summaryrefslogtreecommitdiffstats
path: root/Lib
diff options
context:
space:
mode:
authorR. David Murray <rdmurray@bitdance.com>2011-01-07 21:57:25 (GMT)
committerR. David Murray <rdmurray@bitdance.com>2011-01-07 21:57:25 (GMT)
commit6f0022d84af15d51ffa1606991f2b6e9e56448ed (patch)
treea47fdc84c7487741c7f07b3612f96e70facd677f /Lib
parent7088abdca6c3e1285c66f51fe907e6c3446773ed (diff)
downloadcpython-6f0022d84af15d51ffa1606991f2b6e9e56448ed.zip
cpython-6f0022d84af15d51ffa1606991f2b6e9e56448ed.tar.gz
cpython-6f0022d84af15d51ffa1606991f2b6e9e56448ed.tar.bz2
Fix formatting of values with embedded newlines when rfc2047 encoding
Before this patch if a value being encoded had an embedded newline, the line following the newline would have no leading whitespace, and the whitespace it did have was encoded into the word. Now the existing whitespace gets turned into a blank, the way it does in other header reformatting, and the _continuation_ws gets added at the beginning of the encoded line.
Diffstat (limited to 'Lib')
-rw-r--r--Lib/email/header.py11
-rw-r--r--Lib/email/test/test_email.py13
2 files changed, 21 insertions, 3 deletions
diff --git a/Lib/email/header.py b/Lib/email/header.py
index 94eb1a9..d462bf0 100644
--- a/Lib/email/header.py
+++ b/Lib/email/header.py
@@ -305,10 +305,15 @@ class Header:
self._continuation_ws, splitchars)
for string, charset in self._chunks:
lines = string.splitlines()
- for line in lines:
+ formatter.feed(lines[0], charset)
+ for line in lines[1:]:
+ formatter.newline()
+ if charset.header_encoding is not None:
+ formatter.feed(self._continuation_ws, USASCII)
+ line = ' ' + line.lstrip()
formatter.feed(line, charset)
- if len(lines) > 1:
- formatter.newline()
+ if len(lines) > 1:
+ formatter.newline()
formatter.add_transition()
return formatter._str(linesep)
diff --git a/Lib/email/test/test_email.py b/Lib/email/test/test_email.py
index e7fcee3..4855371 100644
--- a/Lib/email/test/test_email.py
+++ b/Lib/email/test/test_email.py
@@ -968,6 +968,19 @@ List: List-Unsubscribe: <http://lists.sourceforge.net/lists/listinfo/spamassassi
""")
+ def test_long_rfc2047_header_with_embedded_fws(self):
+ h = Header(textwrap.dedent("""\
+ We're going to pretend this header is in a non-ascii character set
+ \tto see if line wrapping with encoded words and embedded
+ folding white space works"""),
+ charset='utf-8',
+ header_name='Test')
+ self.assertEqual(h.encode()+'\n', textwrap.dedent("""\
+ =?utf-8?q?We=27re_going_to_pretend_this_header_is_in_a_non-ascii_chara?=
+ =?utf-8?q?cter_set?=
+ =?utf-8?q?_to_see_if_line_wrapping_with_encoded_words_and_embedded?=
+ =?utf-8?q?_folding_white_space_works?=""")+'\n')
+
# Test mangling of "From " lines in the body of a message