1
# Copyright (C) 2005 by Canonical Ltd
3
# This program is free software; you can redistribute it and/or modify
4
# it under the terms of the GNU General Public License as published by
5
# the Free Software Foundation; either version 2 of the License, or
6
# (at your option) any later version.
8
# This program is distributed in the hope that it will be useful,
9
# but WITHOUT ANY WARRANTY; without even the implied warranty of
10
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
11
# GNU General Public License for more details.
13
# You should have received a copy of the GNU General Public License
14
# along with this program; if not, write to the Free Software
15
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
19
from cStringIO import StringIO
22
import bzrlib.errors as errors
23
from bzrlib.errors import (InstallFailed, NoSuchRevision, WeaveError,
25
from bzrlib.trace import mutter, note, warning
26
from bzrlib.branch import Branch
27
from bzrlib.progress import ProgressBar
28
from bzrlib.revision import NULL_REVISION
29
from bzrlib.xml5 import serializer_v5
30
from bzrlib.osutils import sha_string, split_lines
32
"""Copying of history from one branch to another.
34
The basic plan is that every branch knows the history of everything
35
that has merged into it. As the first step of a merge, pull, or
36
branch operation we copy history from the source into the destination
39
The copying is done in a slightly complicated order. We don't want to
40
add a revision to the store until everything it refers to is also
41
stored, so that if a revision is present we can totally recreate it.
42
However, we can't know what files are included in a revision until we
43
read its inventory. Therefore, we first pull the XML and hold it in
44
memory until we've updated all of the files referenced.
47
# TODO: Avoid repeatedly opening weaves so many times.
49
# XXX: This doesn't handle ghost (not present in branch) revisions at
50
# all yet. I'm not sure they really should be supported.
52
# NOTE: This doesn't copy revisions which may be present but not
53
# merged into the last revision. I'm not sure we want to do that.
55
# - get a list of revisions that need to be pulled in
56
# - for each one, pull in that revision file
57
# and get the inventory, and store the inventory with right
59
# - and get the ancestry, and store that with right parents too
60
# - and keep a note of all file ids and version seen
61
# - then go through all files; for each one get the weave,
62
# and add in all file versions
66
def greedy_fetch(to_branch, from_branch, revision=None, pb=None):
67
f = Fetcher(to_branch, from_branch, revision, pb)
68
return f.count_copied, f.failed_revisions
71
class RepoFetcher(object):
72
"""Pull revisions and texts from one repository to another.
75
if set, try to limit to the data this revision references.
78
count_copied -- number of revisions copied
79
count_weaves -- number of file weaves copied
81
def __init__(self, to_repository, from_repository, last_revision=NULL_REVISION, pb=None):
82
if to_repository.bzrdir.transport.base == from_repository.bzrdir.transport.base:
83
raise Exception("can't fetch from a repository to itself %s, %s" %
84
(from_repository.bzrdir.transport.base,
85
to_repository.bzrdir.transport.base))
86
self.to_repository = to_repository
87
self.from_repository = from_repository
88
# must not mutate self._last_revision as its potentially a shared instance
89
self._last_revision = last_revision
91
self.pb = bzrlib.ui.ui_factory.progress_bar()
94
self.from_repository.lock_read()
96
self.to_repository.lock_write()
100
self.to_repository.unlock()
102
self.from_repository.unlock()
105
"""Primary worker function.
107
This initialises all the needed variables, and then fetches the
108
requested revisions, finally clearing the progress bar.
110
self.to_weaves = self.to_repository.weave_store
111
self.to_control = self.to_repository.control_weaves
112
self.from_weaves = self.from_repository.weave_store
113
self.from_control = self.from_repository.control_weaves
114
self.failed_revisions = []
115
self.count_copied = 0
117
self.count_weaves = 0
118
self.copied_file_ids = set()
119
self.file_ids_names = {}
121
revs = self._revids_to_fetch()
124
self._fetch_weave_texts(revs)
125
self._fetch_inventory_weave(revs)
126
self._fetch_revision_texts(revs)
127
self.count_copied += len(revs)
131
def _revids_to_fetch(self):
132
mutter('fetch up to rev {%s}', self._last_revision)
133
if self._last_revision is None:
134
# explicit limit of None
136
if (self._last_revision != NULL_REVISION and
137
self.to_repository.has_revision(self._last_revision)):
141
if self._last_revision is NULL_REVISION:
142
branch_from_revs = set(self.from_repository.all_revision_ids() +
145
branch_from_revs = set(
146
self.from_repository.get_ancestry(self._last_revision))
147
except errors.NoSuchRevision:
148
raise InstallFailed([self._last_revision])
150
branch_to_revs = set(self.to_repository.all_revision_ids() + [None])
151
return branch_from_revs.difference(branch_to_revs)
153
def _fetch_revision_texts(self, revs):
154
self.to_repository.revision_store.copy_multi(
155
self.from_repository.revision_store,
159
def _fetch_weave_texts(self, revs):
160
file_ids = self.from_repository.fileid_involved_by_set(revs)
162
num_file_ids = len(file_ids)
163
for file_id in file_ids:
164
self.pb.update("merge weave merge", count, num_file_ids)
166
to_weave = self.to_weaves.get_weave_or_empty(file_id,
167
self.to_repository.get_transaction())
168
from_weave = self.from_weaves.get_weave(file_id,
169
self.from_repository.get_transaction())
171
if to_weave.numversions() > 0:
172
# destination has contents, must merge
174
to_weave.join(from_weave)
175
except errors.WeaveParentMismatch:
176
to_weave.reweave(from_weave)
178
# destination is empty, just replace it
179
to_weave = from_weave.copy()
181
self.to_weaves.put_weave(file_id, to_weave,
182
self.to_repository.get_transaction())
185
def _fetch_inventory_weave(self, revs):
186
self.pb.update("inventory fetch", 0, 2)
187
from_weave = self.from_repository.get_inventory_weave()
188
to_weave = self.to_repository.get_inventory_weave()
189
self.pb.update("inventory fetch", 1, 2)
190
to_weave = self.to_control.get_weave('inventory',
191
self.to_repository.get_transaction())
192
self.pb.update("inventory fetch", 2, 2)
194
if to_weave.numversions() > 0:
195
# destination has contents, must merge
197
to_weave.join(from_weave, pb=self.pb, msg='merge inventory')
198
except errors.WeaveParentMismatch:
199
to_weave.reweave(from_weave, pb=self.pb, msg='reweave inventory')
201
# destination is empty, just replace it
202
to_weave = from_weave.copy()
204
self.to_control.put_weave('inventory', to_weave,
205
self.to_repository.get_transaction())
210
class Fetcher(object):
211
"""Pull revisions and texts from one branch to another.
213
This doesn't update the destination's history; that can be done
214
separately if desired.
217
If set, pull only up to this revision_id.
221
last_revision -- if last_revision
222
is given it will be that, otherwise the last revision of
225
count_copied -- number of revisions copied
227
count_weaves -- number of file weaves copied
229
def __init__(self, to_branch, from_branch, last_revision=None, pb=None):
230
if to_branch.base == from_branch.base:
231
raise Exception("can't fetch from a branch to itself %s, %s" %
232
(from_branch.base, to_branch.base))
234
self.to_branch = to_branch
235
self.from_branch = from_branch
236
self._last_revision = last_revision
238
self.pb = bzrlib.ui.ui_factory.progress_bar()
241
self.from_branch.lock_read()
243
self.to_branch.lock_write()
247
self.to_branch.unlock()
249
self.from_branch.unlock()
252
self._find_last_revision()
253
repo_fetcher = RepoFetcher(to_repository=self.to_branch.repository,
254
from_repository=self.from_branch.repository,
256
last_revision=self._last_revision)
257
self.failed_revisions = repo_fetcher.failed_revisions
258
self.count_copied = repo_fetcher.count_copied
259
self.count_total = repo_fetcher.count_total
260
self.count_weaves = repo_fetcher.count_weaves
261
self.copied_file_ids = repo_fetcher.copied_file_ids
263
def _find_last_revision(self):
264
"""Find the limiting source revision.
266
Every ancestor of that revision will be merged across.
268
Returns the revision_id, or returns None if there's no history
269
in the source branch."""
270
if self._last_revision:
272
self.pb.update('get source history')
273
from_history = self.from_branch.revision_history()
274
self.pb.update('get destination history')
276
self._last_revision = from_history[-1]
278
# no history in the source branch
279
self._last_revision = None
added
removed
bzrlib/fetch.py
