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
from bzrlib.trace import mutter, note, warning
22
from bzrlib.branch import Branch, INVENTORY_FILEID, ANCESTRY_FILEID
23
from bzrlib.progress import ProgressBar
24
from bzrlib.xml5 import serializer_v5
25
from bzrlib.osutils import sha_string, split_lines
26
from bzrlib.errors import NoSuchRevision
28
"""Copying of history from one branch to another.
30
The basic plan is that every branch knows the history of everything
31
that has merged into it. As the first step of a merge, pull, or
32
branch operation we copy history from the source into the destination
35
The copying is done in a slightly complicated order. We don't want to
36
add a revision to the store until everything it refers to is also
37
stored, so that if a revision is present we can totally recreate it.
38
However, we can't know what files are included in a revision until we
39
read its inventory. Therefore, we first pull the XML and hold it in
40
memory until we've updated all of the files referenced.
43
# TODO: Avoid repeatedly opening weaves so many times.
45
# XXX: This doesn't handle ghost (not present in branch) revisions at
46
# all yet. I'm not sure they really should be supported.
48
# TODO: This doesn't handle revisions which may be present but not
49
# merged into the last revision.
51
# - get a list of revisions that need to be pulled in
52
# - for each one, pull in that revision file
53
# and get the inventory, and store the inventory with right
55
# - and get the ancestry, and store that with right parents too
56
# - and keep a note of all file ids and version seen
57
# - then go through all files; for each one get the weave,
58
# and add in all file versions
62
def greedy_fetch(to_branch, from_branch, revision, pb):
63
f = Fetcher(to_branch, from_branch, revision, pb)
64
return f.count_copied, f.failed_revisions
67
class Fetcher(object):
68
"""Pull history from one branch to another.
71
If set, pull only up to this revision_id.
73
def __init__(self, to_branch, from_branch, revision_limit=None, pb=None):
74
self.to_branch = to_branch
75
self.from_branch = from_branch
76
self.failed_revisions = []
80
self.pb = bzrlib.ui.ui_factory.progress_bar()
83
self.revision_limit = self._find_revision_limit(revision_limit)
84
revs_to_fetch = self._compare_ancestries()
85
self._copy_revisions(revs_to_fetch)
89
def _find_revision_limit(self, revision_limit):
90
"""Find the limiting source revision.
92
Every ancestor of that revision will be merged across.
94
Returns the revision_id, or returns None if there's no history
95
in the source branch."""
96
self.pb.update('get source history')
97
from_history = self.from_branch.revision_history()
98
self.pb.update('get destination history')
100
if revision_limit not in from_history:
101
raise NoSuchRevision(self.from_branch, revision_limit)
103
return revision_limit
105
return from_history[-1]
107
return None # no history in the source branch
110
def _compare_ancestries(self):
111
"""Get a list of revisions that must be copied.
113
That is, every revision that's in the ancestry of the source
114
branch and not in the destination branch."""
115
self.pb.update('get source ancestry')
116
self.from_ancestry = self.from_branch.get_ancestry(self.revision_limit)
118
dest_last_rev = self.to_branch.last_revision()
119
self.pb.update('get destination ancestry')
121
dest_ancestry = self.to_branch.get_ancestry(dest_last_rev)
124
ss = set(dest_ancestry)
126
for rev_id in self.from_ancestry:
128
to_fetch.append(rev_id)
129
mutter('need to get revision {%s}', rev_id)
130
mutter('need to get %d revisions in total', len(to_fetch))
131
self.count_total = len(to_fetch)
136
def _copy_revisions(self, revs_to_fetch):
138
for rev_id in revs_to_fetch:
139
self.pb.update('fetch revision', i, self.count_total)
140
self._copy_one_revision(rev_id)
144
def _copy_one_revision(self, rev_id):
145
"""Copy revision and everything referenced by it."""
146
mutter('copying revision {%s}', rev_id)
147
rev_xml = self.from_branch.get_revision_xml(rev_id)
148
inv_xml = self.from_branch.get_inventory_xml(rev_id)
149
rev = serializer_v5.read_revision_from_string(rev_xml)
150
inv = serializer_v5.read_inventory_from_string(inv_xml)
151
assert rev.revision_id == rev_id
152
assert rev.inventory_sha1 == sha_string(inv_xml)
153
mutter(' commiter %s, %d parents',
156
self._copy_new_texts(rev_id, inv)
157
self.to_branch.weave_store.add_text(INVENTORY_FILEID, rev_id,
158
split_lines(inv_xml), rev.parents)
159
self.to_branch.revision_store.add(StringIO(rev_xml), rev_id)
162
def _copy_new_texts(self, rev_id, inv):
163
"""Copy any new texts occuring in this revision."""
164
# TODO: Rather than writing out weaves every time, hold them
165
# in memory until everything's done? But this way is nicer
166
# if it's interrupted.
167
for path, ie in inv.iter_entries():
168
if ie.kind != 'file':
170
if ie.text_version != rev_id:
172
mutter('%s {%s} is changed in this revision',
174
self._copy_one_text(rev_id, ie.file_id)
177
def _copy_one_text(self, rev_id, file_id):
178
"""Copy one file text."""
179
from_weave = self.from_branch.weave_store.get_weave(file_id)
180
from_idx = from_weave.lookup(rev_id)
181
from_parents = map(from_weave.idx_to_name, from_weave.parents(from_idx))
182
text_lines = from_weave.get(from_idx)
183
to_weave = self.to_branch.weave_store.get_weave_or_empty(file_id)
184
to_parents = map(to_weave.lookup, from_parents)
185
# it's ok to add even if the text is already there
186
to_weave.add(rev_id, to_parents, text_lines)
187
self.to_branch.weave_store.put_weave(file_id, to_weave)
added
removed
bzrlib/fetch.py
