summaryrefslogtreecommitdiff
path: root/hgext/largefiles/reposetup.py
blob: 04ab7048521371ef437b5af597e98fbcdcc288d8 (plain)
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
# Copyright 2009-2010 Gregory P. Ward
# Copyright 2009-2010 Intelerad Medical Systems Incorporated
# Copyright 2010-2011 Fog Creek Software
# Copyright 2010-2011 Unity Technologies
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

'''setup for largefiles repositories: reposetup'''
import copy
import types
import os

from mercurial import context, error, manifest, match as match_, util
from mercurial import node as node_
from mercurial.i18n import _

import lfcommands
import proto
import lfutil

def reposetup(ui, repo):
    # wire repositories should be given new wireproto functions but not the
    # other largefiles modifications
    if not repo.local():
        return proto.wirereposetup(ui, repo)

    for name in ('status', 'commitctx', 'commit', 'push'):
        method = getattr(repo, name)
        if (isinstance(method, types.FunctionType) and
            method.func_name == 'wrap'):
            ui.warn(_('largefiles: repo method %r appears to have already been'
                    ' wrapped by another extension: '
                    'largefiles may behave incorrectly\n')
                    % name)

    class lfilesrepo(repo.__class__):
        lfstatus = False
        def status_nolfiles(self, *args, **kwargs):
            return super(lfilesrepo, self).status(*args, **kwargs)

        # When lfstatus is set, return a context that gives the names
        # of largefiles instead of their corresponding standins and
        # identifies the largefiles as always binary, regardless of
        # their actual contents.
        def __getitem__(self, changeid):
            ctx = super(lfilesrepo, self).__getitem__(changeid)
            if self.lfstatus:
                class lfilesmanifestdict(manifest.manifestdict):
                    def __contains__(self, filename):
                        if super(lfilesmanifestdict,
                                self).__contains__(filename):
                            return True
                        return super(lfilesmanifestdict,
                            self).__contains__(lfutil.standin(filename))
                class lfilesctx(ctx.__class__):
                    def files(self):
                        filenames = super(lfilesctx, self).files()
                        return [lfutil.splitstandin(f) or f for f in filenames]
                    def manifest(self):
                        man1 = super(lfilesctx, self).manifest()
                        man1.__class__ = lfilesmanifestdict
                        return man1
                    def filectx(self, path, fileid=None, filelog=None):
                        try:
                            if filelog is not None:
                                result = super(lfilesctx, self).filectx(
                                    path, fileid, filelog)
                            else:
                                result = super(lfilesctx, self).filectx(
                                    path, fileid)
                        except error.LookupError:
                            # Adding a null character will cause Mercurial to
                            # identify this as a binary file.
                            if filelog is not None:
                                result = super(lfilesctx, self).filectx(
                                    lfutil.standin(path), fileid, filelog)
                            else:
                                result = super(lfilesctx, self).filectx(
                                    lfutil.standin(path), fileid)
                            olddata = result.data
                            result.data = lambda: olddata() + '\0'
                        return result
                ctx.__class__ = lfilesctx
            return ctx

        # Figure out the status of big files and insert them into the
        # appropriate list in the result. Also removes standin files
        # from the listing. Revert to the original status if
        # self.lfstatus is False.
        def status(self, node1='.', node2=None, match=None, ignored=False,
                clean=False, unknown=False, listsubrepos=False):
            listignored, listclean, listunknown = ignored, clean, unknown
            if not self.lfstatus:
                return super(lfilesrepo, self).status(node1, node2, match,
                    listignored, listclean, listunknown, listsubrepos)
            else:
                # some calls in this function rely on the old version of status
                self.lfstatus = False
                if isinstance(node1, context.changectx):
                    ctx1 = node1
                else:
                    ctx1 = repo[node1]
                if isinstance(node2, context.changectx):
                    ctx2 = node2
                else:
                    ctx2 = repo[node2]
                working = ctx2.rev() is None
                parentworking = working and ctx1 == self['.']

                def inctx(file, ctx):
                    try:
                        if ctx.rev() is None:
                            return file in ctx.manifest()
                        ctx[file]
                        return True
                    except KeyError:
                        return False

                if match is None:
                    match = match_.always(self.root, self.getcwd())

                # First check if there were files specified on the
                # command line.  If there were, and none of them were
                # largefiles, we should just bail here and let super
                # handle it -- thus gaining a big performance boost.
                lfdirstate = lfutil.openlfdirstate(ui, self)
                if match.files() and not match.anypats():
                    for f in lfdirstate:
                        if match(f):
                            break
                    else:
                        return super(lfilesrepo, self).status(node1, node2,
                                match, listignored, listclean,
                                listunknown, listsubrepos)

                # Create a copy of match that matches standins instead
                # of largefiles.
                def tostandins(files):
                    if not working:
                        return files
                    newfiles = []
                    dirstate = repo.dirstate
                    for f in files:
                        sf = lfutil.standin(f)
                        if sf in dirstate:
                            newfiles.append(sf)
                        elif sf in dirstate.dirs():
                            # Directory entries could be regular or
                            # standin, check both
                            newfiles.extend((f, sf))
                        else:
                            newfiles.append(f)
                    return newfiles

                # Create a function that we can use to override what is
                # normally the ignore matcher.  We've already checked
                # for ignored files on the first dirstate walk, and
                # unecessarily re-checking here causes a huge performance
                # hit because lfdirstate only knows about largefiles
                def _ignoreoverride(self):
                    return False

                m = copy.copy(match)
                m._files = tostandins(m._files)

                # Get ignored files here even if we weren't asked for them; we
                # must use the result here for filtering later
                result = super(lfilesrepo, self).status(node1, node2, m,
                    True, clean, unknown, listsubrepos)
                if working:
                    try:
                        # Any non-largefiles that were explicitly listed must be
                        # taken out or lfdirstate.status will report an error.
                        # The status of these files was already computed using
                        # super's status.
                        # Override lfdirstate's ignore matcher to not do
                        # anything
                        origignore = lfdirstate._ignore
                        lfdirstate._ignore = _ignoreoverride

                        def sfindirstate(f):
                            sf = lfutil.standin(f)
                            dirstate = repo.dirstate
                            return sf in dirstate or sf in dirstate.dirs()
                        match._files = [f for f in match._files
                                        if sfindirstate(f)]
                        # Don't waste time getting the ignored and unknown
                        # files again; we already have them
                        s = lfdirstate.status(match, [], False,
                                listclean, False)
                        (unsure, modified, added, removed, missing, unknown,
                                ignored, clean) = s
                        # Replace the list of ignored and unknown files with
                        # the previously caclulated lists, and strip out the
                        # largefiles
                        lfiles = set(lfdirstate._map)
                        ignored = set(result[5]).difference(lfiles)
                        unknown = set(result[4]).difference(lfiles)
                        if parentworking:
                            for lfile in unsure:
                                standin = lfutil.standin(lfile)
                                if standin not in ctx1:
                                    # from second parent
                                    modified.append(lfile)
                                elif ctx1[standin].data().strip() \
                                        != lfutil.hashfile(self.wjoin(lfile)):
                                    modified.append(lfile)
                                else:
                                    clean.append(lfile)
                                    lfdirstate.normal(lfile)
                        else:
                            tocheck = unsure + modified + added + clean
                            modified, added, clean = [], [], []

                            for lfile in tocheck:
                                standin = lfutil.standin(lfile)
                                if inctx(standin, ctx1):
                                    if ctx1[standin].data().strip() != \
                                            lfutil.hashfile(self.wjoin(lfile)):
                                        modified.append(lfile)
                                    else:
                                        clean.append(lfile)
                                else:
                                    added.append(lfile)
                    finally:
                        # Replace the original ignore function
                        lfdirstate._ignore = origignore

                    for standin in ctx1.manifest():
                        if not lfutil.isstandin(standin):
                            continue
                        lfile = lfutil.splitstandin(standin)
                        if not match(lfile):
                            continue
                        if lfile not in lfdirstate:
                            removed.append(lfile)

                    # Filter result lists
                    result = list(result)

                    # Largefiles are not really removed when they're
                    # still in the normal dirstate. Likewise, normal
                    # files are not really removed if it's still in
                    # lfdirstate. This happens in merges where files
                    # change type.
                    removed = [f for f in removed if f not in repo.dirstate]
                    result[2] = [f for f in result[2] if f not in lfdirstate]

                    # Unknown files
                    unknown = set(unknown).difference(ignored)
                    result[4] = [f for f in unknown
                                 if (repo.dirstate[f] == '?' and
                                     not lfutil.isstandin(f))]
                    # Ignored files were calculated earlier by the dirstate,
                    # and we already stripped out the largefiles from the list
                    result[5] = ignored
                    # combine normal files and largefiles
                    normals = [[fn for fn in filelist
                                if not lfutil.isstandin(fn)]
                               for filelist in result]
                    lfiles = (modified, added, removed, missing, [], [], clean)
                    result = [sorted(list1 + list2)
                              for (list1, list2) in zip(normals, lfiles)]
                else:
                    def toname(f):
                        if lfutil.isstandin(f):
                            return lfutil.splitstandin(f)
                        return f
                    result = [[toname(f) for f in items] for items in result]

                if not listunknown:
                    result[4] = []
                if not listignored:
                    result[5] = []
                if not listclean:
                    result[6] = []
                self.lfstatus = True
                return result

        # As part of committing, copy all of the largefiles into the
        # cache.
        def commitctx(self, *args, **kwargs):
            node = super(lfilesrepo, self).commitctx(*args, **kwargs)
            lfutil.copyalltostore(self, node)
            return node

        # Before commit, largefile standins have not had their
        # contents updated to reflect the hash of their largefile.
        # Do that here.
        def commit(self, text="", user=None, date=None, match=None,
                force=False, editor=False, extra={}):
            orig = super(lfilesrepo, self).commit

            wlock = repo.wlock()
            try:
                # Case 0: Rebase or Transplant
                # We have to take the time to pull down the new largefiles now.
                # Otherwise, any largefiles that were modified in the
                # destination changesets get overwritten, either by the rebase
                # or in the first commit after the rebase or transplant.
                # updatelfiles will update the dirstate to mark any pulled
                # largefiles as modified
                if getattr(repo, "_isrebasing", False) or \
                        getattr(repo, "_istransplanting", False):
                    lfcommands.updatelfiles(repo.ui, repo, filelist=None,
                                            printmessage=False)
                    result = orig(text=text, user=user, date=date, match=match,
                                    force=force, editor=editor, extra=extra)
                    return result
                # Case 1: user calls commit with no specific files or
                # include/exclude patterns: refresh and commit all files that
                # are "dirty".
                if ((match is None) or
                    (not match.anypats() and not match.files())):
                    # Spend a bit of time here to get a list of files we know
                    # are modified so we can compare only against those.
                    # It can cost a lot of time (several seconds)
                    # otherwise to update all standins if the largefiles are
                    # large.
                    lfdirstate = lfutil.openlfdirstate(ui, self)
                    dirtymatch = match_.always(repo.root, repo.getcwd())
                    s = lfdirstate.status(dirtymatch, [], False, False, False)
                    modifiedfiles = []
                    for i in s:
                        modifiedfiles.extend(i)
                    lfiles = lfutil.listlfiles(self)
                    # this only loops through largefiles that exist (not
                    # removed/renamed)
                    for lfile in lfiles:
                        if lfile in modifiedfiles:
                            if os.path.exists(
                                    self.wjoin(lfutil.standin(lfile))):
                                # this handles the case where a rebase is being
                                # performed and the working copy is not updated
                                # yet.
                                if os.path.exists(self.wjoin(lfile)):
                                    lfutil.updatestandin(self,
                                        lfutil.standin(lfile))
                                    lfdirstate.normal(lfile)

                    result = orig(text=text, user=user, date=date, match=match,
                                    force=force, editor=editor, extra=extra)

                    if result is not None:
                        for lfile in lfdirstate:
                            if lfile in modifiedfiles:
                                if (not os.path.exists(repo.wjoin(
                                   lfutil.standin(lfile)))) or \
                                   (not os.path.exists(repo.wjoin(lfile))):
                                    lfdirstate.drop(lfile)

                    # This needs to be after commit; otherwise precommit hooks
                    # get the wrong status
                    lfdirstate.write()
                    return result

                for f in match.files():
                    if lfutil.isstandin(f):
                        raise util.Abort(
                            _('file "%s" is a largefile standin') % f,
                            hint=('commit the largefile itself instead'))

                # Case 2: user calls commit with specified patterns: refresh
                # any matching big files.
                smatcher = lfutil.composestandinmatcher(self, match)
                standins = lfutil.dirstatewalk(self.dirstate, smatcher)

                # No matching big files: get out of the way and pass control to
                # the usual commit() method.
                if not standins:
                    return orig(text=text, user=user, date=date, match=match,
                                    force=force, editor=editor, extra=extra)

                # Refresh all matching big files.  It's possible that the
                # commit will end up failing, in which case the big files will
                # stay refreshed.  No harm done: the user modified them and
                # asked to commit them, so sooner or later we're going to
                # refresh the standins.  Might as well leave them refreshed.
                lfdirstate = lfutil.openlfdirstate(ui, self)
                for standin in standins:
                    lfile = lfutil.splitstandin(standin)
                    if lfdirstate[lfile] <> 'r':
                        lfutil.updatestandin(self, standin)
                        lfdirstate.normal(lfile)
                    else:
                        lfdirstate.drop(lfile)

                # Cook up a new matcher that only matches regular files or
                # standins corresponding to the big files requested by the
                # user.  Have to modify _files to prevent commit() from
                # complaining "not tracked" for big files.
                lfiles = lfutil.listlfiles(repo)
                match = copy.copy(match)
                origmatchfn = match.matchfn

                # Check both the list of largefiles and the list of
                # standins because if a largefile was removed, it
                # won't be in the list of largefiles at this point
                match._files += sorted(standins)

                actualfiles = []
                for f in match._files:
                    fstandin = lfutil.standin(f)

                    # ignore known largefiles and standins
                    if f in lfiles or fstandin in standins:
                        continue

                    # append directory separator to avoid collisions
                    if not fstandin.endswith(os.sep):
                        fstandin += os.sep

                    actualfiles.append(f)
                match._files = actualfiles

                def matchfn(f):
                    if origmatchfn(f):
                        return f not in lfiles
                    else:
                        return f in standins

                match.matchfn = matchfn
                result = orig(text=text, user=user, date=date, match=match,
                                force=force, editor=editor, extra=extra)
                # This needs to be after commit; otherwise precommit hooks
                # get the wrong status
                lfdirstate.write()
                return result
            finally:
                wlock.release()

        def push(self, remote, force=False, revs=None, newbranch=False):
            o = lfutil.findoutgoing(repo, remote, force)
            if o:
                toupload = set()
                o = repo.changelog.nodesbetween(o, revs)[0]
                for n in o:
                    parents = [p for p in repo.changelog.parents(n)
                               if p != node_.nullid]
                    ctx = repo[n]
                    files = set(ctx.files())
                    if len(parents) == 2:
                        mc = ctx.manifest()
                        mp1 = ctx.parents()[0].manifest()
                        mp2 = ctx.parents()[1].manifest()
                        for f in mp1:
                            if f not in mc:
                                files.add(f)
                        for f in mp2:
                            if f not in mc:
                                files.add(f)
                        for f in mc:
                            if mc[f] != mp1.get(f, None) or mc[f] != mp2.get(f,
                                    None):
                                files.add(f)

                    toupload = toupload.union(
                        set([ctx[f].data().strip()
                             for f in files
                             if lfutil.isstandin(f) and f in ctx]))
                lfcommands.uploadlfiles(ui, self, remote, toupload)
            return super(lfilesrepo, self).push(remote, force, revs,
                newbranch)

    repo.__class__ = lfilesrepo

    def checkrequireslfiles(ui, repo, **kwargs):
        if 'largefiles' not in repo.requirements and util.any(
                lfutil.shortname+'/' in f[0] for f in repo.store.datafiles()):
            repo.requirements.add('largefiles')
            repo._writerequirements()

    ui.setconfig('hooks', 'changegroup.lfiles', checkrequireslfiles)
    ui.setconfig('hooks', 'commit.lfiles', checkrequireslfiles)