X-Git-Url: https://git.ozlabs.org/?p=patchwork;a=blobdiff_plain;f=apps%2Fpatchwork%2Fbin%2Fparsemail.py;h=19e6e57d5214fa309f5f27068df726c6f3696dfa;hp=1f213933a1e094c782de5f1564357df685fd847f;hb=f09e982f58384946111d4157fd2b7c2b31b78612;hpb=9b7216bc0bd74b30796cdb64ce8b39a6110c9157

diff --git a/apps/patchwork/bin/parsemail.py b/apps/patchwork/bin/parsemail.py
index 1f21393..19e6e57 100755
--- 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>
@@ -24,27 +24,53 @@ import re
 import datetime
 import time
 import operator
+import codecs
 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
-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']
+list_id_headers = ['List-ID', 'X-Mailing-List', 'X-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)
+    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
 
@@ -60,7 +86,7 @@ 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 +119,7 @@ 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
@@ -112,33 +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
 
-        #print "\t%s, %s" % \
-        #    (part.get_content_subtype(), part.get_content_charset())
+        payload = part.get_payload(decode=True)
+        subtype = part.get_content_subtype()
+
+        if not isinstance(payload, unicode):
+            charset = part.get_content_charset()
 
-        charset = part.get_content_charset()
-        if not charset:
-            charset = mail.get_charset()
-        if not charset:
-            charset = 'utf-8'
+            # 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
 
-        payload = unicode(part.get_payload(decode=True), charset, "replace")
+            # 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 part.get_content_subtype() == 'x-patch':
+        if subtype in ['x-patch', 'x-diff']:
             patchbuf = payload
 
-        if part.get_content_subtype() == 'plain':
+        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'
@@ -146,17 +213,16 @@ def find_content(project, mail):
     patch = None
     comment = None
 
-    if patchbuf:
-        mail_headers(mail)
-	name = clean_subject(mail.get('Subject'), [project.linkname])
-        patch = Patch(name = name, content = patchbuf,
+    if pullurl or patchbuf:
+        name = clean_subject(mail.get('Subject'), [project.linkname])
+        patch = Patch(name = name, pull_url = pullurl, content = patchbuf,
                     date = mail_date(mail), headers = mail_headers(mail))
 
     if commentbuf:
         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),
@@ -165,7 +231,7 @@ def find_content(project, 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:
@@ -183,14 +249,14 @@ def find_patch_for_comment(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
@@ -223,7 +289,6 @@ 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.
@@ -265,6 +330,8 @@ def clean_subject(subject, drop_prefixes = None):
     '[bar] meep'
     """
 
+    subject = clean_header(subject)
+
     if drop_prefixes is None:
         drop_prefixes = []
     else:
@@ -275,8 +342,7 @@ 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 = []
 
@@ -290,7 +356,7 @@ 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:
@@ -298,13 +364,31 @@ 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()
 
-def main(args):
-    mail = message_from_file(sys.stdin)
+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
     if 'From' not in mail:
@@ -339,6 +423,9 @@ def main(args):
         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:
@@ -360,5 +447,9 @@ def main(args):
 
     return 0
 
+def main(args):
+    mail = message_from_file(sys.stdin)
+    return parse_mail(mail)
+
 if __name__ == '__main__':
     sys.exit(main(sys.argv))