bpo-39040: Fix parsing of email mime headers with whitespace between encoded-words. (gh-17620)

* bpo-39040: Fix parsing of email headers with encoded-words inside a quoted string.

It is fairly common to find malformed mime headers (especially content-disposition
headers) where the parameter values, instead of being encoded to RFC
standards, are "encoded" by doing RFC 2047 "encoded word" encoding, and
then enclosing the whole thing in quotes.  The processing of these malformed
headers was incorrectly leaving the spaces between encoded words in the decoded
text (whitespace between adjacent encoded words is supposed to be stripped on
decoding).  This changeset fixes the encoded word processing inside quoted strings
(bare-quoted-string) to do correct RFC 2047 decoding by stripping that
whitespace.

3 files changed, 30 insertions, 0 deletions

diff --git a/Lib/email/_header_value_parser.py b/Lib/email/_header_value_parser.py
index 9c55ef7..51d355f 100644
--- a/Lib/email/_header_value_parser.py
+++ b/Lib/email/_header_value_parser.py
@@ -1218,12 +1218,21 @@ def get_bare_quoted_string(value):
         if value[0] in WSP:
             token, value = get_fws(value)
         elif value[:2] == '=?':
+            valid_ew = False
             try:
                 token, value = get_encoded_word(value)
                 bare_quoted_string.defects.append(errors.InvalidHeaderDefect(
                     "encoded word inside quoted string"))
+                valid_ew = True
             except errors.HeaderParseError:
                 token, value = get_qcontent(value)
+            # Collapse the whitespace between two encoded words that occur in a
+            # bare-quoted-string.
+            if valid_ew and len(bare_quoted_string) > 1:
+                if (bare_quoted_string[-1].token_type == 'fws' and
+                        bare_quoted_string[-2].token_type == 'encoded-word'):
+                    bare_quoted_string[-1] = EWWhiteSpaceTerminal(
+                        bare_quoted_string[-1], 'fws')
         else:
             token, value = get_qcontent(value)
         bare_quoted_string.append(token)
diff --git a/Lib/test/test_email/test_headerregistry.py b/Lib/test/test_email/test_headerregistry.py
index 82e1213..68bbc95 100644
--- a/Lib/test/test_email/test_headerregistry.py
+++ b/Lib/test/test_email/test_headerregistry.py
@@ -873,6 +873,25 @@ class TestContentDisposition(TestHeaderBase):
             {'filename': 'foo'},
             [errors.InvalidHeaderDefect]),
 
+        'invalid_parameter_value_with_fws_between_ew': (
+            'attachment; filename="=?UTF-8?Q?Schulbesuchsbest=C3=A4ttigung=2E?='
+            '               =?UTF-8?Q?pdf?="',
+            'attachment',
+            {'filename': 'Schulbesuchsbestättigung.pdf'},
+            [errors.InvalidHeaderDefect]*3,
+            ('attachment; filename="Schulbesuchsbestättigung.pdf"'),
+            ('Content-Disposition: attachment;\n'
+             ' filename*=utf-8\'\'Schulbesuchsbest%C3%A4ttigung.pdf\n'),
+            ),
+
+        'parameter_value_with_fws_between_tokens': (
+            'attachment; filename="File =?utf-8?q?Name?= With Spaces.pdf"',
+            'attachment',
+            {'filename': 'File Name With Spaces.pdf'},
+            [errors.InvalidHeaderDefect],
+            'attachment; filename="File Name With Spaces.pdf"',
+            ('Content-Disposition: attachment; filename="File Name With Spaces.pdf"\n'),
+            )
     }
 
 
diff --git a/Misc/NEWS.d/next/Library/2019-12-15-18-47-20.bpo-39040.tKa0Qs.rst b/Misc/NEWS.d/next/Library/2019-12-15-18-47-20.bpo-39040.tKa0Qs.rst
new file mode 100644
index 0000000..078bce2
--- /dev/null
+++ b/Misc/NEWS.d/next/Library/2019-12-15-18-47-20.bpo-39040.tKa0Qs.rst
@@ -0,0 +1,2 @@
+Fix parsing of invalid mime headers parameters by collapsing whitespace between
+encoded words in a bare-quote-string.