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=None, 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 NULL_REVISION:
134
# explicit limit of no revisions needed
136
if (self._last_revision != None and
137
self.to_repository.has_revision(self._last_revision)):
141
return self.to_repository.missing_revision_ids(self.from_repository,
143
except errors.NoSuchRevision:
144
raise InstallFailed([self._last_revision])
146
def _fetch_revision_texts(self, revs):
147
self.to_repository.revision_store.copy_multi(
148
self.from_repository.revision_store,
152
def _fetch_weave_texts(self, revs):
153
file_ids = self.from_repository.fileid_involved_by_set(revs)
155
num_file_ids = len(file_ids)
156
for file_id in file_ids:
157
self.pb.update("merge weaves", count, num_file_ids)
159
to_weave = self.to_weaves.get_weave_or_empty(file_id,
160
self.to_repository.get_transaction())
161
from_weave = self.from_weaves.get_weave(file_id,
162
self.from_repository.get_transaction())
164
if to_weave.numversions() > 0:
165
# destination has contents, must merge
167
to_weave.join(from_weave)
168
except errors.WeaveParentMismatch:
169
to_weave.reweave(from_weave)
171
# destination is empty, just replace it
172
to_weave = from_weave.copy()
174
self.to_weaves.put_weave(file_id, to_weave,
175
self.to_repository.get_transaction())
178
def _fetch_inventory_weave(self, revs):
179
self.pb.update("inventory fetch", 0, 2)
180
from_weave = self.from_repository.get_inventory_weave()
181
to_weave = self.to_repository.get_inventory_weave()
182
self.pb.update("inventory fetch", 1, 2)
183
to_weave = self.to_control.get_weave('inventory',
184
self.to_repository.get_transaction())
185
self.pb.update("inventory fetch", 2, 2)
187
if to_weave.numversions() > 0:
188
# destination has contents, must merge
190
to_weave.join(from_weave, pb=self.pb, msg='merge inventory')
191
except errors.WeaveParentMismatch:
192
to_weave.reweave(from_weave, pb=self.pb, msg='reweave inventory')
194
# destination is empty, just replace it
195
to_weave = from_weave.copy()
197
self.to_control.put_weave('inventory', to_weave,
198
self.to_repository.get_transaction())
203
class Fetcher(object):
204
"""Pull revisions and texts from one branch to another.
206
This doesn't update the destination's history; that can be done
207
separately if desired.
210
If set, pull only up to this revision_id.
214
last_revision -- if last_revision
215
is given it will be that, otherwise the last revision of
218
count_copied -- number of revisions copied
220
count_weaves -- number of file weaves copied
222
def __init__(self, to_branch, from_branch, last_revision=None, pb=None):
223
if to_branch.base == from_branch.base:
224
raise Exception("can't fetch from a branch to itself %s, %s" %
225
(from_branch.base, to_branch.base))
227
self.to_branch = to_branch
228
self.from_branch = from_branch
229
self._last_revision = last_revision
231
self.pb = bzrlib.ui.ui_factory.progress_bar()
234
self.from_branch.lock_read()
236
self.to_branch.lock_write()
240
self.to_branch.unlock()
242
self.from_branch.unlock()
245
self._find_last_revision()
246
repo_fetcher = RepoFetcher(to_repository=self.to_branch.repository,
247
from_repository=self.from_branch.repository,
249
last_revision=self._last_revision)
250
self.failed_revisions = repo_fetcher.failed_revisions
251
self.count_copied = repo_fetcher.count_copied
252
self.count_total = repo_fetcher.count_total
253
self.count_weaves = repo_fetcher.count_weaves
254
self.copied_file_ids = repo_fetcher.copied_file_ids
256
def _find_last_revision(self):
257
"""Find the limiting source revision.
259
Every ancestor of that revision will be merged across.
261
Returns the revision_id, or returns None if there's no history
262
in the source branch."""
263
if self._last_revision:
265
self.pb.update('get source history')
266
from_history = self.from_branch.revision_history()
267
self.pb.update('get destination history')
269
self._last_revision = from_history[-1]
271
# no history in the source branch
272
self._last_revision = NULL_REVISION
added
removed
bzrlib/fetch.py
