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.

1 files changed, 8 insertions, 3 deletions

diff --git a/Lib/email/utils.py b/Lib/email/utils.py
index 250eb19..ea59c27 100644
--- a/Lib/email/utils.py
+++ b/Lib/email/utils.py
@@ -45,6 +45,7 @@ COMMASPACE = ', '
 EMPTYSTRING = ''
 UEMPTYSTRING = u''
 CRLF = '\r\n'
+TICK = "'"
 
 specialsre = re.compile(r'[][\\()<>@,:;".]')
 escapesre = re.compile(r'[][\\()"]')
@@ -231,10 +232,14 @@ def unquote(str):
 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)