diff options
author | Barry Warsaw <barry@python.org> | 2007-08-31 02:35:00 (GMT) |
---|---|---|
committer | Barry Warsaw <barry@python.org> | 2007-08-31 02:35:00 (GMT) |
commit | 00b34228bb98c378286c0b72a4a4098d5cdd384b (patch) | |
tree | e996cb33cd375a65960df6d5937dbea149f38fca /Lib | |
parent | 3bcc42ad0f18a97ecabb6bb8e645b88d23592a03 (diff) | |
download | cpython-00b34228bb98c378286c0b72a4a4098d5cdd384b.zip cpython-00b34228bb98c378286c0b72a4a4098d5cdd384b.tar.gz cpython-00b34228bb98c378286c0b72a4a4098d5cdd384b.tar.bz2 |
More email package fixes.
This repairs the linear whitespace insertion between RFC 2047 encoded words
without leaving bogus trailing spaces at the end lines that end in encoded
words.
Current status: 7F/9E
Diffstat (limited to 'Lib')
-rw-r--r-- | Lib/email/header.py | 28 | ||||
-rw-r--r-- | Lib/email/test/test_email.py | 2 |
2 files changed, 16 insertions, 14 deletions
diff --git a/Lib/email/header.py b/Lib/email/header.py index 786a71f..cc6b278 100644 --- a/Lib/email/header.py +++ b/Lib/email/header.py @@ -29,7 +29,6 @@ MAXLINELEN = 78 USASCII = Charset('us-ascii') UTF8 = Charset('utf-8') -TRANSITIONAL_SPACE = object() # Match encoded-word strings in the form =?charset?q?Hello_World?= ecre = re.compile(r''' @@ -309,6 +308,7 @@ class Header: formatter.feed(line, charset) if len(lines) > 1: formatter.newline() + formatter.add_transition() return str(formatter) def _normalize(self): @@ -341,19 +341,20 @@ class _ValueFormatter: self._current_line = _Accumulator(headerlen) def __str__(self): - # Remove any trailing TRANSITIONAL_SPACE - if len(self._current_line) > 0: - last_line = self._current_line.pop() - if last_line is not TRANSITIONAL_SPACE: - self._current_line.push(last_line) self.newline() return NL.join(self._lines) def newline(self): + end_of_line = self._current_line.pop() + if end_of_line is not None: + self._current_line.push(end_of_line) if len(self._current_line) > 0: self._lines.append(str(self._current_line)) self._current_line.reset() + def add_transition(self): + self._current_line.push(None) + def feed(self, string, charset): # If the string itself fits on the current line in its encoded format, # then add it now and be done with it. @@ -408,7 +409,6 @@ class _ValueFormatter: # There was only one line. return self._current_line.push(last_line) - self._current_line.push(TRANSITIONAL_SPACE) # Everything else are full lines in themselves. for line in encoded_lines: self._lines.append(self._continuation_ws + line) @@ -554,18 +554,20 @@ class _Accumulator: self._current.append(string) def pop(self): + if not self._current: + return None return self._current.pop() def __len__(self): - return sum((len(string) - for string in self._current - if string is not TRANSITIONAL_SPACE), + return sum(((1 if string is None else len(string)) + for string in self._current), self._initial_size) def __str__(self): - return EMPTYSTRING.join( - (' ' if string is TRANSITIONAL_SPACE else string) - for string in self._current) + if self._current and self._current[-1] is None: + self._current.pop() + return EMPTYSTRING.join((' ' if string is None else string) + for string in self._current) def reset(self, string=None): self._current = [] diff --git a/Lib/email/test/test_email.py b/Lib/email/test/test_email.py index 324332b..ef11e17 100644 --- a/Lib/email/test/test_email.py +++ b/Lib/email/test/test_email.py @@ -1556,7 +1556,7 @@ class TestRFC2047(TestEmailBase): header = make_header(dh) eq(str(header), 'Re: r\xe4ksm\xf6rg\xe5s baz foo bar r\xe4ksm\xf6rg\xe5s') - self.ndiffAssertEqual(header.encode(), """\ + self.ndiffAssertEqual(header.encode(maxlinelen=76), """\ Re: =?mac-iceland?q?r=8Aksm=9Arg=8Cs?= baz foo bar =?mac-iceland?q?r=8Aksm?= =?mac-iceland?q?=9Arg=8Cs?=""") |