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
18
from cStringIO import StringIO
21
import bzrlib.errors as errors
22
from bzrlib.errors import InstallFailed, NoSuchRevision, WeaveError
23
from bzrlib.trace import mutter, note, warning
24
from bzrlib.branch import Branch
25
from bzrlib.progress import ProgressBar
26
from bzrlib.xml5 import serializer_v5
27
from bzrlib.osutils import sha_string, split_lines
29
"""Copying of history from one branch to another.
31
The basic plan is that every branch knows the history of everything
32
that has merged into it. As the first step of a merge, pull, or
33
branch operation we copy history from the source into the destination
36
The copying is done in a slightly complicated order. We don't want to
37
add a revision to the store until everything it refers to is also
38
stored, so that if a revision is present we can totally recreate it.
39
However, we can't know what files are included in a revision until we
40
read its inventory. Therefore, we first pull the XML and hold it in
41
memory until we've updated all of the files referenced.
44
# TODO: Avoid repeatedly opening weaves so many times.
46
# XXX: This doesn't handle ghost (not present in branch) revisions at
47
# all yet. I'm not sure they really should be supported.
49
# NOTE: This doesn't copy revisions which may be present but not
50
# merged into the last revision. I'm not sure we want to do that.
52
# - get a list of revisions that need to be pulled in
53
# - for each one, pull in that revision file
54
# and get the inventory, and store the inventory with right
56
# - and get the ancestry, and store that with right parents too
57
# - and keep a note of all file ids and version seen
58
# - then go through all files; for each one get the weave,
59
# and add in all file versions
63
def greedy_fetch(to_branch, from_branch, revision=None, pb=None):
64
f = Fetcher(to_branch, from_branch, revision, pb)
65
return f.count_copied, f.failed_revisions
69
class Fetcher(object):
70
"""Pull revisions and texts from one branch to another.
72
This doesn't update the destination's history; that can be done
73
separately if desired.
76
If set, pull only up to this revision_id.
80
last_revision -- if last_revision
81
is given it will be that, otherwise the last revision of
84
count_copied -- number of revisions copied
86
count_weaves -- number of file weaves copied
88
def __init__(self, to_branch, from_branch, last_revision=None, pb=None):
89
if to_branch == from_branch:
90
raise Exception("can't fetch from a branch to itself")
91
self.to_branch = to_branch
92
self.to_weaves = to_branch.weave_store
93
self.to_control = to_branch.control_weaves
94
self.from_branch = from_branch
95
self.from_weaves = from_branch.weave_store
96
self.from_control = from_branch.control_weaves
97
self.failed_revisions = []
100
self.count_weaves = 0
101
self.copied_file_ids = set()
103
self.pb = bzrlib.ui.ui_factory.progress_bar()
106
self.from_branch.lock_read()
108
self._fetch_revisions(last_revision)
110
self.from_branch.unlock()
113
def _fetch_revisions(self, last_revision):
115
self.last_revision = self._find_last_revision(last_revision)
116
except NoSuchRevision, e:
117
mutter('failed getting last revision: %s', e)
118
raise InstallFailed([last_revision])
119
mutter('fetch up to rev {%s}', self.last_revision)
120
if (self.last_revision is not None and
121
self.to_branch.has_revision(self.last_revision)):
124
revs_to_fetch = self._compare_ancestries()
126
raise InstallFailed([self.last_revision])
127
self._copy_revisions(revs_to_fetch)
128
self.new_ancestry = revs_to_fetch
130
def _find_last_revision(self, last_revision):
131
"""Find the limiting source revision.
133
Every ancestor of that revision will be merged across.
135
Returns the revision_id, or returns None if there's no history
136
in the source branch."""
137
self.pb.update('get source history')
138
from_history = self.from_branch.revision_history()
139
self.pb.update('get destination history')
141
self.from_branch.get_revision(last_revision)
144
return from_history[-1]
146
return None # no history in the source branch
149
def _compare_ancestries(self):
150
"""Get a list of revisions that must be copied.
152
That is, every revision that's in the ancestry of the source
153
branch and not in the destination branch."""
154
self.pb.update('get source ancestry')
155
self.from_ancestry = self.from_branch.get_ancestry(self.last_revision)
157
dest_last_rev = self.to_branch.last_revision()
158
self.pb.update('get destination ancestry')
160
dest_ancestry = self.to_branch.get_ancestry(dest_last_rev)
163
ss = set(dest_ancestry)
165
for rev_id in self.from_ancestry:
167
to_fetch.append(rev_id)
168
mutter('need to get revision {%s}', rev_id)
169
mutter('need to get %d revisions in total', len(to_fetch))
170
self.count_total = len(to_fetch)
173
def _copy_revisions(self, revs_to_fetch):
175
for rev_id in revs_to_fetch:
179
if self.to_branch.has_revision(rev_id):
181
self.pb.update('fetch revision', i, self.count_total)
182
self._copy_one_revision(rev_id)
183
self.count_copied += 1
186
def _copy_one_revision(self, rev_id):
187
"""Copy revision and everything referenced by it."""
188
mutter('copying revision {%s}', rev_id)
189
rev_xml = self.from_branch.get_revision_xml(rev_id)
190
inv_xml = self.from_branch.get_inventory_xml(rev_id)
191
rev = serializer_v5.read_revision_from_string(rev_xml)
192
inv = serializer_v5.read_inventory_from_string(inv_xml)
193
assert rev.revision_id == rev_id
194
assert rev.inventory_sha1 == sha_string(inv_xml)
195
mutter(' commiter %s, %d parents',
198
self._copy_new_texts(rev_id, inv)
199
parents = rev.parent_ids
200
for parent in parents:
201
if not self.to_branch.has_revision(parent):
202
parents.pop(parents.index(parent))
203
self._copy_inventory(rev_id, inv_xml, parents)
204
self.to_branch.revision_store.add(StringIO(rev_xml), rev_id)
205
mutter('copied revision %s', rev_id)
208
def _copy_inventory(self, rev_id, inv_xml, parent_ids):
209
self.to_control.add_text('inventory', rev_id,
210
split_lines(inv_xml), parent_ids,
211
self.to_branch.get_transaction())
213
def _copy_new_texts(self, rev_id, inv):
214
"""Copy any new texts occuring in this revision."""
215
# TODO: Rather than writing out weaves every time, hold them
216
# in memory until everything's done? But this way is nicer
217
# if it's interrupted.
218
for path, ie in inv.iter_entries():
219
if ie.revision != rev_id:
221
mutter('%s {%s} is changed in this revision',
223
self._copy_one_weave(rev_id, ie.file_id)
226
def _copy_one_weave(self, rev_id, file_id):
227
"""Copy one file weave."""
228
mutter('copy file {%s} modified in {%s}', file_id, rev_id)
229
if file_id in self.copied_file_ids:
230
mutter('file {%s} already copied', file_id)
232
from_weave = self.from_weaves.get_weave(file_id,
233
self.from_branch.get_transaction())
234
to_weave = self.to_weaves.get_weave_or_empty(file_id,
235
self.to_branch.get_transaction())
237
to_weave.join(from_weave)
238
except errors.WeaveParentMismatch:
239
to_weave.reweave(from_weave)
240
self.to_weaves.put_weave(file_id, to_weave,
241
self.to_branch.get_transaction())
242
self.count_weaves += 1
243
self.copied_file_ids.add(file_id)
244
mutter('copied file {%s}', file_id)
added
removed
bzrlib/fetch.py
