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.xml5 import serializer_v5
29
from bzrlib.osutils import sha_string, split_lines
31
"""Copying of history from one branch to another.
33
The basic plan is that every branch knows the history of everything
34
that has merged into it. As the first step of a merge, pull, or
35
branch operation we copy history from the source into the destination
38
The copying is done in a slightly complicated order. We don't want to
39
add a revision to the store until everything it refers to is also
40
stored, so that if a revision is present we can totally recreate it.
41
However, we can't know what files are included in a revision until we
42
read its inventory. Therefore, we first pull the XML and hold it in
43
memory until we've updated all of the files referenced.
46
# TODO: Avoid repeatedly opening weaves so many times.
48
# XXX: This doesn't handle ghost (not present in branch) revisions at
49
# all yet. I'm not sure they really should be supported.
51
# NOTE: This doesn't copy revisions which may be present but not
52
# merged into the last revision. I'm not sure we want to do that.
54
# - get a list of revisions that need to be pulled in
55
# - for each one, pull in that revision file
56
# and get the inventory, and store the inventory with right
58
# - and get the ancestry, and store that with right parents too
59
# - and keep a note of all file ids and version seen
60
# - then go through all files; for each one get the weave,
61
# and add in all file versions
65
def greedy_fetch(to_branch, from_branch, revision=None, pb=None):
66
f = Fetcher(to_branch, from_branch, revision, pb)
67
return f.count_copied, f.failed_revisions
71
class Fetcher(object):
72
"""Pull revisions and texts from one branch to another.
74
This doesn't update the destination's history; that can be done
75
separately if desired.
78
If set, pull only up to this revision_id.
82
last_revision -- if last_revision
83
is given it will be that, otherwise the last revision of
86
count_copied -- number of revisions copied
88
count_weaves -- number of file weaves copied
90
def __init__(self, to_branch, from_branch, last_revision=None, pb=None):
91
if to_branch == from_branch:
92
raise Exception("can't fetch from a branch to itself")
93
self.to_branch = to_branch
94
self.to_weaves = to_branch.weave_store
95
self.to_control = to_branch.control_weaves
96
self.from_branch = from_branch
97
self.from_weaves = from_branch.weave_store
98
self.from_control = from_branch.control_weaves
99
self.failed_revisions = []
100
self.count_copied = 0
102
self.count_weaves = 0
103
self.copied_file_ids = set()
105
self.pb = bzrlib.ui.ui_factory.progress_bar()
108
self.from_branch.lock_read()
110
self._fetch_revisions(last_revision)
112
self.from_branch.unlock()
115
def _fetch_revisions(self, last_revision):
116
self.last_revision = self._find_last_revision(last_revision)
117
mutter('fetch up to rev {%s}', self.last_revision)
118
if (self.last_revision is not None and
119
self.to_branch.has_revision(self.last_revision)):
122
revs_to_fetch = self._compare_ancestries()
124
raise InstallFailed([self.last_revision])
125
self._copy_revisions(revs_to_fetch)
126
self.new_ancestry = revs_to_fetch
128
def _find_last_revision(self, last_revision):
129
"""Find the limiting source revision.
131
Every ancestor of that revision will be merged across.
133
Returns the revision_id, or returns None if there's no history
134
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
return from_history[-1]
143
return None # no history in the source branch
146
def _compare_ancestries(self):
147
"""Get a list of revisions that must be copied.
149
That is, every revision that's in the ancestry of the source
150
branch and not in the destination branch."""
151
self.pb.update('get source ancestry')
152
self.from_ancestry = self.from_branch.get_ancestry(self.last_revision)
154
dest_last_rev = self.to_branch.last_revision()
155
self.pb.update('get destination ancestry')
157
dest_ancestry = self.to_branch.get_ancestry(dest_last_rev)
160
ss = set(dest_ancestry)
162
for rev_id in self.from_ancestry:
164
to_fetch.append(rev_id)
165
mutter('need to get revision {%s}', rev_id)
166
mutter('need to get %d revisions in total', len(to_fetch))
167
self.count_total = len(to_fetch)
170
def _copy_revisions(self, revs_to_fetch):
172
for rev_id in revs_to_fetch:
176
if self.to_branch.has_revision(rev_id):
178
self.pb.update('fetch revision', i, self.count_total)
179
self._copy_one_revision(rev_id)
180
self.count_copied += 1
183
def _copy_one_revision(self, rev_id):
184
"""Copy revision and everything referenced by it."""
185
mutter('copying revision {%s}', rev_id)
186
rev_xml = self.from_branch.get_revision_xml(rev_id)
187
inv_xml = self.from_branch.get_inventory_xml(rev_id)
188
rev = serializer_v5.read_revision_from_string(rev_xml)
189
inv = serializer_v5.read_inventory_from_string(inv_xml)
190
assert rev.revision_id == rev_id
191
assert rev.inventory_sha1 == sha_string(inv_xml)
192
mutter(' commiter %s, %d parents',
195
self._copy_new_texts(rev_id, inv)
196
parents = rev.parent_ids
197
new_parents = copy(parents)
198
for parent in parents:
199
if not self.to_branch.has_revision(parent):
200
new_parents.pop(new_parents.index(parent))
201
self._copy_inventory(rev_id, inv_xml, new_parents)
202
self.to_branch.revision_store.add(StringIO(rev_xml), rev_id)
203
mutter('copied revision %s', rev_id)
205
def _copy_inventory(self, rev_id, inv_xml, parent_ids):
206
self.to_control.add_text('inventory', rev_id,
207
split_lines(inv_xml), parent_ids,
208
self.to_branch.get_transaction())
210
def _copy_new_texts(self, rev_id, inv):
211
"""Copy any new texts occuring in this revision."""
212
# TODO: Rather than writing out weaves every time, hold them
213
# in memory until everything's done? But this way is nicer
214
# if it's interrupted.
215
for path, ie in inv.iter_entries():
216
self._copy_one_weave(rev_id, ie.file_id, ie.revision)
218
def _copy_one_weave(self, rev_id, file_id, text_revision):
219
"""Copy one file weave, esuring the result contains text_revision."""
220
to_weave = self.to_weaves.get_weave_or_empty(file_id,
221
self.to_branch.get_transaction())
222
if text_revision in to_weave:
224
from_weave = self.from_weaves.get_weave(file_id,
225
self.from_branch.get_transaction())
226
if text_revision not in from_weave:
227
raise MissingText(self.from_branch, text_revision, file_id)
228
mutter('copy file {%s} modified in {%s}', file_id, rev_id)
230
to_weave.join(from_weave)
231
except errors.WeaveParentMismatch:
232
to_weave.reweave(from_weave)
233
self.to_weaves.put_weave(file_id, to_weave,
234
self.to_branch.get_transaction())
235
self.count_weaves += 1
236
self.copied_file_ids.add(file_id)
237
mutter('copied file {%s}', file_id)
added
removed
bzrlib/fetch.py
