bpo-41048: mimetypes should read the rule file using UTF-8, not the locale encoding (GH-20998)

2 files changed, 13 insertions, 1 deletions

diff --git a/Lib/mimetypes.py b/Lib/mimetypes.py
index 61bfff1..f3343c8 100644
--- a/Lib/mimetypes.py
+++ b/Lib/mimetypes.py
@@ -372,7 +372,7 @@ def init(files=None):
 
 def read_mime_types(file):
     try:
-        f = open(file)
+        f = open(file, encoding='utf-8')
     except OSError:
         return None
     with f:
diff --git a/Lib/test/test_mimetypes.py b/Lib/test/test_mimetypes.py
index 9cac6ce..683d393 100644
--- a/Lib/test/test_mimetypes.py
+++ b/Lib/test/test_mimetypes.py
@@ -67,6 +67,18 @@ class MimeTypesTestCase(unittest.TestCase):
             mime_dict = mimetypes.read_mime_types(file)
             eq(mime_dict[".pyunit"], "x-application/x-unittest")
 
+        # bpo-41048: read_mime_types should read the rule file with 'utf-8' encoding.
+        # Not with locale encoding. _bootlocale has been imported because io.open(...)
+        # uses it.
+        with support.temp_dir() as directory:
+            data = "application/no-mans-land  Fran\u00E7ais"
+            file = pathlib.Path(directory, "sample.mimetype")
+            file.write_text(data, encoding='utf-8')
+            import _bootlocale
+            with support.swap_attr(_bootlocale, 'getpreferredencoding', lambda do_setlocale=True: 'ASCII'):
+                mime_dict = mimetypes.read_mime_types(file)
+            eq(mime_dict[".Français"], "application/no-mans-land")
+
     def test_non_standard_types(self):
         eq = self.assertEqual
         # First try strict