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

5 files changed, 26 insertions, 14 deletions

diff --git a/Doc/library/mimetypes.rst b/Doc/library/mimetypes.rst
index ccda1e9..8891e7a 100644
--- 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:: 2.7
       Previously, Windows registry settings were ignored.
 
diff --git a/Lib/mimetypes.py b/Lib/mimetypes.py
index 18ade73..3dde4cd 100644
--- a/Lib/mimetypes.py
+++ b/Lib/mimetypes.py
@@ -254,23 +254,26 @@ class MimeTypes:
                 i += 1
 
         default_encoding = sys.getdefaultencoding()
-        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')
+                    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
+                        try:
+                            mimetype = mimetype.encode(default_encoding)
+                            subkeyname = subkeyname.encode(default_encoding)
+                        except UnicodeEncodeError:
+                            continue
+                        self.add_type(mimetype, subkeyname, strict)
                 except EnvironmentError:
                     continue
-                if datatype != _winreg.REG_SZ:
-                    continue
-                try:
-                    suffix = suffix.encode(default_encoding) # omit in 3.x!
-                except UnicodeEncodeError:
-                    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
index 788d7a8..f8e1e63 100644
--- a/Lib/test/test_mimetypes.py
+++ b/Lib/test/test_mimetypes.py
@@ -85,6 +85,8 @@ class Win32MimeTypesTestCase(unittest.TestCase):
         # 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():
     test_support.run_unittest(MimeTypesTestCase,
diff --git a/Misc/ACKS b/Misc/ACKS
index ffa3154..e276960 100644
--- a/Misc/ACKS
+++ b/Misc/ACKS
@@ -166,6 +166,7 @@ Jesús Cea Avión
 Per Cederqvist
 Carl Cerecke
 Octavian Cerna
+Dave Chambers
 Pascal Chambon
 John Chandler
 Hye-Shik Chang
diff --git a/Misc/NEWS b/Misc/NEWS
index 80a1a23..3ee2643 100644
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -40,6 +40,9 @@ Core and Builtins
 Library
 -------
 
+- Issue #15207: Fix mimetypes to read from correct part of Windows registry
+  Original patch by Dave Chambers
+
 - Issue #8964: fix platform._sys_version to handle IronPython 2.6+.
   Patch by Martin Matusiak.