diff options
| author | Miss Islington (bot) <31488909+miss-islington@users.noreply.github.com> | 2020-06-29 12:07:41 (GMT) |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2020-06-29 12:07:41 (GMT) |
| commit | 7731139b7af655b9f5df6d1b5493f8dfdf41d569 (patch) | |
| tree | 54720f127940f2f0c02bef2fe86b36159a74e8ba | |
| parent | 12bb0b69ec237a4d6d666bb385d87eb61dbb2bf5 (diff) | |
| download | cpython-7731139b7af655b9f5df6d1b5493f8dfdf41d569.zip cpython-7731139b7af655b9f5df6d1b5493f8dfdf41d569.tar.gz cpython-7731139b7af655b9f5df6d1b5493f8dfdf41d569.tar.bz2 | |
bpo-41048: mimetypes should read the rule file using UTF-8, not the locale encoding (GH-20998)
(cherry picked from commit 7f569c9bc0079906012b3034d30fe8abc742e7fc)
Co-authored-by: Srinivas Reddy Thatiparthy (శ్రీనివాస్ రెడ్డి తాటిపర్తి) <thatiparthysreenivas@gmail.com>
| -rw-r--r-- | Lib/mimetypes.py | 2 | ||||
| -rw-r--r-- | Lib/test/test_mimetypes.py | 12 | ||||
| -rw-r--r-- | Misc/ACKS | 1 | ||||
| -rw-r--r-- | Misc/NEWS.d/next/Library/2020-06-20-10-16-57.bpo-41048.hEXB-B.rst | 2 |
4 files changed, 16 insertions, 1 deletions
diff --git a/Lib/mimetypes.py b/Lib/mimetypes.py index 434f5b3..954bb0a 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 @@ -1669,6 +1669,7 @@ Mikhail Terekhov Victor Terrón Pablo Galindo Richard M. Tew +Srinivas Reddy Thatiparthy Tobias Thelen Christian Theune Févry Thibault diff --git a/Misc/NEWS.d/next/Library/2020-06-20-10-16-57.bpo-41048.hEXB-B.rst b/Misc/NEWS.d/next/Library/2020-06-20-10-16-57.bpo-41048.hEXB-B.rst new file mode 100644 index 0000000..2595900 --- /dev/null +++ b/Misc/NEWS.d/next/Library/2020-06-20-10-16-57.bpo-41048.hEXB-B.rst @@ -0,0 +1,2 @@ +:func:`mimetypes.read_mime_types` function reads the rule file using UTF-8 encoding, not the locale encoding. +Patch by Srinivas Reddy Thatiparthy.
\ No newline at end of file |