list_id_headers = ['List-ID', 'X-Mailing-List']
+whitespace_re = re.compile('\s+')
+def normalise_space(str):
+ return whitespace_re.sub(' ', str).strip()
+
def clean_header(header):
""" Decode (possibly non-ascii) headers """
- def decode(str, fragment):
+ def decode(fragment):
(frag_str, frag_encoding) = fragment
if frag_encoding:
- return str + frag_str.decode(frag_encoding)
- return str + frag_str.decode()
+ return frag_str.decode(frag_encoding)
+ return frag_str.decode()
- return reduce(decode, decode_header(header), u'').strip()
+ fragments = map(decode, decode_header(header))
+
+ return normalise_space(u' '.join(fragments))
def find_project(mail):
project = None
- listid_re = re.compile('.*<([^>]+)>.*', re.S)
+ listid_res = [re.compile('.*<([^>]+)>.*', re.S),
+ re.compile('^([\S]+)$', re.S)]
for header in list_id_headers:
if header in mail:
- match = listid_re.match(mail.get(header))
+
+ for listid_re in listid_res:
+ match = listid_re.match(mail.get(header))
+ if match:
+ break
+
if not match:
continue
new_person = False
try:
- person = Person.objects.get(email = email)
+ person = Person.objects.get(email__iexact = email)
except Person.DoesNotExist:
person = Person(name = name, email = email)
new_person = True
if part.get_content_maintype() != 'text':
continue
- #print "\t%s, %s" % \
- # (part.get_content_subtype(), part.get_content_charset())
-
+ payload = part.get_payload(decode=True)
charset = part.get_content_charset()
- if not charset:
- charset = mail.get_charset()
- if not charset:
+ subtype = part.get_content_subtype()
+
+ # if we don't have a charset, assume utf-8
+ if charset is None:
charset = 'utf-8'
- payload = unicode(part.get_payload(decode=True), charset, "replace")
+ if not isinstance(payload, unicode):
+ payload = unicode(payload, charset)
- if part.get_content_subtype() == 'x-patch':
+ if subtype in ['x-patch', 'x-diff']:
patchbuf = payload
- if part.get_content_subtype() == 'plain':
+ elif subtype == 'plain':
if not patchbuf:
(patchbuf, c) = parse_patch(payload)
else:
if patch:
cpatch = patch
else:
- cpatch = find_patch_for_comment(mail)
+ cpatch = find_patch_for_comment(project, mail)
if not cpatch:
return (None, None)
comment = Comment(patch = cpatch, date = mail_date(mail),
return (patch, comment)
-def find_patch_for_comment(mail):
+def find_patch_for_comment(project, mail):
# construct a list of possible reply message ids
refs = []
if 'In-Reply-To' in mail:
# first, check for a direct reply
try:
- patch = Patch.objects.get(msgid = ref)
+ patch = Patch.objects.get(project = project, msgid = ref)
return patch
except Patch.DoesNotExist:
pass
# see if we have comments that refer to a patch
try:
- comment = Comment.objects.get(msgid = ref)
+ comment = Comment.objects.get(patch__project = project, msgid = ref)
return comment.patch
except Comment.DoesNotExist:
pass
re_re = re.compile('^(re|fwd?)[:\s]\s*', re.I)
prefix_re = re.compile('^\[([^\]]*)\]\s*(.*)$')
-whitespace_re = re.compile('\s+')
def clean_subject(subject, drop_prefixes = None):
""" Clean a Subject: header from an incoming patch.
# remove Re:, Fwd:, etc
subject = re_re.sub(' ', subject)
- # normalise whitespace
- subject = whitespace_re.sub(' ', subject)
+ subject = normalise_space(subject)
prefixes = []
subject = match.group(2)
match = prefix_re.match(subject)
- subject = whitespace_re.sub(' ', subject)
+ subject = normalise_space(subject)
subject = subject.strip()
if prefixes:
str = sig_re.sub('', str)
return str.strip()
-def main(args):
- mail = message_from_file(sys.stdin)
+def parse_mail(mail):
# some basic sanity checks
if 'From' not in mail:
return 0
+def main(args):
+ mail = message_from_file(sys.stdin)
+ return parse_mail(mail)
+
if __name__ == '__main__':
sys.exit(main(sys.argv))