Add option to use ICU as global locale provider

This adds the option to use ICU as the default locale provider for
either the whole cluster or a database.  New options for initdb,
createdb, and CREATE DATABASE are used to select this.

Since some (legacy) code still uses the libc locale facilities
directly, we still need to set the libc global locale settings even if
ICU is otherwise selected.  So pg_database now has three
locale-related fields: the existing datcollate and datctype, which are
always set, and a new daticulocale, which is only set if ICU is
selected.  A similar change is made in pg_collation for consistency,
but in that case, only the libc-related fields or the ICU-related
field is set, never both.

Reviewed-by: Julien Rouhaud <rjuju123@gmail.com>
Discussion: https://www.postgresql.org/message-id/flat/5e756dd6-0e91-d778-96fd-b1bcb06c161a%402ndquadrant.com

2 files changed, 109 insertions, 56 deletions

diff --git a/src/backend/utils/adt/pg_locale.c b/src/backend/utils/adt/pg_locale.c
index 871a710967c..4019255f8ea 100644
--- a/src/backend/utils/adt/pg_locale.c
+++ b/src/backend/utils/adt/pg_locale.c
@@ -1288,26 +1288,37 @@ lookup_collation_cache(Oid collation, bool set_flags)
 	{
 		/* Attempt to set the flags */
 		HeapTuple	tp;
-		Datum		datum;
-		bool		isnull;
-		const char *collcollate;
-		const char *collctype;
+		Form_pg_collation collform;
 
 		tp = SearchSysCache1(COLLOID, ObjectIdGetDatum(collation));
 		if (!HeapTupleIsValid(tp))
 			elog(ERROR, "cache lookup failed for collation %u", collation);
+		collform = (Form_pg_collation) GETSTRUCT(tp);
 
-		datum = SysCacheGetAttr(COLLOID, tp, Anum_pg_collation_collcollate, &isnull);
-		Assert(!isnull);
-		collcollate = TextDatumGetCString(datum);
-		datum = SysCacheGetAttr(COLLOID, tp, Anum_pg_collation_collctype, &isnull);
-		Assert(!isnull);
-		collctype = TextDatumGetCString(datum);
-
-		cache_entry->collate_is_c = ((strcmp(collcollate, "C") == 0) ||
-									 (strcmp(collcollate, "POSIX") == 0));
-		cache_entry->ctype_is_c = ((strcmp(collctype, "C") == 0) ||
-								   (strcmp(collctype, "POSIX") == 0));
+		if (collform->collprovider == COLLPROVIDER_LIBC)
+		{
+			Datum		datum;
+			bool		isnull;
+			const char *collcollate;
+			const char *collctype;
+
+			datum = SysCacheGetAttr(COLLOID, tp, Anum_pg_collation_collcollate, &isnull);
+			Assert(!isnull);
+			collcollate = TextDatumGetCString(datum);
+			datum = SysCacheGetAttr(COLLOID, tp, Anum_pg_collation_collctype, &isnull);
+			Assert(!isnull);
+			collctype = TextDatumGetCString(datum);
+
+			cache_entry->collate_is_c = ((strcmp(collcollate, "C") == 0) ||
+										 (strcmp(collcollate, "POSIX") == 0));
+			cache_entry->ctype_is_c = ((strcmp(collctype, "C") == 0) ||
+									   (strcmp(collctype, "POSIX") == 0));
+		}
+		else
+		{
+			cache_entry->collate_is_c = false;
+			cache_entry->ctype_is_c = false;
+		}
 
 		cache_entry->flags_valid = true;
 
@@ -1340,6 +1351,9 @@ lc_collate_is_c(Oid collation)
 		static int	result = -1;
 		char	   *localeptr;
 
+		if (default_locale.provider == COLLPROVIDER_ICU)
+			return false;
+
 		if (result >= 0)
 			return (bool) result;
 		localeptr = setlocale(LC_COLLATE, NULL);
@@ -1390,6 +1404,9 @@ lc_ctype_is_c(Oid collation)
 		static int	result = -1;
 		char	   *localeptr;
 
+		if (default_locale.provider == COLLPROVIDER_ICU)
+			return false;
+
 		if (result >= 0)
 			return (bool) result;
 		localeptr = setlocale(LC_CTYPE, NULL);
@@ -1418,6 +1435,38 @@ lc_ctype_is_c(Oid collation)
 	return (lookup_collation_cache(collation, true))->ctype_is_c;
 }
 
+struct pg_locale_struct default_locale;
+
+void
+make_icu_collator(const char *iculocstr,
+				  struct pg_locale_struct *resultp)
+{
+#ifdef USE_ICU
+	UCollator  *collator;
+	UErrorCode	status;
+
+	status = U_ZERO_ERROR;
+	collator = ucol_open(iculocstr, &status);
+	if (U_FAILURE(status))
+		ereport(ERROR,
+				(errmsg("could not open collator for locale \"%s\": %s",
+						iculocstr, u_errorName(status))));
+
+	if (U_ICU_VERSION_MAJOR_NUM < 54)
+		icu_set_collation_attributes(collator, iculocstr);
+
+	/* We will leak this string if the caller errors later :-( */
+	resultp->info.icu.locale = MemoryContextStrdup(TopMemoryContext, iculocstr);
+	resultp->info.icu.ucol = collator;
+#else							/* not USE_ICU */
+	/* could get here if a collation was created by a build with ICU */
+	ereport(ERROR,
+			(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+			 errmsg("ICU is not supported in this build"), \
+			 errhint("You need to rebuild PostgreSQL using %s.", "--with-icu")));
+#endif							/* not USE_ICU */
+}
+
 
 /* simple subroutine for reporting errors from newlocale() */
 #ifdef HAVE_LOCALE_T
@@ -1475,7 +1524,12 @@ pg_newlocale_from_collation(Oid collid)
 	Assert(OidIsValid(collid));
 
 	if (collid == DEFAULT_COLLATION_OID)
-		return (pg_locale_t) 0;
+	{
+		if (default_locale.provider == COLLPROVIDER_ICU)
+			return &default_locale;
+		else
+			return (pg_locale_t) 0;
+	}
 
 	cache_entry = lookup_collation_cache(collid, false);
 
@@ -1484,8 +1538,6 @@ pg_newlocale_from_collation(Oid collid)
 		/* We haven't computed this yet in this session, so do it */
 		HeapTuple	tp;
 		Form_pg_collation collform;
-		const char *collcollate;
-		const char *collctype pg_attribute_unused();
 		struct pg_locale_struct result;
 		pg_locale_t resultp;
 		Datum		datum;
@@ -1496,13 +1548,6 @@ pg_newlocale_from_collation(Oid collid)
 			elog(ERROR, "cache lookup failed for collation %u", collid);
 		collform = (Form_pg_collation) GETSTRUCT(tp);
 
-		datum = SysCacheGetAttr(COLLOID, tp, Anum_pg_collation_collcollate, &isnull);
-		Assert(!isnull);
-		collcollate = TextDatumGetCString(datum);
-		datum = SysCacheGetAttr(COLLOID, tp, Anum_pg_collation_collctype, &isnull);
-		Assert(!isnull);
-		collctype = TextDatumGetCString(datum);
-
 		/* We'll fill in the result struct locally before allocating memory */
 		memset(&result, 0, sizeof(result));
 		result.provider = collform->collprovider;
@@ -1511,8 +1556,17 @@ pg_newlocale_from_collation(Oid collid)
 		if (collform->collprovider == COLLPROVIDER_LIBC)
 		{
 #ifdef HAVE_LOCALE_T
+			const char *collcollate;
+			const char *collctype pg_attribute_unused();
 			locale_t	loc;
 
+			datum = SysCacheGetAttr(COLLOID, tp, Anum_pg_collation_collcollate, &isnull);
+			Assert(!isnull);
+			collcollate = TextDatumGetCString(datum);
+			datum = SysCacheGetAttr(COLLOID, tp, Anum_pg_collation_collctype, &isnull);
+			Assert(!isnull);
+			collctype = TextDatumGetCString(datum);
+
 			if (strcmp(collcollate, collctype) == 0)
 			{
 				/* Normal case where they're the same */
@@ -1563,36 +1617,12 @@ pg_newlocale_from_collation(Oid collid)
 		}
 		else if (collform->collprovider == COLLPROVIDER_ICU)
 		{
-#ifdef USE_ICU
-			UCollator  *collator;
-			UErrorCode	status;
-
-			if (strcmp(collcollate, collctype) != 0)
-				ereport(ERROR,
-						(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
-						 errmsg("collations with different collate and ctype values are not supported by ICU")));
-
-			status = U_ZERO_ERROR;
-			collator = ucol_open(collcollate, &status);
-			if (U_FAILURE(status))
-				ereport(ERROR,
-						(errmsg("could not open collator for locale \"%s\": %s",
-								collcollate, u_errorName(status))));
+			const char *iculocstr;
 
-			if (U_ICU_VERSION_MAJOR_NUM < 54)
-				icu_set_collation_attributes(collator, collcollate);
-
-			/* We will leak this string if we get an error below :-( */
-			result.info.icu.locale = MemoryContextStrdup(TopMemoryContext,
-														 collcollate);
-			result.info.icu.ucol = collator;
-#else							/* not USE_ICU */
-			/* could get here if a collation was created by a build with ICU */
-			ereport(ERROR,
-					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
-					 errmsg("ICU is not supported in this build"), \
-					 errhint("You need to rebuild PostgreSQL using %s.", "--with-icu")));
-#endif							/* not USE_ICU */
+			datum = SysCacheGetAttr(COLLOID, tp, Anum_pg_collation_colliculocale, &isnull);
+			Assert(!isnull);
+			iculocstr = TextDatumGetCString(datum);
+			make_icu_collator(iculocstr, &result);
 		}
 
 		datum = SysCacheGetAttr(COLLOID, tp, Anum_pg_collation_collversion,
@@ -1604,7 +1634,11 @@ pg_newlocale_from_collation(Oid collid)
 
 			collversionstr = TextDatumGetCString(datum);
 
-			actual_versionstr = get_collation_actual_version(collform->collprovider, collcollate);
+			datum = SysCacheGetAttr(COLLOID, tp, collform->collprovider == COLLPROVIDER_ICU ? Anum_pg_collation_colliculocale : Anum_pg_collation_collcollate, &isnull);
+			Assert(!isnull);
+
+			actual_versionstr = get_collation_actual_version(collform->collprovider,
+															 TextDatumGetCString(datum));
 			if (!actual_versionstr)
 			{
 				/*
diff --git a/src/backend/utils/init/postinit.c b/src/backend/utils/init/postinit.c
index 86d193c89fc..6452b42dbff 100644
--- a/src/backend/utils/init/postinit.c
+++ b/src/backend/utils/init/postinit.c
@@ -318,6 +318,7 @@ CheckMyDatabase(const char *name, bool am_superuser, bool override_allow_connect
 	bool		isnull;
 	char	   *collate;
 	char	   *ctype;
+	char	   *iculocale;
 
 	/* Fetch our pg_database row normally, via syscache */
 	tup = SearchSysCache1(DATABASEOID, ObjectIdGetDatum(MyDatabaseId));
@@ -420,6 +421,24 @@ CheckMyDatabase(const char *name, bool am_superuser, bool override_allow_connect
 						   " which is not recognized by setlocale().", ctype),
 				 errhint("Recreate the database with another locale or install the missing locale.")));
 
+	if (dbform->datlocprovider == COLLPROVIDER_ICU)
+	{
+		datum = SysCacheGetAttr(DATABASEOID, tup, Anum_pg_database_daticulocale, &isnull);
+		Assert(!isnull);
+		iculocale = TextDatumGetCString(datum);
+		make_icu_collator(iculocale, &default_locale);
+	}
+	else
+		iculocale = NULL;
+
+	default_locale.provider = dbform->datlocprovider;
+	/*
+	 * Default locale is currently always deterministic.  Nondeterministic
+	 * locales currently don't support pattern matching, which would break a
+	 * lot of things if applied globally.
+	 */
+	default_locale.deterministic = true;
+
 	/*
 	 * Check collation version.  See similar code in
 	 * pg_newlocale_from_collation().  Note that here we warn instead of error
@@ -434,7 +453,7 @@ CheckMyDatabase(const char *name, bool am_superuser, bool override_allow_connect
 
 		collversionstr = TextDatumGetCString(datum);
 
-		actual_versionstr = get_collation_actual_version(COLLPROVIDER_LIBC, collate);
+		actual_versionstr = get_collation_actual_version(dbform->datlocprovider, dbform->datlocprovider == COLLPROVIDER_ICU ? iculocale : collate);
 		if (!actual_versionstr)
 			ereport(WARNING,
 					(errmsg("database \"%s\" has no actual collation version, but a version was recorded",