1
# Copyright (C) 2005, 2006 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
18
"""Copying of history from one branch to another.
20
The basic plan is that every branch knows the history of everything
21
that has merged into it. As the first step of a merge, pull, or
22
branch operation we copy history from the source into the destination
25
The copying is done in a slightly complicated order. We don't want to
26
add a revision to the store until everything it refers to is also
27
stored, so that if a revision is present we can totally recreate it.
28
However, we can't know what files are included in a revision until we
29
read its inventory. So we query the inventory store of the source for
30
the ids we need, and then pull those ids and finally actually join
35
import bzrlib.errors as errors
36
from bzrlib.errors import (InstallFailed,
38
from bzrlib.progress import ProgressPhase
39
from bzrlib.revision import NULL_REVISION
40
from bzrlib.symbol_versioning import (deprecated_function,
44
from bzrlib.trace import mutter
47
from bzrlib.lazy_import import lazy_import
48
lazy_import(globals(), '''
49
from bzrlib.remote import RemoteRepository
52
# TODO: Avoid repeatedly opening weaves so many times.
54
# XXX: This doesn't handle ghost (not present in branch) revisions at
55
# all yet. I'm not sure they really should be supported.
57
# NOTE: This doesn't copy revisions which may be present but not
58
# merged into the last revision. I'm not sure we want to do that.
60
# - get a list of revisions that need to be pulled in
61
# - for each one, pull in that revision file
62
# and get the inventory, and store the inventory with right
64
# - and get the ancestry, and store that with right parents too
65
# - and keep a note of all file ids and version seen
66
# - then go through all files; for each one get the weave,
67
# and add in all file versions
70
@deprecated_function(zero_eight)
71
def greedy_fetch(to_branch, from_branch, revision=None, pb=None):
72
"""Legacy API, please see branch.fetch(from_branch, last_revision, pb)."""
73
f = Fetcher(to_branch, from_branch, revision, pb)
74
return f.count_copied, f.failed_revisions
79
class RepoFetcher(object):
80
"""Pull revisions and texts from one repository to another.
83
if set, try to limit to the data this revision references.
86
count_copied -- number of revisions copied
88
This should not be used directory, its essential a object to encapsulate
89
the logic in InterRepository.fetch().
91
def __init__(self, to_repository, from_repository, last_revision=None, pb=None):
93
self.failed_revisions = []
95
if isinstance(to_repository, RemoteRepository):
96
to_repository._ensure_real()
97
to_repository = to_repository._real_repository
98
if isinstance(from_repository, RemoteRepository):
99
from_repository._ensure_real()
100
from_repository = from_repository._real_repository
101
if to_repository.control_files._transport.base == from_repository.control_files._transport.base:
102
# check that last_revision is in 'from' and then return a no-operation.
103
if last_revision not in (None, NULL_REVISION):
104
from_repository.get_revision(last_revision)
106
self.to_repository = to_repository
107
self.from_repository = from_repository
108
# must not mutate self._last_revision as its potentially a shared instance
109
self._last_revision = last_revision
111
self.pb = bzrlib.ui.ui_factory.nested_progress_bar()
112
self.nested_pb = self.pb
115
self.nested_pb = None
116
self.from_repository.lock_read()
118
self.to_repository.lock_write()
122
if self.nested_pb is not None:
123
self.nested_pb.finished()
124
self.to_repository.unlock()
126
self.from_repository.unlock()
129
"""Primary worker function.
131
This initialises all the needed variables, and then fetches the
132
requested revisions, finally clearing the progress bar.
134
self.to_weaves = self.to_repository.weave_store
135
self.to_control = self.to_repository.control_weaves
136
self.from_weaves = self.from_repository.weave_store
137
self.from_control = self.from_repository.control_weaves
139
self.file_ids_names = {}
140
pp = ProgressPhase('Fetch phase', 4, self.pb)
143
revs = self._revids_to_fetch()
147
self._fetch_weave_texts(revs)
149
self._fetch_inventory_weave(revs)
151
self._fetch_revision_texts(revs)
152
self.count_copied += len(revs)
156
def _revids_to_fetch(self):
157
mutter('fetch up to rev {%s}', self._last_revision)
158
if self._last_revision is NULL_REVISION:
159
# explicit limit of no revisions needed
161
if (self._last_revision is not None and
162
self.to_repository.has_revision(self._last_revision)):
166
return self.to_repository.missing_revision_ids(self.from_repository,
168
except errors.NoSuchRevision:
169
raise InstallFailed([self._last_revision])
171
def _fetch_weave_texts(self, revs):
172
texts_pb = bzrlib.ui.ui_factory.nested_progress_bar()
174
# fileids_altered_by_revision_ids requires reading the inventory
175
# weave, we will need to read the inventory weave again when
176
# all this is done, so enable caching for that specific weave
177
inv_w = self.from_repository.get_inventory_weave()
179
file_ids = self.from_repository.fileids_altered_by_revision_ids(revs)
181
num_file_ids = len(file_ids)
182
for file_id, required_versions in file_ids.items():
183
texts_pb.update("fetch texts", count, num_file_ids)
185
to_weave = self.to_weaves.get_weave_or_empty(file_id,
186
self.to_repository.get_transaction())
187
from_weave = self.from_weaves.get_weave(file_id,
188
self.from_repository.get_transaction())
189
# we fetch all the texts, because texts do
190
# not reference anything, and its cheap enough
191
to_weave.join(from_weave, version_ids=required_versions)
192
# we don't need *all* of this data anymore, but we dont know
193
# what we do. This cache clearing will result in a new read
194
# of the knit data when we do the checkout, but probably we
195
# want to emit the needed data on the fly rather than at the
197
# the from weave should know not to cache data being joined,
198
# but its ok to ask it to clear.
199
from_weave.clear_cache()
200
to_weave.clear_cache()
204
def _fetch_inventory_weave(self, revs):
205
pb = bzrlib.ui.ui_factory.nested_progress_bar()
207
pb.update("fetch inventory", 0, 2)
208
to_weave = self.to_control.get_weave('inventory',
209
self.to_repository.get_transaction())
211
child_pb = bzrlib.ui.ui_factory.nested_progress_bar()
213
# just merge, this is optimisable and its means we don't
214
# copy unreferenced data such as not-needed inventories.
215
pb.update("fetch inventory", 1, 3)
216
from_weave = self.from_repository.get_inventory_weave()
217
pb.update("fetch inventory", 2, 3)
218
# we fetch only the referenced inventories because we do not
219
# know for unselected inventories whether all their required
220
# texts are present in the other repository - it could be
222
to_weave.join(from_weave, pb=child_pb, msg='merge inventory',
224
from_weave.clear_cache()
231
class GenericRepoFetcher(RepoFetcher):
232
"""This is a generic repo to repo fetcher.
234
This makes minimal assumptions about repo layout and contents.
235
It triggers a reconciliation after fetching to ensure integrity.
238
def _fetch_revision_texts(self, revs):
239
"""Fetch revision object texts"""
240
rev_pb = bzrlib.ui.ui_factory.nested_progress_bar()
242
to_txn = self.to_transaction = self.to_repository.get_transaction()
245
to_store = self.to_repository._revision_store
247
pb = bzrlib.ui.ui_factory.nested_progress_bar()
249
pb.update('copying revisions', count, total)
251
sig_text = self.from_repository.get_signature_text(rev)
252
to_store.add_revision_signature_text(rev, sig_text, to_txn)
253
except errors.NoSuchRevision:
256
to_store.add_revision(self.from_repository.get_revision(rev),
261
# fixup inventory if needed:
262
# this is expensive because we have no inverse index to current ghosts.
263
# but on local disk its a few seconds and sftp push is already insane.
265
# FIXME: repository should inform if this is needed.
266
self.to_repository.reconcile()
271
class KnitRepoFetcher(RepoFetcher):
272
"""This is a knit format repository specific fetcher.
274
This differs from the GenericRepoFetcher by not doing a
275
reconciliation after copying, and using knit joining to
279
def _fetch_revision_texts(self, revs):
280
# may need to be a InterRevisionStore call here.
281
from_transaction = self.from_repository.get_transaction()
282
to_transaction = self.to_repository.get_transaction()
283
to_sf = self.to_repository._revision_store.get_signature_file(
285
from_sf = self.from_repository._revision_store.get_signature_file(
287
to_sf.join(from_sf, version_ids=revs, ignore_missing=True)
288
to_rf = self.to_repository._revision_store.get_revision_file(
290
from_rf = self.from_repository._revision_store.get_revision_file(
292
to_rf.join(from_rf, version_ids=revs)
295
class Inter1and2Helper(object):
296
"""Helper for operations that convert data from model 1 and 2
298
This is for use by fetchers and converters.
301
def __init__(self, source, target):
304
:param source: The repository data comes from
305
:param target: The repository data goes to
310
def iter_rev_trees(self, revs):
311
"""Iterate through RevisionTrees efficiently.
313
Additionally, the inventory's revision_id is set if unset.
315
Trees are retrieved in batches of 100, and then yielded in the order
318
:param revs: A list of revision ids
321
for tree in self.source.revision_trees(revs[:100]):
322
if tree.inventory.revision_id is None:
323
tree.inventory.revision_id = tree.get_revision_id()
327
def generate_root_texts(self, revs):
328
"""Generate VersionedFiles for all root ids.
330
:param revs: the revisions to include
332
inventory_weave = self.source.get_inventory_weave()
335
to_store = self.target.weave_store
336
for tree in self.iter_rev_trees(revs):
337
revision_id = tree.inventory.root.revision
338
root_id = tree.inventory.root.file_id
339
parents = inventory_weave.get_parents(revision_id)
340
if root_id not in versionedfile:
341
versionedfile[root_id] = to_store.get_weave_or_empty(root_id,
342
self.target.get_transaction())
343
parent_texts[root_id] = versionedfile[root_id].add_lines(
344
revision_id, parents, [], parent_texts)
346
def regenerate_inventory(self, revs):
347
"""Generate a new inventory versionedfile in target, convertin data.
349
The inventory is retrieved from the source, (deserializing it), and
350
stored in the target (reserializing it in a different format).
351
:param revs: The revisions to include
353
inventory_weave = self.source.get_inventory_weave()
354
for tree in self.iter_rev_trees(revs):
355
parents = inventory_weave.get_parents(tree.get_revision_id())
356
self.target.add_inventory(tree.get_revision_id(), tree.inventory,
360
class Model1toKnit2Fetcher(GenericRepoFetcher):
361
"""Fetch from a Model1 repository into a Knit2 repository
363
def __init__(self, to_repository, from_repository, last_revision=None,
365
self.helper = Inter1and2Helper(from_repository, to_repository)
366
GenericRepoFetcher.__init__(self, to_repository, from_repository,
369
def _fetch_weave_texts(self, revs):
370
GenericRepoFetcher._fetch_weave_texts(self, revs)
371
# Now generate a weave for the tree root
372
self.helper.generate_root_texts(revs)
374
def _fetch_inventory_weave(self, revs):
375
self.helper.regenerate_inventory(revs)
378
class Knit1to2Fetcher(KnitRepoFetcher):
379
"""Fetch from a Knit1 repository into a Knit2 repository"""
381
def __init__(self, to_repository, from_repository, last_revision=None,
383
self.helper = Inter1and2Helper(from_repository, to_repository)
384
KnitRepoFetcher.__init__(self, to_repository, from_repository,
387
def _fetch_weave_texts(self, revs):
388
KnitRepoFetcher._fetch_weave_texts(self, revs)
389
# Now generate a weave for the tree root
390
self.helper.generate_root_texts(revs)
392
def _fetch_inventory_weave(self, revs):
393
self.helper.regenerate_inventory(revs)
396
class Fetcher(object):
397
"""Backwards compatibility glue for branch.fetch()."""
399
@deprecated_method(zero_eight)
400
def __init__(self, to_branch, from_branch, last_revision=None, pb=None):
401
"""Please see branch.fetch()."""
402
to_branch.fetch(from_branch, last_revision, pb)
added
removed
bzrlib/fetch.py
