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

Lib/email/_header_value_parser.py

@@ -1218,12 +1218,23 @@ 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)

Lib/test/test_email/test_headerregistry.py

@@ -873,6 +873,16 @@ def content_disp_as_value(self,
  {'filename': 'foo'},
  [errors.InvalidHeaderDefect]),
 
+ 'invalid_value_with_fws_bw_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'),
+ )
  }
 
 

Misc/NEWS.d/next/Library/2019-12-15-18-47-20.bpo-39040.tKa0Qs.rst

@@ -0,0 +1,2 @@
+Fix parsing of invalid Content-Disposition email headers by collapsing
+whitespace between encoded words in a bare-quote-string.