Introduce "builtin" collation provider.

New provider for collations, like "libc" or "icu", but without any
external dependency.

Initially, the only locale supported by the builtin provider is "C",
which is identical to the libc provider's "C" locale. The libc
provider's "C" locale has always been treated as a special case that
uses an internal implementation, without using libc at all -- so the
new builtin provider uses the same implementation.

The builtin provider's locale is independent of the server environment
variables LC_COLLATE and LC_CTYPE. Using the builtin provider, the
database collation locale can be "C" while LC_COLLATE and LC_CTYPE are
set to "en_US", which is impossible with the libc provider.

By offering a new builtin provider, it clarifies that the semantics of
a collation using this provider will never depend on libc, and makes
it easier to document the behavior.

Discussion: https://postgr.es/m/ab925f69-5f9d-f85e-b87c-bd2a44798659@joeconway.com
Discussion: https://postgr.es/m/dd9261f4-7a98-4565-93ec-336c1c110d90@manitou-mail.org
Discussion: https://postgr.es/m/ff4c2f2f9c8fc7ca27c1c24ae37ecaeaeaff6b53.camel%40j-davis.com
Reviewed-by: Daniel Vérité, Peter Eisentraut, Jeremy Schneider

6 files changed, 286 insertions, 71 deletions

diff --git a/src/backend/catalog/pg_collation.c b/src/backend/catalog/pg_collation.c
index e42f2afccbc..7f2f7012299 100644
--- a/src/backend/catalog/pg_collation.c
+++ b/src/backend/catalog/pg_collation.c
@@ -64,7 +64,10 @@ CollationCreate(const char *collname, Oid collnamespace,
 	Assert(collname);
 	Assert(collnamespace);
 	Assert(collowner);
-	Assert((collcollate && collctype) || colllocale);
+	Assert((collprovider == COLLPROVIDER_LIBC &&
+			collcollate && collctype && !colllocale) ||
+		   (collprovider != COLLPROVIDER_LIBC &&
+			!collcollate && !collctype && colllocale));
 
 	/*
 	 * Make sure there is no existing collation of same name & encoding.
diff --git a/src/backend/commands/collationcmds.c b/src/backend/commands/collationcmds.c
index 59d7e17804b..9059f8b3efd 100644
--- a/src/backend/commands/collationcmds.c
+++ b/src/backend/commands/collationcmds.c
@@ -66,7 +66,7 @@ DefineCollation(ParseState *pstate, List *names, List *parameters, bool if_not_e
 	DefElem    *versionEl = NULL;
 	char	   *collcollate;
 	char	   *collctype;
-	char	   *colllocale;
+	const char *colllocale;
 	char	   *collicurules;
 	bool		collisdeterministic;
 	int			collencoding;
@@ -213,7 +213,9 @@ DefineCollation(ParseState *pstate, List *names, List *parameters, bool if_not_e
 
 		if (collproviderstr)
 		{
-			if (pg_strcasecmp(collproviderstr, "icu") == 0)
+			if (pg_strcasecmp(collproviderstr, "builtin") == 0)
+				collprovider = COLLPROVIDER_BUILTIN;
+			else if (pg_strcasecmp(collproviderstr, "icu") == 0)
 				collprovider = COLLPROVIDER_ICU;
 			else if (pg_strcasecmp(collproviderstr, "libc") == 0)
 				collprovider = COLLPROVIDER_LIBC;
@@ -243,7 +245,18 @@ DefineCollation(ParseState *pstate, List *names, List *parameters, bool if_not_e
 		if (lcctypeEl)
 			collctype = defGetString(lcctypeEl);
 
-		if (collprovider == COLLPROVIDER_LIBC)
+		if (collprovider == COLLPROVIDER_BUILTIN)
+		{
+			if (!colllocale)
+				ereport(ERROR,
+						(errcode(ERRCODE_INVALID_OBJECT_DEFINITION),
+						 errmsg("parameter \"%s\" must be specified",
+								"locale")));
+
+			colllocale = builtin_validate_locale(GetDatabaseEncoding(),
+												 colllocale);
+		}
+		else if (collprovider == COLLPROVIDER_LIBC)
 		{
 			if (!collcollate)
 				ereport(ERROR,
@@ -303,7 +316,11 @@ DefineCollation(ParseState *pstate, List *names, List *parameters, bool if_not_e
 					(errcode(ERRCODE_INVALID_OBJECT_DEFINITION),
 					 errmsg("ICU rules cannot be specified unless locale provider is ICU")));
 
-		if (collprovider == COLLPROVIDER_ICU)
+		if (collprovider == COLLPROVIDER_BUILTIN)
+		{
+			collencoding = GetDatabaseEncoding();
+		}
+		else if (collprovider == COLLPROVIDER_ICU)
 		{
 #ifdef USE_ICU
 			/*
@@ -332,7 +349,16 @@ DefineCollation(ParseState *pstate, List *names, List *parameters, bool if_not_e
 	}
 
 	if (!collversion)
-		collversion = get_collation_actual_version(collprovider, collprovider == COLLPROVIDER_ICU ? colllocale : collcollate);
+	{
+		const char *locale;
+
+		if (collprovider == COLLPROVIDER_LIBC)
+			locale = collcollate;
+		else
+			locale = colllocale;
+
+		collversion = get_collation_actual_version(collprovider, locale);
+	}
 
 	newoid = CollationCreate(collName,
 							 collNamespace,
@@ -433,8 +459,13 @@ AlterCollation(AlterCollationStmt *stmt)
 	datum = SysCacheGetAttr(COLLOID, tup, Anum_pg_collation_collversion, &isnull);
 	oldversion = isnull ? NULL : TextDatumGetCString(datum);
 
-	datum = SysCacheGetAttrNotNull(COLLOID, tup, collForm->collprovider == COLLPROVIDER_ICU ? Anum_pg_collation_colllocale : Anum_pg_collation_collcollate);
-	newversion = get_collation_actual_version(collForm->collprovider, TextDatumGetCString(datum));
+	if (collForm->collprovider == COLLPROVIDER_LIBC)
+		datum = SysCacheGetAttrNotNull(COLLOID, tup, Anum_pg_collation_collcollate);
+	else
+		datum = SysCacheGetAttrNotNull(COLLOID, tup, Anum_pg_collation_colllocale);
+
+	newversion = get_collation_actual_version(collForm->collprovider,
+											  TextDatumGetCString(datum));
 
 	/* cannot change from NULL to non-NULL or vice versa */
 	if ((!oldversion && newversion) || (oldversion && !newversion))
@@ -498,11 +529,16 @@ pg_collation_actual_version(PG_FUNCTION_ARGS)
 
 		provider = ((Form_pg_database) GETSTRUCT(dbtup))->datlocprovider;
 
-		datum = SysCacheGetAttrNotNull(DATABASEOID, dbtup,
-									   provider == COLLPROVIDER_ICU ?
-									   Anum_pg_database_datlocale : Anum_pg_database_datcollate);
-
-		locale = TextDatumGetCString(datum);
+		if (provider == COLLPROVIDER_LIBC)
+		{
+			datum = SysCacheGetAttrNotNull(DATABASEOID, dbtup, Anum_pg_database_datcollate);
+			locale = TextDatumGetCString(datum);
+		}
+		else
+		{
+			datum = SysCacheGetAttrNotNull(DATABASEOID, dbtup, Anum_pg_database_datlocale);
+			locale = TextDatumGetCString(datum);
+		}
 
 		ReleaseSysCache(dbtup);
 	}
@@ -519,11 +555,17 @@ pg_collation_actual_version(PG_FUNCTION_ARGS)
 
 		provider = ((Form_pg_collation) GETSTRUCT(colltp))->collprovider;
 		Assert(provider != COLLPROVIDER_DEFAULT);
-		datum = SysCacheGetAttrNotNull(COLLOID, colltp,
-									   provider == COLLPROVIDER_ICU ?
-									   Anum_pg_collation_colllocale : Anum_pg_collation_collcollate);
 
-		locale = TextDatumGetCString(datum);
+		if (provider == COLLPROVIDER_LIBC)
+		{
+			datum = SysCacheGetAttrNotNull(COLLOID, colltp, Anum_pg_collation_collcollate);
+			locale = TextDatumGetCString(datum);
+		}
+		else
+		{
+			datum = SysCacheGetAttrNotNull(COLLOID, colltp, Anum_pg_collation_colllocale);
+			locale = TextDatumGetCString(datum);
+		}
 
 		ReleaseSysCache(colltp);
 	}
diff --git a/src/backend/commands/dbcommands.c b/src/backend/commands/dbcommands.c
index 0f27d7b14cf..65464fac8e5 100644
--- a/src/backend/commands/dbcommands.c
+++ b/src/backend/commands/dbcommands.c
@@ -697,6 +697,7 @@ createdb(ParseState *pstate, const CreatedbStmt *stmt)
 	DefElem    *dtemplate = NULL;
 	DefElem    *dencoding = NULL;
 	DefElem    *dlocale = NULL;
+	DefElem    *dbuiltinlocale = NULL;
 	DefElem    *dcollate = NULL;
 	DefElem    *dctype = NULL;
 	DefElem    *diculocale = NULL;
@@ -712,7 +713,7 @@ createdb(ParseState *pstate, const CreatedbStmt *stmt)
 	const char *dbtemplate = NULL;
 	char	   *dbcollate = NULL;
 	char	   *dbctype = NULL;
-	char	   *dblocale = NULL;
+	const char *dblocale = NULL;
 	char	   *dbicurules = NULL;
 	char		dblocprovider = '\0';
 	char	   *canonname;
@@ -761,6 +762,12 @@ createdb(ParseState *pstate, const CreatedbStmt *stmt)
 				errorConflictingDefElem(defel, pstate);
 			dlocale = defel;
 		}
+		else if (strcmp(defel->defname, "builtin_locale") == 0)
+		{
+			if (dbuiltinlocale)
+				errorConflictingDefElem(defel, pstate);
+			dbuiltinlocale = defel;
+		}
 		else if (strcmp(defel->defname, "lc_collate") == 0)
 		{
 			if (dcollate)
@@ -896,7 +903,10 @@ createdb(ParseState *pstate, const CreatedbStmt *stmt)
 	{
 		dbcollate = defGetString(dlocale);
 		dbctype = defGetString(dlocale);
+		dblocale = defGetString(dlocale);
 	}
+	if (dbuiltinlocale && dbuiltinlocale->arg)
+		dblocale = defGetString(dbuiltinlocale);
 	if (dcollate && dcollate->arg)
 		dbcollate = defGetString(dcollate);
 	if (dctype && dctype->arg)
@@ -909,7 +919,9 @@ createdb(ParseState *pstate, const CreatedbStmt *stmt)
 	{
 		char	   *locproviderstr = defGetString(dlocprovider);
 
-		if (pg_strcasecmp(locproviderstr, "icu") == 0)
+		if (pg_strcasecmp(locproviderstr, "builtin") == 0)
+			dblocprovider = COLLPROVIDER_BUILTIN;
+		else if (pg_strcasecmp(locproviderstr, "icu") == 0)
 			dblocprovider = COLLPROVIDER_ICU;
 		else if (pg_strcasecmp(locproviderstr, "libc") == 0)
 			dblocprovider = COLLPROVIDER_LIBC;
@@ -1026,14 +1038,9 @@ createdb(ParseState *pstate, const CreatedbStmt *stmt)
 		dbctype = src_ctype;
 	if (dblocprovider == '\0')
 		dblocprovider = src_locprovider;
-	if (dblocale == NULL && dblocprovider == COLLPROVIDER_ICU)
-	{
-		if (dlocale && dlocale->arg)
-			dblocale = defGetString(dlocale);
-		else
-			dblocale = src_locale;
-	}
-	if (dbicurules == NULL && dblocprovider == COLLPROVIDER_ICU)
+	if (dblocale == NULL)
+		dblocale = src_locale;
+	if (dbicurules == NULL)
 		dbicurules = src_icurules;
 
 	/* Some encodings are client only */
@@ -1058,7 +1065,42 @@ createdb(ParseState *pstate, const CreatedbStmt *stmt)
 
 	check_encoding_locale_matches(encoding, dbcollate, dbctype);
 
-	if (dblocprovider == COLLPROVIDER_ICU)
+	/* validate provider-specific parameters */
+	if (dblocprovider != COLLPROVIDER_BUILTIN)
+	{
+		if (dbuiltinlocale)
+			ereport(ERROR,
+					(errcode(ERRCODE_INVALID_OBJECT_DEFINITION),
+					 errmsg("BUILTIN_LOCALE cannot be specified unless locale provider is builtin")));
+	}
+	else if (dblocprovider != COLLPROVIDER_ICU)
+	{
+		if (diculocale)
+			ereport(ERROR,
+					(errcode(ERRCODE_INVALID_OBJECT_DEFINITION),
+					 errmsg("ICU locale cannot be specified unless locale provider is ICU")));
+
+		if (dbicurules)
+			ereport(ERROR,
+					(errcode(ERRCODE_INVALID_OBJECT_DEFINITION),
+					 errmsg("ICU rules cannot be specified unless locale provider is ICU")));
+	}
+
+	/* validate and canonicalize locale for the provider */
+	if (dblocprovider == COLLPROVIDER_BUILTIN)
+	{
+		/*
+		 * This would happen if template0 uses the libc provider but the new
+		 * database uses builtin.
+		 */
+		if (!dblocale)
+			ereport(ERROR,
+					(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+					 errmsg("LOCALE or BUILTIN_LOCALE must be specified")));
+
+		dblocale = builtin_validate_locale(encoding, dblocale);
+	}
+	else if (dblocprovider == COLLPROVIDER_ICU)
 	{
 		if (!(is_encoding_supported_by_icu(encoding)))
 			ereport(ERROR,
@@ -1097,18 +1139,10 @@ createdb(ParseState *pstate, const CreatedbStmt *stmt)
 
 		icu_validate_locale(dblocale);
 	}
-	else
-	{
-		if (dblocale)
-			ereport(ERROR,
-					(errcode(ERRCODE_INVALID_OBJECT_DEFINITION),
-					 errmsg("ICU locale cannot be specified unless locale provider is ICU")));
 
-		if (dbicurules)
-			ereport(ERROR,
-					(errcode(ERRCODE_INVALID_OBJECT_DEFINITION),
-					 errmsg("ICU rules cannot be specified unless locale provider is ICU")));
-	}
+	/* for libc, locale comes from datcollate and datctype */
+	if (dblocprovider == COLLPROVIDER_LIBC)
+		dblocale = NULL;
 
 	/*
 	 * Check that the new encoding and locale settings match the source
@@ -1195,8 +1229,14 @@ createdb(ParseState *pstate, const CreatedbStmt *stmt)
 	if (src_collversion && !dcollversion)
 	{
 		char	   *actual_versionstr;
+		const char *locale;
+
+		if (dblocprovider == COLLPROVIDER_LIBC)
+			locale = dbcollate;
+		else
+			locale = dblocale;
 
-		actual_versionstr = get_collation_actual_version(dblocprovider, dblocprovider == COLLPROVIDER_ICU ? dblocale : dbcollate);
+		actual_versionstr = get_collation_actual_version(dblocprovider, locale);
 		if (!actual_versionstr)
 			ereport(ERROR,
 					(errmsg("template database \"%s\" has a collation version, but no actual collation version could be determined",
@@ -1224,7 +1264,16 @@ createdb(ParseState *pstate, const CreatedbStmt *stmt)
 	 * collation version, which is normally only the case for template0.
 	 */
 	if (dbcollversion == NULL)
-		dbcollversion = get_collation_actual_version(dblocprovider, dblocprovider == COLLPROVIDER_ICU ? dblocale : dbcollate);
+	{
+		const char *locale;
+
+		if (dblocprovider == COLLPROVIDER_LIBC)
+			locale = dbcollate;
+		else
+			locale = dblocale;
+
+		dbcollversion = get_collation_actual_version(dblocprovider, locale);
+	}
 
 	/* Resolve default tablespace for new database */
 	if (dtablespacename && dtablespacename->arg)
@@ -1363,8 +1412,8 @@ createdb(ParseState *pstate, const CreatedbStmt *stmt)
 	 * block on the unique index, and fail after we commit).
 	 */
 
-	Assert((dblocprovider == COLLPROVIDER_ICU && dblocale) ||
-		   (dblocprovider != COLLPROVIDER_ICU && !dblocale));
+	Assert((dblocprovider != COLLPROVIDER_LIBC && dblocale) ||
+		   (dblocprovider == COLLPROVIDER_LIBC && !dblocale));
 
 	/* Form tuple */
 	new_record[Anum_pg_database_oid - 1] = ObjectIdGetDatum(dboid);
@@ -2471,10 +2520,21 @@ AlterDatabaseRefreshColl(AlterDatabaseRefreshCollStmt *stmt)
 	datum = heap_getattr(tuple, Anum_pg_database_datcollversion, RelationGetDescr(rel), &isnull);
 	oldversion = isnull ? NULL : TextDatumGetCString(datum);
 
-	datum = heap_getattr(tuple, datForm->datlocprovider == COLLPROVIDER_ICU ? Anum_pg_database_datlocale : Anum_pg_database_datcollate, RelationGetDescr(rel), &isnull);
-	if (isnull)
-		elog(ERROR, "unexpected null in pg_database");
-	newversion = get_collation_actual_version(datForm->datlocprovider, TextDatumGetCString(datum));
+	if (datForm->datlocprovider == COLLPROVIDER_LIBC)
+	{
+		datum = heap_getattr(tuple, Anum_pg_database_datcollate, RelationGetDescr(rel), &isnull);
+		if (isnull)
+			elog(ERROR, "unexpected null in pg_database");
+	}
+	else
+	{
+		datum = heap_getattr(tuple, Anum_pg_database_datlocale, RelationGetDescr(rel), &isnull);
+		if (isnull)
+			elog(ERROR, "unexpected null in pg_database");
+	}
+
+	newversion = get_collation_actual_version(datForm->datlocprovider,
+											  TextDatumGetCString(datum));
 
 	/* cannot change from NULL to non-NULL or vice versa */
 	if ((!oldversion && newversion) || (oldversion && !newversion))
@@ -2669,8 +2729,13 @@ pg_database_collation_actual_version(PG_FUNCTION_ARGS)
 
 	datlocprovider = ((Form_pg_database) GETSTRUCT(tp))->datlocprovider;
 
-	datum = SysCacheGetAttrNotNull(DATABASEOID, tp, datlocprovider == COLLPROVIDER_ICU ? Anum_pg_database_datlocale : Anum_pg_database_datcollate);
-	version = get_collation_actual_version(datlocprovider, TextDatumGetCString(datum));
+	if (datlocprovider == COLLPROVIDER_LIBC)
+		datum = SysCacheGetAttrNotNull(DATABASEOID, tp, Anum_pg_database_datcollate);
+	else
+		datum = SysCacheGetAttrNotNull(DATABASEOID, tp, Anum_pg_database_datlocale);
+
+	version = get_collation_actual_version(datlocprovider,
+										   TextDatumGetCString(datum));
 
 	ReleaseSysCache(tp);
 
diff --git a/src/backend/utils/adt/formatting.c b/src/backend/utils/adt/formatting.c
index 036a463491c..5f483b8dbc2 100644
--- a/src/backend/utils/adt/formatting.c
+++ b/src/backend/utils/adt/formatting.c
@@ -1680,6 +1680,8 @@ str_tolower(const char *buff, size_t nbytes, Oid collid)
 		else
 #endif
 		{
+			Assert(!mylocale || mylocale->provider == COLLPROVIDER_LIBC);
+
 			if (pg_database_encoding_max_length() > 1)
 			{
 				wchar_t    *workspace;
@@ -1798,6 +1800,8 @@ str_toupper(const char *buff, size_t nbytes, Oid collid)
 		else
 #endif
 		{
+			Assert(!mylocale || mylocale->provider == COLLPROVIDER_LIBC);
+
 			if (pg_database_encoding_max_length() > 1)
 			{
 				wchar_t    *workspace;
@@ -1917,6 +1921,8 @@ str_initcap(const char *buff, size_t nbytes, Oid collid)
 		else
 #endif
 		{
+			Assert(!mylocale || mylocale->provider == COLLPROVIDER_LIBC);
+
 			if (pg_database_encoding_max_length() > 1)
 			{
 				wchar_t    *workspace;
diff --git a/src/backend/utils/adt/pg_locale.c b/src/backend/utils/adt/pg_locale.c
index 77d5752dc8e..39390fbe4eb 100644
--- a/src/backend/utils/adt/pg_locale.c
+++ b/src/backend/utils/adt/pg_locale.c
@@ -1268,7 +1268,18 @@ lookup_collation_cache(Oid collation, bool set_flags)
 			elog(ERROR, "cache lookup failed for collation %u", collation);
 		collform = (Form_pg_collation) GETSTRUCT(tp);
 
-		if (collform->collprovider == COLLPROVIDER_LIBC)
+		if (collform->collprovider == COLLPROVIDER_BUILTIN)
+		{
+			Datum		datum;
+			const char *colllocale;
+
+			datum = SysCacheGetAttrNotNull(COLLOID, tp, Anum_pg_collation_colllocale);
+			colllocale = TextDatumGetCString(datum);
+
+			cache_entry->collate_is_c = true;
+			cache_entry->ctype_is_c = (strcmp(colllocale, "C") == 0);
+		}
+		else if (collform->collprovider == COLLPROVIDER_LIBC)
 		{
 			Datum		datum;
 			const char *collcollate;
@@ -1319,16 +1330,30 @@ 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_BUILTIN)
+		{
+			result = true;
+			return (bool) result;
+		}
+		else if (default_locale.provider == COLLPROVIDER_ICU)
+		{
+			result = false;
+			return (bool) result;
+		}
+		else if (default_locale.provider == COLLPROVIDER_LIBC)
+		{
+			localeptr = setlocale(LC_CTYPE, NULL);
+			if (!localeptr)
+				elog(ERROR, "invalid LC_CTYPE setting");
+		}
+		else
+			elog(ERROR, "unexpected collation provider '%c'",
+				 default_locale.provider);
 
 		if (strcmp(localeptr, "C") == 0)
 			result = true;
@@ -1372,16 +1397,29 @@ 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_BUILTIN)
+		{
+			localeptr = default_locale.info.builtin.locale;
+		}
+		else if (default_locale.provider == COLLPROVIDER_ICU)
+		{
+			result = false;
+			return (bool) result;
+		}
+		else if (default_locale.provider == COLLPROVIDER_LIBC)
+		{
+			localeptr = setlocale(LC_CTYPE, NULL);
+			if (!localeptr)
+				elog(ERROR, "invalid LC_CTYPE setting");
+		}
+		else
+			elog(ERROR, "unexpected collation provider '%c'",
+				 default_locale.provider);
 
 		if (strcmp(localeptr, "C") == 0)
 			result = true;
@@ -1519,10 +1557,10 @@ pg_newlocale_from_collation(Oid collid)
 
 	if (collid == DEFAULT_COLLATION_OID)
 	{
-		if (default_locale.provider == COLLPROVIDER_ICU)
-			return &default_locale;
-		else
+		if (default_locale.provider == COLLPROVIDER_LIBC)
 			return (pg_locale_t) 0;
+		else
+			return &default_locale;
 	}
 
 	cache_entry = lookup_collation_cache(collid, false);
@@ -1547,7 +1585,19 @@ pg_newlocale_from_collation(Oid collid)
 		result.provider = collform->collprovider;
 		result.deterministic = collform->collisdeterministic;
 
-		if (collform->collprovider == COLLPROVIDER_LIBC)
+		if (collform->collprovider == COLLPROVIDER_BUILTIN)
+		{
+			const char *locstr;
+
+			datum = SysCacheGetAttrNotNull(COLLOID, tp, Anum_pg_collation_colllocale);
+			locstr = TextDatumGetCString(datum);
+
+			builtin_validate_locale(GetDatabaseEncoding(), locstr);
+
+			result.info.builtin.locale = MemoryContextStrdup(TopMemoryContext,
+															 locstr);
+		}
+		else if (collform->collprovider == COLLPROVIDER_LIBC)
 		{
 			const char *collcollate;
 			const char *collctype pg_attribute_unused();
@@ -1626,7 +1676,11 @@ pg_newlocale_from_collation(Oid collid)
 
 			collversionstr = TextDatumGetCString(datum);
 
-			datum = SysCacheGetAttrNotNull(COLLOID, tp, collform->collprovider == COLLPROVIDER_ICU ? Anum_pg_collation_colllocale : Anum_pg_collation_collcollate);
+			Assert(collform->collprovider != COLLPROVIDER_BUILTIN);
+			if (collform->collprovider == COLLPROVIDER_LIBC)
+				datum = SysCacheGetAttrNotNull(COLLOID, tp, Anum_pg_collation_collcollate);
+			else
+				datum = SysCacheGetAttrNotNull(COLLOID, tp, Anum_pg_collation_colllocale);
 
 			actual_versionstr = get_collation_actual_version(collform->collprovider,
 															 TextDatumGetCString(datum));
@@ -1677,6 +1731,10 @@ get_collation_actual_version(char collprovider, const char *collcollate)
 {
 	char	   *collversion = NULL;
 
+	/* the builtin collation provider is not versioned */
+	if (collprovider == COLLPROVIDER_BUILTIN)
+		return NULL;
+
 #ifdef USE_ICU
 	if (collprovider == COLLPROVIDER_ICU)
 	{
@@ -2443,6 +2501,31 @@ pg_strnxfrm_prefix(char *dest, size_t destsize, const char *src,
 	return result;
 }
 
+const char *
+builtin_validate_locale(int encoding, const char *locale)
+{
+	const char *canonical_name = NULL;
+	int			required_encoding = -1;
+
+	if (strcmp(locale, "C") == 0)
+		canonical_name = "C";
+
+	if (!canonical_name)
+		ereport(ERROR,
+				(errcode(ERRCODE_WRONG_OBJECT_TYPE),
+				 errmsg("invalid locale name \"%s\" for builtin provider",
+						locale)));
+
+	if (required_encoding >= 0 && encoding != required_encoding)
+		ereport(ERROR,
+				(errcode(ERRCODE_WRONG_OBJECT_TYPE),
+				 errmsg("encoding \"%s\" does not match locale \"%s\"",
+						pg_encoding_to_char(encoding), locale)));
+
+	return canonical_name;
+}
+
+
 #ifdef USE_ICU
 
 /*
diff --git a/src/backend/utils/init/postinit.c b/src/backend/utils/init/postinit.c
index 2875bc97d3b..0805398e24d 100644
--- a/src/backend/utils/init/postinit.c
+++ b/src/backend/utils/init/postinit.c
@@ -423,7 +423,17 @@ CheckMyDatabase(const char *name, bool am_superuser, bool override_allow_connect
 		strcmp(ctype, "POSIX") == 0)
 		database_ctype_is_c = true;
 
-	if (dbform->datlocprovider == COLLPROVIDER_ICU)
+	if (dbform->datlocprovider == COLLPROVIDER_BUILTIN)
+	{
+		datum = SysCacheGetAttrNotNull(DATABASEOID, tup, Anum_pg_database_datlocale);
+		datlocale = TextDatumGetCString(datum);
+
+		builtin_validate_locale(dbform->encoding, datlocale);
+
+		default_locale.info.builtin.locale = MemoryContextStrdup(
+																 TopMemoryContext, datlocale);
+	}
+	else if (dbform->datlocprovider == COLLPROVIDER_ICU)
 	{
 		char	   *icurules;
 
@@ -461,10 +471,16 @@ CheckMyDatabase(const char *name, bool am_superuser, bool override_allow_connect
 	{
 		char	   *actual_versionstr;
 		char	   *collversionstr;
+		char	   *locale;
 
 		collversionstr = TextDatumGetCString(datum);
 
-		actual_versionstr = get_collation_actual_version(dbform->datlocprovider, dbform->datlocprovider == COLLPROVIDER_ICU ? datlocale : collate);
+		if (dbform->datlocprovider == COLLPROVIDER_LIBC)
+			locale = collate;
+		else
+			locale = datlocale;
+
+		actual_versionstr = get_collation_actual_version(dbform->datlocprovider, locale);
 		if (!actual_versionstr)
 			/* should not happen */
 			elog(WARNING,