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
|
# Copyright (C) 2005, 2006 by Canonical Ltd
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or
# (at your option) any later version.
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
"""Copying of history from one branch to another.
The basic plan is that every branch knows the history of everything
that has merged into it. As the first step of a merge, pull, or
branch operation we copy history from the source into the destination
branch.
The copying is done in a slightly complicated order. We don't want to
add a revision to the store until everything it refers to is also
stored, so that if a revision is present we can totally recreate it.
However, we can't know what files are included in a revision until we
read its inventory. So we query the inventory store of the source for
the ids we need, and then pull those ids and finally actually join
the inventories.
"""
import bzrlib
import bzrlib.errors as errors
from bzrlib.errors import (InstallFailed, NoSuchRevision,
MissingText)
from bzrlib.trace import mutter
from bzrlib.progress import ProgressBar, ProgressPhase
from bzrlib.reconcile import RepoReconciler
from bzrlib.revision import NULL_REVISION
from bzrlib.symbol_versioning import *
# TODO: Avoid repeatedly opening weaves so many times.
# XXX: This doesn't handle ghost (not present in branch) revisions at
# all yet. I'm not sure they really should be supported.
# NOTE: This doesn't copy revisions which may be present but not
# merged into the last revision. I'm not sure we want to do that.
# - get a list of revisions that need to be pulled in
# - for each one, pull in that revision file
# and get the inventory, and store the inventory with right
# parents.
# - and get the ancestry, and store that with right parents too
# - and keep a note of all file ids and version seen
# - then go through all files; for each one get the weave,
# and add in all file versions
@deprecated_function(zero_eight)
def greedy_fetch(to_branch, from_branch, revision=None, pb=None):
"""Legacy API, please see branch.fetch(from_branch, last_revision, pb)."""
f = Fetcher(to_branch, from_branch, revision, pb)
return f.count_copied, f.failed_revisions
fetch = greedy_fetch
class RepoFetcher(object):
"""Pull revisions and texts from one repository to another.
last_revision
if set, try to limit to the data this revision references.
after running:
count_copied -- number of revisions copied
This should not be used directory, its essential a object to encapsulate
the logic in InterRepository.fetch().
"""
def __init__(self, to_repository, from_repository, last_revision=None, pb=None):
# result variables.
self.failed_revisions = []
self.count_copied = 0
if to_repository.control_files._transport.base == from_repository.control_files._transport.base:
# check that last_revision is in 'from' and then return a no-operation.
if last_revision not in (None, NULL_REVISION):
from_repository.get_revision(last_revision)
return
self.to_repository = to_repository
self.from_repository = from_repository
# must not mutate self._last_revision as its potentially a shared instance
self._last_revision = last_revision
if pb is None:
self.pb = bzrlib.ui.ui_factory.nested_progress_bar()
self.nested_pb = self.pb
else:
self.pb = pb
self.nested_pb = None
self.from_repository.lock_read()
try:
self.to_repository.lock_write()
try:
self.__fetch()
finally:
if self.nested_pb is not None:
self.nested_pb.finished()
self.to_repository.unlock()
finally:
self.from_repository.unlock()
def __fetch(self):
"""Primary worker function.
This initialises all the needed variables, and then fetches the
requested revisions, finally clearing the progress bar.
"""
self.to_weaves = self.to_repository.weave_store
self.to_control = self.to_repository.control_weaves
self.from_weaves = self.from_repository.weave_store
self.from_control = self.from_repository.control_weaves
self.count_total = 0
self.file_ids_names = {}
pp = ProgressPhase('Fetch phase', 4, self.pb)
try:
pp.next_phase()
revs = self._revids_to_fetch()
# something to do ?
if revs:
pp.next_phase()
self._fetch_weave_texts(revs)
pp.next_phase()
self._fetch_inventory_weave(revs)
pp.next_phase()
self._fetch_revision_texts(revs)
self.count_copied += len(revs)
finally:
self.pb.clear()
def _revids_to_fetch(self):
mutter('fetch up to rev {%s}', self._last_revision)
if self._last_revision is NULL_REVISION:
# explicit limit of no revisions needed
return None
if (self._last_revision != None and
self.to_repository.has_revision(self._last_revision)):
return None
try:
return self.to_repository.missing_revision_ids(self.from_repository,
self._last_revision)
except errors.NoSuchRevision:
raise InstallFailed([self._last_revision])
def _fetch_weave_texts(self, revs):
texts_pb = bzrlib.ui.ui_factory.nested_progress_bar()
try:
file_ids = self.from_repository.fileids_altered_by_revision_ids(revs)
count = 0
num_file_ids = len(file_ids)
for file_id, required_versions in file_ids.items():
texts_pb.update("fetch texts", count, num_file_ids)
count +=1
to_weave = self.to_weaves.get_weave_or_empty(file_id,
self.to_repository.get_transaction())
from_weave = self.from_weaves.get_weave(file_id,
self.from_repository.get_transaction())
# we fetch all the texts, because texts do
# not reference anything, and its cheap enough
to_weave.join(from_weave, version_ids=required_versions)
# we don't need *all* of this data anymore, but we dont know
# what we do. This cache clearing will result in a new read
# of the knit data when we do the checkout, but probably we
# want to emit the needed data on the fly rather than at the
# end anyhow.
# the from weave should know not to cache data being joined,
# but its ok to ask it to clear.
from_weave.clear_cache()
to_weave.clear_cache()
finally:
texts_pb.finished()
def _fetch_inventory_weave(self, revs):
pb = bzrlib.ui.ui_factory.nested_progress_bar()
try:
pb.update("fetch inventory", 0, 2)
to_weave = self.to_control.get_weave('inventory',
self.to_repository.get_transaction())
child_pb = bzrlib.ui.ui_factory.nested_progress_bar()
try:
# just merge, this is optimisable and its means we don't
# copy unreferenced data such as not-needed inventories.
pb.update("fetch inventory", 1, 3)
from_weave = self.from_repository.get_inventory_weave()
pb.update("fetch inventory", 2, 3)
# we fetch only the referenced inventories because we do not
# know for unselected inventories whether all their required
# texts are present in the other repository - it could be
# corrupt.
to_weave.join(from_weave, pb=child_pb, msg='merge inventory',
version_ids=revs)
finally:
child_pb.finished()
finally:
pb.finished()
class GenericRepoFetcher(RepoFetcher):
"""This is a generic repo to repo fetcher.
This makes minimal assumptions about repo layout and contents.
It triggers a reconciliation after fetching to ensure integrity.
"""
def _fetch_revision_texts(self, revs):
"""Fetch revision object texts"""
rev_pb = bzrlib.ui.ui_factory.nested_progress_bar()
try:
to_txn = self.to_transaction = self.to_repository.get_transaction()
count = 0
total = len(revs)
to_store = self.to_repository._revision_store
for rev in revs:
pb = bzrlib.ui.ui_factory.nested_progress_bar()
try:
pb.update('copying revisions', count, total)
try:
sig_text = self.from_repository.get_signature_text(rev)
to_store.add_revision_signature_text(rev, sig_text, to_txn)
except errors.NoSuchRevision:
# not signed.
pass
to_store.add_revision(self.from_repository.get_revision(rev),
to_txn)
count += 1
finally:
pb.finished()
# fixup inventory if needed:
# this is expensive because we have no inverse index to current ghosts.
# but on local disk its a few seconds and sftp push is already insane.
# so we just-do-it.
# FIXME: repository should inform if this is needed.
self.to_repository.reconcile()
finally:
rev_pb.finished()
class KnitRepoFetcher(RepoFetcher):
"""This is a knit format repository specific fetcher.
This differs from the GenericRepoFetcher by not doing a
reconciliation after copying, and using knit joining to
copy revision texts.
"""
def _fetch_revision_texts(self, revs):
# may need to be a InterRevisionStore call here.
from_transaction = self.from_repository.get_transaction()
to_transaction = self.to_repository.get_transaction()
to_sf = self.to_repository._revision_store.get_signature_file(
to_transaction)
from_sf = self.from_repository._revision_store.get_signature_file(
from_transaction)
to_sf.join(from_sf, version_ids=revs, ignore_missing=True)
to_rf = self.to_repository._revision_store.get_revision_file(
to_transaction)
from_rf = self.from_repository._revision_store.get_revision_file(
from_transaction)
to_rf.join(from_rf, version_ids=revs)
class Fetcher(object):
"""Backwards compatibility glue for branch.fetch()."""
@deprecated_method(zero_eight)
def __init__(self, to_branch, from_branch, last_revision=None, pb=None):
"""Please see branch.fetch()."""
to_branch.fetch(from_branch, last_revision, pb)
|