Skip to content
Navigation Menu
{{ message }}
forked from conan-io/python-patch-ng
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathpatch_ng.py
More file actions
executable file
·1381 lines (1173 loc) · 43.9 KB
/
Copy pathpatch_ng.py
File metadata and controls
executable file
·1381 lines (1173 loc) · 43.9 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
#!/usr/bin/env python
"""
Patch utility to apply unified diffs
Brute-force line-by-line non-recursive parsing
Copyright (c) 2008-2016 anatoly techtonik
Available under the terms of MIT license
---
The MIT License (MIT)
Copyright (c) 2019 JFrog LTD
Permission is hereby granted, free of charge, to any person obtaining a copy of this software
and associated documentation files (the "Software"), to deal in the Software without
restriction, including without limitation the rights to use, copy, modify, merge, publish,
distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the
Software is furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all copies or
substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED,
INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR
PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR
ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
"""
from __future__ import print_function
__author__ = "Conan.io <info@conan.io>"
__version__ = "1.17.4"
__license__ = "MIT"
__url__ = "https://github.com/conan-io/python-patch"
import copy
import logging
import re
import tempfile
import codecs
# cStringIO doesn't support unicode in 2.5
try:
from StringIO import StringIO
except ImportError:
from io import BytesIO as StringIO # python 3
try:
import urllib2 as urllib_request
except ImportError:
import urllib.request as urllib_request
from os.path import exists, isfile, abspath
import os
import posixpath
import shutil
import sys
import stat
PY3K = sys.version_info >= (3, 0)
# PEP 3114
if not PY3K:
compat_next = lambda gen: gen.next()
else:
compat_next = lambda gen: gen.__next__()
def tostr(b):
""" Python 3 bytes encoder. Used to print filename in
diffstat output. Assumes that filenames are in utf-8.
"""
if not PY3K:
return b
# [ ] figure out how to print non-utf-8 filenames without
# information loss
return b.decode('utf-8')
#------------------------------------------------
# Logging is controlled by logger named after the
# module name (e.g. 'patch' for patch_ng.py module)
logger = logging.getLogger("patch_ng")
debug = logger.debug
info = logger.info
warning = logger.warning
error = logger.error
class NullHandler(logging.Handler):
""" Copied from Python 2.7 to avoid getting
`No handlers could be found for logger "patch"`
http://bugs.python.org/issue16539
"""
def handle(self, record):
pass
def emit(self, record):
pass
def createLock(self):
self.lock = None
streamhandler = logging.StreamHandler()
# initialize logger itself
logger.addHandler(NullHandler())
debugmode = False
def setdebug():
global debugmode, streamhandler
debugmode = True
loglevel = logging.DEBUG
logformat = "%(levelname)8s %(message)s"
logger.setLevel(loglevel)
if streamhandler not in logger.handlers:
# when used as a library, streamhandler is not added
# by default
logger.addHandler(streamhandler)
streamhandler.setFormatter(logging.Formatter(logformat))
#------------------------------------------------
# Constants for Patch/PatchSet types
DIFF = PLAIN = "plain"
GIT = "git"
HG = MERCURIAL = "mercurial"
SVN = SUBVERSION = "svn"
# mixed type is only actual when PatchSet contains
# Patches of different type
MIXED = MIXED = "mixed"
#------------------------------------------------
# Helpers (these could come with Python stdlib)
# x...() function are used to work with paths in
# cross-platform manner - all paths use forward
# slashes even on Windows.
def xisabs(filename):
""" Cross-platform version of `os.path.isabs()`
Returns True if `filename` is absolute on
Linux, OS X or Windows.
"""
if filename.startswith(b'/'): # Linux/Unix
return True
elif filename.startswith(b'\\'): # Windows
return True
elif re.match(b'\\w:[\\\\/]', filename): # Windows
return True
return False
def xnormpath(path):
""" Cross-platform version of os.path.normpath """
# replace escapes and Windows slashes
normalized = posixpath.normpath(path).replace(b'\\', b'/')
# fold the result
return posixpath.normpath(normalized)
def xstrip(filename):
""" Make relative path out of absolute by stripping
prefixes used on Linux, OS X and Windows.
This function is critical for security.
"""
while xisabs(filename):
# strip windows drive with all slashes
if re.match(b'\\w:[\\\\/]', filename):
filename = re.sub(b'^\\w+:[\\\\/]+', b'', filename)
# strip all slashes
elif re.match(b'[\\\\/]', filename):
filename = re.sub(b'^[\\\\/]+', b'', filename)
return filename
def safe_unlink(filepath):
os.chmod(filepath, stat.S_IWUSR | stat.S_IWGRP | stat.S_IWOTH)
os.unlink(filepath)
#-----------------------------------------------
# Main API functions
def fromfile(filename):
""" Parse patch file. If successful, returns
PatchSet() object. Otherwise returns False.
"""
patchset = PatchSet()
debug("reading %s" % filename)
fp = open(filename, "rb")
res = patchset.parse(fp)
fp.close()
if res == True:
return patchset
return False
def fromstring(s):
""" Parse text string and return PatchSet()
object (or False if parsing fails)
"""
ps = PatchSet( StringIO(s) )
if ps.errors == 0:
return ps
return False
def fromurl(url):
""" Parse patch from an URL, return False
if an error occured. Note that this also
can throw urlopen() exceptions.
"""
ps = PatchSet( urllib_request.urlopen(url) )
if ps.errors == 0:
return ps
return False
# --- Utility functions ---
# [ ] reuse more universal pathsplit()
def pathstrip(path, n):
""" Strip n leading components from the given path """
pathlist = [path]
while os.path.dirname(pathlist[0]) != b'':
pathlist[0:1] = os.path.split(pathlist[0])
return b'/'.join(pathlist[n:])
# --- /Utility function ---
def decode_text(text):
encodings = {codecs.BOM_UTF8: "utf_8_sig",
codecs.BOM_UTF16_BE: "utf_16_be",
codecs.BOM_UTF16_LE: "utf_16_le",
codecs.BOM_UTF32_BE: "utf_32_be",
codecs.BOM_UTF32_LE: "utf_32_le",
b'\x2b\x2f\x76\x38': "utf_7",
b'\x2b\x2f\x76\x39': "utf_7",
b'\x2b\x2f\x76\x2b': "utf_7",
b'\x2b\x2f\x76\x2f': "utf_7",
b'\x2b\x2f\x76\x38\x2d': "utf_7"}
for bom in sorted(encodings, key=len, reverse=True):
if text.startswith(bom):
try:
return text[len(bom):].decode(encodings[bom])
except UnicodeDecodeError:
continue
decoders = ["utf-8", "Windows-1252"]
for decoder in decoders:
try:
return text.decode(decoder)
except UnicodeDecodeError:
continue
logger.warning("can't decode %s" % str(text))
return text.decode("utf-8", "ignore") # Ignore not compatible characters
def to_file_bytes(content):
if PY3K:
if not isinstance(content, bytes):
content = bytes(content, "utf-8")
elif isinstance(content, unicode):
content = content.encode("utf-8")
return content
def load(path, binary=False):
""" Loads a file content """
with open(path, 'rb') as handle:
tmp = handle.read()
return tmp if binary else decode_text(tmp)
def save(path, content, only_if_modified=False):
"""
Saves a file with given content
Params:
path: path to write file to
content: contents to save in the file
only_if_modified: file won't be modified if the content hasn't changed
"""
try:
os.makedirs(os.path.dirname(path))
except Exception:
pass
new_content = to_file_bytes(content)
if only_if_modified and os.path.exists(path):
old_content = load(path, binary=True)
if old_content == new_content:
return
with open(path, "wb") as handle:
handle.write(new_content)
class Hunk(object):
""" Parsed hunk data container (hunk starts with @@ -R +R @@) """
def __init__(self):
self.startsrc=None #: line count starts with 1
self.linessrc=None
self.starttgt=None
self.linestgt=None
self.invalid=False
self.desc=''
self.text=[]
class Patch(object):
""" Patch for a single file.
If used as an iterable, returns hunks.
"""
def __init__(self):
self.source = None
self.target = None
self.hunks = []
self.hunkends = []
self.header = []
self.type = None
def __iter__(self):
for h in self.hunks:
yield h
class PatchSet(object):
""" PatchSet is a patch parser and container.
When used as an iterable, returns patches.
"""
def __init__(self, stream=None):
# --- API accessible fields ---
# name of the PatchSet (filename or ...)
self.name = None
# patch set type - one of constants
self.type = None
# list of Patch objects
self.items = []
self.errors = 0 # fatal parsing errors
self.warnings = 0 # non-critical warnings
# --- /API ---
if stream:
self.parse(stream)
def __len__(self):
return len(self.items)
def __iter__(self):
for i in self.items:
yield i
def parse(self, stream):
""" parse unified diff
return True on success
"""
lineends = dict(lf=0, crlf=0, cr=0)
nexthunkno = 0 #: even if index starts with 0 user messages number hunks from 1
p = None
hunk = None
# hunkactual variable is used to calculate hunk lines for comparison
hunkactual = dict(linessrc=None, linestgt=None)
class wrapumerate(enumerate):
"""Enumerate wrapper that uses boolean end of stream status instead of
StopIteration exception, and properties to access line information.
"""
def __init__(self, *args, **kwargs):
# we don't call parent, it is magically created by __new__ method
self._exhausted = False
self._lineno = False # after end of stream equal to the num of lines
self._line = False # will be reset to False after end of stream
def next(self):
"""Try to read the next line and return True if it is available,
False if end of stream is reached."""
if self._exhausted:
return False
try:
self._lineno, self._line = compat_next(super(wrapumerate, self))
except StopIteration:
self._exhausted = True
self._line = False
return False
return True
@property
def is_empty(self):
return self._exhausted
@property
def line(self):
return self._line
@property
def lineno(self):
return self._lineno
# define states (possible file regions) that direct parse flow
headscan = True # start with scanning header
filenames = False # lines starting with --- and +++
hunkhead = False # @@ -R +R @@ sequence
hunkbody = False #
hunkskip = False # skipping invalid hunk mode
hunkparsed = False # state after successfully parsed hunk
# regexp to match start of hunk, used groups - 1,3,4,6
re_hunk_start = re.compile(b"^@@ -(\d+)(,(\d+))? \+(\d+)(,(\d+))? @@")
self.errors = 0
# temp buffers for header and filenames info
header = []
srcname = None
tgtname = None
# start of main cycle
# each parsing block already has line available in fe.line
fe = wrapumerate(stream)
while fe.next():
# -- deciders: these only switch state to decide who should process
# -- line fetched at the start of this cycle
if hunkparsed:
hunkparsed = False
if re_hunk_start.match(fe.line):
hunkhead = True
elif fe.line.startswith(b"--- "):
filenames = True
else:
headscan = True
# -- ------------------------------------
# read out header
if headscan:
while not fe.is_empty and not fe.line.startswith(b"--- "):
header.append(fe.line)
fe.next()
if fe.is_empty:
if p is None:
debug("no patch data found") # error is shown later
self.errors += 1
else:
info("%d unparsed bytes left at the end of stream" % len(b''.join(header)))
self.warnings += 1
# TODO check for \No new line at the end..
# TODO test for unparsed bytes
# otherwise error += 1
# this is actually a loop exit
continue
headscan = False
# switch to filenames state
filenames = True
line = fe.line
lineno = fe.lineno
# hunkskip and hunkbody code skipped until definition of hunkhead is parsed
if hunkbody:
# [x] treat empty lines inside hunks as containing single space
# (this happens when diff is saved by copy/pasting to editor
# that strips trailing whitespace)
if line.strip(b"\r\n") == b"":
debug("expanding empty line in a middle of hunk body")
self.warnings += 1
line = b' ' + line
# process line first
if re.match(b"^[- \\+\\\\]", line):
# gather stats about line endings
if line.endswith(b"\r\n"):
p.hunkends["crlf"] += 1
elif line.endswith(b"\n"):
p.hunkends["lf"] += 1
elif line.endswith(b"\r"):
p.hunkends["cr"] += 1
if line.startswith(b"-"):
hunkactual["linessrc"] += 1
elif line.startswith(b"+"):
hunkactual["linestgt"] += 1
elif not line.startswith(b"\\"):
hunkactual["linessrc"] += 1
hunkactual["linestgt"] += 1
hunk.text.append(line)
# todo: handle \ No newline cases
else:
warning("invalid hunk no.%d at %d for target file %s" % (nexthunkno, lineno+1, p.target))
# add hunk status node
hunk.invalid = True
p.hunks.append(hunk)
self.errors += 1
# switch to hunkskip state
hunkbody = False
hunkskip = True
# check exit conditions
if hunkactual["linessrc"] > hunk.linessrc or hunkactual["linestgt"] > hunk.linestgt:
warning("extra lines for hunk no.%d at %d for target %s" % (nexthunkno, lineno+1, p.target))
# add hunk status node
hunk.invalid = True
p.hunks.append(hunk)
self.errors += 1
# switch to hunkskip state
hunkbody = False
hunkskip = True
elif hunk.linessrc == hunkactual["linessrc"] and hunk.linestgt == hunkactual["linestgt"]:
# hunk parsed successfully
p.hunks.append(hunk)
# switch to hunkparsed state
hunkbody = False
hunkparsed = True
# detect mixed window/unix line ends
ends = p.hunkends
if ((ends["cr"]!=0) + (ends["crlf"]!=0) + (ends["lf"]!=0)) > 1:
warning("inconsistent line ends in patch hunks for %s" % p.source)
self.warnings += 1
if debugmode:
debuglines = dict(ends)
debuglines.update(file=p.target, hunk=nexthunkno)
debug("crlf: %(crlf)d lf: %(lf)d cr: %(cr)d\t - file: %(file)s hunk: %(hunk)d" % debuglines)
# fetch next line
continue
if hunkskip:
if re_hunk_start.match(line):
# switch to hunkhead state
hunkskip = False
hunkhead = True
elif line.startswith(b"--- "):
# switch to filenames state
hunkskip = False
filenames = True
if debugmode and len(self.items) > 0:
debug("- %2d hunks for %s" % (len(p.hunks), p.source))
if filenames:
if line.startswith(b"--- "):
if srcname != None:
# XXX testcase
warning("skipping false patch for %s" % srcname)
srcname = None
# XXX header += srcname
# double source filename line is encountered
# attempt to restart from this second line
# Files dated at Unix epoch don't exist, e.g.:
# '1970-01-01 01:00:00.000000000 +0100'
# They include timezone offsets.
# .. which can be parsed (if we remove the nanoseconds)
# .. by strptime() with:
# '%Y-%m-%d %H:%M:%S %z'
# .. but unfortunately this relies on the OSes libc
# strptime function and %z support is patchy, so we drop
# everything from the . onwards and group the year and time
# separately.
re_filename_date_time = b"^--- ([^\t]+)(?:\s([0-9-]+)\s([0-9:]+)|.*)"
match = re.match(re_filename_date_time, line)
# todo: support spaces in filenames
if match:
srcname = match.group(1).strip()
date = match.group(2)
time = match.group(3)
if (date == b'1970-01-01' or date == b'1969-12-31') and time.split(b':',1)[1] == b'00:00':
srcname = b'/dev/null'
else:
warning("skipping invalid filename at line %d" % (lineno+1))
self.errors += 1
# XXX p.header += line
# switch back to headscan state
filenames = False
headscan = True
elif not line.startswith(b"+++ "):
if srcname != None:
warning("skipping invalid patch with no target for %s" % srcname)
self.errors += 1
srcname = None
# XXX header += srcname
# XXX header += line
else:
# this should be unreachable
warning("skipping invalid target patch")
filenames = False
headscan = True
else:
if tgtname != None:
# XXX seems to be a dead branch
warning("skipping invalid patch - double target at line %d" % (lineno+1))
self.errors += 1
srcname = None
tgtname = None
# XXX header += srcname
# XXX header += tgtname
# XXX header += line
# double target filename line is encountered
# switch back to headscan state
filenames = False
headscan = True
else:
re_filename_date_time = b"^\+\+\+ ([^\t]+)(?:\s([0-9-]+)\s([0-9:]+)|.*)"
match = re.match(re_filename_date_time, line)
if not match:
warning("skipping invalid patch - no target filename at line %d" % (lineno+1))
self.errors += 1
srcname = None
# switch back to headscan state
filenames = False
headscan = True
else:
tgtname = match.group(1).strip()
date = match.group(2)
time = match.group(3)
if (date == b'1970-01-01' or date == b'1969-12-31') and time.split(b':',1)[1] == b'00:00':
tgtname = b'/dev/null'
if p: # for the first run p is None
self.items.append(p)
p = Patch()
p.source = srcname
srcname = None
p.target = tgtname
tgtname = None
p.header = header
header = []
# switch to hunkhead state
filenames = False
hunkhead = True
nexthunkno = 0
p.hunkends = lineends.copy()
continue
if hunkhead:
match = re.match(b"^@@ -(\d+)(,(\d+))? \+(\d+)(,(\d+))? @@(.*)", line)
if not match:
if not p.hunks:
warning("skipping invalid patch with no hunks for file %s" % p.source)
self.errors += 1
# XXX review switch
# switch to headscan state
hunkhead = False
headscan = True
continue
else:
# TODO review condition case
# switch to headscan state
hunkhead = False
headscan = True
else:
hunk = Hunk()
hunk.startsrc = int(match.group(1))
hunk.linessrc = 1
if match.group(3): hunk.linessrc = int(match.group(3))
hunk.starttgt = int(match.group(4))
hunk.linestgt = 1
if match.group(6): hunk.linestgt = int(match.group(6))
hunk.invalid = False
hunk.desc = match.group(7)[1:].rstrip()
hunk.text = []
hunkactual["linessrc"] = hunkactual["linestgt"] = 0
# switch to hunkbody state
hunkhead = False
hunkbody = True
nexthunkno += 1
continue
# /while fe.next()
if p:
self.items.append(p)
if not hunkparsed:
if hunkskip:
warning("warning: finished with errors, some hunks may be invalid")
elif headscan:
if len(self.items) == 0:
warning("error: no patch data found!")
return False
else: # extra data at the end of file
pass
else:
warning("error: patch stream is incomplete!")
self.errors += 1
if len(self.items) == 0:
return False
if debugmode and len(self.items) > 0:
debug("- %2d hunks for %s" % (len(p.hunks), p.source))
# XXX fix total hunks calculation
debug("total files: %d total hunks: %d" % (len(self.items),
sum(len(p.hunks) for p in self.items)))
# ---- detect patch and patchset types ----
for idx, p in enumerate(self.items):
self.items[idx].type = self._detect_type(p)
types = set([p.type for p in self.items])
if len(types) > 1:
self.type = MIXED
else:
self.type = types.pop()
# --------
self._normalize_filenames()
return (self.errors == 0)
def _detect_type(self, p):
""" detect and return type for the specified Patch object
analyzes header and filenames info
NOTE: must be run before filenames are normalized
"""
# check for SVN
# - header starts with Index:
# - next line is ===... delimiter
# - filename is followed by revision number
# TODO add SVN revision
if (len(p.header) > 1 and p.header[-2].startswith(b"Index: ")
and p.header[-1].startswith(b"="*67)):
return SVN
# common checks for both HG and GIT
DVCS = ((p.source.startswith(b'a/') or p.source == b'/dev/null')
and (p.target.startswith(b'b/') or p.target == b'/dev/null'))
# GIT type check
# - header[-2] is like "diff --git a/oldname b/newname"
# - header[-1] is like "index <hash>..<hash> <mode>"
# TODO add git rename diffs and add/remove diffs
# add git diff with spaced filename
# TODO http://www.kernel.org/pub/software/scm/git/docs/git-diff.html
# Git patch header len is 2 min
if len(p.header) > 1:
# detect the start of diff header - there might be some comments before
for idx in reversed(range(len(p.header))):
if p.header[idx].startswith(b"diff --git"):
break
if p.header[idx].startswith(b'diff --git a/'):
if (idx+1 < len(p.header)
and re.match(b'(?:index \\w{7}..\\w{7} \\d{6}|new file mode \\d*)', p.header[idx+1])):
if DVCS:
return GIT
# HG check
#
# - for plain HG format header is like "diff -r b2d9961ff1f5 filename"
# - for Git-style HG patches it is "diff --git a/oldname b/newname"
# - filename starts with a/, b/ or is equal to /dev/null
# - exported changesets also contain the header
# # HG changeset patch
# # User name@example.com
# ...
# TODO add MQ
# TODO add revision info
if len(p.header) > 0:
if DVCS and re.match(b'diff -r \\w{12} .*', p.header[-1]):
return HG
if DVCS and p.header[-1].startswith(b'diff --git a/'):
if len(p.header) == 1: # native Git patch header len is 2
return HG
elif p.header[0].startswith(b'# HG changeset patch'):
return HG
return PLAIN
def _normalize_filenames(self):
""" sanitize filenames, normalizing paths, i.e.:
1. strip a/ and b/ prefixes from GIT and HG style patches
2. remove all references to parent directories (with warning)
3. translate any absolute paths to relative (with warning)
[x] always use forward slashes to be crossplatform
(diff/patch were born as a unix utility after all)
return None
"""
if debugmode:
debug("normalize filenames")
for i,p in enumerate(self.items):
if debugmode:
debug(" patch type = %s" % p.type)
debug(" source = %s" % p.source)
debug(" target = %s" % p.target)
if p.type in (HG, GIT):
debug("stripping a/ and b/ prefixes")
if p.source != b'/dev/null':
if not p.source.startswith(b"a/"):
warning("invalid source filename")
else:
p.source = p.source[2:]
if p.target != b'/dev/null':
if not p.target.startswith(b"b/"):
warning("invalid target filename")
else:
p.target = p.target[2:]
p.source = xnormpath(p.source)
p.target = xnormpath(p.target)
sep = b'/' # sep value can be hardcoded, but it looks nice this way
# references to parent are not allowed
if p.source.startswith(b".." + sep):
warning("error: stripping parent path for source file patch no.%d" % (i+1))
self.warnings += 1
while p.source.startswith(b".." + sep):
p.source = p.source.partition(sep)[2]
if p.target.startswith(b".." + sep):
warning("error: stripping parent path for target file patch no.%d" % (i+1))
self.warnings += 1
while p.target.startswith(b".." + sep):
p.target = p.target.partition(sep)[2]
# absolute paths are not allowed
if (xisabs(p.source) and p.source != b'/dev/null') or \
(xisabs(p.target) and p.target != b'/dev/null'):
warning("error: absolute paths are not allowed - file no.%d" % (i+1))
self.warnings += 1
if xisabs(p.source) and p.source != b'/dev/null':
warning("stripping absolute path from source name '%s'" % p.source)
p.source = xstrip(p.source)
if xisabs(p.target) and p.target != b'/dev/null':
warning("stripping absolute path from target name '%s'" % p.target)
p.target = xstrip(p.target)
self.items[i].source = p.source
self.items[i].target = p.target
def diffstat(self):
""" calculate diffstat and return as a string
Notes:
- original diffstat ouputs target filename
- single + or - shouldn't escape histogram
"""
names = []
insert = []
delete = []
delta = 0 # size change in bytes
namelen = 0
maxdiff = 0 # max number of changes for single file
# (for histogram width calculation)
for patch in self.items:
i,d = 0,0
for hunk in patch.hunks:
for line in hunk.text:
if line.startswith(b'+'):
i += 1
delta += len(line)-1
elif line.startswith(b'-'):
d += 1
delta -= len(line)-1
names.append(patch.target)
insert.append(i)
delete.append(d)
namelen = max(namelen, len(patch.target))
maxdiff = max(maxdiff, i+d)
output = ''
statlen = len(str(maxdiff)) # stats column width
for i,n in enumerate(names):
# %-19s | %-4d %s
format = " %-" + str(namelen) + "s | %" + str(statlen) + "s %s\n"
hist = ''
# -- calculating histogram --
width = len(format % ('', '', ''))
histwidth = max(2, 80 - width)
if maxdiff < histwidth:
hist = "+"*insert[i] + "-"*delete[i]
else:
iratio = (float(insert[i]) / maxdiff) * histwidth
dratio = (float(delete[i]) / maxdiff) * histwidth
# make sure every entry gets at least one + or -
iwidth = 1 if 0 < iratio < 1 else int(iratio)
dwidth = 1 if 0 < dratio < 1 else int(dratio)
#print(iratio, dratio, iwidth, dwidth, histwidth)
hist = "+"*int(iwidth) + "-"*int(dwidth)
# -- /calculating +- histogram --
output += (format % (tostr(names[i]), str(insert[i] + delete[i]), hist))
output += (" %d files changed, %d insertions(+), %d deletions(-), %+d bytes"
% (len(names), sum(insert), sum(delete), delta))
return output
def findfiles(self, old, new):
""" return tuple of source file, target file """
if old == b'/dev/null':
handle, abspath = tempfile.mkstemp(suffix='pypatch')
abspath = abspath.encode()
# The source file must contain a line for the hunk matching to succeed.
os.write(handle, b' ')
os.close(handle)
if not exists(new):
handle = open(new, 'wb')
handle.close()
return abspath, new
elif exists(old):
return old, old
elif exists(new):
return new, new
elif new == b'/dev/null':
return None, None
else:
# [w] Google Code generates broken patches with its online editor
debug("broken patch from Google Code, stripping prefixes..")
if old.startswith(b'a/') and new.startswith(b'b/'):
old, new = old[2:], new[2:]
debug(" %s" % old)
debug(" %s" % new)
if exists(old):
return old, old
elif exists(new):
return new, new
return None, None
def _strip_prefix(self, filename):
if filename.startswith(b'a/') or filename.startswith(b'b/'):
return filename[2:]
return filename
def decode_clean(self, path, prefix):
path = path.decode("utf-8").replace("\\", "/")
if path.startswith(prefix):
path = path[2:]
return path
def strip_path(self, path, base_path, strip=0):
tokens = path.split("/")
if len(tokens) > 1:
tokens = tokens[strip:]
path = "/".join(tokens)
if base_path:
path = os.path.join(base_path, path)
return path
# account for new and deleted files, upstream dep won't fix them
def apply(self, strip=0, root=None, fuzz=False):
""" Apply parsed patch, optionally stripping leading components
from file paths. `root` parameter specifies working dir.
:param strip: Strip patch path
:param root: Folder to apply the patch
:param fuzz: Accept fuzzy patches
return True on success
"""
items = []
for item in self.items:
source = self.decode_clean(item.source, "a/")
target = self.decode_clean(item.target, "b/")
if "dev/null" in source:
target = self.strip_path(target, root, strip)
hunks = [s.decode("utf-8") for s in item.hunks[0].text]
new_file = "".join(hunk[1:] for hunk in hunks)
save(target, new_file)
elif "dev/null" in target:
source = self.strip_path(source, root, strip)
safe_unlink(source)
else:
items.append(item)
self.items = items
if root:
prevdir = os.getcwd()
os.chdir(root)
total = len(self.items)
errors = 0
if strip:
# [ ] test strip level exceeds nesting level
# [ ] test the same only for selected files
# [ ] test if files end up being on the same level
You can’t perform that action at this time.