Update of /cvsroot/tmda/tmda/TMDA/pythonlib/email
In directory usw-pr-cvs1:/tmp/cvs-serv13083
Modified Files:
Charset.py Message.py Parser.py __init__.py
Log Message:
Sync TMDA/pythonlib/email with email v2.4.2, which contains some
very important bugfixes.
Index: Charset.py
===================================================================
RCS file: /cvsroot/tmda/tmda/TMDA/pythonlib/email/Charset.py,v
retrieving revision 1.2
retrieving revision 1.3
diff -u -r1.2 -r1.3
--- Charset.py 1 Oct 2002 20:06:22 -0000 1.2
+++ Charset.py 10 Oct 2002 17:27:35 -0000 1.3
@@ -177,13 +177,15 @@
this attribute will have the same value as the input_codec.
"""
def __init__(self, input_charset=DEFAULT_CHARSET):
+ # RFC 2046, $4.1.2 says charsets are not case sensitive
+ input_charset = input_charset.lower()
# Set the input charset after filtering through the aliases
self.input_charset = ALIASES.get(input_charset, input_charset)
# We can try to guess which encoding and conversion to use by the
# charset_map dictionary. Try that first, but let the user override
# it.
henc, benc, conv = CHARSETS.get(self.input_charset,
- (SHORTEST, SHORTEST, None))
+ (SHORTEST, BASE64, None))
# Set the attributes, allowing the arguments to override the default.
self.header_encoding = henc
self.body_encoding = benc
Index: Message.py
===================================================================
RCS file: /cvsroot/tmda/tmda/TMDA/pythonlib/email/Message.py,v
retrieving revision 1.2
retrieving revision 1.3
diff -u -r1.2 -r1.3
--- Message.py 1 Oct 2002 20:06:22 -0000 1.2
+++ Message.py 10 Oct 2002 17:27:35 -0000 1.3
@@ -760,8 +760,9 @@
def get_content_charset(self, failobj=None):
"""Return the charset parameter of the Content-Type header.
- If there is no Content-Type header, or if that header has no charset
- parameter, failobj is returned.
+ The returned string is always coerced to lower case. If there is no
+ Content-Type header, or if that header has no charset parameter,
+ failobj is returned.
"""
missing = []
charset = self.get_param('charset', missing)
@@ -769,8 +770,9 @@
return failobj
if isinstance(charset, TupleType):
# RFC 2231 encoded, so decode it, and it better end up as ascii.
- return unicode(charset[2], charset[0]).encode('us-ascii')
- return charset
+ charset = unicode(charset[2], charset[0]).encode('us-ascii')
+ # RFC 2046, $4.1.2 says charsets are not case sensitive
+ return charset.lower()
def get_charsets(self, failobj=None):
"""Return a list containing the charset(s) used in this message.
Index: Parser.py
===================================================================
RCS file: /cvsroot/tmda/tmda/TMDA/pythonlib/email/Parser.py,v
retrieving revision 1.2
retrieving revision 1.3
diff -u -r1.2 -r1.3
--- Parser.py 1 Oct 2002 20:06:22 -0000 1.2
+++ Parser.py 10 Oct 2002 17:27:35 -0000 1.3
@@ -20,6 +20,8 @@
True = 1
False = 0
+nlcre = re.compile('\r\n|\r|\n')
+
class Parser:
@@ -137,7 +139,7 @@
# Parse the body, but first split the payload on the content-type
# boundary if present.
boundary = container.get_boundary()
- isdigest = (container.get_type() == 'multipart/digest')
+ isdigest = (container.get_content_type() == 'multipart/digest')
# If there's a boundary, split the payload text into its constituent
# parts and parse each separately. Otherwise, just parse the rest of
# the body as a single message. Note: any exceptions raised in the
@@ -167,8 +169,7 @@
preamble = payload[0:start]
# Find out what kind of line endings we're using
start += len(mo.group('sep')) + len(mo.group('ws'))
- cre = re.compile('\r\n|\r|\n')
- mo = cre.search(payload, start)
+ mo = nlcre.search(payload, start)
if mo:
start += len(mo.group(0))
# We create a compiled regexp first because we need to be able to
@@ -209,12 +210,12 @@
payload[start:terminator])
for part in parts:
if isdigest:
- if part[0] == linesep:
+ if part.startswith(linesep):
# There's no header block so create an empty message
# object as the container, and lop off the newline so
# we can parse the sub-subobject
msgobj = self._class()
- part = part[1:]
+ part = part[len(linesep):]
else:
parthdrs, part = part.split(linesep+linesep, 1)
# msgobj in this case is the "message/rfc822" container
Index: __init__.py
===================================================================
RCS file: /cvsroot/tmda/tmda/TMDA/pythonlib/email/__init__.py,v
retrieving revision 1.2
retrieving revision 1.3
diff -u -r1.2 -r1.3
--- __init__.py 1 Oct 2002 20:06:22 -0000 1.2
+++ __init__.py 10 Oct 2002 17:27:36 -0000 1.3
@@ -4,7 +4,7 @@
"""A package for parsing, handling, and generating email messages.
"""
-__version__ = '2.4'
+__version__ = '2.4.2'
__all__ = [
'base64MIME',
_______________________________________
tmda-cvs mailing list
http://tmda.net/lists/listinfo/tmda-cvs
