Add overrides for mimetype -> extension conversion

Python 3.6 gets some of those "wrong":
https://bugs.python.org/issue1043134

This has been fixed in Python 3.7:
https://github.com/python/cpython/pull/14375

The override dict has been generated by copying the types_map from the
current git master:
https://github.com/python/cpython/blob/v3.10.0a3/Lib/mimetypes.py#L414-L547

And then running the following with Python 3.6:

    import mimetypes

    reverse = {}
    for ext, mimetype in types_map.items():
        if mimetype not in reverse:
            reverse[mimetype] = ext
    assert reverse['text/plain'] == '.txt'

    for mimetype, ext in reverse.items():
        got = mimetypes.guess_extension(mimetype)
        if got != ext:
            print(f'    "{mimetype}": "{ext}",  # not {got}')

3 files changed, 47 insertions, 1 deletions

diff --git a/qutebrowser/utils/urlutils.py b/qutebrowser/utils/urlutils.py
index b5afe958c..af5c997da 100644
--- a/qutebrowser/utils/urlutils.py
+++ b/qutebrowser/utils/urlutils.py
@@ -412,7 +412,7 @@ def filename_from_url(url: QUrl, fallback: str = None) -> Optional[str]:
         if not mimetype:
             return fallback
 
-        ext = mimetypes.guess_extension(mimetype, strict=False) or ''
+        ext = utils.mimetype_extension(mimetype) or ''
         return 'download' + ext
 
     pathname = posixpath.basename(url.path())
diff --git a/qutebrowser/utils/utils.py b/qutebrowser/utils/utils.py
index cf239805c..e49309ef2 100644
--- a/qutebrowser/utils/utils.py
+++ b/qutebrowser/utils/utils.py
@@ -803,3 +803,38 @@ def parse_duration(duration: str) -> int:
     hours = float(hours_string.rstrip('h'))
     milliseconds = int((seconds + minutes * 60 + hours * 3600) * 1000)
     return milliseconds
+
+
+def mimetype_extension(mimetype: str) -> Optional[str]:
+    """Get a suitable extension for a given mimetype.
+
+    This mostly delegates to Python's mimetypes.guess_extension(), but backports some
+    changes (via a simple override dict) which are missing from earlier Python versions.
+    Most likely, this can be dropped once the minimum Python version is raised to 3.7.
+    """
+    overrides = {
+        # Added around 3.8
+        "application/manifest+json": ".webmanifest",
+        "application/x-hdf5": ".h5",
+
+        # Added in Python 3.7
+        "application/wasm": ".wasm",
+
+        # Wrong values for Python 3.6
+        # https://bugs.python.org/issue1043134
+        # https://github.com/python/cpython/pull/14375
+        "application/octet-stream": ".bin",  # not .a
+        "application/postscript": ".ps",  # not .ai
+        "application/vnd.ms-excel": ".xls",  # not .xlb
+        "application/vnd.ms-powerpoint": ".ppt",  # not .pot
+        "application/xml": ".xsl",  # not .rdf
+        "audio/mpeg": ".mp3",  # not .mp2
+        "image/jpeg": ".jpg",  # not .jpe
+        "image/tiff": ".tiff",  # not .tif
+        "text/html": ".html",  # not .htm
+        "text/plain": ".txt",  # not .bat
+        "video/mpeg": ".mpeg",  # not .m1v
+    }
+    if mimetype in overrides:
+        return overrides[mimetype]
+    return mimetypes.guess_extension(mimetype, strict=False)
diff --git a/tests/unit/utils/test_utils.py b/tests/unit/utils/test_utils.py
index 404185548..2b1392664 100644
--- a/tests/unit/utils/test_utils.py
+++ b/tests/unit/utils/test_utils.py
@@ -867,3 +867,14 @@ def test_parse_duration_hypothesis(duration):
         utils.parse_duration(duration)
     except ValueError:
         pass
+
+
+@pytest.mark.parametrize('mimetype, extension', [
+    ('application/pdf', '.pdf'),  # handled by Python
+    ('text/plain', '.txt'),  # wrong in Python 3.6, overridden
+    ('application/manifest+json', '.webmanifest'),  # newer
+    ('text/xul', '.xul'),  # strict=False
+    ('doesnot/exist', None),
+])
+def test_mimetype_extension(mimetype, extension):
+    assert utils.mimetype_extension(mimetype) == extension