Source

ml-hgext / checkfiles.py

Full commit
Jesse Glick 426b3d7 




Jesse Glick d7b6ce2 
Jesse Glick 426b3d7 







Jesse Glick 974eb59 
Jesse Glick 426b3d7 
Jesse Glick d7b6ce2 
Jesse Glick 426b3d7 

Marcus Lindblom … 09f3802 
Jesse Glick 426b3d7 









Marcus Lindblom … 09f3802 




Jesse Glick 426b3d7 




Marcus Lindblom … 09f3802 
Anton Maklakov 051e0fa 
Jesse Glick 426b3d7 








Jesse Glick c236e6c 
Jesse Glick 426b3d7 

Marcus Lindblom … 66d93b7 
Jesse Glick 426b3d7 
Marcus Lindblom … ec506db 
Marcus Lindblom … 66d93b7 

Jesse Glick 426b3d7 
Stephen Belknap 89cde5e 

Jesse Glick 426b3d7 
Marcus Lindblom … ec506db 
Philibert Peruss… 93ec890 


mrapson 40d4863 



Anton Maklakov 051e0fa 
Jesse Glick 515204b 
Marcus Lindblom … ec506db 
Anton Maklakov 051e0fa 


Marcus Lindblom … ec506db 


Jesse Glick 426b3d7 


Jesse Glick 515204b 

Jesse Glick 426b3d7 
Anton Maklakov 051e0fa 

Jesse Glick 426b3d7 
Marcus Lindblom … 09f3802 
Jesse Glick 426b3d7 



Jesse Glick ee548b2 
Marcus Lindblom … 66d93b7 

Jesse Glick 426b3d7 
Stephen Belknap 89cde5e 
Jesse Glick 515204b 
Anton Maklakov 051e0fa 
Jesse Glick 426b3d7 
Vsevolod Parfeno… f0f7727 
Philibert Peruss… 93ec890 
mrapson 40d4863 
Jesse Glick 426b3d7 
Marcus Lindblom … 09f3802 


Marcus Lindblom … f378498 



Anton Maklakov 051e0fa 
Søren Løvborg 3b8498b 


Vsevolod Parfeno… b10bf61 
Anton Maklakov 051e0fa 
Vsevolod Parfeno… b10bf61 
Marcus Lindblom … 66d93b7 
Vsevolod Parfeno… a5f1920 

Marcus Lindblom … 66d93b7 


Jesse Glick 426b3d7 
Stephen Belknap 89cde5e 
Vsevolod Parfeno… 9b84c58 
Vsevolod Parfeno… f0f7727 
Stephen Belknap 89cde5e 
Philibert Peruss… 93ec890 
mrapson 40d4863 

Jesse Glick 426b3d7 
Søren Løvborg 3b8498b 









Marcus Lindblom … a71cacf 
Marcus Lindblom … 09f3802 
Jesse Glick 426b3d7 
Stephen Belknap 89cde5e 

Jesse Glick 426b3d7 



Marcus Lindblom … 66d93b7 



Jesse Glick 426b3d7 



Stephen Belknap 89cde5e 



Jesse Glick 426b3d7 




Vsevolod Parfeno… 54d5323 
Vsevolod Parfeno… 05ab512 


Jesse Glick 426b3d7 
Vsevolod Parfeno… 05ab512 




Vsevolod Parfeno… 54d5323 
Jesse Glick 426b3d7 






Marcus Lindblom … a71cacf 

Vsevolod Parfeno… f0f7727 




Jesse Glick 515204b 


Vsevolod Parfeno… fb1786d 


Jesse Glick 515204b 




Vsevolod Parfeno… fb1786d 
Jesse Glick 515204b 
Vsevolod Parfeno… fb1786d 




Jesse Glick 515204b 

Vsevolod Parfeno… fb1786d 

Jesse Glick 515204b 
Vsevolod Parfeno… fb1786d 




Jesse Glick 515204b 

Jesse Glick 426b3d7 
Jesse Glick 515204b 



Marcus Lindblom … 45a4024 
Marcus Lindblom … dc6c253 

Marcus Lindblom … 45a4024 
Marcus Lindblom … dc6c253 

Marcus Lindblom … 45a4024 
Jesse Glick 515204b 
Jesse Glick 4fd3978 

Jesse Glick 515204b 


Marcus Lindblom … dc6c253 
Vsevolod Parfeno… f0815fc 

Jesse Glick 515204b 






Jesse Glick 4fd3978 

Vsevolod Parfeno… c8201b8 
Philibert Peruss… 93ec890 







mrapson 40d4863 









Vsevolod Parfeno… f0f7727 
Vsevolod Parfeno… fb1786d 
Vsevolod Parfeno… f0f7727 




Jesse Glick 4fd3978 
Jesse Glick 515204b 



Marcus Lindblom … 09f3802 
Jesse Glick 515204b 

Jesse Glick 426b3d7 
mrapson 40d4863 



Jesse Glick 515204b 
Philibert Peruss… 93ec890 







Jesse Glick 426b3d7 
Jesse Glick 515204b 
Philibert Peruss… 93ec890 







Jesse Glick 426b3d7 
mrapson 40d4863 









Jesse Glick 515204b 



Jesse Glick 426b3d7 
Vsevolod Parfeno… f0f7727 
Jesse Glick 426b3d7 
Jesse Glick 515204b 
Jesse Glick 426b3d7 
Jesse Glick 515204b 
Jesse Glick 426b3d7 

Jesse Glick 515204b 
Jesse Glick 426b3d7 

Jesse Glick 515204b 
Jesse Glick 426b3d7 
Anton Maklakov 051e0fa 
Jesse Glick 426b3d7 

Anton Maklakov 051e0fa 


Vsevolod Parfeno… f0f7727 
Anton Maklakov 051e0fa 
Jesse Glick 426b3d7 
mrapson 40d4863 
Anton Maklakov 051e0fa 



mrapson 40d4863 



Anton Maklakov 051e0fa 




Vsevolod Parfeno… f0f7727 



mrapson 40d4863 




Vsevolod Parfeno… f0f7727 
mrapson 40d4863 



Anton Maklakov 051e0fa 




Jesse Glick 426b3d7 
Anton Maklakov 051e0fa 









































mrapson 40d4863 


Anton Maklakov 051e0fa 












mrapson 40d4863 
Anton Maklakov 051e0fa 

mrapson 40d4863 
Anton Maklakov 051e0fa 




mrapson 40d4863 
Anton Maklakov 051e0fa 


mrapson 40d4863 



Anton Maklakov 051e0fa 





mrapson 40d4863 




Anton Maklakov 051e0fa 
mrapson 40d4863 



Anton Maklakov 051e0fa 



Jesse Glick 426b3d7 
Vsevolod Parfeno… f0f7727 



























Jesse Glick 426b3d7 

Marcus Lindblom … 5428a2c 
Jesse Glick 426b3d7 

Marcus Lindblom … 5428a2c 





Jesse Glick 426b3d7 
Jesse Glick 0b3af05 
Marcus Lindblom … 5428a2c 

Jesse Glick 426b3d7 



Marcus Lindblom … 2f49101 




Jesse Glick 426b3d7 
Jesse Glick 0b3af05 
Marcus Lindblom … a71cacf 
Jesse Glick 426b3d7 
Marcus Lindblom … 5428a2c 
Jesse Glick 426b3d7 
Marcus Lindblom … 2f49101 
Søren Løvborg 3b8498b 
Marcus Lindblom … a71cacf 
Jesse Glick 426b3d7 
















Marcus Lindblom … 09f3802 
Jesse Glick 426b3d7 








Marcus Lindblom … 09f3802 

Jesse Glick 426b3d7 
Marcus Lindblom … 09f3802 












Jesse Glick 426b3d7 



Marcus Lindblom … 09f3802 

Marcus Lindblom … f378498 

Marcus Lindblom … 09f3802 



Anton Maklakov 051e0fa 

Marcus Lindblom … 09f3802 
Jesse Glick 0b3af05 
  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
# checkfiles.py detect and fix tabs and(or trailing whitespace in commits
#
# Copyright: Marcus Lindblom 2010
# License: GPLv2+

'''detects (and optionally fixes) tabs and trailing whitespace in committed files

== The hooks ==

check_hook: prevents commits containing tabs or trailing whitespace, without actually touching
            any files. Use as pretxncommit locally or pretxnchangegroup on a central repo.

fixup_hook: automatically fixes any problematic files before commit. Useful in pre-commit.
             (As this hook may changes files on disc, you will need to recompile your
             project after committing if any files needed fixing)

             If you're not comfortable with this kind of magic, use the check_hook and
             manually run the command with the --fixup option.

== The commands ==

hg checkfiles [options]

checks changed files in the working directory for tabs or trailing whitespace

    - --verbose shows the location of offending characters in each line
    - --quiet hides filenames and only reports summary information
    - --debug shows settings and details about each file considered for checking

    If problems are found, the command returns 1, otherwise 0.

hg fixwhitespace [options]

Replaces tabs -> spaces and removes trailing whitespace

    If --fixup is given, the return value is always 0 (unless an error occurs).

options:

 -t --tabsize VALUE  set the tab length (default: 4)
    --all            fix all files in working directory, not just the changes ones
    --diff           fix only modified lines!

== Example usage ==

[extensions]
checkfiles = /path/to/checkfiles.py enable command

[hooks]
pretxnchangegroup.checkfiles = python:/path/to/checkfiles.py:check_hook
pretxncommit.checkfiles = python:/path/to/checkfiles.py:check_hook
precommit.checkfiles = python:/path/to/checkfiles.py:fixup_hook

[checkfiles]
# default is all text files
checked_exts = .c .h .cpp .xml .cs .html .js .css .txt .py .nsi .java .aspx .asp .bat .cmd .glsl

# default is .sln .suo .vcproj .csproj .ui
ignored_exts = .xslt
ignored_files = foo/contains_tabs.txt bar/contains_trailing_ws.txt
# ignore everything in the /res directory, including those files in subdirectories
ignored_patterns = res/.*
tab_size = 4

# for check_hook to only check for tabs  (and ignore trailing whitespace) set to True. Default, if not present is False
check_ignores_trailing_ws = False

# for check_hook to ignore CRLF set to True. Default, if not present is False
# NB: this flag is under development and may convert CRLF ending under some circumstances
check_ignores_CRLF = False

# to examine only modified lines from check_hook, use:
# check_diffs = True

# to fix only modified lines from fixup_hook, use:
# fixup_diff = True

# to replace spaces with tabs (instead of tabs -> spaces), set use_spaces to False
use_spaces = True

'''

from mercurial.i18n import _
from mercurial import cmdutil, patch
import re

hunk_re = re.compile('@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@')

class CheckFiles(object):
    def __init__(self, ui, repo, ctx, opts = {}):
        self.ui = ui
        self.repo = repo

        self.checked_exts = ui.configlist('checkfiles', 'checked_exts',
            default='""')
        self.ignored_exts = ui.configlist('checkfiles', 'ignored_exts',
            default='.sln .suo .vcproj .csproj .ui') # some common autogenerated filetypes
        self.ignored_files = ui.configlist('checkfiles', 'ignored_files')
        self.ignored_patterns = ui.configlist('checkfiles', 'ignored_patterns')
        self.check_diffs = ui.configbool('checkfiles', 'check_diffs')
        self.fixup_diffs = ui.configbool('checkfiles', 'fixup_diffs')
        self.tab_size = int(ui.config('checkfiles', 'tab_size', default='4'))
        self.use_spaces = ui.configbool('checkfiles', 'use_spaces', True)
        self.check_ignores_trailing_ws = ui.configbool('checkfiles', 'check_ignores_trailing_ws', False)
        self.check_ignores_CRLF = ui.configbool('checkfiles', 'check_ignores_CRLF', False)

        if 'tabsize' in opts:
            self.tab_size = int(opts['tabsize'])

        if opts.get('all', False) and opts.get('diff', False):
            raise util.Abort("--all and --diff options are mutually exclusive")

        self.check_diffs = opts.get('diff', self.check_diffs)
        self.fixup_diffs = opts.get('diff', self.fixup_diffs)
        self.opt_all = opts.get('all', False)

        if self.opt_all:
            self.check_diffs = False
            self.fixup_diffs = False

        if self.checked_exts == '""':
            self.ui.debug('checkfiles: checked extensions: (all text files)\n')
        else:
            self.ui.debug('checkfiles: checked extensions: %s\n' % ' '.join(self.checked_exts))

        self.ui.debug('checkfiles: ignored extensions: %s\n' % ' '.join(self.ignored_exts))
        self.ui.debug('checkfiles: ignored files: %s\n' % ' '.join(self.ignored_files))
        self.ui.debug('checkfiles: ignored patterns: %s\n' % ' '.join(self.ignored_patterns))
        self.ui.debug('checkfiles: check diffs only: %r\n' % self.check_diffs)
        self.ui.debug('checkfiles: use spaces: %r\n' % self.use_spaces)
        self.ui.debug('checkfiles: tab size: %r\n' % self.tab_size)
        self.ui.debug('checkfiles: ignore trailing ws: %r\n' % self.check_ignores_trailing_ws)
        self.ui.debug('checkfiles: check ignores CRLF: %r\n' % self.check_ignores_CRLF)


        if ctx:
            self.set_changectx(ctx)

    def set_changectx(self, ctx):
        self.ctx = ctx

        if self.opt_all:
            modified, added, removed, deleted, unknown, ignored, clean = self.repo.status(clean=True)
            self.files = modified + added + clean # we can't get filecontext for unknown files
        else:
            self.files = ctx.files() if ctx else []

    def is_relevant(self, file):
        import re

        if file in self.ignored_files:
            self.ui.debug('checkfiles: ignoring %s (explicit ignore)\n' % file)
            return False

        if any(map(lambda e:file.endswith(e), self.ignored_exts)):
            self.ui.debug('checkfiles: ignoring %s (ignored extension)\n' % file)
            return False

        if not any(map(lambda e:file.endswith(e), self.checked_exts)):
            self.ui.debug('checkfiles: ignoring %s (non-checked extension)\n' % file)
            return False

        if any(map(lambda e:re.search(e, file) is not None, self.ignored_patterns)):
            self.ui.debug('checkfiles: ignoring %s (ignored pattern)\n' % file)
            return False

        try:
            fctx = self.ctx[file]
        except LookupError:
            self.ui.debug('checkfiles: skipping %s (deleted)\n' % file)
            return False

        if fctx == None:
            self.ui.debug('checkfiles: skipping %s (deleted)\n' % file)
            return False

        try:
            data = fctx.data()
        except:
            self.ui.debug('checkfiles: skipping %s (deleted)\n' % file)
            return False

        if '\0' in fctx.data():
            self.ui.debug('checkfiles: skipping %s (binary)\n' % file)
            return False

        return True

    def check(self):
        self.ui.debug('checkfiles: considering files:\n  %s\n' % '\n  '.join(self.files))

        if self.use_spaces:
            indicator = '^' * self.tab_size
        else:
            indicator = '^'

        class State:
            def __init__(self, ui):
                self.ui = ui
                self.ws_begin = False
                self.ws_end = False
                self.all_ws = False
                self.filecount = 0
                self.probcount = 0
            def endfile(self, file):
                if file is None:
                    return
                if self.ws_begin or self.ws_end or self.all_ws:
                    self.filecount += 1
                    self.ui.status('checkfiles: %s:%s%s%s\n' %
                        (file, ' whitespace_begin' if self.ws_begin else '', ' whitespace_end' if self.ws_end else '', ' all_whitespace' if self.all_ws else ''))
                    self.ws_begin = False
                    self.ws_end = False
                    self.all_ws = False
                else:
                    self.ui.note('checkfiles: %s: ok\n' % file)
            def found_all_ws(self):
                self.all_ws = True
                self.probcount += 1
            def found_ws_end(self):
                self.ws_end = True
                self.probcount += 1
            def found_ws_begin(self):
                self.ws_begin = True
                self.probcount += 1
        state = State(self.ui)

        if self.check_diffs:
            if len(self.ctx.parents()) == 1:
                # XXX would be nicer if checked_exts were a proper pattern;
                # then cmdutil.match would work naturally with it
                try:
                    from mercurial.scmutil import match
                    ctx = self.repo[None]
                except ImportError:
                    from mercurial.cmdutil import match
                    ctx = self.repo

                file = None
                hunk = None
                lastlabel = None
                for chunk, label in patch.diffui(self.repo,
                                                 self.ctx.p1().node(),
                                                 self.ctx.node(),
                                                 match(ctx)):
                    if len(label) > 0 or chunk != '\n':
                        self.ui.debug('checkfiles: %s="%s"\n' % (label, chunk))
                    if label == 'diff.file_b':
                        state.endfile(file)
                        file = re.sub(r'^[+][+][+] b/(.+)\t.+$', r'\1', chunk)
                        if self.is_relevant(file):
                            self.ui.debug('checkfiles: checking %s ...\n' % file)
                        else:
                            file = None
                    elif label == 'diff.hunk':
                        hunk = chunk
                    elif file and label == 'diff.trailingwhitespace' and lastlabel == 'diff.inserted' and chunk != '\r':
                        if self.check_ignores_trailing_ws:
                            # still check for presence of \t tough
                            if self.use_spaces and  ('\t' in chunk):
                                state.found_ws_end()
                                self.ui.note('%s: trailing tab in %s\n' % (file, hunk))
                        else:
                            state.found_ws_end()
                            self.ui.note('%s: trailing whitespace in %s\n' % (file, hunk))
                    elif file and label == 'diff.trailingwhitespace' and lastlabel == 'diff.inserted' and chunk == '\r':
                        if self.check_ignores_CRLF == False:
                            if self.check_ignores_trailing_ws:
                                # still check for presence of \t tough
                                if self.use_spaces and  ('\t' in chunk):
                                    state.found_ws_end()
                                    self.ui.note('%s: CRLF and trailing tab in %s\n' % (file, hunk))
                            else:
                                state.found_ws_end()
                                self.ui.note('%s: trailing whitespace and possibly CRLF in %s\n' % (file, hunk))
                    elif file and label == 'diff.inserted' and self.is_ws_before_text(chunk[1:]):
                        state.found_ws_begin()
                        if self.use_spaces:
                            self.ui.note('%s: tab character(s) in %s\n' % (file, hunk))
                        else:
                            self.ui.note('%s: space(s) before text in %s\n' % (file, hunk))

                    lastlabel = label
                state.endfile(file)
            else:
                self.ui.note('checkfiles: skipping merge changeset\n')
        else:
            for file in filter(self.is_relevant, self.files):
                self.ui.debug('checkfiles: checking %s ...\n' % file)
                fctx = self.ctx[file]

                for num, line in enumerate(fctx.data().splitlines(1), 1):
                    line = line.rstrip('\n')
                    if self.check_ignores_CRLF:
                        line = line.rstrip('\r')
                    if line.isspace():
                        if self.check_ignores_trailing_ws:
                            # still check for presence of \t
                            if self.use_spaces and ('\t' in line):
                                state.found_all_ws()
                                self.ui.note('%s (%i): tabs in all whitespace line\n' % (file, num))
                        else:
                            state.found_all_ws()
                            self.ui.note('%s (%i): all whitespace\n' % (file, num))

                    elif line.endswith((' ', '\t')):
                        if self.check_ignores_trailing_ws:
                            # still check for presence of \t
                            if self.use_spaces and ('\t' in line):
                                state.found_ws_end()
                                self.ui.note('%s (%i): trailing tabs\n' % (file, num))
                        else:
                            state.found_ws_end()
                            self.ui.note('%s (%i): trailing whitespace\n' % (file, num))

                    elif line.endswith(('\r')):
                        if self.check_ignores_trailing_ws:
                            # still check for presence of \t
                            if self.use_spaces and ('\t' in line):
                                state.found_ws_end()
                                self.ui.note('%s (%i): trailing tabs\n' % (file, num))
                        else:
                            state.found_ws_end()
                            self.ui.note('%s (%i): CRLF and possibly trailing whitespace\n' % (file, num))

                        line = line.expandtabs(self.tab_size)
                        non_ws_len = len(line.rstrip())
                        line_show = ' ' * non_ws_len + '^' * (len(line) - non_ws_len)
                        self.ui.note('  %s\n  %s\n' % (line, line_show))

                    self.detect_ws_before_text(file, num, line, indicator, state)

                state.endfile(file)

        if state.filecount > 0:
            from mercurial.node import short
            self.ui.warn('checkfiles: %i issues(s) found in %i file(s) in %s\n' %
                (state.probcount, state.filecount,
                short(self.ctx.node()) if self.ctx.node() else 'working directory'))

        return state.filecount > 0

    def fixup_line_num_in_file(self, file, line_num):
        import os.path

        data = self.ctx[file].data()
        lines = data.splitlines()
        nl_at_eof = data.endswith('\n')

        self.ui.status('checkfiles: fixing in %s:%d\n' % (file, line_num))

        with open(os.path.join(self.repo.root, file), 'wb') as fileobj:
            def fixline():
                if self.use_spaces:
                    for num, line in enumerate(lines, 1):
                        if num == line_num:
                            if self.check_ignores_CRLF and line.rstrip('\n').endswith('\r'):
                                yield line.rstrip().expandtabs(self.tab_size) + '\r'
                            else:
                                yield line.rstrip().expandtabs(self.tab_size)
                        else:
                            yield line
                else:
                    for num, line in enumerate(lines, 1):
                        if num == line_num:
                            match = re.match(r'^(\t*( \t*)+)[^ \t]', line)
                            if match:
                                ws = match.group(1)
                                text = line[len(ws):]
                                
                                if self.check_ignores_CRLF and line.rstrip('\n').endswith('\r'):
                                    yield ws.expandtabs(self.tab_size).replace(' ' * self.tab_size, '\t') + text.rstrip() + '\r'
                                else:
                                    yield ws.expandtabs(self.tab_size).replace(' ' * self.tab_size, '\t') + text.rstrip()
                            else:
                                if self.check_ignores_CRLF and line.rstrip('\n').endswith('\r'):
                                    yield line.rstrip() + '\r'
                                else:
                                    yield line.rstrip()
                        else:
                            yield line
            fileobj.writelines('\n'.join(fixline()))
            if nl_at_eof:
                fileobj.write('\n')

    def fixup(self):
        import os.path

        if self.fixup_diffs:
            if len(self.ctx.parents()) == 1:
                # XXX would be nicer if checked_exts were a proper pattern;
                # then cmdutil.match would work naturally with it
                try:
                    from mercurial.scmutil import match
                    ctx = self.repo[None]
                except ImportError:
                    from mercurial.cmdutil import match
                    ctx = self.repo

                file = None
                hunk = None
                lastlabel = None
                line_num = None
                for chunk, label in patch.diffui(self.repo,
                                                 self.ctx.p1().node(),
                                                 self.ctx.node(),
                                                 match(ctx)):

                    if (len(label) == 0 and chunk != '\n') or label == 'diff.inserted':
                        line_num += 1
                    if len(label) > 0 or chunk != '\n':
                        self.ui.debug('checkfiles: %s="%s"\n' % (label, chunk))
                    if label == 'diff.file_b':
                        file = re.sub(r'^[+][+][+] b/(.+)\t.+$', r'\1', chunk)
                        if self.is_relevant(file):
                            self.ui.debug('checkfiles: checking %s ...\n' % file)
                        else:
                            file = None
                    elif label == 'diff.hunk':
                        hunk = chunk
                        m = re.match(hunk_re, hunk);
                        (start_a, len_a, start_b, len_b) = m.groups()
                        self.ui.debug('checkfiles: parsed: %s,  %s, %s, %s\n' % m.groups())
                        line_num = int(start_b) - 1
                    elif file and label == 'diff.trailingwhitespace' and lastlabel == 'diff.inserted' and chunk != '\r':
                        self.ui.note('%s:%d: trailing whitespace in %s\n' % (file, line_num, hunk))
                        self.fixup_line_num_in_file(file, line_num)
                    elif file and label == 'diff.trailingwhitespace' and lastlabel == 'diff.inserted' and chunk == '\r':
                        self.ui.note('%s:%d: CRLF and possibly trailing whitespace in %s\n' % (file, line_num, hunk))
                        self.fixup_line_num_in_file(file, line_num)
                    elif file and label == 'diff.inserted' and self.is_ws_before_text(chunk[1:]):
                        if self.use_spaces:
                            self.ui.note('%s:%d: tab character(s) in %s\n' % (file, line_num, hunk))
                        else:
                            self.ui.note('%s:%d: space(s) before text in %s\n' % (file, line_num,  hunk))
                        self.fixup_line_num_in_file(file, line_num)

                    lastlabel = label
            else:
                self.ui.note('checkfiles: skipping merge changeset\n')
        else:
            for file in filter(self.is_relevant, self.files):
                data = self.ctx[file].data()
                lines = data.splitlines(1)
                nl_at_eof = data.endswith('\n')

                if not any(line.rstrip('\n').isspace() or self.is_ws_before_text(line.rstrip('\n')) or line.rstrip('\n').endswith((' ', '\t')) or line.rstrip('\n').endswith(('\r')) for line in lines):
                    self.ui.note('checkfiles: %s ok\n' % file)
                    continue

                self.ui.status('checkfiles: fixing %s\n' % file)

                with open(os.path.join(self.repo.root, file), 'wb') as fileobj:
                    def fixline():
                        if self.use_spaces:
                            for line in lines:
                                if self.check_ignores_CRLF and line.rstrip('\n').endswith('\r'):
                                    yield line.rstrip().expandtabs(self.tab_size) + '\r'
                                else:
                                    yield line.rstrip().expandtabs(self.tab_size)
                        else:
                            for line in lines:
                                match = re.match(r'^(\t*( \t*)+)[^ \t]', line)
                                if match:
                                    ws = match.group(1)
                                    text = line[len(ws):]
                                    
                                    if self.check_ignores_CRLF and line.rstrip('\n').endswith('\r'):
                                        yield ws.expandtabs(self.tab_size).replace(' ' * self.tab_size, '\t') + text.rstrip() + '\r'
                                    else:
                                        yield ws.expandtabs(self.tab_size).replace(' ' * self.tab_size, '\t') + text.rstrip()
                                else:
                                    if self.check_ignores_CRLF and line.rstrip('\n').endswith('\r'):
                                        yield line.rstrip() + '\r'
                                    else:
                                        yield line.rstrip()

                    fileobj.writelines('\n'.join(fixline()))
                    if nl_at_eof:
                        fileobj.write('\n')

    def match_spaces_before_text(self, line):
        return re.match(r'^\t*( \t*)+[^ \t]', line)

    def is_ws_before_text(self, line):
        if self.use_spaces:
            return '\t' in line
        else:
            return self.match_spaces_before_text(line)

    def detect_ws_before_text(self, file, num, line, indicator, state):
        if self.use_spaces:
            if self.is_ws_before_text(line):
                state.found_ws_begin()
                self.ui.note('%s (%i): tab character(s)\n' % (file, num))

                line_show = ''.join(indicator if c == '\t' else ' ' for c in line)
                line = line.expandtabs(self.tab_size)
                self.ui.note('  %s\n  %s\n' % (line, line_show))
        else:
            match = self.match_spaces_before_text(line)
            if match:
                state.found_ws_begin()
                self.ui.note('%s (%i): space(s) before text\n' % (file, num))

                line = line.expandtabs(self.tab_size)
                line_show = match.group()[0:-1].replace(' ', indicator).expandtabs(self.tab_size)
                self.ui.note('  %s\n  %s\n' % (line, line_show))

################################################################################################

def check_hook(ui, repo, hooktype, **kwargs):
    '''blocks commits/changesets containing tabs or trailing whitespace'''

    if hooktype == 'precommit':
        ui.note('checkfiles: checking for tabs and/or trailing whitespace in changed files...\n')

        cf = CheckFiles(ui, repo, repo[None])
        return cf.check()

    if hooktype == 'pretxncommit':
        ui.note('checkfiles: checking commit for tabs or trailing whitespace...\n')

        node = kwargs['node']
        cf = CheckFiles(ui, repo, repo.changectx(node))
        return cf.check()

    elif hooktype == 'pretxnchangegroup':
        try:
            from mercurial.scmutil import revrange
        except ImportError:
            # 1.8 and earlier
            from mercurial.cmdutil import revrange

        ui.note('checkfiles: checking incoming changes for tabs or trailing whitespace...\n')
        cf = CheckFiles(ui, repo, repo[None])
        fail = False
        node = kwargs['node']

        for rev in revrange(repo, ['%s::' % node]):
            cf.set_changectx(repo.changectx(rev))
            cf.files = cf.ctx.files()
            fail = cf.check() or fail

        return fail
    else:
        from mercurial import util
        raise util.Abort(_('checkfiles: check_hook installed as unsupported hooktype: %s') %
                           hooktype)

def fixup_hook(ui, repo, hooktype, **kwargs):
    '''Removes tabs and/or trailing whitespace from modified files in the working directory'''

    ui.note('checkfiles: removing tabs and/or trailing whitespace in changed files...\n')

    cf = CheckFiles(ui, repo, repo[None])
    cf.fixup()
    return False

def check_cmd(ui, repo, **opts):
    '''checks changed files in the working directory for tabs or trailing whitespace

    - --verbose shows the location of offending characters in each line
    - --quiet hides filenames and only reports summary information
    - --debug shows settings and details about each file considered for checking

    If problems are found, the command returns 1, otherwise 0.
    '''

    ui.note('checkfiles: checking %s files for tabs or trailing whitespace...\n'
             % ('all' if opts['all'] else 'modified'))

    cf = CheckFiles(ui, repo, repo[None], opts)
    return cf.check()

def fixup_cmd(ui, repo, **opts):
    '''Replaces tabs with spaces and removes trailing whitespace from changed files
    '''

    ui.note('checkfiles: removing tabs and/or trailing whitespace in %s files...\n'
             % ('all' if opts['all'] else 'modified'))

    cf = CheckFiles(ui, repo, repo[None], opts)
    cf.fixup()
    return 0

################################################################################################

cmdtable = {
    'checkfiles': (check_cmd,
                   [('t', 'tabsize', 4, 'set the tab length'),
                     ('', 'all', None, 'check all tracked files (not just changed)'),
                     ('', 'diff', None, 'check only diff lines (not entire file)')],
                   'hg checkfiles [options]'),

    'fixwhitespace': (fixup_cmd,
                     [('t', 'tabsize', 4, 'set the tab length'),
                      ('', 'all', None, 'fix all tracked files (not just changed)'),
                      ('', 'diff', None, 'fix only diff lines (not entire file)')],
                      'hg fixwhitespace [options]')
}