handle headers with no key (closes #19996)

Patch by Cory Benfield.

diff --git a/Lib/email/feedparser.py b/Lib/email/feedparser.py
index 0c3b572684f432e1560f34ba31f0b5f5171177ca..c95b27f12f3131376dc41b410f7fe6dd02594d66 100644 (file)
--- a/Lib/email/feedparser.py
+++ b/Lib/email/feedparser.py
@@ -33,7 +33,7 @@ NLCRE_eol = re.compile('(\r\n|\r|\n)\Z')
 NLCRE_crack = re.compile('(\r\n|\r|\n)')
 # RFC 2822 $3.6.8 Optional fields.  ftext is %d33-57 / %d59-126, Any character
 # except controls, SP, and ":".
-headerRE = re.compile(r'^(From |[\041-\071\073-\176]{1,}:|[\t ])')
+headerRE = re.compile(r'^(From |[\041-\071\073-\176]*:|[\t ])')
 EMPTYSTRING = ''
 NL = '\n'
 
@@ -511,6 +511,15 @@ class FeedParser:
             # There will always be a colon, because if there wasn't the part of
             # the parser that calls us would have started parsing the body.
             i = line.find(':')
+
+            # If the colon is on the start of the line the header is clearly
+            # malformed, but we might be able to salvage the rest of the
+            # message. Track the error but keep going.
+            if i == 0:
+                defect = errors.InvalidHeaderDefect("Missing header name.")
+                self._cur.defects.append(defect)
+                continue
+
             assert i>0, "_parse_headers fed line with no : and no leading WS"
             lastheader = line[:i]
             lastvalue = [line]

diff --git a/Lib/test/test_email/test_email.py b/Lib/test/test_email/test_email.py
index c3ecd0ab2217d9df50b929d91e8a2c05e815aa84..227110ffb11513e374619dd93014818b0f951b94 100644 (file)
--- a/Lib/test/test_email/test_email.py
+++ b/Lib/test/test_email/test_email.py
@@ -3389,6 +3389,12 @@ class TestFeedParsers(TestEmailBase):
             feedparser.feed(chunk)
         return feedparser.close()
 
+    def test_empty_header_name_handled(self):
+        # Issue 19996
+        msg = self.parse("First: val\n: bad\nSecond: val")
+        self.assertEqual(msg['First'], 'val')
+        self.assertEqual(msg['Second'], 'val')
+
     def test_newlines(self):
         m = self.parse(['a:\nb:\rc:\r\nd:\n'])
         self.assertEqual(m.keys(), ['a', 'b', 'c', 'd'])

diff --git a/Lib/test/test_httplib.py b/Lib/test/test_httplib.py
index fa962b36692d19eeb66f5119c935d60d5f4354c4..3fc34665da4047b9e46b5d50762e2cdc8c41e144 100644 (file)
--- a/Lib/test/test_httplib.py
+++ b/Lib/test/test_httplib.py
@@ -167,6 +167,16 @@ class HeaderTests(TestCase):
         conn.request('GET', '/foo')
         self.assertTrue(sock.data.startswith(expected))
 
+    def test_malformed_headers_coped_with(self):
+        # Issue 19996
+        body = "HTTP/1.1 200 OK\r\nFirst: val\r\n: nval\r\nSecond: val\r\n\r\n"
+        sock = FakeSocket(body)
+        resp = client.HTTPResponse(sock)
+        resp.begin()
+
+        self.assertEqual(resp.getheader('First'), 'val')
+        self.assertEqual(resp.getheader('Second'), 'val')
+
 
 class BasicTest(TestCase):
     def test_status_lines(self):

diff --git a/Misc/NEWS b/Misc/NEWS
index 4c4db0f9b0b25e11330add530bf8216a1084bc41..06df4db08b5d86d1426ce4fcb4e9791c5c27e0f0 100644 (file)
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -47,6 +47,9 @@ Core and Builtins
 Library
 -------
 
+- Issue #19996: :class:`email.feedparser.FeedParser` now handles (malformed)
+  headers with no key rather than amusing the body has started.
+
 - Issue #23248: Update ssl error codes from latest OpenSSL git master.
 
 - Issue #23098: 64-bit dev_t is now supported in the os module.