v6-0001-ICU-support-locale-C-with-the-same-behavior-as-li.patch

From b6cbf986e1f0b32009ed060ad52a145a01e999d0 Mon Sep 17 00:00:00 2001
From: Jeff Davis <jeff@j-davis.com>
Date: Mon, 24 Apr 2023 15:46:17 -0700
Subject: [PATCH v6 1/4] ICU: support locale "C" with the same behavior as
 libc.

The "C" locale doesn't actually use a provider at all, it's a special
locale that uses memcmp() and built-in character classification. Make
it behave the same in ICU as libc (even though it doesn't actually
make use of either provider).

Discussion: https://postgr.es/m/87v8hoexdv.fsf@news-spur.riddles.org.uk
---
 src/backend/commands/collationcmds.c          | 43 ++++++----
 src/backend/commands/dbcommands.c             | 42 ++++++----
 src/backend/utils/adt/pg_locale.c             | 83 ++++++++++++++-----
 .../regress/expected/collate.icu.utf8.out     |  6 ++
 src/test/regress/sql/collate.icu.utf8.sql     |  4 +
 5 files changed, 127 insertions(+), 51 deletions(-)

diff --git a/src/backend/commands/collationcmds.c b/src/backend/commands/collationcmds.c
index 2969a2bb21..dd6cd2682f 100644
--- a/src/backend/commands/collationcmds.c
+++ b/src/backend/commands/collationcmds.c
@@ -264,26 +264,39 @@ DefineCollation(ParseState *pstate, List *names, List *parameters, bool if_not_e
 						(errcode(ERRCODE_INVALID_OBJECT_DEFINITION),
 						 errmsg("parameter \"locale\" must be specified")));
 
-			/*
-			 * During binary upgrade, preserve the locale string. Otherwise,
-			 * canonicalize to a language tag.
-			 */
-			if (!IsBinaryUpgrade)
+			if (strcmp(colliculocale, "C") == 0 ||
+				strcmp(colliculocale, "POSIX") == 0)
 			{
-				char	   *langtag = icu_language_tag(colliculocale,
-													   icu_validation_level);
-
-				if (langtag && strcmp(colliculocale, langtag) != 0)
+				if (!collisdeterministic)
+					ereport(ERROR,
+							(errmsg("nondeterministic collations not supported for C or POSIX locale")));
+				if (collicurules != NULL)
+					ereport(ERROR,
+							(errmsg("RULES not supported for C or POSIX locale")));
+			}
+			else
+			{
+				/*
+				 * During binary upgrade, preserve the locale
+				 * string. Otherwise, canonicalize to a language tag.
+				 */
+				if (!IsBinaryUpgrade)
 				{
-					ereport(NOTICE,
-							(errmsg("using standard form \"%s\" for locale \"%s\"",
-									langtag, colliculocale)));
+					char	   *langtag = icu_language_tag(colliculocale,
+														   icu_validation_level);
+
+					if (langtag && strcmp(colliculocale, langtag) != 0)
+					{
+						ereport(NOTICE,
+								(errmsg("using standard form \"%s\" for locale \"%s\"",
+										langtag, colliculocale)));
 
-					colliculocale = langtag;
+						colliculocale = langtag;
+					}
 				}
-			}
 
-			icu_validate_locale(colliculocale);
+				icu_validate_locale(colliculocale);
+			}
 		}
 
 		/*
diff --git a/src/backend/commands/dbcommands.c b/src/backend/commands/dbcommands.c
index 99d4080ea9..bfce8dc348 100644
--- a/src/backend/commands/dbcommands.c
+++ b/src/backend/commands/dbcommands.c
@@ -1058,27 +1058,37 @@ createdb(ParseState *pstate, const CreatedbStmt *stmt)
 					(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
 					 errmsg("ICU locale must be specified")));
 
-		/*
-		 * During binary upgrade, or when the locale came from the template
-		 * database, preserve locale string. Otherwise, canonicalize to a
-		 * language tag.
-		 */
-		if (!IsBinaryUpgrade && dbiculocale != src_iculocale)
+		if (strcmp(dbiculocale, "C") == 0 ||
+			strcmp(dbiculocale, "POSIX") == 0)
 		{
-			char	   *langtag = icu_language_tag(dbiculocale,
-												   icu_validation_level);
-
-			if (langtag && strcmp(dbiculocale, langtag) != 0)
+			if (dbicurules != NULL)
+				ereport(ERROR,
+						(errmsg("ICU_RULES not supported for C or POSIX locale")));
+		}
+		else
+		{
+			/*
+			 * During binary upgrade, or when the locale came from the
+			 * template database, preserve locale string. Otherwise,
+			 * canonicalize to a language tag.
+			 */
+			if (!IsBinaryUpgrade && dbiculocale != src_iculocale)
 			{
-				ereport(NOTICE,
-						(errmsg("using standard form \"%s\" for locale \"%s\"",
-								langtag, dbiculocale)));
+				char	   *langtag = icu_language_tag(dbiculocale,
+													   icu_validation_level);
+
+				if (langtag && strcmp(dbiculocale, langtag) != 0)
+				{
+					ereport(NOTICE,
+							(errmsg("using standard form \"%s\" for locale \"%s\"",
+									langtag, dbiculocale)));
 
-				dbiculocale = langtag;
+					dbiculocale = langtag;
+				}
 			}
-		}
 
-		icu_validate_locale(dbiculocale);
+			icu_validate_locale(dbiculocale);
+		}
 	}
 	else
 	{
diff --git a/src/backend/utils/adt/pg_locale.c b/src/backend/utils/adt/pg_locale.c
index 31e3b16ae0..986dcbd2a7 100644
--- a/src/backend/utils/adt/pg_locale.c
+++ b/src/backend/utils/adt/pg_locale.c
@@ -1246,8 +1246,15 @@ lookup_collation_cache(Oid collation, bool set_flags)
 		}
 		else
 		{
-			cache_entry->collate_is_c = false;
-			cache_entry->ctype_is_c = false;
+			Datum		datum;
+			const char *colliculocale;
+
+			datum = SysCacheGetAttrNotNull(COLLOID, tp, Anum_pg_collation_colliculocale);
+			colliculocale = TextDatumGetCString(datum);
+
+			cache_entry->collate_is_c = ((strcmp(colliculocale, "C") == 0) ||
+										 (strcmp(colliculocale, "POSIX") == 0));
+			cache_entry->ctype_is_c = cache_entry->collate_is_c;
 		}
 
 		cache_entry->flags_valid = true;
@@ -1279,16 +1286,27 @@ lc_collate_is_c(Oid collation)
 	if (collation == DEFAULT_COLLATION_OID)
 	{
 		static int	result = -1;
-		char	   *localeptr;
-
-		if (default_locale.provider == COLLPROVIDER_ICU)
-			return false;
+		const char *localeptr;
 
 		if (result >= 0)
 			return (bool) result;
-		localeptr = setlocale(LC_COLLATE, NULL);
-		if (!localeptr)
-			elog(ERROR, "invalid LC_COLLATE setting");
+
+		if (default_locale.provider == COLLPROVIDER_ICU)
+		{
+#ifdef USE_ICU
+			localeptr = default_locale.info.icu.locale;
+#else
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("ICU is not supported in this build")));
+#endif
+		}
+		else
+		{
+			localeptr = setlocale(LC_COLLATE, NULL);
+			if (!localeptr)
+				elog(ERROR, "invalid LC_COLLATE setting");
+		}
 
 		if (strcmp(localeptr, "C") == 0)
 			result = true;
@@ -1332,16 +1350,27 @@ lc_ctype_is_c(Oid collation)
 	if (collation == DEFAULT_COLLATION_OID)
 	{
 		static int	result = -1;
-		char	   *localeptr;
-
-		if (default_locale.provider == COLLPROVIDER_ICU)
-			return false;
+		const char *localeptr;
 
 		if (result >= 0)
 			return (bool) result;
-		localeptr = setlocale(LC_CTYPE, NULL);
-		if (!localeptr)
-			elog(ERROR, "invalid LC_CTYPE setting");
+
+		if (default_locale.provider == COLLPROVIDER_ICU)
+		{
+#ifdef USE_ICU
+			localeptr = default_locale.info.icu.locale;
+#else
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("ICU is not supported in this build")));
+#endif
+		}
+		else
+		{
+			localeptr = setlocale(LC_CTYPE, NULL);
+			if (!localeptr)
+				elog(ERROR, "invalid LC_CTYPE setting");
+		}
 
 		if (strcmp(localeptr, "C") == 0)
 			result = true;
@@ -1375,7 +1404,13 @@ make_icu_collator(const char *iculocstr,
 #ifdef USE_ICU
 	UCollator  *collator;
 
-	collator = pg_ucol_open(iculocstr);
+	if (strcmp(iculocstr, "C") == 0 || strcmp(iculocstr, "POSIX") == 0)
+	{
+		Assert(icurules == NULL);
+		collator = NULL;
+	}
+	else
+		collator = pg_ucol_open(iculocstr);
 
 	/*
 	 * If rules are specified, we extract the rules of the standard collation,
@@ -1650,6 +1685,9 @@ get_collation_actual_version(char collprovider, const char *collcollate)
 {
 	char	   *collversion = NULL;
 
+	if (strcmp("C", collcollate) == 0 || strcmp("POSIX", collcollate) == 0)
+		return NULL;
+
 #ifdef USE_ICU
 	if (collprovider == COLLPROVIDER_ICU)
 	{
@@ -1668,9 +1706,7 @@ get_collation_actual_version(char collprovider, const char *collcollate)
 	else
 #endif
 		if (collprovider == COLLPROVIDER_LIBC &&
-			pg_strcasecmp("C", collcollate) != 0 &&
-			pg_strncasecmp("C.", collcollate, 2) != 0 &&
-			pg_strcasecmp("POSIX", collcollate) != 0)
+			pg_strncasecmp("C.", collcollate, 2) != 0)
 	{
 #if defined(__GLIBC__)
 		/* Use the glibc version because we don't have anything better. */
@@ -2457,6 +2493,13 @@ pg_ucol_open(const char *loc_str)
 	if (loc_str == NULL)
 		elog(ERROR, "opening default collator is not supported");
 
+	/*
+	 * Must never open special values C or POSIX, which are treated specially
+	 * and not passed to the provider.
+	 */
+	if (strcmp(loc_str, "C") == 0 || strcmp(loc_str, "POSIX") == 0)
+		elog(ERROR, "unexpected ICU locale string: %s", loc_str);
+
 	/*
 	 * In ICU versions 54 and earlier, "und" is not a recognized spelling of
 	 * the root locale. If the first component of the locale is "und", replace
diff --git a/src/test/regress/expected/collate.icu.utf8.out b/src/test/regress/expected/collate.icu.utf8.out
index c658ee1404..bfc28ecfcf 100644
--- a/src/test/regress/expected/collate.icu.utf8.out
+++ b/src/test/regress/expected/collate.icu.utf8.out
@@ -1043,12 +1043,18 @@ ERROR:  ICU locale "nonsense-nowhere" has unknown language "nonsense"
 HINT:  To disable ICU locale validation, set parameter icu_validation_level to DISABLED.
 CREATE COLLATION testx (provider = icu, locale = '@colStrength=primary;nonsense=yes'); -- fails
 ERROR:  could not convert locale name "@colStrength=primary;nonsense=yes" to language tag: U_ILLEGAL_ARGUMENT_ERROR
+CREATE COLLATION testx (provider = icu, locale = 'C', deterministic = false); -- fails
+ERROR:  nondeterministic collations not supported for C or POSIX locale
+CREATE COLLATION testx (provider = icu, locale = 'C', rules = '&V << w <<< W'); -- fails
+ERROR:  RULES not supported for C or POSIX locale
 RESET icu_validation_level;
 CREATE COLLATION testx (provider = icu, locale = '@colStrength=primary;nonsense=yes'); DROP COLLATION testx;
 WARNING:  could not convert locale name "@colStrength=primary;nonsense=yes" to language tag: U_ILLEGAL_ARGUMENT_ERROR
 CREATE COLLATION testx (provider = icu, locale = 'nonsense-nowhere'); DROP COLLATION testx;
 WARNING:  ICU locale "nonsense-nowhere" has unknown language "nonsense"
 HINT:  To disable ICU locale validation, set parameter icu_validation_level to DISABLED.
+CREATE COLLATION testx (provider = icu, locale = 'C'); DROP COLLATION testx;
+CREATE COLLATION testx (provider = icu, locale = 'POSIX'); DROP COLLATION testx;
 CREATE COLLATION test4 FROM nonsense;
 ERROR:  collation "nonsense" for encoding "UTF8" does not exist
 CREATE COLLATION test5 FROM test0;
diff --git a/src/test/regress/sql/collate.icu.utf8.sql b/src/test/regress/sql/collate.icu.utf8.sql
index 7bd0901281..572dc5a50a 100644
--- a/src/test/regress/sql/collate.icu.utf8.sql
+++ b/src/test/regress/sql/collate.icu.utf8.sql
@@ -379,9 +379,13 @@ CREATE COLLATION test3 (provider = icu, lc_collate = 'en_US.utf8'); -- fail, nee
 SET icu_validation_level = ERROR;
 CREATE COLLATION testx (provider = icu, locale = 'nonsense-nowhere'); -- fails
 CREATE COLLATION testx (provider = icu, locale = '@colStrength=primary;nonsense=yes'); -- fails
+CREATE COLLATION testx (provider = icu, locale = 'C', deterministic = false); -- fails
+CREATE COLLATION testx (provider = icu, locale = 'C', rules = '&V << w <<< W'); -- fails
 RESET icu_validation_level;
 CREATE COLLATION testx (provider = icu, locale = '@colStrength=primary;nonsense=yes'); DROP COLLATION testx;
 CREATE COLLATION testx (provider = icu, locale = 'nonsense-nowhere'); DROP COLLATION testx;
+CREATE COLLATION testx (provider = icu, locale = 'C'); DROP COLLATION testx;
+CREATE COLLATION testx (provider = icu, locale = 'POSIX'); DROP COLLATION testx;
 
 CREATE COLLATION test4 FROM nonsense;
 CREATE COLLATION test5 FROM test0;
-- 
2.34.1