[Python-checkins] r50693 - in python/trunk/Lib/email: __init__.py test/test_email_renamed.py utils.py

[barry.warsaw]

Author: barry.warsaw
Date: Tue Jul 18 01:07:51 2006
New Revision: 50693

Modified:
   python/trunk/Lib/email/__init__.py
   python/trunk/Lib/email/test/test_email_renamed.py
   python/trunk/Lib/email/utils.py
Log:
decode_rfc2231(): Be more robust against buggy RFC 2231 encodings.
Specifically, instead of raising a ValueError when there is a single tick in
the parameter, simply return that the entire string unquoted, with None for
both the charset and the language.  Also, if there are more than 2 ticks in
the parameter, interpret the first three parts as the standard RFC 2231 parts,
then the rest of the parts as the encoded string.

Test cases added.

Original fewer-than-3-parts fix by Tokio Kikuchi.

Resolves SF bug # 1218081.  I will back port the fix and tests to Python 2.4
(email 3.0) and Python 2.3 (email 2.5).

Also, bump the version number to email 4.0.1, removing the 'alpha' moniker.


Modified: python/trunk/Lib/email/__init__.py
==============================================================================
--- python/trunk/Lib/email/__init__.py	(original)
+++ python/trunk/Lib/email/__init__.py	Tue Jul 18 01:07:51 2006
@@ -4,7 +4,7 @@
 
 """A package for parsing, handling, and generating email messages."""
 
-__version__ = '4.0a2'
+__version__ = '4.0.1'
 
 __all__ = [
     # Old names

Modified: python/trunk/Lib/email/test/test_email_renamed.py
==============================================================================
--- python/trunk/Lib/email/test/test_email_renamed.py	(original)
+++ python/trunk/Lib/email/test/test_email_renamed.py	Tue Jul 18 01:07:51 2006
@@ -3060,6 +3060,40 @@
         msg = email.message_from_string(m)
         self.assertEqual(msg.get_filename(), 'myfile.txt')
 
+    def test_rfc2231_single_tick_in_filename(self):
+        eq = self.assertEqual
+        m = """\
+Content-Type: application/x-foo; name*0=\"Frank's\"; name*1=\" Document\"
+
+"""
+        msg = email.message_from_string(m)
+        charset, language, s = msg.get_param('name')
+        eq(charset, None)
+        eq(language, None)
+        eq(s, "Frank's Document")
+
+    def test_rfc2231_tick_attack(self):
+        eq = self.assertEqual
+        m = """\
+Content-Type: application/x-foo;
+\tname*0=\"us-ascii'en-us'Frank's\"; name*1=\" Document\"
+
+"""
+        msg = email.message_from_string(m)
+        charset, language, s = msg.get_param('name')
+        eq(charset, 'us-ascii')
+        eq(language, 'en-us')
+        eq(s, "Frank's Document")
+
+    def test_rfc2231_no_extended_values(self):
+        eq = self.assertEqual
+        m = """\
+Content-Type: application/x-foo; name=\"Frank's Document\"
+
+"""
+        msg = email.message_from_string(m)
+        eq(msg.get_param('name'), "Frank's Document")
+
 
 
 def _testclasses():

Modified: python/trunk/Lib/email/utils.py
==============================================================================
--- python/trunk/Lib/email/utils.py	(original)
+++ python/trunk/Lib/email/utils.py	Tue Jul 18 01:07:51 2006
@@ -45,6 +45,7 @@
 EMPTYSTRING = ''
 UEMPTYSTRING = u''
 CRLF = '\r\n'
+TICK = "'"
 
 specialsre = re.compile(r'[][\\()<>@,:;".]')
 escapesre = re.compile(r'[][\\()"]')
@@ -231,10 +232,14 @@
 def decode_rfc2231(s):
     """Decode string according to RFC 2231"""
     import urllib
-    parts = s.split("'", 2)
-    if len(parts) == 1:
+    parts = s.split(TICK, 2)
+    if len(parts) <= 2:
         return None, None, urllib.unquote(s)
-    charset, language, s = parts
+    if len(parts) > 3:
+        charset, language = parts[:2]
+        s = TICK.join(parts[2:])
+    else:
+        charset, language, s = parts
     return charset, language, urllib.unquote(s)