Repository navigation
Expand file tree
/
Copy pathparser.py
More file actions
1543 lines (1246 loc) · 48.4 KB
/
Copy pathparser.py
File metadata and controls
1543 lines (1246 loc) · 48.4 KB
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
28
29
30
31
32
33
34
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
93
94
95
96
97
98
99
100
101
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
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
# Patchwork - automated patch tracking system
# Copyright (C) 2008 Jeremy Kerr <jk@ozlabs.org>
#
# SPDX-License-Identifier: GPL-2.0-or-later
import codecs
import datetime
from datetime import timezone
from email.header import decode_header
from email.header import make_header
from email.utils import mktime_tz
from email.utils import parsedate_tz
from email.errors import HeaderParseError
from fnmatch import fnmatch
import logging
import re
from urllib.parse import urlparse, parse_qs
from django.contrib.auth.models import User
from django.db.utils import IntegrityError
from django.db import transaction
from django.utils import timezone as tz_utils
from django.urls import resolve, Resolver404
from patchwork.models import Cover
from patchwork.models import CoverComment
from patchwork.models import DelegationRule
from patchwork.models import get_default_initial_patch_state
from patchwork.models import Patch
from patchwork.models import PatchComment
from patchwork.models import Person
from patchwork.models import Project
from patchwork.models import Series
from patchwork.models import SeriesReference
from patchwork.models import State
_msgid_re = re.compile(r'<[^>]+>')
_hunk_re = re.compile(r'^\@\@ -\d+(?:,(\d+))? \+\d+(?:,(\d+))? \@\@')
_filename_re = re.compile(r'^(---|\+\+\+) (\S+)')
list_id_headers = ['List-ID', 'X-Mailing-List', 'X-list']
# How many minutes must pass since the first email of a series before we
# say that subsequent mails are definitely not part of that same series?
#
# Only used when there are not proper references to determine the series
# (such as when the mail is not threaded)
SERIES_DELAY_INTERVAL = 20
# @see https://git-scm.com/docs/git-diff#_generating_patches_with_p
EXTENDED_HEADER_LINES = (
'old mode ',
'new mode ',
'deleted file mode ',
'new file mode ',
'copy from ',
'copy to ',
'rename from ',
'rename to ',
'similarity index ',
'dissimilarity index ',
'new file mode ',
'index ',
)
logger = logging.getLogger(__name__)
class DuplicateMailError(Exception):
def __init__(self, msgid):
self.msgid = msgid
class DuplicateSeriesError(Exception):
pass
def normalise_space(value):
whitespace_re = re.compile(r'\s+')
return whitespace_re.sub(' ', value).strip()
def sanitise_header(header_contents, header_name=None):
"""Clean and individual mail header.
Given a header with header_contents, optionally labelled
header_name, decode it with decode_header, sanitise it to make
sure it decodes correctly and contains no invalid characters,
then encode the result with make_header()
"""
try:
value = decode_header(header_contents)
except HeaderParseError:
# something has gone really wrong with header parsing.
# (e.g. base64 decoding) We probably can't recover, so:
return None
# We have some issues here.
#
# Firstly, in the email parser (before we get here) headers with weird
# chars are email.header.Header class, others as str
#
# Secondly, the behaviour of decode_header: weird headers are labelled
# as unknown-8bit
#
# We solve this by catching any Unicode errors, and then manually
# handling any interesting headers.
try:
header = make_header(
value, header_name=header_name, continuation_ws='\t'
)
except (UnicodeDecodeError, LookupError, ValueError):
# - a part cannot be encoded as ascii. (UnicodeDecodeError), or
# - we don't have a codec matching the hint (LookupError)
# - the codec has a null byte (ValueError)
# Find out which part and fix it somehow.
#
# We get here under where decoding with the coding hint fails.
new_value = []
for part, _ in value:
# We have random bytes that aren't properly coded.
# If we had a coding hint, it failed to help.
# python3 - force coding to unknown-8bit
new_value += [(part, 'unknown-8bit')]
header = make_header(
new_value, header_name=header_name, continuation_ws='\t'
)
try:
header.encode()
except (HeaderParseError, IndexError):
# despite our best efforts, the header is stuffed
# HeaderParseError: some very weird multi-line headers
# IndexError: bug, thrown by make_header(decode_header(' ')).encode()
return None
return header
def clean_header(header):
"""Decode (possibly non-ascii) headers."""
sane_header = sanitise_header(header)
if sane_header is None:
return None
header_str = str(sane_header)
header_str = header_str.replace('\x00', '')
return normalise_space(header_str)
def find_project_by_id_and_subject(list_id, subject):
"""Find a `project` object based on `list_id` and subject match.
Since empty `subject_match` field matches everything, project with
given `list_id` and empty `subject_match` field serves as a default
(in case it exists) if no other match is found.
"""
projects = Project.objects.filter(listid=list_id)
default = None
for project in projects:
if not project.subject_match:
default = project
elif re.search(
project.subject_match, subject, re.MULTILINE | re.IGNORECASE
):
return project
return default
def find_project(mail, list_id=None):
clean_subject = clean_header(mail.get('Subject', ''))
if list_id:
return find_project_by_id_and_subject(list_id, clean_subject)
project = None
listid_res = [
re.compile(r'.*<([^>]+)>.*', re.S),
re.compile(r'^([\S]+)$', re.S),
]
for header in list_id_headers:
if header in mail:
h = clean_header(mail.get(header))
if not h:
continue
for listid_re in listid_res:
match = listid_re.match(h)
if match:
break
if not match:
continue
listid = match.group(1)
project = find_project_by_id_and_subject(listid, clean_subject)
if project:
break
if not project:
logger.debug(
'Could not find a valid project for given list-id and subject.'
)
return project
def _find_series_by_references(project, mail):
"""Find a patch's series using message references.
Traverse RFC822 headers, starting with most recent first, to find
ancestors and the related series. Headers are traversed in reverse
to handle series sent in reply to previous series, like so:
[PATCH 0/3] A cover letter
[PATCH 1/3] The first patch
...
[PATCH v2 0/3] A cover letter
[PATCH v2 1/3] The first patch
...
This means we evaluate headers like so:
- first, check for a Series that directly matches this message's
Message-ID
- then, check for a series that matches the In-Reply-To
- then, check for a series that matches the References, from most
recent (the patch's closest ancestor) to least recent
Args:
project (patchwork.Project): The project that the series
belongs to
mail (email.message.Message): The mail to extract series from
Returns:
The matching ``Series`` instance, if any
"""
subject = mail.get('Subject')
name, prefixes = clean_subject(subject, [project.linkname])
version = parse_version(name, prefixes)
msg_id = find_message_id(mail)
refs = [msg_id] + find_references(mail)
for ref in refs:
try:
series = SeriesReference.objects.get(
msgid=ref[:255],
project=project,
).series
if series.version != version:
# if the versions don't match, at least make sure these were
# sent around the same time
date = find_date(mail)
delta = datetime.timedelta(minutes=SERIES_DELAY_INTERVAL)
start_date = date - delta
end_date = date + delta
# ...and if they don't, this probably isn't our series
if start_date > series.date > end_date:
continue
# we want to return a queryset like '_find_series_by_markers'
return Series.objects.filter(id=series.id)
except SeriesReference.DoesNotExist:
continue
def _find_series_by_markers(project, mail, author):
"""Find a patch's series using series markers and sender.
Identify suitable series for a patch using a combination of the
series markers found in the subject (version, number of patches)
and the patch author. This is less reliable indicator than message
headers and is subject to two main types of false positives that we
must handle:
- Series that are resubmitted, either by mistake or for some odd
reason (perhaps the patches didn't show up immediately)
- Series that have the same author, the same number of patches, and
the same version, but which are in fact completely different
series.
To mitigate both cases, patches are also timeboxed such that any
patches arriving SERIES_DELAY_INTERVAL minutes after the first
patch in the series was created will not be grouped together. This
still won't help us if someone spams the mailing list with
duplicate series but that's a tricky situation for anyone to parse.
"""
subject = mail.get('Subject')
name, prefixes = clean_subject(subject, [project.linkname])
_, total = parse_series_marker(prefixes)
version = parse_version(name, prefixes)
date = find_date(mail)
delta = datetime.timedelta(minutes=SERIES_DELAY_INTERVAL)
start_date = date - delta
end_date = date + delta
return Series.objects.filter(
submitter=author,
project=project,
version=version,
total=total,
date__range=[start_date, end_date],
)
def find_series(project, mail, author):
"""Find a series, if any, for a given patch.
Args:
project (patchwork.Project): The project that the series
belongs to
mail (email.message.Message): The mail to extract series from
Returns:
The matching ``Series`` instance, if any
"""
series = _find_series_by_references(project, mail)
if series:
return series
return _find_series_by_markers(project, mail, author)
def split_from_header(from_header):
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(r'"?(.*?)"?\s*<([^>]+)>'), (lambda g: (g[0], g[1]))),
# for example at example.com (Firstname Lastname) style addresses
(
re.compile(r'(.*?)\sat\s(.*?)\s*\(([^\)]+)\)'),
(lambda g: (g[2], '@'.join(g[0:2]))),
),
# for example@example.com (Firstname Lastname) style addresses
(re.compile(r'"?(.*?)"?\s*\(([^\)]+)\)'), (lambda g: (g[1], g[0]))),
# everything else
(re.compile(r'(.*)'), (lambda g: (None, g[0]))),
]
for regex, fn in from_res:
match = regex.match(from_header)
if match:
(name, email) = fn(match.groups())
break
# Checking for real email address.
email_pattern = (
r'^[\w!#$%&"*+/=?^`{|}~-]+(?:\.[\w!#$%&"*+/=?^`{|}~-]+)*'
r'@(?:[a-zA-Z0-9](?:[a-zA-Z0-9-]*[a-zA-Z0-9])?\.)+'
r'[a-zA-Z0-9](?:[a-zA-Z0-9-]*[a-zA-Z0-9])?$'
)
if not re.match(email_pattern, email):
email = None
return (name, email)
# Unmangle From addresses that have been mangled for DMARC purposes.
#
# To avoid triggering spam filters due to failed signature validation, many
# mailing lists mangle the From header to change the From address to be the
# address of the list, typically where the sender's domain has a strict
# DMARC policy enabled.
#
# Unfortunately, there's no standardised way of preserving the original
# From address.
#
# Google Groups adds an X-Original-From header. If present, we use that.
#
# Mailman preserves the original address by adding a Reply-To, except in the
# case where the list is set to either reply to list, or reply to a specific
# address, in which case the original From is added to Cc instead. These corner
# cases are dumb, but we try and handle things as sensibly as possible by
# looking for a name in Reply-To/Cc that matches From. It's inexact but should
# be good enough for our purposes.
def get_original_sender(mail, name, email):
if name and ' via ' in name:
# Mailman uses the format "<name> via <list>"
# Google Groups uses "'<name>' via <list>"
stripped_name = name[: name.rfind(' via ')].strip().strip("'")
elif name.endswith(' via'):
# Sometimes this seems to happen (perhaps if Mailman isn't set up with
# any list name)
stripped_name = name[: name.rfind(' via')].strip().strip("'")
else:
# We've hit a format that we don't expect
stripped_name = None
original_from = clean_header(mail.get('X-Original-From', ''))
if original_from:
new_email = split_from_header(original_from)[1].strip()[:255]
return (stripped_name, new_email)
addrs = []
reply_to_headers = mail.get_all('Reply-To') or []
cc_headers = mail.get_all('Cc') or []
for header in reply_to_headers + cc_headers:
header = clean_header(header)
addrs = header.split(',')
for addr in addrs:
new_name, new_email = split_from_header(addr)
if new_name:
new_name = new_name.strip()[:255]
if new_email:
new_email = new_email.strip()[:255]
if new_name == stripped_name:
return (stripped_name, new_email)
# If we can't figure out the original sender, just keep it as is
return (name, email)
def get_or_create_author(mail, project=None):
from_header = clean_header(mail.get('From'))
if not from_header:
raise ValueError("Invalid 'From' header")
name, email = split_from_header(from_header)
if not email:
raise ValueError("Invalid 'From' header")
email = email.strip()[:255]
if name is not None:
name = name.strip()[:255]
if project and email.lower() == project.listemail.lower():
name, email = get_original_sender(mail, name, email)
# this correctly handles the case where we lose the race to create
# the person and another process beats us to it. (If the record
# does not exist, g_o_c invokes _create_object_from_params which
# catches the IntegrityError and repeats the SELECT.)
person = Person.objects.get_or_create(
email__iexact=email, defaults={'name': name, 'email': email}
)[0]
if name and name != person.name: # use the latest provided name
person.name = name
person.save()
return person
def find_date(mail):
h = clean_header(mail.get('Date', ''))
if not h:
return tz_utils.now()
t = parsedate_tz(h)
if not t:
return tz_utils.now()
try:
d = datetime.datetime.fromtimestamp(
mktime_tz(t), tz=timezone.utc
).replace(tzinfo=None)
except (OverflowError, ValueError, OSError):
# If you have a date like:
# - Date: Wed, 4 Jun 207777777777777777777714 17:50:46 0
# -> OverflowError
# - Date:, 11 Sep 2016 23:22:904070804030804 +0100
# -> ValueError
# - Date:, 11 Sep 2016 407080403080105:04 +0100
# -> OSError (Python 3)
d = tz_utils.now()
return d
def find_headers(mail):
headers = [
(key, sanitise_header(value, header_name=key))
for key, value in mail.items()
]
strings = [
('%s: %s' % (key, header.encode()))
for (key, header) in headers
if header is not None
]
return '\n'.join(strings).replace('\x00', '')
def find_message_id(mail):
"""Extract the 'message-id' headers from a given mail and validate it.
The validation here is simply checking that the Message-ID is correctly
formatted per RFC-2822. However, even if it's not we'll attempt to use what
we're given because a patch tracked in Patchwork with janky threading is
better than no patch whatsoever.
"""
header = clean_header(mail.get('Message-Id'))
if not header:
raise ValueError("Broken 'Message-Id' header")
msgid = _msgid_re.search(header)
if msgid:
msgid = msgid.group(0)
else:
# This is only info level since the admin likely can't do anything
# about this
logger.info(
"Malformed 'Message-Id' header. The 'msg-id' component should be "
'surrounded by angle brackets. Saving raw header. This may '
'include comments and extra whitespace.'
)
msgid = header.strip()
return msgid[:255]
def find_references(mail):
"""Construct a list of possible reply message ids.
Extract 'in-reply-to' and 'references' headers from a given mail
and return the combined set of each. Because headers can be
duplicated, 'get_all' is used rather than 'get'.
"""
refs = []
for header in mail.get_all('In-Reply-To', []):
header = clean_header(header)
if not header:
continue
ref = _msgid_re.search(header)
if ref:
ref = ref.group(0)
else:
logger.info(
"Malformed 'In-Reply-To' header. The 'msg-id' component "
'should be surrounded by angle brackets. Saving raw header. '
'This may include comments and extra whitespace.'
)
ref = header.strip()
refs.append(ref)
for header in mail.get_all('References', []):
header = clean_header(header)
if not header:
continue
# NOTE: We can't really implement a fallback here since without angle
# brackets there is no obvious way to delimit headers.
references = _msgid_re.findall(header)
references.reverse()
for ref in references:
if ref not in refs:
refs.append(ref)
return refs
def _find_matching_prefix(subject_prefixes, regex):
for prefix in subject_prefixes:
m = regex.match(prefix)
if m:
return m
def parse_series_marker(subject_prefixes):
"""Extract series markers from subject.
Extract the markers of multi-patches series, i.e. 'x/n', from the
provided subject series.
Args:
subject_prefixes: List of subject prefixes to extract markers
from
Returns:
(x, n) if markers found, else (None, None)
"""
# Allow for there to be stuff before the number. This allows for
# e.g. "PATCH1/8" which we have seen in the wild. To allow
# e.g. PATCH100/123 to work, make the pre-number match
# non-greedy. To allow really pathological cases like v2PATCH12/15
# to work, allow it to match everthing (don't exclude numbers).
regex = re.compile(r'.*?([0-9]+)(?:/| of )([0-9]+)$')
m = _find_matching_prefix(subject_prefixes, regex)
if m:
return (int(m.group(1)), int(m.group(2)))
return (None, None)
def parse_version(subject, subject_prefixes):
"""Extract patch version.
Args:
subject: Main body of subject line
subject_prefixes: List of subject prefixes to extract version
from
Returns:
version if found, else 1
"""
regex = re.compile(r'^[vV](\d+)$')
m = _find_matching_prefix(subject_prefixes, regex)
if m:
return int(m.group(1))
m = re.search(r'\([vV](\d+)\)', subject)
if m:
return int(m.group(1))
return 1
def _find_content(mail):
"""Extract the payload(s) from a mail.
Handles various payload types.
:returns: A list of tuples, corresponding the payload and subtype
of payload.
"""
results = []
for part in mail.walk():
if part.get_content_maintype() != 'text':
continue
payload = part.get_payload(decode=True)
subtype = part.get_content_subtype()
if not isinstance(payload, str):
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:
codecs.lookup(charset)
except (LookupError, ValueError, TypeError):
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:
try:
new_payload = payload.decode(cset)
break
except UnicodeDecodeError:
new_payload = None
payload = new_payload
# Could not find a valid decoded payload. Fail.
if payload is None:
continue
results.append((payload, subtype))
return results
def find_patch_content(mail):
"""Extract a comment and potential diff from a mail."""
patchbuf = None
commentbuf = ''
for payload, subtype in _find_content(mail):
if subtype in ['x-patch', 'x-diff']:
patchbuf = payload
elif subtype == 'plain':
c = payload
if not patchbuf:
patchbuf, c = parse_patch(payload)
if c is not None:
commentbuf += c.strip() + '\n'
commentbuf = clean_content(commentbuf)
if patchbuf:
patchbuf = patchbuf.replace('\x00', '')
return patchbuf, commentbuf
def find_comment_content(mail):
"""Extract content from a mail."""
commentbuf = ''
for payload, subtype in _find_content(mail):
if not payload:
continue
if subtype != 'plain':
continue
commentbuf += payload.strip() + '\n'
commentbuf = clean_content(commentbuf)
# keep the method signature the same as find_patch_content
return None, commentbuf
def find_patch_for_comment(project, refs):
for ref in refs:
ref = ref[:255]
# first, check for a direct reply
try:
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 = PatchComment.objects.get(
patch__project=project,
msgid=ref,
)
return comment.patch
except PatchComment.MultipleObjectsReturned:
# NOTE(stephenfin): This is a artifact of prior lack of support
# for cover letters in Patchwork. Previously all replies to
# patches were saved as comments. However, it's possible that
# someone could have created a new series as a reply to one of the
# comments on the original patch series. For example,
# '2015-November/002096.html' from the Patchwork archives. In this
# case, reparsing the archives will result in creation of a cover
# letter with the same message ID as the existing comment. Follow
# up comments will then apply to both this cover letter and the
# linked patch from the comment previously created. We choose to
# apply the comment to the cover letter. Note that this only
# happens when running 'parsearchive' or similar, so it should not
# affect every day use in any way.
comments = PatchComment.objects.filter(
patch__project=project,
msgid=ref,
)
# The latter item will be the cover letter
return comments.reverse()[0].patch
except PatchComment.DoesNotExist:
pass
return None
def find_cover_for_comment(project, refs):
for ref in refs:
ref = ref[:255]
# first, check for a direct reply
try:
cover = Cover.objects.get(project=project, msgid=ref)
return cover
except Cover.DoesNotExist:
pass
# see if we have comments that refer to a patch
try:
comment = CoverComment.objects.get(
cover__project=project,
msgid=ref,
)
return comment.cover
except CoverComment.DoesNotExist:
pass
return None
def split_prefixes(prefix):
"""Turn a prefix string into a list of prefix tokens."""
tokens = []
# detect mercurial series marker (M of N)
series_re = re.compile(r'^PATCH (\d+ of \d+)(.*)$')
match = series_re.match(prefix)
if match is not None:
series, prefix = match.groups()
tokens.extend(['PATCH', series])
split_re = re.compile(r'[,\s]+')
matches = split_re.split(prefix)
tokens.extend([s for s in matches if s != ''])
return tokens
def clean_subject(subject, drop_prefixes=None):
"""Clean a Subject: header from an incoming patch.
Removes Re: and Fwd: strings, as well as [PATCH]-style prefixes. By
default, only [PATCH] is removed, and we keep any other bracketed
data in the subject. If drop_prefixes is provided, remove those
too, comparing case-insensitively.
Args:
subject: Subject to be cleaned
drop_prefixes: Additional, case-insensitive prefixes to remove
from the subject
"""
re_re = re.compile(r'^(re|fwd?)[:\s]\s*', re.I)
prefix_re = re.compile(r'^\[([^\]]*)\]\s*(.*)$')
subject = clean_header(subject)
if subject is None:
raise ValueError("Invalid 'Subject' header")
if drop_prefixes is None:
drop_prefixes = []
else:
drop_prefixes = [s.lower() for s in drop_prefixes]
drop_prefixes.append('patch')
# remove Re:, Fwd:, etc
subject = re_re.sub(' ', subject)
subject = normalise_space(subject)
prefixes = []
match = prefix_re.match(subject)
while match:
prefix_str = match.group(1)
prefixes += [
p
for p in split_prefixes(prefix_str)
if p.lower() not in drop_prefixes
]
subject = match.group(2)
match = prefix_re.match(subject)
subject = normalise_space(subject)
if prefixes:
subject = '[%s] %s' % (','.join(prefixes), subject)
return (subject, prefixes)
def subject_check(subject):
"""Determine if a mail is a reply."""
comment_re = re.compile(r'^(re)[:\s]\s*', re.I)
h = clean_header(subject)
if not h:
return False
return comment_re.match(h)
def clean_content(content):
"""Remove cruft from the email message.
Catch signature (-- ) and list footer (_____) cruft.
"""
sig_re = re.compile(r'^(-- |_+)\n.*', re.S | re.M)
content = sig_re.sub('', content)
return content.strip().replace('\x00', '')
def parse_patch(content):
"""Split a mail's contents into a diff and comment.
This is a state machine that takes a patch, generally in UNIX mbox
format, and splits it into the component comments and diff.
Args:
content: The mail to be split
Returns:
A tuple containing the diff and comment. Either one or both of
these can be empty.
Raises:
Exception: The state machine transitioned to an invalid state.
"""
patchbuf = ''
commentbuf = ''
buf = ''
# state specified the line we just saw, and what to expect next
state = 0
# 0: text
# 1: suspected patch header (diff, Index:)
# 2: patch header line 1 (---)
# 3: patch header line 2 (+++)
# 4: patch hunk header line (@@ line)
# 5: patch hunk content
# 6: patch meta header (rename from/rename to/new file/index)
# 7: binary patch hunk
#
# valid transitions:
# 0 -> 1 (diff, Index:)
# 0 -> 2 (---)
# 1 -> 2 (---)
# 2 -> 3 (+++)
# 3 -> 4 (@@ line)
# 4 -> 5 (patch content)
# 5 -> 1 (ran out of lines from @@-specified count)
# 1 -> 6 (extended header lines)
# 6 -> 2 (---)
# 6 -> 7 (GIT binary patch)
# 6 -> 1 (other text)
# 7 -> 1 (diff)
#
# Suspected patch header is stored into buf, and appended to
# patchbuf if we find a following hunk. Otherwise, append to
# comment after parsing.
# line counts while parsing a patch hunk
lc = (0, 0)
hunk = 0
for line in content.split('\n'):
line += '\n'
if state == 0:
if line.startswith('diff ') or line.startswith('Index: '):
state = 1
buf += line
elif line.startswith('--- '):
state = 2
buf += line
else:
commentbuf += line
elif state == 1:
buf += line
if line.startswith('--- '):
state = 2
if line.startswith(EXTENDED_HEADER_LINES):
state = 6
elif state == 2:
if line.startswith('+++ '):
state = 3
buf += line
elif hunk:
state = 1
buf += line
else:
state = 0
commentbuf += buf + line
buf = ''
elif state == 3:
match = _hunk_re.match(line)
if match:
def fn(x):
if not x:
return 1
return int(x)
lc = [fn(x) for x in match.groups()]
state = 4
patchbuf += buf + line
buf = ''
elif line.startswith('--- '):
patchbuf += buf + line
buf = ''
state = 2
elif hunk and line.startswith(r'\ No newline at end of file'):
# If we had a hunk and now we see this, it's part of the patch,
# and we're still expecting another @@ line.
patchbuf += line
elif hunk:
state = 1
buf += line
else:
state = 0
commentbuf += buf + line
buf = ''
elif state in [4, 5]:
if line.startswith('-'):
lc[0] -= 1
elif line.startswith('+'):
lc[1] -= 1
elif line.startswith(r'\ No newline at end of file'):
# Special case: Not included as part of the hunk's line count