v2-0001-Hold-datcollate-datctype-in-global_libc_locale.patch

From 52a2be3ac85314212e0ce7949e1341e6a8560f7c Mon Sep 17 00:00:00 2001
From: Jeff Davis <jeff@j-davis.com>
Date: Fri, 6 Jun 2025 14:13:16 -0700
Subject: [PATCH v2 1/7] Hold datcollate/datctype in global_libc_locale.

Callers of locale-aware ctype operations should use the "_l" variants
of the functions and pass global_libc_locale for the locale. Doing so
avoids depending on setlocale().

Discussion: https://postgr.es/m/9875f7f9-50f1-4b5d-86fc-ee8b03e8c162@eisentraut.org
---
 src/backend/utils/adt/pg_locale_libc.c | 77 ++++++++++++++++++++++++++
 src/backend/utils/init/postinit.c      |  2 +
 src/include/utils/pg_locale.h          |  7 +++
 3 files changed, 86 insertions(+)

diff --git a/src/backend/utils/adt/pg_locale_libc.c b/src/backend/utils/adt/pg_locale_libc.c
index 199857e22db..d6eef885ce0 100644
--- a/src/backend/utils/adt/pg_locale_libc.c
+++ b/src/backend/utils/adt/pg_locale_libc.c
@@ -85,6 +85,12 @@ static size_t strupper_libc_mb(char *dest, size_t destsize,
 							   const char *src, ssize_t srclen,
 							   pg_locale_t locale);
 
+/*
+ * Represents datcollate and datctype locales in a global variable, so that we
+ * don't need to rely on setlocale() anywhere.
+ */
+locale_t	global_libc_locale = NULL;
+
 static const struct collate_methods collate_methods_libc = {
 	.strncoll = strncoll_libc,
 	.strnxfrm = strnxfrm_libc,
@@ -417,6 +423,77 @@ strupper_libc_mb(char *dest, size_t destsize, const char *src, ssize_t srclen,
 	return result_size;
 }
 
+/*
+ * Initialize global locale for LC_COLLATE and LC_CTYPE from datcollate and
+ * datctype, respectively.
+ *
+ * NB: should be consistent with make_libc_collator(), except that it must
+ * create the locale even for "C" and "POSIX".
+ */
+void
+init_global_libc_locale(const char *collate, const char *ctype)
+{
+	locale_t	loc = 0;
+
+	if (strcmp(collate, ctype) == 0)
+	{
+		/* Normal case where they're the same */
+		errno = 0;
+#ifndef WIN32
+		loc = newlocale(LC_COLLATE_MASK | LC_CTYPE_MASK, collate, NULL);
+#else
+		loc = _create_locale(LC_ALL, collate);
+#endif
+		if (!loc)
+			ereport(FATAL,
+					(errmsg("database locale is incompatible with operating system"),
+					 errdetail("The database was initialized with LC_COLLATE \"%s\", "
+							   " which is not recognized by setlocale().", collate),
+					 errhint("Recreate the database with another locale or install the missing locale.")));
+	}
+	else
+	{
+#ifndef WIN32
+		/* We need two newlocale() steps */
+		locale_t	loc1 = 0;
+
+		errno = 0;
+		loc1 = newlocale(LC_COLLATE_MASK, collate, NULL);
+		if (!loc1)
+			ereport(FATAL,
+					(errmsg("database locale is incompatible with operating system"),
+					 errdetail("The database was initialized with LC_COLLATE \"%s\", "
+							   " which is not recognized by setlocale().", collate),
+					 errhint("Recreate the database with another locale or install the missing locale.")));
+
+		errno = 0;
+		loc = newlocale(LC_CTYPE_MASK, ctype, loc1);
+		if (!loc)
+		{
+			if (loc1)
+				freelocale(loc1);
+			ereport(FATAL,
+					(errmsg("database locale is incompatible with operating system"),
+					 errdetail("The database was initialized with LC_CTYPE \"%s\", "
+							   " which is not recognized by setlocale().", ctype),
+					 errhint("Recreate the database with another locale or install the missing locale.")));
+		}
+#else
+
+		/*
+		 * XXX The _create_locale() API doesn't appear to support this. Could
+		 * perhaps be worked around by changing pg_locale_t to contain two
+		 * separate fields.
+		 */
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("collations with different collate and ctype values are not supported on this platform")));
+#endif
+	}
+
+	global_libc_locale = loc;
+}
+
 pg_locale_t
 create_pg_locale_libc(Oid collid, MemoryContext context)
 {
diff --git a/src/backend/utils/init/postinit.c b/src/backend/utils/init/postinit.c
index c86ceefda94..74f9df84fde 100644
--- a/src/backend/utils/init/postinit.c
+++ b/src/backend/utils/init/postinit.c
@@ -431,6 +431,8 @@ 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.")));
 
+	init_global_libc_locale(collate, ctype);
+
 	if (strcmp(ctype, "C") == 0 ||
 		strcmp(ctype, "POSIX") == 0)
 		database_ctype_is_c = true;
diff --git a/src/include/utils/pg_locale.h b/src/include/utils/pg_locale.h
index 7b8cbf58d2c..3ea16e83ee1 100644
--- a/src/include/utils/pg_locale.h
+++ b/src/include/utils/pg_locale.h
@@ -32,6 +32,12 @@ extern PGDLLIMPORT char *localized_full_days[];
 extern PGDLLIMPORT char *localized_abbrev_months[];
 extern PGDLLIMPORT char *localized_full_months[];
 
+/*
+ * Represents datcollate and datctype locales in a global variable, so that we
+ * don't need to rely on setlocale() anywhere.
+ */
+extern PGDLLIMPORT locale_t global_libc_locale;
+
 /* is the databases's LC_CTYPE the C locale? */
 extern PGDLLIMPORT bool database_ctype_is_c;
 
@@ -121,6 +127,7 @@ struct pg_locale_struct
 	}			info;
 };
 
+extern void init_global_libc_locale(const char *collate, const char *ctype);
 extern void init_database_collation(void);
 extern pg_locale_t pg_newlocale_from_collation(Oid collid);
 
-- 
2.43.0