Merged revisions 87873 via svnmerge from

svn+ssh://pythondev@svn.python.org/python/branches/py3k

........
  r87873 | r.david.murray | 2011-01-08 21:35:24 -0500 (Sat, 08 Jan 2011) | 12 lines

  #5871: protect against header injection attacks.

  This makes Header.encode throw a HeaderParseError if it winds up
  formatting a header such that a continuation line has no leading
  whitespace and looks like a header.  Since Header accepts values
  containing newlines and preserves them (and this is by design), without
  this fix any program that took user input (say, a subject in a web form)
  and passed it to the email package as a header was vulnerable to header
  injection attacks.  (As far as we know this has never been exploited.)

  Thanks to Jakub Wilk for reporting this vulnerability.
........

3 files changed, 27 insertions, 1 deletions

diff --git a/Lib/email/header.py b/Lib/email/header.py
index 9e91dc2..702adf1 100644
--- a/Lib/email/header.py
+++ b/Lib/email/header.py
@@ -47,6 +47,10 @@ ecre = re.compile(r'''
 # For use with .match()
 fcre = re.compile(r'[\041-\176]+:$')
 
+# Find a header embeded in a putative header value.  Used to check for
+# header injection attack.
+_embeded_header = re.compile(r'\n[^ \t]+:')
+
 
 
 # Helpers
@@ -403,7 +407,11 @@ class Header:
             newchunks += self._split(s, charset, targetlen, splitchars)
             lastchunk, lastcharset = newchunks[-1]
             lastlen = lastcharset.encoded_header_len(lastchunk)
-        return self._encode_chunks(newchunks, maxlinelen)
+        value = self._encode_chunks(newchunks, maxlinelen)
+        if _embeded_header.search(value):
+            raise HeaderParseError("header value appears to contain "
+                "an embedded header: {!r}".format(value))
+        return value
 
 
 
diff --git a/Lib/email/test/test_email.py b/Lib/email/test/test_email.py
index 4aac500..5c9a725 100644
--- a/Lib/email/test/test_email.py
+++ b/Lib/email/test/test_email.py
@@ -553,6 +553,17 @@ class TestMessageAPI(TestEmailBase):
         msg.set_charset(u'us-ascii')
         self.assertEqual('us-ascii', msg.get_content_charset())
 
+    # Issue 5871: reject an attempt to embed a header inside a header value
+    # (header injection attack).
+    def test_embeded_header_via_Header_rejected(self):
+        msg = Message()
+        msg['Dummy'] = Header('dummy\nX-Injected-Header: test')
+        self.assertRaises(Errors.HeaderParseError, msg.as_string)
+
+    def test_embeded_header_via_string_rejected(self):
+        msg = Message()
+        msg['Dummy'] = 'dummy\nX-Injected-Header: test'
+        self.assertRaises(Errors.HeaderParseError, msg.as_string)
 
 
 # Test the email.Encoders module
diff --git a/Misc/NEWS b/Misc/NEWS
index e436278..0c53aef 100644
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -36,6 +36,13 @@ Library
   dependent, but ``time.mktime`` will now accept full range supported
   by the OS.  Conversion of 2-digit years to 4-digit is deprecated.
 
+- Issue #10827: Changed the rules for 2-digit years.  The time.asctime
+  function will now format any year when ``time.accept2dyear`` is
+  false and will accept years >= 1000 otherwise.  The year range
+  accepted by ``time.mktime`` and ``time.strftime`` is still system
+  dependent, but ``time.mktime`` will now accept full range supported
+  by the OS.  Conversion of 2-digit years to 4-digit is deprecated.
+
 - Issue #7858: Raise an error properly when os.utime() fails under Windows
   on an existing file.