parsemail.py 7.38 KB
Newer Older
Jeremy Kerr's avatar
Jeremy Kerr committed
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
#!/usr/bin/python
#
# Patchwork - automated patch tracking system
# Copyright (C) 2008 Jeremy Kerr <jk@ozlabs.org>
#
# This file is part of the Patchwork package.
#
# Patchwork is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or
# (at your option) any later version.
#
# Patchwork is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with Patchwork; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA

import sys
import re
import datetime
import time
import operator
from email import message_from_file
28
29
30
31
32
33
34
try:
    from email.header import Header
    from email.utils import parsedate_tz, mktime_tz
except ImportError:
    # Python 2.4 compatibility
    from email.Header import Header
    from email.Utils import parsedate_tz, mktime_tz
Jeremy Kerr's avatar
Jeremy Kerr committed
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92

from patchparser import parse_patch
from patchwork.models import Patch, Project, Person, Comment

list_id_headers = ['List-ID', 'X-Mailing-List']

def find_project(mail):
    project = None
    listid_re = re.compile('.*<([^>]+)>.*', re.S)

    for header in list_id_headers:
        if header in mail:
            match = listid_re.match(mail.get(header))
            if not match:
                continue

            listid = match.group(1)

            try:
                project = Project.objects.get(listid = listid)
                break
            except:
                pass

    return project

def find_author(mail):

    from_header = mail.get('From').strip()
    (name, email) = (None, None)

    # tuple of (regex, fn)
    #  - where fn returns a (name, email) tuple from the match groups resulting
    #    from re.match().groups()
    from_res = [
        # for "Firstname Lastname" <example@example.com> style addresses
       (re.compile('"?(.*?)"?\s*<([^>]+)>'), (lambda g: (g[0], g[1]))),

       # for example@example.com (Firstname Lastname) style addresses
       (re.compile('"?(.*?)"?\s*\(([^\)]+)\)'), (lambda g: (g[1], g[0]))),

       # everything else
       (re.compile('(.*)'), (lambda g: (None, g[0]))),
    ]

    for regex, fn in from_res:
        match = regex.match(from_header)
        if match:
            (name, email) = fn(match.groups())
            break

    if email is None:
        raise Exception("Could not parse From: header")

    email = email.strip()
    if name is not None:
        name = name.strip()

Jeremy Kerr's avatar
Jeremy Kerr committed
93
94
    new_person = False

Jeremy Kerr's avatar
Jeremy Kerr committed
95
96
97
98
    try:
        person = Person.objects.get(email = email)
    except Person.DoesNotExist:
        person = Person(name = name, email = email)
Jeremy Kerr's avatar
Jeremy Kerr committed
99
        new_person = True
Jeremy Kerr's avatar
Jeremy Kerr committed
100

Jeremy Kerr's avatar
Jeremy Kerr committed
101
    return (person, new_person)
Jeremy Kerr's avatar
Jeremy Kerr committed
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240

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))

def mail_headers(mail):
    return reduce(operator.__concat__,
            ['%s: %s\n' % (k, Header(v, header_name = k, \
                    continuation_ws = '\t').encode()) \
                for (k, v) in mail.items()])

def find_content(project, mail):
    patchbuf = None
    commentbuf = ''

    for part in mail.walk():
        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 = unicode(part.get_payload(decode=True), charset, "replace")

        if part.get_content_subtype() == 'x-patch':
            patchbuf = payload

        if part.get_content_subtype() == 'plain':
            if not patchbuf:
                (patchbuf, c) = parse_patch(payload)
            else:
                c = payload

            if c is not None:
                commentbuf += c.strip() + '\n'

    patch = None
    comment = None

    if patchbuf:
        mail_headers(mail)
        patch = Patch(name = clean_subject(mail.get('Subject')),
                content = patchbuf, date = mail_date(mail),
                headers = mail_headers(mail))

    if commentbuf:
        if patch:
	    cpatch = patch
	else:
            cpatch = find_patch_for_comment(mail)
            if not cpatch:
                return (None, None)
        comment = Comment(patch = cpatch, date = mail_date(mail),
                content = clean_content(commentbuf),
                headers = mail_headers(mail))

    return (patch, comment)

def find_patch_for_comment(mail):
    # construct a list of possible reply message ids
    refs = []
    if 'In-Reply-To' in mail:
        refs.append(mail.get('In-Reply-To'))

    if 'References' in mail:
        rs = mail.get('References').split()
        rs.reverse()
        for r in rs:
            if r not in refs:
                refs.append(r)

    for ref in refs:
        patch = None

        # first, check for a direct reply
        try:
            patch = Patch.objects.get(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)
            return comment.patch
        except Comment.DoesNotExist:
            pass


    return None

re_re = re.compile('^(re|fwd?)[:\s]\s*', re.I)
prefix_re = re.compile('^\[.*\]\s*')
whitespace_re = re.compile('\s+')

def clean_subject(subject):
    subject = re_re.sub(' ', subject)
    subject = prefix_re.sub('', subject)
    subject = whitespace_re.sub(' ', subject)
    return subject.strip()

sig_re = re.compile('^(-{2,3} ?|_+)\n.*', re.S | re.M)
def clean_content(str):
    str = sig_re.sub('', str)
    return str.strip()

def main(args):
    mail = message_from_file(sys.stdin)

    # some basic sanity checks
    if 'From' not in mail:
        return 0

    if 'Subject' not in mail:
        return 0

    if 'Message-Id' not in mail:
        return 0

    hint = mail.get('X-Patchwork-Hint', '').lower()
    if hint == 'ignore':
        return 0;

    project = find_project(mail)
    if project is None:
        print "no project found"
        return 0

    msgid = mail.get('Message-Id').strip()

Jeremy Kerr's avatar
Jeremy Kerr committed
241
    (author, save_required) = find_author(mail)
Jeremy Kerr's avatar
Jeremy Kerr committed
242
243
244
245

    (patch, comment) = find_content(project, mail)

    if patch:
Jeremy Kerr's avatar
Jeremy Kerr committed
246
247
248
249
        # we delay the saving until we know we have a patch.
        if save_required:
            author.save()
            save_required = False
Jeremy Kerr's avatar
Jeremy Kerr committed
250
251
252
253
254
255
256
257
258
        patch.submitter = author
        patch.msgid = msgid
        patch.project = project
        try:
            patch.save()
        except Exception, ex:
            print ex.message

    if comment:
Jeremy Kerr's avatar
Jeremy Kerr committed
259
260
        if save_required:
            author.save()
Jeremy Kerr's avatar
Jeremy Kerr committed
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
        # looks like the original constructor for Comment takes the pk
        # when the Comment is created. reset it here.
        if patch:
            comment.patch = patch
        comment.submitter = author
        comment.msgid = msgid
        try:
            comment.save()
        except Exception, ex:
            print ex.message

    return 0

if __name__ == '__main__':
    sys.exit(main(sys.argv))