tox: Add tox.ini file

[patchwork] / apps / patchwork / bin / parsemail.py

diff --git a/apps/patchwork/bin/parsemail.py b/apps/patchwork/bin/parsemail.py
index fddd2e9b3ecaa039f150ca02cd2927ff209cc9af..19e6e57d5214fa309f5f27068df726c6f3696dfa 100755 (executable)
--- a/apps/patchwork/bin/parsemail.py
+++ b/apps/patchwork/bin/parsemail.py
@@ -1,4 +1,4 @@
-#!/usr/bin/python
+#!/usr/bin/env python
 #
 # Patchwork - automated patch tracking system
 # Copyright (C) 2008 Jeremy Kerr <jk@ozlabs.org>
@@ -24,6 +24,7 @@ import re
 import datetime
 import time
 import operator
+import codecs
 from email import message_from_file
 try:
     from email.header import Header, decode_header
@@ -34,7 +35,9 @@ except ImportError:
     from email.Utils import parsedate_tz, mktime_tz
 
 from patchwork.parser import parse_patch
-from patchwork.models import Patch, Project, Person, Comment
+from patchwork.models import Patch, Project, Person, Comment, State, \
+        get_default_initial_patch_state
+from django.contrib.auth.models import User
 
 list_id_headers = ['List-ID', 'X-Mailing-List', 'X-list']
 
@@ -135,33 +138,74 @@ def mail_headers(mail):
                     continuation_ws = '\t').encode()) \
                 for (k, v) in mail.items()])
 
+def find_pull_request(content):
+    git_re = re.compile('^The following changes since commit.*' +
+                        '^are available in the git repository at:\n'
+                        '^\s*([\S]+://[^\n]+)$',
+                           re.DOTALL | re.MULTILINE)
+    match = git_re.search(content)
+    if match:
+        return match.group(1)
+    return None
+
+def try_decode(payload, charset):
+    try:
+        payload = unicode(payload, charset)
+    except UnicodeDecodeError:
+        return None
+    return payload
+
 def find_content(project, mail):
     patchbuf = None
     commentbuf = ''
+    pullurl = None
 
     for part in mail.walk():
         if part.get_content_maintype() != 'text':
             continue
 
         payload = part.get_payload(decode=True)
-        charset = part.get_content_charset()
         subtype = part.get_content_subtype()
 
-        # if we don't have a charset, assume utf-8
-        if charset is None:
-            charset = 'utf-8'
-
         if not isinstance(payload, unicode):
-            payload = unicode(payload, charset)
+            charset = part.get_content_charset()
+
+            # Check that we have a charset that we understand. Otherwise,
+            # ignore it and fallback to our standard set.
+            if charset is not None:
+                try:
+                    codec = codecs.lookup(charset)
+                except LookupError:
+                    charset = None
+
+            # If there is no charset or if it is unknown, then try some common
+            # charsets before we fail.
+            if charset is None:
+                try_charsets = ['utf-8', 'windows-1252', 'iso-8859-1']
+            else:
+                try_charsets = [charset]
+
+            for cset in try_charsets:
+                decoded_payload = try_decode(payload, cset)
+                if decoded_payload is not None:
+                    break
+            payload = decoded_payload
+
+            # Could not find a valid decoded payload.  Fail.
+            if payload is None:
+                return (None, None)
 
         if subtype in ['x-patch', 'x-diff']:
             patchbuf = payload
 
         elif subtype == 'plain':
+            c = payload
+
             if not patchbuf:
                 (patchbuf, c) = parse_patch(payload)
-            else:
-                c = payload
+
+            if not pullurl:
+                pullurl = find_pull_request(payload)
 
             if c is not None:
                 commentbuf += c.strip() + '\n'
@@ -169,10 +213,9 @@ def find_content(project, mail):
     patch = None
     comment = None
 
-    if patchbuf:
-        mail_headers(mail)
+    if pullurl or patchbuf:
         name = clean_subject(mail.get('Subject'), [project.linkname])
-        patch = Patch(name = name, content = patchbuf,
+        patch = Patch(name = name, pull_url = pullurl, content = patchbuf,
                     date = mail_date(mail), headers = mail_headers(mail))
 
     if commentbuf:
@@ -287,6 +330,8 @@ def clean_subject(subject, drop_prefixes = None):
     '[bar] meep'
     """
 
+    subject = clean_header(subject)
+
     if drop_prefixes is None:
         drop_prefixes = []
     else:
@@ -325,6 +370,24 @@ def clean_content(str):
     str = sig_re.sub('', str)
     return str.strip()
 
+def get_state(state_name):
+    """ Return the state with the given name or the default State """
+    if state_name:
+        try:
+            return State.objects.get(name__iexact=state_name)
+        except State.DoesNotExist:
+            pass
+    return get_default_initial_patch_state()
+
+def get_delegate(delegate_email):
+    """ Return the delegate with the given email or None """
+    if delegate_email:
+        try:
+            return User.objects.get(email__iexact=delegate_email)
+        except User.DoesNotExist:
+            pass
+    return None
+
 def parse_mail(mail):
 
     # some basic sanity checks
@@ -360,6 +423,9 @@ def parse_mail(mail):
         patch.submitter = author
         patch.msgid = msgid
         patch.project = project
+        patch.state = get_state(mail.get('X-Patchwork-State', '').strip())
+        patch.delegate = get_delegate(
+                mail.get('X-Patchwork-Delegate', '').strip())
         try:
             patch.save()
         except Exception, ex: