X-Git-Url: https://git.ozlabs.org/?a=blobdiff_plain;f=apps%2Fpatchwork%2Fbin%2Fparsemail.py;h=d73343a9407fd5a0c36f2af0604f414189f3595c;hb=406d17e8df324c235172ed673ef65e998ca1f6a4;hp=3fbe4735101c31e31a4d5b6c9384e910b062f339;hpb=ae13beca83bcd061d7b0158ed4bdd45abf2eb855;p=patchwork

diff --git a/apps/patchwork/bin/parsemail.py b/apps/patchwork/bin/parsemail.py
index 3fbe473..d73343a 100755
--- a/apps/patchwork/bin/parsemail.py
+++ b/apps/patchwork/bin/parsemail.py
@@ -26,11 +26,11 @@ import time
 import operator
 from email import message_from_file
 try:
-    from email.header import Header
+    from email.header import Header, decode_header
     from email.utils import parsedate_tz, mktime_tz
 except ImportError:
     # Python 2.4 compatibility
-    from email.Header import Header
+    from email.Header import Header, decode_header
     from email.Utils import parsedate_tz, mktime_tz
 
 from patchwork.parser import parse_patch
@@ -38,6 +38,23 @@ from patchwork.models import Patch, Project, Person, Comment
 
 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(fragment):
+        (frag_str, frag_encoding) = fragment
+        if frag_encoding:
+            return frag_str.decode(frag_encoding)
+        return frag_str.decode()
+
+    fragments = map(decode, decode_header(header))
+
+    return normalise_space(u' '.join(fragments))
+
 def find_project(mail):
     project = None
     listid_re = re.compile('.*<([^>]+)>.*', re.S)
@@ -60,7 +77,7 @@ def find_project(mail):
 
 def find_author(mail):
 
-    from_header = mail.get('From').strip()
+    from_header = clean_header(mail.get('From'))
     (name, email) = (None, None)
 
     # tuple of (regex, fn)
@@ -93,7 +110,7 @@ def find_author(mail):
     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
@@ -103,7 +120,6 @@ def find_author(mail):
 def mail_date(mail):
     t = parsedate_tz(mail.get('Date', ''))
     if not t:
-        print "using now()"
         return datetime.datetime.utcnow()
     return datetime.datetime.utcfromtimestamp(mktime_tz(t))
 
@@ -121,21 +137,13 @@ def find_content(project, mail):
         if part.get_content_maintype() != 'text':
             continue
 
-        #print "\t%s, %s" % \
-        #    (part.get_content_subtype(), part.get_content_charset())
-
-        charset = part.get_content_charset()
-        if not charset:
-            charset = mail.get_charset()
-        if not charset:
-            charset = 'utf-8'
+        payload = part.get_payload(decode=True)
+        subtype = part.get_content_subtype()
 
-        payload = unicode(part.get_payload(decode=True), charset, "replace")
-
-        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:
@@ -224,7 +232,6 @@ def split_prefixes(prefix):
 
 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.
@@ -276,8 +283,7 @@ def clean_subject(subject, drop_prefixes = None):
     # remove Re:, Fwd:, etc
     subject = re_re.sub(' ', subject)
 
-    # normalise whitespace
-    subject = whitespace_re.sub(' ', subject)
+    subject = normalise_space(subject)
 
     prefixes = []
 
@@ -291,7 +297,7 @@ def clean_subject(subject, drop_prefixes = None):
         subject = match.group(2)
         match = prefix_re.match(subject)
 
-    subject = whitespace_re.sub(' ', subject)
+    subject = normalise_space(subject)
 
     subject = subject.strip()
     if prefixes:
@@ -299,8 +305,9 @@ def clean_subject(subject, drop_prefixes = None):
 
     return subject
 
-sig_re = re.compile('^(-{2,3} ?|_+)\n.*', re.S | re.M)
+sig_re = re.compile('^(-- |_+)\n.*', re.S | re.M)
 def clean_content(str):
+    """ Try to remove signature (-- ) and list footer (_____) cruft """
     str = sig_re.sub('', str)
     return str.strip()