summaryrefslogtreecommitdiffstats
path: root/Lib/email
diff options
context:
space:
mode:
authorBarry Warsaw <barry@python.org>2002-09-26 17:19:34 (GMT)
committerBarry Warsaw <barry@python.org>2002-09-26 17:19:34 (GMT)
commit15aefa94d065cbb7408484ff98406cffd5002e2b (patch)
tree6aab24ba6555383e55ed566d72459d5be5769955 /Lib/email
parent9b1a80baf407e5a0bee40e28357d35e64263233e (diff)
downloadcpython-15aefa94d065cbb7408484ff98406cffd5002e2b.zip
cpython-15aefa94d065cbb7408484ff98406cffd5002e2b.tar.gz
cpython-15aefa94d065cbb7408484ff98406cffd5002e2b.tar.bz2
Fixing some RFC 2231 related issues as reported in the Spambayes
project, and with assistance from Oleg Broytmann. Specifically, get_param(), get_params(): Document that these methods may return parameter values that are either strings, or 3-tuples in the case of RFC 2231 encoded parameters. The application should be prepared to deal with such return values. get_boundary(): Be prepared to deal with RFC 2231 encoded boundary parameters. It makes little sense to have boundaries that are anything but ascii, so if we get back a 3-tuple from get_param() we will decode it into ascii and let any failures percolate up. get_content_charset(): New method which treats the charset parameter just like the boundary parameter in get_boundary(). Note that "get_charset()" was already taken to return the default Charset object. get_charsets(): Rewrite to use get_content_charset().
Diffstat (limited to 'Lib/email')
-rw-r--r--Lib/email/Message.py48
1 files changed, 39 insertions, 9 deletions
diff --git a/Lib/email/Message.py b/Lib/email/Message.py
index c018ae7..8bc82a6 100644
--- a/Lib/email/Message.py
+++ b/Lib/email/Message.py
@@ -53,7 +53,7 @@ def _formatparam(param, value=None, quote=1):
def _unquotevalue(value):
if isinstance(value, TupleType):
- return (value[0], value[1], Utils.unquote(value[2]))
+ return value[0], value[1], Utils.unquote(value[2])
else:
return Utils.unquote(value)
@@ -509,8 +509,8 @@ class Message:
The elements of the returned list are 2-tuples of key/value pairs, as
split on the `=' sign. The left hand side of the `=' is the key,
while the right hand side is the value. If there is no `=' sign in
- the parameter the value is the empty string. The value is always
- unquoted, unless unquote is set to a false value.
+ the parameter the value is the empty string. The value is as
+ described in the get_param() method.
Optional failobj is the object to return if there is no Content-Type:
header. Optional header is the header to search instead of
@@ -529,11 +529,23 @@ class Message:
"""Return the parameter value if found in the Content-Type: header.
Optional failobj is the object to return if there is no Content-Type:
- header. Optional header is the header to search instead of
- Content-Type:
-
- Parameter keys are always compared case insensitively. Values are
- always unquoted, unless unquote is set to a false value.
+ header, or the Content-Type header has no such parameter. Optional
+ header is the header to search instead of Content-Type:
+
+ Parameter keys are always compared case insensitively. The return
+ value can either be a string, or a 3-tuple if the parameter was RFC
+ 2231 encoded. When it's a 3-tuple, the elements of the value are of
+ the form (CHARSET, LANGUAGE, VALUE), where LANGUAGE may be the empty
+ string. Your application should be prepared to deal with these, and
+ can convert the parameter to a Unicode string like so:
+
+ param = msg.get_param('foo')
+ if isinstance(param, tuple):
+ param = unicode(param[2], param[0])
+
+ In any case, the parameter value (either the returned string, or the
+ VALUE item in the 3-tuple) is always unquoted, unless unquote is set
+ to a false value.
"""
if not self.has_key(header):
return failobj
@@ -674,6 +686,9 @@ class Message:
boundary = self.get_param('boundary', missing)
if boundary is missing:
return failobj
+ if isinstance(boundary, TupleType):
+ # RFC 2231 encoded, so decode. It better end up as ascii
+ return unicode(boundary[2], boundary[0]).encode('us-ascii')
return _unquotevalue(boundary.strip())
def set_boundary(self, boundary):
@@ -727,6 +742,21 @@ class Message:
# Must be using Python 2.1
from email._compat21 import walk
+ 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.
+ """
+ missing = []
+ charset = self.get_param('charset', missing)
+ if charset is missing:
+ 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
+
def get_charsets(self, failobj=None):
"""Return a list containing the charset(s) used in this message.
@@ -743,4 +773,4 @@ class Message:
one for the container message (i.e. self), so that a non-multipart
message will still return a list of length 1.
"""
- return [part.get_param('charset', failobj) for part in self.walk()]
+ return [part.get_content_charset(failobj) for part in self.walk()]