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

1 files changed, 58 insertions, 16 deletions

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);
 	}