gh-133967: Do not normalize locale name 'C.UTF-8' to 'en_US.UTF-8' (#135347)

serhiy-storchaka · web-flow · commit 0f866cbfefd7 · 2025-06-10T13:38:32.000Z
diff --git a/Lib/locale.py b/Lib/locale.py
@@ -883,6 +883,10 @@ def getpreferredencoding(do_setlocale=True):
 #    updated 'sr@latn' -> 'sr_CS.UTF-8@latin' to 'sr_RS.UTF-8@latin'
 #    removed 'univ'
 #    removed 'universal'
+#
+# SS 2025-06-10:
+# Remove 'c.utf8' -> 'en_US.UTF-8' because 'en_US.UTF-8' does not exist
+# on all platforms.
 
 locale_alias = {
     'a3':                                   'az_AZ.KOI8-C',
@@ -962,7 +966,6 @@ def getpreferredencoding(do_setlocale=True):
     'c.ascii':                              'C',
     'c.en':                                 'C',
     'c.iso88591':                           'en_US.ISO8859-1',
-    'c.utf8':                               'en_US.UTF-8',
     'c_c':                                  'C',
     'c_c.c':                                'C',
     'ca':                                   'ca_ES.ISO8859-1',
diff --git a/Lib/test/test_locale.py b/Lib/test/test_locale.py
@@ -387,6 +387,10 @@ def test_c(self):
         self.check('c', 'C')
         self.check('posix', 'C')
 
+    def test_c_utf8(self):
+        self.check('c.utf8', 'C.UTF-8')
+        self.check('C.UTF-8', 'C.UTF-8')
+
     def test_english(self):
         self.check('en', 'en_US.ISO8859-1')
         self.check('EN', 'en_US.ISO8859-1')
diff --git a/Misc/NEWS.d/next/Library/2025-06-10-16-11-00.gh-issue-133967.P0c24q.rst b/Misc/NEWS.d/next/Library/2025-06-10-16-11-00.gh-issue-133967.P0c24q.rst
@@ -0,0 +1 @@
+Do not normalize :mod:`locale` name 'C.UTF-8' to 'en_US.UTF-8'.
diff --git a/Tools/i18n/makelocalealias.py b/Tools/i18n/makelocalealias.py
@@ -140,6 +140,9 @@ def check(data):
     data = locale.locale_alias.copy()
     data.update(parse_glibc_supported(args.glibc_supported))
     data.update(parse(args.locale_alias))
+    # Hardcode 'c.utf8' -> 'C.UTF-8' because 'en_US.UTF-8' does not exist
+    # on all platforms.
+    data['c.utf8'] = 'C.UTF-8'
     while True:
         # Repeat optimization while the size is decreased.
         n = len(data)
