
+		 * equal.  Believing that would be bad news for a number of reasons,
+		 * so we follow Perl's lead and sort "equal" strings according to
+		 * strcmp().
+		 */
+		if (result == 0)
+			result = strcmp(a1p, a2p);
+
 		if (len1 >= STACKBUFLEN)
 			pfree(a1p);
 		if (len2 >= STACKBUFLEN)
@@ -931,11 +940,15 @@ texteq(PG_FUNCTION_ARGS)
 	text	   *arg2 = PG_GETARG_TEXT_P(1);
 	bool		result;
 
-	/* 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 (VARSIZE(arg1) != VARSIZE(arg2))
 		result = false;
 	else
-		result = (text_cmp(arg1, arg2) == 0);
+		result = (strncmp(VARDATA(arg1), VARDATA(arg2),
+						  VARSIZE(arg1) - VARHDRSZ) == 0);
 
 	PG_FREE_IF_COPY(arg1, 0);
 	PG_FREE_IF_COPY(arg2, 1);
@@ -950,11 +963,15 @@ textne(PG_FUNCTION_ARGS)
 	text	   *arg2 = PG_GETARG_TEXT_P(1);
 	bool		result;
 
-	/* 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 (VARSIZE(arg1) != VARSIZE(arg2))
 		result = true;
 	else
-		result = (text_cmp(arg1, arg2) != 0);
+		result = (strncmp(VARDATA(arg1), VARDATA(arg2),
+						  VARSIZE(arg1) - VARHDRSZ) != 0);
 
 	PG_FREE_IF_COPY(arg1, 0);
 	PG_FREE_IF_COPY(arg2, 1);