(Merge 3.2) Issue #13025: mimetypes is now reading MIME types using the UTF-8

encoding, instead of the locale encoding.

Lib/mimetypes.py

@@ -199,7 +199,7 @@ class MimeTypes:
         list of standard types, else to the list of non-standard
         types.
         """
-        with open(filename) as fp:
+        with open(filename, encoding='utf-8') as fp:
             self.readfp(fp, strict)
 
     def readfp(self, fp, strict=True):

Lib/test/test_mimetypes.py

-import mimetypes
 import io
-import unittest
+import locale
+import mimetypes
 import sys
+import unittest
 
 from test import support
 
@@ -62,6 +63,18 @@ class MimeTypesTestCase(unittest.TestCase):
         all = self.db.guess_all_extensions('image/jpg', strict=True)
         eq(all, [])
 
+    def test_encoding(self):
+        getpreferredencoding = locale.getpreferredencoding
+        self.addCleanup(setattr, locale, 'getpreferredencoding',
+                                 getpreferredencoding)
+        locale.getpreferredencoding = lambda: 'ascii'
+
+        filename = support.findfile("mime.types")
+        mimes = mimetypes.MimeTypes([filename])
+        exts = mimes.guess_all_extensions('application/vnd.geocube+xml',
+                                          strict=True)
+        self.assertEqual(exts, ['.g3', '.g\xb3'])
+
 
 @unittest.skipUnless(sys.platform.startswith("win"), "Windows only")
 class Win32MimeTypesTestCase(unittest.TestCase):

Misc/NEWS

@@ -305,6 +305,9 @@ Core and Builtins
 Library
 -------
 
+- Issue #13025: mimetypes is now reading MIME types using the UTF-8 encoding,
+  instead of the locale encoding.
+
 - Issue #10653: On Windows, use strftime() instead of wcsftime() because
   wcsftime() doesn't format time zone correctly.