pg_upgrade: copy locale and encoding information to new cluster.

Previously, pg_upgrade checked that the old and new clusters were
compatible, including the locale and encoding. But the new cluster was
just created, and only template0 from the new cluster will be
preserved (template1 and postgres are both recreated during the
upgrade process).

Because template0 is not sensitive to locale or encoding, just update
the pg_database entry to be the same as template0 from the original
cluster.

This commit makes it easier to change the default initdb locale or
encoding settings without causing needless incompatibilities.

Discussion: https://postgr.es/m/d62b2874-729b-d26a-2d0a-0d64f509eca4@enterprisedb.com
Reviewed-by: Peter Eisentraut

Author: jeff-davis

src/bin/pg_upgrade/Makefile

@@ -51,6 +51,8 @@ clean distclean maintainer-clean:
 	rm -rf delete_old_cluster.sh log/ tmp_check/ \
 	       reindex_hash.sql
 
+export with_icu
+
 check:
 	$(prove_check)
 

src/bin/pg_upgrade/check.c

@@ -16,9 +16,6 @@
 #include "pg_upgrade.h"
 
 static void check_new_cluster_is_empty(void);
-static void check_databases_are_compatible(void);
-static void check_locale_and_encoding(DbInfo *olddb, DbInfo *newdb);
-static bool equivalent_locale(int category, const char *loca, const char *locb);
 static void check_is_install_user(ClusterInfo *cluster);
 static void check_proper_datallowconn(ClusterInfo *cluster);
 static void check_for_prepared_transactions(ClusterInfo *cluster);
@@ -33,7 +30,6 @@ static void check_for_jsonb_9_4_usage(ClusterInfo *cluster);
 static void check_for_pg_role_prefix(ClusterInfo *cluster);
 static void check_for_new_tablespace_dir(ClusterInfo *new_cluster);
 static void check_for_user_defined_encoding_conversions(ClusterInfo *cluster);
-static char *get_canonical_locale_name(int category, const char *locale);
 
 
 /*
@@ -194,7 +190,6 @@ check_new_cluster(void)
 	get_db_and_rel_infos(&new_cluster);
 
 	check_new_cluster_is_empty();
-	check_databases_are_compatible();
 
 	check_loadable_libraries();
 
@@ -349,94 +344,6 @@ check_cluster_compatibility(bool live_check)
 }
 
 
-/*
- * check_locale_and_encoding()
- *
- * Check that locale and encoding of a database in the old and new clusters
- * are compatible.
- */
-static void
-check_locale_and_encoding(DbInfo *olddb, DbInfo *newdb)
-{
-	if (olddb->db_encoding != newdb->db_encoding)
-		pg_fatal("encodings for database \"%s\" do not match:  old \"%s\", new \"%s\"",
-				 olddb->db_name,
-				 pg_encoding_to_char(olddb->db_encoding),
-				 pg_encoding_to_char(newdb->db_encoding));
-	if (!equivalent_locale(LC_COLLATE, olddb->db_collate, newdb->db_collate))
-		pg_fatal("lc_collate values for database \"%s\" do not match:  old \"%s\", new \"%s\"",
-				 olddb->db_name, olddb->db_collate, newdb->db_collate);
-	if (!equivalent_locale(LC_CTYPE, olddb->db_ctype, newdb->db_ctype))
-		pg_fatal("lc_ctype values for database \"%s\" do not match:  old \"%s\", new \"%s\"",
-				 olddb->db_name, olddb->db_ctype, newdb->db_ctype);
-	if (olddb->db_collprovider != newdb->db_collprovider)
-		pg_fatal("locale providers for database \"%s\" do not match:  old \"%s\", new \"%s\"",
-				 olddb->db_name,
-				 collprovider_name(olddb->db_collprovider),
-				 collprovider_name(newdb->db_collprovider));
-	if ((olddb->db_iculocale == NULL && newdb->db_iculocale != NULL) ||
-		(olddb->db_iculocale != NULL && newdb->db_iculocale == NULL) ||
-		(olddb->db_iculocale != NULL && newdb->db_iculocale != NULL && strcmp(olddb->db_iculocale, newdb->db_iculocale) != 0))
-		pg_fatal("ICU locale values for database \"%s\" do not match:  old \"%s\", new \"%s\"",
-				 olddb->db_name,
-				 olddb->db_iculocale ? olddb->db_iculocale : "(null)",
-				 newdb->db_iculocale ? newdb->db_iculocale : "(null)");
-}
-
-/*
- * equivalent_locale()
- *
- * Best effort locale-name comparison.  Return false if we are not 100% sure
- * the locales are equivalent.
- *
- * Note: The encoding parts of the names are ignored. This function is
- * currently used to compare locale names stored in pg_database, and
- * pg_database contains a separate encoding field. That's compared directly
- * in check_locale_and_encoding().
- */
-static bool
-equivalent_locale(int category, const char *loca, const char *locb)
-{
-	const char *chara;
-	const char *charb;
-	char	   *canona;
-	char	   *canonb;
-	int			lena;
-	int			lenb;
-
-	/*
-	 * If the names are equal, the locales are equivalent. Checking this first
-	 * avoids calling setlocale() in the common case that the names are equal.
-	 * That's a good thing, if setlocale() is buggy, for example.
-	 */
-	if (pg_strcasecmp(loca, locb) == 0)
-		return true;
-
-	/*
-	 * Not identical. Canonicalize both names, remove the encoding parts, and
-	 * try again.
-	 */
-	canona = get_canonical_locale_name(category, loca);
-	chara = strrchr(canona, '.');
-	lena = chara ? (chara - canona) : strlen(canona);
-
-	canonb = get_canonical_locale_name(category, locb);
-	charb = strrchr(canonb, '.');
-	lenb = charb ? (charb - canonb) : strlen(canonb);
-
-	if (lena == lenb && pg_strncasecmp(canona, canonb, lena) == 0)
-	{
-		pg_free(canona);
-		pg_free(canonb);
-		return true;
-	}
-
-	pg_free(canona);
-	pg_free(canonb);
-	return false;
-}
-
-
 static void
 check_new_cluster_is_empty(void)
 {
@@ -460,35 +367,6 @@ check_new_cluster_is_empty(void)
 	}
 }
 
-/*
- * Check that every database that already exists in the new cluster is
- * compatible with the corresponding database in the old one.
- */
-static void
-check_databases_are_compatible(void)
-{
-	int			newdbnum;
-	int			olddbnum;
-	DbInfo	   *newdbinfo;
-	DbInfo	   *olddbinfo;
-
-	for (newdbnum = 0; newdbnum < new_cluster.dbarr.ndbs; newdbnum++)
-	{
-		newdbinfo = &new_cluster.dbarr.dbs[newdbnum];
-
-		/* Find the corresponding database in the old cluster */
-		for (olddbnum = 0; olddbnum < old_cluster.dbarr.ndbs; olddbnum++)
-		{
-			olddbinfo = &old_cluster.dbarr.dbs[olddbnum];
-			if (strcmp(newdbinfo->db_name, olddbinfo->db_name) == 0)
-			{
-				check_locale_and_encoding(olddbinfo, newdbinfo);
-				break;
-			}
-		}
-	}
-}
-
 /*
  * A previous run of pg_upgrade might have failed and the new cluster
  * directory recreated, but they might have forgotten to remove
@@ -1524,41 +1402,3 @@ check_for_user_defined_encoding_conversions(ClusterInfo *cluster)
 	else
 		check_ok();
 }
-
-
-/*
- * get_canonical_locale_name
- *
- * Send the locale name to the system, and hope we get back a canonical
- * version.  This should match the backend's check_locale() function.
- */
-static char *
-get_canonical_locale_name(int category, const char *locale)
-{
-	char	   *save;
-	char	   *res;
-
-	/* get the current setting, so we can restore it. */
-	save = setlocale(category, NULL);
-	if (!save)
-		pg_fatal("failed to get the current locale");
-
-	/* 'save' may be pointing at a modifiable scratch variable, so copy it. */
-	save = pg_strdup(save);
-
-	/* set the locale with setlocale, to see if it accepts it. */
-	res = setlocale(category, locale);
-
-	if (!res)
-		pg_fatal("failed to get system locale name for \"%s\"", locale);
-
-	res = pg_strdup(res);
-
-	/* restore old value. */
-	if (!setlocale(category, save))
-		pg_fatal("failed to restore old locale \"%s\"", save);
-
-	pg_free(save);
-
-	return res;
-}

src/bin/pg_upgrade/info.c

@@ -20,6 +20,7 @@ static void create_rel_filename_map(const char *old_data, const char *new_data,
 static void report_unmatched_relation(const RelInfo *rel, const DbInfo *db,
 									  bool is_new_db);
 static void free_db_and_rel_infos(DbInfoArr *db_arr);
+static void get_template0_info(ClusterInfo *cluster);
 static void get_db_infos(ClusterInfo *cluster);
 static void get_rel_infos(ClusterInfo *cluster, DbInfo *dbinfo);
 static void free_rel_infos(RelInfoArr *rel_arr);
@@ -278,6 +279,7 @@ get_db_and_rel_infos(ClusterInfo *cluster)
 	if (cluster->dbarr.dbs != NULL)
 		free_db_and_rel_infos(&cluster->dbarr);
 
+	get_template0_info(cluster);
 	get_db_infos(cluster);
 
 	for (dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++)
@@ -293,6 +295,55 @@ get_db_and_rel_infos(ClusterInfo *cluster)
 }
 
 
+/*
+ * Get information about template0, which will be copied from the old cluster
+ * to the new cluster.
+ */
+static void
+get_template0_info(ClusterInfo *cluster)
+{
+	PGconn			*conn = connectToServer(cluster, "template1");
+	DbLocaleInfo	*locale;
+	PGresult		*dbres;
+	int				 i_datencoding;
+	int				 i_datlocprovider;
+	int				 i_datcollate;
+	int				 i_datctype;
+	int				 i_daticulocale;
+
+	dbres = executeQueryOrDie(conn,
+							  "SELECT encoding, datlocprovider, "
+							  "       datcollate, datctype, daticulocale "
+							  "FROM	pg_catalog.pg_database "
+							  "WHERE datname='template0'");
+
+	if (PQntuples(dbres) != 1)
+		pg_fatal("template0 not found");
+
+	locale = pg_malloc(sizeof(DbLocaleInfo));
+
+	i_datencoding = PQfnumber(dbres, "encoding");
+	i_datlocprovider = PQfnumber(dbres, "datlocprovider");
+	i_datcollate = PQfnumber(dbres, "datcollate");
+	i_datctype = PQfnumber(dbres, "datctype");
+	i_daticulocale = PQfnumber(dbres, "daticulocale");
+
+	locale->db_encoding = atoi(PQgetvalue(dbres, 0, i_datencoding));
+	locale->db_collprovider = PQgetvalue(dbres, 0, i_datlocprovider)[0];
+	locale->db_collate = pg_strdup(PQgetvalue(dbres, 0, i_datcollate));
+	locale->db_ctype = pg_strdup(PQgetvalue(dbres, 0, i_datctype));
+	if (PQgetisnull(dbres, 0, i_daticulocale))
+		locale->db_iculocale = NULL;
+	else
+		locale->db_iculocale = pg_strdup(PQgetvalue(dbres, 0, i_daticulocale));
+
+	cluster->template0 = locale;
+
+	PQclear(dbres);
+	PQfinish(conn);
+}
+
+
 /*
  * get_db_infos()
  *
@@ -309,11 +360,6 @@ get_db_infos(ClusterInfo *cluster)
 	DbInfo	   *dbinfos;
 	int			i_datname,
 				i_oid,
-				i_encoding,
-				i_datcollate,
-				i_datctype,
-				i_datlocprovider,
-				i_daticulocale,
 				i_spclocation;
 	char		query[QUERY_ALLOC];
 
@@ -337,11 +383,6 @@ get_db_infos(ClusterInfo *cluster)
 
 	i_oid = PQfnumber(res, "oid");
 	i_datname = PQfnumber(res, "datname");
-	i_encoding = PQfnumber(res, "encoding");
-	i_datcollate = PQfnumber(res, "datcollate");
-	i_datctype = PQfnumber(res, "datctype");
-	i_datlocprovider = PQfnumber(res, "datlocprovider");
-	i_daticulocale = PQfnumber(res, "daticulocale");
 	i_spclocation = PQfnumber(res, "spclocation");
 
 	ntups = PQntuples(res);
@@ -351,14 +392,6 @@ get_db_infos(ClusterInfo *cluster)
 	{
 		dbinfos[tupnum].db_oid = atooid(PQgetvalue(res, tupnum, i_oid));
 		dbinfos[tupnum].db_name = pg_strdup(PQgetvalue(res, tupnum, i_datname));
-		dbinfos[tupnum].db_encoding = atoi(PQgetvalue(res, tupnum, i_encoding));
-		dbinfos[tupnum].db_collate = pg_strdup(PQgetvalue(res, tupnum, i_datcollate));
-		dbinfos[tupnum].db_ctype = pg_strdup(PQgetvalue(res, tupnum, i_datctype));
-		dbinfos[tupnum].db_collprovider = PQgetvalue(res, tupnum, i_datlocprovider)[0];
-		if (PQgetisnull(res, tupnum, i_daticulocale))
-			dbinfos[tupnum].db_iculocale = NULL;
-		else
-			dbinfos[tupnum].db_iculocale = pg_strdup(PQgetvalue(res, tupnum, i_daticulocale));
 		snprintf(dbinfos[tupnum].db_tablespace, sizeof(dbinfos[tupnum].db_tablespace), "%s",
 				 PQgetvalue(res, tupnum, i_spclocation));
 	}

src/bin/pg_upgrade/meson.build

@@ -38,6 +38,7 @@ tests += {
   'sd': meson.current_source_dir(),
   'bd': meson.current_build_dir(),
   'tap': {
+    'env': {'with_icu': icu.found() ? 'yes' : 'no'},
     'tests': [
       't/001_basic.pl',
       't/002_pg_upgrade.pl',