diff options
Diffstat (limited to 'Lib/email')
| -rw-r--r-- | Lib/email/_header_value_parser.py | 19 |
1 files changed, 16 insertions, 3 deletions
diff --git a/Lib/email/_header_value_parser.py b/Lib/email/_header_value_parser.py index b500394..16c1990 100644 --- a/Lib/email/_header_value_parser.py +++ b/Lib/email/_header_value_parser.py @@ -935,6 +935,10 @@ class EWWhiteSpaceTerminal(WhiteSpaceTerminal): return '' +class _InvalidEwError(errors.HeaderParseError): + """Invalid encoded word found while parsing headers.""" + + # XXX these need to become classes and used as instances so # that a program can't change them in a parse tree and screw # up other parse trees. Maybe should have tests for that, too. @@ -1039,7 +1043,10 @@ def get_encoded_word(value): raise errors.HeaderParseError( "expected encoded word but found {}".format(value)) remstr = ''.join(remainder) - if len(remstr) > 1 and remstr[0] in hexdigits and remstr[1] in hexdigits: + if (len(remstr) > 1 and + remstr[0] in hexdigits and + remstr[1] in hexdigits and + tok.count('?') < 2): # The ? after the CTE was followed by an encoded word escape (=XX). rest, *remainder = remstr.split('?=', 1) tok = tok + '?=' + rest @@ -1051,7 +1058,7 @@ def get_encoded_word(value): try: text, charset, lang, defects = _ew.decode('=?' + tok + '?=') except ValueError: - raise errors.HeaderParseError( + raise _InvalidEwError( "encoded word format invalid: '{}'".format(ew.cte)) ew.charset = charset ew.lang = lang @@ -1101,9 +1108,12 @@ def get_unstructured(value): token, value = get_fws(value) unstructured.append(token) continue + valid_ew = True if value.startswith('=?'): try: token, value = get_encoded_word(value) + except _InvalidEwError: + valid_ew = False except errors.HeaderParseError: # XXX: Need to figure out how to register defects when # appropriate here. @@ -1125,7 +1135,10 @@ def get_unstructured(value): # Split in the middle of an atom if there is a rfc2047 encoded word # which does not have WSP on both sides. The defect will be registered # the next time through the loop. - if rfc2047_matcher.search(tok): + # This needs to only be performed when the encoded word is valid; + # otherwise, performing it on an invalid encoded word can cause + # the parser to go in an infinite loop. + if valid_ew and rfc2047_matcher.search(tok): tok, *remainder = value.partition('=?') vtext = ValueTerminal(tok, 'vtext') _validate_xtext(vtext) |