From 041015cc70465c8a008d4ef45ffe3fe05041fad2 Mon Sep 17 00:00:00 2001 From: R David Murray Date: Fri, 25 Mar 2011 15:10:55 -0400 Subject: [PATCH] #11584: Since __getitem__ returns headers, make decode_header handle them. Why I consider this a bug rather than an API change: the API change was to Message, which didn't used to return Headers unless you added them yourself. Now it does (for 8bit binary header input), so decode_header needs to be able to handle them. --- Lib/email/header.py | 6 ++++++ Lib/email/test/test_email.py | 14 ++++++++++++++ 2 files changed, 20 insertions(+) diff --git a/Lib/email/header.py b/Lib/email/header.py index 8c325145aa8..2562b30c167 100644 --- a/Lib/email/header.py +++ b/Lib/email/header.py @@ -66,9 +66,15 @@ def decode_header(header): otherwise a lower-case string containing the name of the character set specified in the encoded string. + header may be a string that may or may not contain RFC2047 encoded words, + or it may be a Header object. + An email.errors.HeaderParseError may be raised when certain decoding error occurs (e.g. a base64 decoding exception). """ + # If it is a Header object, we can just return the chunks. + if hasattr(header, '_chunks'): + return list(header._chunks) # If no encoding, just return the header with no charset. if not ecre.search(header): return [(header, None)] diff --git a/Lib/email/test/test_email.py b/Lib/email/test/test_email.py index 250a6442b72..245f65999b5 100644 --- a/Lib/email/test/test_email.py +++ b/Lib/email/test/test_email.py @@ -3918,6 +3918,20 @@ A very long line that must get split to something other than at the h.append(x, errors='replace') eq(str(h), e) + def test_escaped_8bit_header(self): + x = b'Ynwp4dUEbay Auction Semiar- No Charge \x96 Earn Big' + x = x.decode('ascii', 'surrogateescape') + h = Header(x, charset=email.charset.UNKNOWN8BIT) + self.assertEqual(str(h), + 'Ynwp4dUEbay Auction Semiar- No Charge \uFFFD Earn Big') + self.assertEqual(email.header.decode_header(h), [(x, 'unknown-8bit')]) + + def test_modify_returned_list_does_not_change_header(self): + h = Header('test') + chunks = email.header.decode_header(h) + chunks.append(('ascii', 'test2')) + self.assertEqual(str(h), 'test') + def test_encoded_adjacent_nonencoded(self): eq = self.assertEqual h = Header()