File: bzr.py

package info (click to toggle)
mercurial 4.9-2
  • links: PTS, VCS
  • area: main
  • in suites: sid
  • size: 42,952 kB
  • sloc: python: 159,631; ansic: 40,124; tcl: 3,715; lisp: 1,448; sh: 1,388; makefile: 602; cpp: 451; xml: 36; sql: 30
file content (307 lines) | stat: -rw-r--r-- 11,949 bytes parent folder | download | duplicates (4)
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
# bzr.py - bzr support for the convert extension
#
#  Copyright 2008, 2009 Marek Kubica <marek@xivilization.net> and others
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

# This module is for handling 'bzr', that was formerly known as Bazaar-NG;
# it cannot access 'bar' repositories, but they were never used very much
from __future__ import absolute_import

import os

from mercurial.i18n import _
from mercurial import (
    demandimport,
    error
)
from . import common

# these do not work with demandimport, blacklist
demandimport.IGNORES.update([
        'bzrlib.transactions',
        'bzrlib.urlutils',
        'ElementPath',
    ])

try:
    # bazaar imports
    import bzrlib.bzrdir
    import bzrlib.errors
    import bzrlib.revision
    import bzrlib.revisionspec
    bzrdir = bzrlib.bzrdir
    errors = bzrlib.errors
    revision = bzrlib.revision
    revisionspec = bzrlib.revisionspec
    revisionspec.RevisionSpec
except ImportError:
    pass

supportedkinds = ('file', 'symlink')

class bzr_source(common.converter_source):
    """Reads Bazaar repositories by using the Bazaar Python libraries"""

    def __init__(self, ui, repotype, path, revs=None):
        super(bzr_source, self).__init__(ui, repotype, path, revs=revs)

        if not os.path.exists(os.path.join(path, '.bzr')):
            raise common.NoRepo(_('%s does not look like a Bazaar repository')
                              % path)

        try:
            # access bzrlib stuff
            bzrdir
        except NameError:
            raise common.NoRepo(_('Bazaar modules could not be loaded') +
                         _(' (try installing the %s package)') % 'bzr')

        path = os.path.abspath(path)
        self._checkrepotype(path)
        try:
            self.sourcerepo = bzrdir.BzrDir.open(path).open_repository()
        except errors.NoRepositoryPresent:
            raise common.NoRepo(_('%s does not look like a Bazaar repository')
                              % path)
        self._parentids = {}
        self._saverev = ui.configbool('convert', 'bzr.saverev')

    def _checkrepotype(self, path):
        # Lightweight checkouts detection is informational but probably
        # fragile at API level. It should not terminate the conversion.
        try:
            dir = bzrdir.BzrDir.open_containing(path)[0]
            try:
                tree = dir.open_workingtree(recommend_upgrade=False)
                branch = tree.branch
            except (errors.NoWorkingTree, errors.NotLocalUrl):
                tree = None
                branch = dir.open_branch()
            if (tree is not None and tree.bzrdir.root_transport.base !=
                branch.bzrdir.root_transport.base):
                self.ui.warn(_('warning: lightweight checkouts may cause '
                               'conversion failures, try with a regular '
                               'branch instead.\n'))
        except Exception:
            self.ui.note(_('bzr source type could not be determined\n'))

    def before(self):
        """Before the conversion begins, acquire a read lock
        for all the operations that might need it. Fortunately
        read locks don't block other reads or writes to the
        repository, so this shouldn't have any impact on the usage of
        the source repository.

        The alternative would be locking on every operation that
        needs locks (there are currently two: getting the file and
        getting the parent map) and releasing immediately after,
        but this approach can take even 40% longer."""
        self.sourcerepo.lock_read()

    def after(self):
        self.sourcerepo.unlock()

    def _bzrbranches(self):
        return self.sourcerepo.find_branches(using=True)

    def getheads(self):
        if not self.revs:
            # Set using=True to avoid nested repositories (see issue3254)
            heads = sorted([b.last_revision() for b in self._bzrbranches()])
        else:
            revid = None
            for branch in self._bzrbranches():
                try:
                    r = revisionspec.RevisionSpec.from_string(self.revs[0])
                    info = r.in_history(branch)
                except errors.BzrError:
                    pass
                revid = info.rev_id
            if revid is None:
                raise error.Abort(_('%s is not a valid revision')
                                  % self.revs[0])
            heads = [revid]
        # Empty repositories return 'null:', which cannot be retrieved
        heads = [h for h in heads if h != 'null:']
        return heads

    def getfile(self, name, rev):
        revtree = self.sourcerepo.revision_tree(rev)
        fileid = revtree.path2id(name.decode(self.encoding or 'utf-8'))
        kind = None
        if fileid is not None:
            kind = revtree.kind(fileid)
        if kind not in supportedkinds:
            # the file is not available anymore - was deleted
            return None, None
        mode = self._modecache[(name, rev)]
        if kind == 'symlink':
            target = revtree.get_symlink_target(fileid)
            if target is None:
                raise error.Abort(_('%s.%s symlink has no target')
                                 % (name, rev))
            return target, mode
        else:
            sio = revtree.get_file(fileid)
            return sio.read(), mode

    def getchanges(self, version, full):
        if full:
            raise error.Abort(_("convert from cvs does not support --full"))
        self._modecache = {}
        self._revtree = self.sourcerepo.revision_tree(version)
        # get the parentids from the cache
        parentids = self._parentids.pop(version)
        # only diff against first parent id
        prevtree = self.sourcerepo.revision_tree(parentids[0])
        files, changes = self._gettreechanges(self._revtree, prevtree)
        return files, changes, set()

    def getcommit(self, version):
        rev = self.sourcerepo.get_revision(version)
        # populate parent id cache
        if not rev.parent_ids:
            parents = []
            self._parentids[version] = (revision.NULL_REVISION,)
        else:
            parents = self._filterghosts(rev.parent_ids)
            self._parentids[version] = parents

        branch = self.recode(rev.properties.get('branch-nick', u'default'))
        if branch == 'trunk':
            branch = 'default'
        return common.commit(parents=parents,
                date='%d %d' % (rev.timestamp, -rev.timezone),
                author=self.recode(rev.committer),
                desc=self.recode(rev.message),
                branch=branch,
                rev=version,
                saverev=self._saverev)

    def gettags(self):
        bytetags = {}
        for branch in self._bzrbranches():
            if not branch.supports_tags():
                return {}
            tagdict = branch.tags.get_tag_dict()
            for name, rev in tagdict.iteritems():
                bytetags[self.recode(name)] = rev
        return bytetags

    def getchangedfiles(self, rev, i):
        self._modecache = {}
        curtree = self.sourcerepo.revision_tree(rev)
        if i is not None:
            parentid = self._parentids[rev][i]
        else:
            # no parent id, get the empty revision
            parentid = revision.NULL_REVISION

        prevtree = self.sourcerepo.revision_tree(parentid)
        changes = [e[0] for e in self._gettreechanges(curtree, prevtree)[0]]
        return changes

    def _gettreechanges(self, current, origin):
        revid = current._revision_id
        changes = []
        renames = {}
        seen = set()

        # Fall back to the deprecated attribute for legacy installations.
        try:
            inventory = origin.root_inventory
        except AttributeError:
            inventory = origin.inventory

        # Process the entries by reverse lexicographic name order to
        # handle nested renames correctly, most specific first.
        curchanges = sorted(current.iter_changes(origin),
                            key=lambda c: c[1][0] or c[1][1],
                            reverse=True)
        for (fileid, paths, changed_content, versioned, parent, name,
            kind, executable) in curchanges:

            if paths[0] == u'' or paths[1] == u'':
                # ignore changes to tree root
                continue

            # bazaar tracks directories, mercurial does not, so
            # we have to rename the directory contents
            if kind[1] == 'directory':
                if kind[0] not in (None, 'directory'):
                    # Replacing 'something' with a directory, record it
                    # so it can be removed.
                    changes.append((self.recode(paths[0]), revid))

                if kind[0] == 'directory' and None not in paths:
                    renaming = paths[0] != paths[1]
                    # neither an add nor an delete - a move
                    # rename all directory contents manually
                    subdir = inventory.path2id(paths[0])
                    # get all child-entries of the directory
                    for name, entry in inventory.iter_entries(subdir):
                        # hg does not track directory renames
                        if entry.kind == 'directory':
                            continue
                        frompath = self.recode(paths[0] + '/' + name)
                        if frompath in seen:
                            # Already handled by a more specific change entry
                            # This is important when you have:
                            # a => b
                            # a/c => a/c
                            # Here a/c must not be renamed into b/c
                            continue
                        seen.add(frompath)
                        if not renaming:
                            continue
                        topath = self.recode(paths[1] + '/' + name)
                        # register the files as changed
                        changes.append((frompath, revid))
                        changes.append((topath, revid))
                        # add to mode cache
                        mode = ((entry.executable and 'x')
                                or (entry.kind == 'symlink' and 's')
                                or '')
                        self._modecache[(topath, revid)] = mode
                        # register the change as move
                        renames[topath] = frompath

                # no further changes, go to the next change
                continue

            # we got unicode paths, need to convert them
            path, topath = paths
            if path is not None:
                path = self.recode(path)
            if topath is not None:
                topath = self.recode(topath)
            seen.add(path or topath)

            if topath is None:
                # file deleted
                changes.append((path, revid))
                continue

            # renamed
            if path and path != topath:
                renames[topath] = path
                changes.append((path, revid))

            # populate the mode cache
            kind, executable = [e[1] for e in (kind, executable)]
            mode = ((executable and 'x') or (kind == 'symlink' and 'l')
                    or '')
            self._modecache[(topath, revid)] = mode
            changes.append((topath, revid))

        return changes, renames

    def _filterghosts(self, ids):
        """Filters out ghost revisions which hg does not support, see
        <http://bazaar-vcs.org/GhostRevision>
        """
        parentmap = self.sourcerepo.get_parent_map(ids)
        parents = tuple([parent for parent in ids if parent in parentmap])
        return parents