Issue #18216: gettext now raises an error when a .mo file has an unsupported major version number. Patch by Aaron Hill.

Doc/library/gettext.rst

@@ -344,9 +344,9 @@ will assume message ids as Unicode strings, not byte strings.
 The entire set of key/value pairs are placed into a dictionary and set as the
 "protected" :attr:`_info` instance variable.
 
-If the :file:`.mo` file's magic number is invalid, or if other problems occur
+If the :file:`.mo` file's magic number is invalid, the major version number is
-while reading the file, instantiating a :class:`GNUTranslations` class can raise
+unexpected, or if other problems occur while reading the file, instantiating a
-:exc:`OSError`.
+:class:`GNUTranslations` class can raise :exc:`OSError`.
 
 The following methods are overridden from the base class implementation:
 

Lib/gettext.py

@@ -225,6 +225,13 @@ class GNUTranslations(NullTranslations):
     LE_MAGIC = 0x950412de
     BE_MAGIC = 0xde120495
 
+    # Acceptable .mo versions
+    VERSIONS = (0, 1)
+
+    def _get_versions(self, version):
+        """Returns a tuple of major version, minor version"""
+        return (version >> 16, version & 0xffff)
+
     def _parse(self, fp):
         """Override this method to support alternative .mo formats."""
         unpack = struct.unpack
@@ -245,6 +252,12 @@ class GNUTranslations(NullTranslations):
             ii = '>II'
         else:
             raise OSError(0, 'Bad magic number', filename)
+
+        major_version, minor_version = self._get_versions(version)
+
+        if major_version not in self.VERSIONS:
+            raise OSError(0, 'Bad version number ' + str(major_version), filename)
+
         # Now put all messages from the .mo file buffer into the catalog
         # dictionary.
         for i in range(0, msgcount):

Lib/test/test_gettext.py

@@ -33,6 +33,55 @@ IHNiZSBsYmhlIENsZ3ViYSBjZWJ0ZW56ZiBvbCBjZWJpdnF2YXQgbmEgdmFncmVzbnByIGdiIGd1
 ciBUQUgKdHJnZ3JrZyB6cmZmbnRyIHBuZ255YnQgeXZvZW5lbC4AYmFjb24Ad2luayB3aW5rAA==
 '''
 
+# This data contains an invalid major version number (5)
+# An unexpected major version number should be treated as an error when
+# parsing a .mo file
+
+GNU_MO_DATA_BAD_MAJOR_VERSION = b'''\
+3hIElQAABQAGAAAAHAAAAEwAAAALAAAAfAAAAAAAAACoAAAAFQAAAKkAAAAjAAAAvwAAAKEAAADj
+AAAABwAAAIUBAAALAAAAjQEAAEUBAACZAQAAFgAAAN8CAAAeAAAA9gIAAKEAAAAVAwAABQAAALcD
+AAAJAAAAvQMAAAEAAAADAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAEAAAABQAAAAYAAAACAAAAAFJh
+eW1vbmQgTHV4dXJ5IFlhY2gtdABUaGVyZSBpcyAlcyBmaWxlAFRoZXJlIGFyZSAlcyBmaWxlcwBU
+aGlzIG1vZHVsZSBwcm92aWRlcyBpbnRlcm5hdGlvbmFsaXphdGlvbiBhbmQgbG9jYWxpemF0aW9u
+CnN1cHBvcnQgZm9yIHlvdXIgUHl0aG9uIHByb2dyYW1zIGJ5IHByb3ZpZGluZyBhbiBpbnRlcmZh
+Y2UgdG8gdGhlIEdOVQpnZXR0ZXh0IG1lc3NhZ2UgY2F0YWxvZyBsaWJyYXJ5LgBtdWxsdXNrAG51
+ZGdlIG51ZGdlAFByb2plY3QtSWQtVmVyc2lvbjogMi4wClBPLVJldmlzaW9uLURhdGU6IDIwMDAt
+MDgtMjkgMTI6MTktMDQ6MDAKTGFzdC1UcmFuc2xhdG9yOiBKLiBEYXZpZCBJYsOhw7FleiA8ai1k
+YXZpZEBub29zLmZyPgpMYW5ndWFnZS1UZWFtOiBYWCA8cHl0aG9uLWRldkBweXRob24ub3JnPgpN
+SU1FLVZlcnNpb246IDEuMApDb250ZW50LVR5cGU6IHRleHQvcGxhaW47IGNoYXJzZXQ9aXNvLTg4
+NTktMQpDb250ZW50LVRyYW5zZmVyLUVuY29kaW5nOiBub25lCkdlbmVyYXRlZC1CeTogcHlnZXR0
+ZXh0LnB5IDEuMQpQbHVyYWwtRm9ybXM6IG5wbHVyYWxzPTI7IHBsdXJhbD1uIT0xOwoAVGhyb2F0
+d29iYmxlciBNYW5ncm92ZQBIYXkgJXMgZmljaGVybwBIYXkgJXMgZmljaGVyb3MAR3V2ZiB6YnFo
+eXIgY2ViaXZxcmYgdmFncmVhbmd2YmFueXZtbmd2YmEgbmFxIHlicG55dm1uZ3ZiYQpmaGNjYmVn
+IHNiZSBsYmhlIENsZ3ViYSBjZWJ0ZW56ZiBvbCBjZWJpdnF2YXQgbmEgdmFncmVzbnByIGdiIGd1
+ciBUQUgKdHJnZ3JrZyB6cmZmbnRyIHBuZ255YnQgeXZvZW5lbC4AYmFjb24Ad2luayB3aW5rAA==
+'''
+
+# This data contains an invalid minor version number (7)
+# An unexpected minor version number only indicates that some of the file's
+# contents may not be able to be read. It does not indicate an error.
+
+GNU_MO_DATA_BAD_MINOR_VERSION = b'''\
+3hIElQcAAAAGAAAAHAAAAEwAAAALAAAAfAAAAAAAAACoAAAAFQAAAKkAAAAjAAAAvwAAAKEAAADj
+AAAABwAAAIUBAAALAAAAjQEAAEUBAACZAQAAFgAAAN8CAAAeAAAA9gIAAKEAAAAVAwAABQAAALcD
+AAAJAAAAvQMAAAEAAAADAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAEAAAABQAAAAYAAAACAAAAAFJh
+eW1vbmQgTHV4dXJ5IFlhY2gtdABUaGVyZSBpcyAlcyBmaWxlAFRoZXJlIGFyZSAlcyBmaWxlcwBU
+aGlzIG1vZHVsZSBwcm92aWRlcyBpbnRlcm5hdGlvbmFsaXphdGlvbiBhbmQgbG9jYWxpemF0aW9u
+CnN1cHBvcnQgZm9yIHlvdXIgUHl0aG9uIHByb2dyYW1zIGJ5IHByb3ZpZGluZyBhbiBpbnRlcmZh
+Y2UgdG8gdGhlIEdOVQpnZXR0ZXh0IG1lc3NhZ2UgY2F0YWxvZyBsaWJyYXJ5LgBtdWxsdXNrAG51
+ZGdlIG51ZGdlAFByb2plY3QtSWQtVmVyc2lvbjogMi4wClBPLVJldmlzaW9uLURhdGU6IDIwMDAt
+MDgtMjkgMTI6MTktMDQ6MDAKTGFzdC1UcmFuc2xhdG9yOiBKLiBEYXZpZCBJYsOhw7FleiA8ai1k
+YXZpZEBub29zLmZyPgpMYW5ndWFnZS1UZWFtOiBYWCA8cHl0aG9uLWRldkBweXRob24ub3JnPgpN
+SU1FLVZlcnNpb246IDEuMApDb250ZW50LVR5cGU6IHRleHQvcGxhaW47IGNoYXJzZXQ9aXNvLTg4
+NTktMQpDb250ZW50LVRyYW5zZmVyLUVuY29kaW5nOiBub25lCkdlbmVyYXRlZC1CeTogcHlnZXR0
+ZXh0LnB5IDEuMQpQbHVyYWwtRm9ybXM6IG5wbHVyYWxzPTI7IHBsdXJhbD1uIT0xOwoAVGhyb2F0
+d29iYmxlciBNYW5ncm92ZQBIYXkgJXMgZmljaGVybwBIYXkgJXMgZmljaGVyb3MAR3V2ZiB6YnFo
+eXIgY2ViaXZxcmYgdmFncmVhbmd2YmFueXZtbmd2YmEgbmFxIHlicG55dm1uZ3ZiYQpmaGNjYmVn
+IHNiZSBsYmhlIENsZ3ViYSBjZWJ0ZW56ZiBvbCBjZWJpdnF2YXQgbmEgdmFncmVzbnByIGdiIGd1
+ciBUQUgKdHJnZ3JrZyB6cmZmbnRyIHBuZ255YnQgeXZvZW5lbC4AYmFjb24Ad2luayB3aW5rAA==
+'''
+
+
 UMO_DATA = b'''\
 3hIElQAAAAACAAAAHAAAACwAAAAFAAAAPAAAAAAAAABQAAAABAAAAFEAAAAPAQAAVgAAAAQAAABm
 AQAAAQAAAAIAAAAAAAAAAAAAAAAAAAAAYWLDngBQcm9qZWN0LUlkLVZlcnNpb246IDIuMApQTy1S
@@ -56,6 +105,8 @@ bGUKR2VuZXJhdGVkLUJ5OiBweWdldHRleHQucHkgMS4zCgA=
 
 LOCALEDIR = os.path.join('xx', 'LC_MESSAGES')
 MOFILE = os.path.join(LOCALEDIR, 'gettext.mo')
+MOFILE_BAD_MAJOR_VERSION = os.path.join(LOCALEDIR, 'gettext_bad_major_version.mo')
+MOFILE_BAD_MINOR_VERSION = os.path.join(LOCALEDIR, 'gettext_bad_minor_version.mo')
 UMOFILE = os.path.join(LOCALEDIR, 'ugettext.mo')
 MMOFILE = os.path.join(LOCALEDIR, 'metadata.mo')
 
@@ -66,6 +117,10 @@ class GettextBaseTest(unittest.TestCase):
             os.makedirs(LOCALEDIR)
         with open(MOFILE, 'wb') as fp:
             fp.write(base64.decodebytes(GNU_MO_DATA))
+        with open(MOFILE_BAD_MAJOR_VERSION, 'wb') as fp:
+            fp.write(base64.decodebytes(GNU_MO_DATA_BAD_MAJOR_VERSION))
+        with open(MOFILE_BAD_MINOR_VERSION, 'wb') as fp:
+            fp.write(base64.decodebytes(GNU_MO_DATA_BAD_MINOR_VERSION))
         with open(UMOFILE, 'wb') as fp:
             fp.write(base64.decodebytes(UMO_DATA))
         with open(MMOFILE, 'wb') as fp:
@@ -166,6 +221,21 @@ class GettextTestCase2(GettextBaseTest):
     def test_textdomain(self):
         self.assertEqual(gettext.textdomain(), 'gettext')
 
+    def test_bad_major_version(self):
+        with open(MOFILE_BAD_MAJOR_VERSION, 'rb') as fp:
+            with self.assertRaises(OSError) as cm:
+                gettext.GNUTranslations(fp)
+
+            exception = cm.exception
+            self.assertEqual(exception.errno, 0)
+            self.assertEqual(exception.strerror, "Bad version number 5")
+            self.assertEqual(exception.filename, MOFILE_BAD_MAJOR_VERSION)
+
+    def test_bad_minor_version(self):
+        with open(MOFILE_BAD_MINOR_VERSION, 'rb') as fp:
+            # Check that no error is thrown with a bad minor version number
+            gettext.GNUTranslations(fp)
+
     def test_some_translations(self):
         eq = self.assertEqual
         # test some translations

Misc/ACKS

@@ -567,6 +567,7 @@ Kevan Heydon
 Wouter van Heyst
 Kelsey Hightower
 Jason Hildebrand
+Aaron Hill
 Richie Hindle
 Konrad Hinsen
 David Hobley

Misc/NEWS

@@ -181,6 +181,9 @@ Core and Builtins
 Library
 -------
 
+- Issue #18216: gettext now raises an error when a .mo file has an
+  unsupported major version number.  Patch by Aaron Hill.
+
 - Issue #13918: Provide a locale.delocalize() function which can remove
   locale-specific number formatting from a string representing a number,
   without then converting it to a specific type.  Patch by Cédric Krier.