Issue #15207: Fix mimetypes to read from correct area in Windows registry (Original patch by Dave Chambers)

tjguk · tjguk · commit a4df90ceb92f · 2013-10-22T20:03:47.000+01:00
diff --git a/Doc/library/mimetypes.rst b/Doc/library/mimetypes.rst
@@ -85,6 +85,9 @@ behavior of the module.
    :const:`knownfiles` takes precedence over those named before it.  Calling
    :func:`init` repeatedly is allowed.
 
+   Specifying an empty list for *files* will prevent the system defaults from
+   being applied: only the well-known values will be present from a built-in list.
+
    .. versionchanged:: 3.2
       Previously, Windows registry settings were ignored.
 
diff --git a/Lib/mimetypes.py b/Lib/mimetypes.py
@@ -243,25 +243,27 @@ def enum_types(mimedb):
             while True:
                 try:
                     ctype = _winreg.EnumKey(mimedb, i)
-                except OSError:
+                except EnvironmentError:
                     break
                 else:
                     yield ctype
                 i += 1
 
-        with _winreg.OpenKey(_winreg.HKEY_CLASSES_ROOT,
-                             r'MIME\Database\Content Type') as mimedb:
-            for ctype in enum_types(mimedb):
+        with _winreg.OpenKey(_winreg.HKEY_CLASSES_ROOT, '') as hkcr:
+            for subkeyname in enum_types(hkcr):
                 try:
-                    with _winreg.OpenKey(mimedb, ctype) as key:
-                        suffix, datatype = _winreg.QueryValueEx(key,
-                                                                'Extension')
-                except OSError:
+                    with _winreg.OpenKey(hkcr, subkeyname) as subkey:
+                        # Only check file extensions
+                        if not subkeyname.startswith("."):
+                            continue
+                        # raises EnvironmentError if no 'Content Type' value
+                        mimetype, datatype = _winreg.QueryValueEx(
+                            subkey, 'Content Type')
+                        if datatype != _winreg.REG_SZ:
+                            continue
+                        self.add_type(mimetype, subkeyname, strict)
+                except EnvironmentError:
                     continue
-                if datatype != _winreg.REG_SZ:
-                    continue
-                self.add_type(ctype, suffix, strict)
-
 
 def guess_type(url, strict=True):
     """Guess the type of a file based on its URL.
diff --git a/Lib/test/test_mimetypes.py b/Lib/test/test_mimetypes.py
@@ -98,7 +98,8 @@ def test_registry_parsing(self):
         # Use file types that should *always* exist:
         eq = self.assertEqual
         eq(self.db.guess_type("foo.txt"), ("text/plain", None))
-
+        eq(self.db.guess_type("image.jpg"), ("image/jpeg", None))
+        eq(self.db.guess_type("image.png"), ("image/png", None))
 
 def test_main():
     support.run_unittest(MimeTypesTestCase,
diff --git a/Misc/ACKS b/Misc/ACKS
@@ -209,6 +209,7 @@ Per Cederqvist
 Matej Cepl
 Carl Cerecke
 Octavian Cerna
+Dave Chambers
 Pascal Chambon
 John Chandler
 Hye-Shik Chang
diff --git a/Misc/NEWS b/Misc/NEWS
@@ -19,6 +19,9 @@ Core and Builtins
 Library
 -------
 
+- Issue #15207: Fix mimetypes to read from correct part of Windows registry
+  Original patch by Dave Chambers
+
 - Issue #16595: Add prlimit() to resource module.
 
 - Issue #19324: Expose Linux-specific constants in resource module.
