Ralf Schlatterbeck <r...@runtux.com> added the comment:
Attached please find a patch that
- keeps all spaces between non-encoded and encoded parts
- doesn't create spaces between non-encoded and encoded parts in case
these are already there or not needed (because they are non-ctext
characters of RFC822 like ')') in the methods "encode" and "__str__"
of class Header.
in all other cases spaces are still inserted, this keeps many tests
happy and probably won't break too much existing code.
I've re-read RFC2047 (and parts of 822) and now share your opinion that
it requires that encoded parts *must* be followed by a
'linear-white-space' if the following (or preceding) token is text or ctext.
(p.7 5. Use of encoded-words in message headers)
With the special-casing of ctext characters mentioned above,
roundtripping is now possible, so if you parse a normalized string
consisting of encoded and non-encoded parts, (even multiple) whitespace
is preserved.
I still think we should do it like everyone else and *not* automatically
insert whitespace at boundaries between encoded and non-encoded words,
even if the RFC requires it. Someone wanting to create headers
consisting of mixed encoded/non-encoded parts without whitespace must
know what to do anyway -- the previous implementation also didn't check
for all border cases.
I've *not yet* tested this against the email6 branch you mentioned.
Note that I didn't have to make the regex non-greedy, it already
was. I've just removed the whitespace at the end of the regex.
I've changed all the tests that test for removal of whitespace between
non-encoded and encoded parts. Obviously I've also changed a test that
relied on failing to parse adjacent encoded strings. But please look at
my changes of the tests.
The rfc2047 tests now all pass.
The patch also fixes issue1467619 "Header.decode_header eats up spaces"
Ralf
--
Dr. Ralf Schlatterbeck Tel: +43/2243/26465-16
Open Source Consulting www: http://www.runtux.com
Reichergasse 131, A-3411 Weidling email: off...@runtux.com
osAlliance member email: r...@osalliance.com
----------
Added file: http://bugs.python.org/file24133/python.patch3
_______________________________________
Python tracker <rep...@bugs.python.org>
<http://bugs.python.org/issue1079>
_______________________________________
diff -r 3609d32cec46 Lib/email/header.py
--- a/Lib/email/header.py Tue Jan 03 17:48:19 2012 +0100
+++ b/Lib/email/header.py Tue Jan 03 22:19:30 2012 +0100
@@ -40,7 +40,6 @@
\? # literal ?
(?P<encoded>.*?) # non-greedy up to the next ?= is the encoded string
\?= # literal ?=
- (?=[ \t]|$) # whitespace or the end of the string
''', re.VERBOSE | re.IGNORECASE | re.MULTILINE)
# Field name regexp, including trailing colon, but not separating whitespace,
@@ -86,8 +85,12 @@
words = []
for line in header.splitlines():
parts = ecre.split(line)
+ first = True
while parts:
- unencoded = parts.pop(0).strip()
+ unencoded = parts.pop(0)
+ if first:
+ unencoded = unencoded.lstrip()
+ first = False
if unencoded:
words.append((unencoded, None, None))
if parts:
@@ -95,6 +98,16 @@
encoding = parts.pop(0).lower()
encoded = parts.pop(0)
words.append((encoded, encoding, charset))
+ # Now loop over words and remove words that consist of whitespace
+ # between two encoded strings.
+ import sys
+ droplist = []
+ for n, w in enumerate(words):
+ if n>1 and w[1] and words[n-2][1] and words[n-1][0].isspace():
+ droplist.append(n-1)
+ for d in reversed(droplist):
+ del words[d]
+
# The next step is to decode each encoded word by applying the reverse
# base64 or quopri transformation. decoded_words is now a list of the
# form (decoded_word, charset).
@@ -217,22 +230,27 @@
self._normalize()
uchunks = []
lastcs = None
+ lastspace = None
for string, charset in self._chunks:
# We must preserve spaces between encoded and non-encoded word
# boundaries, which means for us we need to add a space when we go
# from a charset to None/us-ascii, or from None/us-ascii to a
# charset. Only do this for the second and subsequent chunks.
+ # Don't add a space if the None/us-ascii string already has
+ # a space (trailing or leading depending on transition)
nextcs = charset
if nextcs == _charset.UNKNOWN8BIT:
original_bytes = string.encode('ascii', 'surrogateescape')
string = original_bytes.decode('ascii', 'replace')
if uchunks:
+ hasspace = string and self._nonctext(string[0])
if lastcs not in (None, 'us-ascii'):
- if nextcs in (None, 'us-ascii'):
+ if nextcs in (None, 'us-ascii') and not hasspace:
uchunks.append(SPACE)
nextcs = None
- elif nextcs not in (None, 'us-ascii'):
+ elif nextcs not in (None, 'us-ascii') and not lastspace:
uchunks.append(SPACE)
+ lastspace = string and self._nonctext(string[-1])
lastcs = nextcs
uchunks.append(string)
return EMPTYSTRING.join(uchunks)
@@ -286,6 +304,11 @@
s.encode(output_charset, errors)
self._chunks.append((s, charset))
+ def _nonctext(self, s):
+ """True if string s is not a ctext character of RFC822.
+ """
+ return s.isspace() or s in ('(', ')', '\\')
+
def encode(self, splitchars=';, \t', maxlinelen=None, linesep='\n'):
r"""Encode a message header into an RFC-compliant format.
@@ -329,7 +352,20 @@
maxlinelen = 1000000
formatter = _ValueFormatter(self._headerlen, maxlinelen,
self._continuation_ws, splitchars)
+ lastcs = None
+ hasspace = lastspace = None
for string, charset in self._chunks:
+ if hasspace is not None:
+ hasspace = string and self._nonctext(string[0])
+ import sys
+ if lastcs not in (None, 'us-ascii'):
+ if not hasspace or charset not in (None, 'us-ascii'):
+ formatter.add_transition()
+ elif charset not in (None, 'us-ascii') and not lastspace:
+ formatter.add_transition()
+ lastspace = string and self._nonctext(string[-1])
+ lastcs = charset
+ hasspace = False
lines = string.splitlines()
if lines:
formatter.feed('', lines[0], charset)
@@ -346,6 +382,7 @@
formatter.feed(fws, sline, charset)
if len(lines) > 1:
formatter.newline()
+ if self._chunks:
formatter.add_transition()
value = formatter._str(linesep)
if _embeded_header.search(value):
diff -r 3609d32cec46 Lib/test/test_email/test_asian_codecs.py
--- a/Lib/test/test_email/test_asian_codecs.py Tue Jan 03 17:48:19 2012 +0100
+++ b/Lib/test/test_email/test_asian_codecs.py Tue Jan 03 22:19:30 2012 +0100
@@ -41,7 +41,7 @@
Hello World! =?iso-2022-jp?b?GyRCJU8lbSE8JW8hPCVrJUkhKhsoQg==?=
=?iso-8859-1?q?Gr=FC=DF_Gott!?=""")
eq(decode_header(h.encode()),
- [(b'Hello World!', None),
+ [(b'Hello World! ', None),
(b'\x1b$B%O%m!<%o!<%k%I!*\x1b(B', 'iso-2022-jp'),
(b'Gr\xfc\xdf Gott!', gcode)])
subject_bytes = (b'test-ja \xa4\xd8\xc5\xea\xb9\xc6\xa4\xb5'
diff -r 3609d32cec46 Lib/test/test_email/test_email.py
--- a/Lib/test/test_email/test_email.py Tue Jan 03 17:48:19 2012 +0100
+++ b/Lib/test/test_email/test_email.py Tue Jan 03 22:19:30 2012 +0100
@@ -1999,9 +1999,9 @@
foo bar =?mac-iceland?q?r=8Aksm=9Arg=8Cs?="""
dh = decode_header(s)
eq(dh, [
- (b'Re:', None),
+ (b'Re: ', None),
(b'r\x8aksm\x9arg\x8cs', 'mac-iceland'),
- (b'baz foo bar', None),
+ (b' baz foo bar ', None),
(b'r\x8aksm\x9arg\x8cs', 'mac-iceland')])
header = make_header(dh)
eq(str(header),
@@ -2010,36 +2010,38 @@
Re: =?mac-iceland?q?r=8Aksm=9Arg=8Cs?= baz foo bar =?mac-iceland?q?r=8Aksm?=
=?mac-iceland?q?=9Arg=8Cs?=""")
- def test_whitespace_eater_unicode(self):
+ def test_whitespace_keeper_unicode(self):
eq = self.assertEqual
s = '=?ISO-8859-1?Q?Andr=E9?= Pirard <pir...@dom.ain>'
dh = decode_header(s)
eq(dh, [(b'Andr\xe9', 'iso-8859-1'),
- (b'Pirard <pir...@dom.ain>', None)])
+ (b' Pirard <pir...@dom.ain>', None)])
header = str(make_header(dh))
eq(header, 'Andr\xe9 Pirard <pir...@dom.ain>')
- def test_whitespace_eater_unicode_2(self):
+ def test_whitespace_keeper_unicode_2(self):
eq = self.assertEqual
s = 'The =?iso-8859-1?b?cXVpY2sgYnJvd24gZm94?= jumped over the
=?iso-8859-1?b?bGF6eSBkb2c=?='
dh = decode_header(s)
- eq(dh, [(b'The', None), (b'quick brown fox', 'iso-8859-1'),
- (b'jumped over the', None), (b'lazy dog', 'iso-8859-1')])
+ eq(dh, [(b'The ', None), (b'quick brown fox', 'iso-8859-1'),
+ (b' jumped over the ', None), (b'lazy dog', 'iso-8859-1')])
hu = str(make_header(dh))
eq(hu, 'The quick brown fox jumped over the lazy dog')
def test_rfc2047_missing_whitespace(self):
s = 'Sm=?ISO-8859-1?B?9g==?=rg=?ISO-8859-1?B?5Q==?=sbord'
dh = decode_header(s)
- self.assertEqual(dh, [(s, None)])
-
- def test_rfc2047_with_whitespace(self):
- s = 'Sm =?ISO-8859-1?B?9g==?= rg =?ISO-8859-1?B?5Q==?= sbord'
- dh = decode_header(s)
self.assertEqual(dh, [(b'Sm', None), (b'\xf6', 'iso-8859-1'),
(b'rg', None), (b'\xe5', 'iso-8859-1'),
(b'sbord', None)])
+ def test_rfc2047_with_whitespace(self):
+ s = 'Sm =?ISO-8859-1?B?9g==?= rg =?ISO-8859-1?B?5Q==?= sbord'
+ dh = decode_header(s)
+ self.assertEqual(dh, [(b'Sm ', None), (b'\xf6', 'iso-8859-1'),
+ (b' rg ', None), (b'\xe5', 'iso-8859-1'),
+ (b' sbord', None)])
+
def test_rfc2047_B_bad_padding(self):
s = '=?iso-8859-1?B?%s?='
data = [ # only test complete bytes
@@ -2056,62 +2058,56 @@
self.assertEqual(decode_header(s),
[(b'andr\xe9=zz', 'iso-8659-1')])
- @unittest.expectedFailure
def test_rfc2047_rfc2047_1(self):
# 1st testcase at end of rfc2047
s = '(=?ISO-8859-1?Q?a?=)'
self.assertEqual(decode_header(s),
[(b'(', None), (b'a', 'iso-8859-1'), (b')', None)])
- @unittest.expectedFailure
def test_rfc2047_rfc2047_2(self):
# 2nd testcase at end of rfc2047
s = '(=?ISO-8859-1?Q?a?= b)'
self.assertEqual(decode_header(s),
[(b'(', None), (b'a', 'iso-8859-1'), (b' b)', None)])
- @unittest.expectedFailure
def test_rfc2047_rfc2047_3(self):
# 3rd testcase at end of rfc2047
s = '(=?ISO-8859-1?Q?a?= =?ISO-8859-1?Q?b?=)'
self.assertEqual(decode_header(s),
[(b'(', None), (b'ab', 'iso-8859-1'), (b')', None)])
- @unittest.expectedFailure
def test_rfc2047_rfc2047_4(self):
# 4th testcase at end of rfc2047
s = '(=?ISO-8859-1?Q?a?= =?ISO-8859-1?Q?b?=)'
self.assertEqual(decode_header(s),
[(b'(', None), (b'ab', 'iso-8859-1'), (b')', None)])
- @unittest.expectedFailure
def test_rfc2047_rfc2047_5a(self):
# 5th testcase at end of rfc2047 newline is \r\n
s = '(=?ISO-8859-1?Q?a?=\r\n =?ISO-8859-1?Q?b?=)'
self.assertEqual(decode_header(s),
[(b'(', None), (b'ab', 'iso-8859-1'), (b')', None)])
- @unittest.expectedFailure
def test_rfc2047_rfc2047_5b(self):
# 5th testcase at end of rfc2047 newline is \n
s = '(=?ISO-8859-1?Q?a?=\n =?ISO-8859-1?Q?b?=)'
self.assertEqual(decode_header(s),
[(b'(', None), (b'ab', 'iso-8859-1'), (b')', None)])
- @unittest.expectedFailure
def test_rfc2047_rfc2047_6(self):
# 6th testcase at end of rfc2047
s = '(=?ISO-8859-1?Q?a_b?=)'
self.assertEqual(decode_header(s),
[(b'(', None), (b'a b', 'iso-8859-1'), (b')', None)])
- @unittest.expectedFailure
def test_rfc2047_rfc2047_7(self):
# 7th testcase at end of rfc2047
s = '(=?ISO-8859-1?Q?a?= =?ISO-8859-2?Q?_b?=)'
self.assertEqual(decode_header(s),
[(b'(', None), (b'a', 'iso-8859-1'), (b' b', 'iso-8859-2'),
(b')', None)])
+ self.assertEqual(make_header(decode_header(s)).encode(), s.lower())
+ self.assertEqual(str(make_header(decode_header(s))), '(a b)')
# Test the MIMEMessage class
@@ -4463,11 +4459,11 @@
h = make_header(decode_header(s))
eq(h.encode(), s)
- def test_whitespace_eater(self):
+ def test_whitespace_keeper(self):
eq = self.assertEqual
s = 'Subject: =?koi8-r?b?8NLP18XSy8EgzsEgxsnOwczYztk=?=
=?koi8-r?q?=CA?= zz.'
parts = decode_header(s)
- eq(parts, [(b'Subject:', None), (b'\xf0\xd2\xcf\xd7\xc5\xd2\xcb\xc1
\xce\xc1 \xc6\xc9\xce\xc1\xcc\xd8\xce\xd9\xca', 'koi8-r'), (b'zz.', None)])
+ eq(parts, [(b'Subject: ', None), (b'\xf0\xd2\xcf\xd7\xc5\xd2\xcb\xc1
\xce\xc1 \xc6\xc9\xce\xc1\xcc\xd8\xce\xd9\xca', 'koi8-r'), (b' zz.', None)])
hdr = make_header(parts)
eq(hdr.encode(),
'Subject: =?koi8-r?b?8NLP18XSy8EgzsEgxsnOwczYztnK?= zz.')
_______________________________________________
Python-bugs-list mailing list
Unsubscribe:
http://mail.python.org/mailman/options/python-bugs-list/archive%40mail-archive.com
