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
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
|
# Copyright (C) 2005-2010 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., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 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.
"""
import operator
from bzrlib.lazy_import import lazy_import
lazy_import(globals(), """
from bzrlib import (
tsort,
versionedfile,
)
""")
import bzrlib
from bzrlib import (
errors,
symbol_versioning,
ui,
)
from bzrlib.revision import NULL_REVISION
from bzrlib.trace import mutter
class RepoFetcher(object):
"""Pull revisions and texts from one repository to another.
This should not be used directly, it's essential a object to encapsulate
the logic in InterRepository.fetch().
"""
def __init__(self, to_repository, from_repository, last_revision=None,
find_ghosts=True, fetch_spec=None):
"""Create a repo fetcher.
:param last_revision: If set, try to limit to the data this revision
references.
:param find_ghosts: If True search the entire history for ghosts.
"""
# repository.fetch has the responsibility for short-circuiting
# attempts to copy between a repository and itself.
self.to_repository = to_repository
self.from_repository = from_repository
self.sink = to_repository._get_sink()
# must not mutate self._last_revision as its potentially a shared instance
self._last_revision = last_revision
self._fetch_spec = fetch_spec
self.find_ghosts = find_ghosts
self.from_repository.lock_read()
mutter("Using fetch logic to copy between %s(%s) and %s(%s)",
self.from_repository, self.from_repository._format,
self.to_repository, self.to_repository._format)
try:
self.__fetch()
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.
"""
# Roughly this is what we're aiming for fetch to become:
#
# missing = self.sink.insert_stream(self.source.get_stream(search))
# if missing:
# missing = self.sink.insert_stream(self.source.get_items(missing))
# assert not missing
self.count_total = 0
self.file_ids_names = {}
pb = ui.ui_factory.nested_progress_bar()
pb.show_pct = pb.show_count = False
try:
pb.update("Finding revisions", 0, 2)
search = self._revids_to_fetch()
if search is None:
return
pb.update("Fetching revisions", 1, 2)
self._fetch_everything_for_search(search)
finally:
pb.finished()
def _fetch_everything_for_search(self, search):
"""Fetch all data for the given set of revisions."""
# The first phase is "file". We pass the progress bar for it directly
# into item_keys_introduced_by, which has more information about how
# that phase is progressing than we do. Progress updates for the other
# phases are taken care of in this function.
# XXX: there should be a clear owner of the progress reporting. Perhaps
# item_keys_introduced_by should have a richer API than it does at the
# moment, so that it can feed the progress information back to this
# function?
if (self.from_repository._format.rich_root_data and
not self.to_repository._format.rich_root_data):
raise errors.IncompatibleRepositories(
self.from_repository, self.to_repository,
"different rich-root support")
pb = ui.ui_factory.nested_progress_bar()
try:
pb.update("Get stream source")
source = self.from_repository._get_source(
self.to_repository._format)
stream = source.get_stream(search)
from_format = self.from_repository._format
pb.update("Inserting stream")
resume_tokens, missing_keys = self.sink.insert_stream(
stream, from_format, [])
if self.to_repository._fallback_repositories:
missing_keys.update(
self._parent_inventories(search.get_keys()))
if missing_keys:
pb.update("Missing keys")
stream = source.get_stream_for_missing_keys(missing_keys)
pb.update("Inserting missing keys")
resume_tokens, missing_keys = self.sink.insert_stream(
stream, from_format, resume_tokens)
if missing_keys:
raise AssertionError(
"second push failed to complete a fetch %r." % (
missing_keys,))
if resume_tokens:
raise AssertionError(
"second push failed to commit the fetch %r." % (
resume_tokens,))
pb.update("Finishing stream")
self.sink.finished()
finally:
pb.finished()
def _revids_to_fetch(self):
"""Determines the exact revisions needed from self.from_repository to
install self._last_revision in self.to_repository.
If no revisions need to be fetched, then this just returns None.
"""
if self._fetch_spec is not None:
return self._fetch_spec
mutter('fetch up to rev {%s}', self._last_revision)
if self._last_revision is NULL_REVISION:
# explicit limit of no revisions needed
return None
return self.to_repository.search_missing_revision_ids(
self.from_repository, self._last_revision,
find_ghosts=self.find_ghosts)
def _parent_inventories(self, revision_ids):
# Find all the parent revisions referenced by the stream, but
# not present in the stream, and make sure we send their
# inventories.
parent_maps = self.to_repository.get_parent_map(revision_ids)
parents = set()
map(parents.update, parent_maps.itervalues())
parents.discard(NULL_REVISION)
parents.difference_update(revision_ids)
missing_keys = set(('inventories', rev_id) for rev_id in parents)
return missing_keys
class Inter1and2Helper(object):
"""Helper for operations that convert data from model 1 and 2
This is for use by fetchers and converters.
"""
def __init__(self, source):
"""Constructor.
:param source: The repository data comes from
"""
self.source = source
def iter_rev_trees(self, revs):
"""Iterate through RevisionTrees efficiently.
Additionally, the inventory's revision_id is set if unset.
Trees are retrieved in batches of 100, and then yielded in the order
they were requested.
:param revs: A list of revision ids
"""
# In case that revs is not a list.
revs = list(revs)
while revs:
for tree in self.source.revision_trees(revs[:100]):
if tree.inventory.revision_id is None:
tree.inventory.revision_id = tree.get_revision_id()
yield tree
revs = revs[100:]
def _find_root_ids(self, revs, parent_map, graph):
revision_root = {}
for tree in self.iter_rev_trees(revs):
revision_id = tree.inventory.root.revision
root_id = tree.get_root_id()
revision_root[revision_id] = root_id
# Find out which parents we don't already know root ids for
parents = set()
for revision_parents in parent_map.itervalues():
parents.update(revision_parents)
parents.difference_update(revision_root.keys() + [NULL_REVISION])
# Limit to revisions present in the versionedfile
parents = graph.get_parent_map(parents).keys()
for tree in self.iter_rev_trees(parents):
root_id = tree.get_root_id()
revision_root[tree.get_revision_id()] = root_id
return revision_root
def generate_root_texts(self, revs):
"""Generate VersionedFiles for all root ids.
:param revs: the revisions to include
"""
graph = self.source.get_graph()
parent_map = graph.get_parent_map(revs)
rev_order = tsort.topo_sort(parent_map)
rev_id_to_root_id = self._find_root_ids(revs, parent_map, graph)
root_id_order = [(rev_id_to_root_id[rev_id], rev_id) for rev_id in
rev_order]
# Guaranteed stable, this groups all the file id operations together
# retaining topological order within the revisions of a file id.
# File id splits and joins would invalidate this, but they don't exist
# yet, and are unlikely to in non-rich-root environments anyway.
root_id_order.sort(key=operator.itemgetter(0))
# Create a record stream containing the roots to create.
if len(revs) > 100:
# XXX: not covered by tests, should have a flag to always run
# this. -- mbp 20100129
graph = self.source_repo.get_known_graph_ancestry(revs)
new_roots_stream = _new_root_data_stream(
root_id_order, rev_id_to_root_id, parent_map, self.source, graph)
return [('texts', new_roots_stream)]
def _get_rich_root_heads_graph(source_repo, revision_ids):
"""Get a Graph object suitable for asking heads() for new rich roots."""
return
def _new_root_data_stream(
root_keys_to_create, rev_id_to_root_id_map, parent_map, repo, graph=None):
"""Generate a texts substream of synthesised root entries.
Used in fetches that do rich-root upgrades.
:param root_keys_to_create: iterable of (root_id, rev_id) pairs describing
the root entries to create.
:param rev_id_to_root_id_map: dict of known rev_id -> root_id mappings for
calculating the parents. If a parent rev_id is not found here then it
will be recalculated.
:param parent_map: a parent map for all the revisions in
root_keys_to_create.
:param graph: a graph to use instead of repo.get_graph().
"""
for root_key in root_keys_to_create:
root_id, rev_id = root_key
parent_keys = _parent_keys_for_root_version(
root_id, rev_id, rev_id_to_root_id_map, parent_map, repo, graph)
yield versionedfile.FulltextContentFactory(
root_key, parent_keys, None, '')
def _parent_keys_for_root_version(
root_id, rev_id, rev_id_to_root_id_map, parent_map, repo, graph=None):
"""Get the parent keys for a given root id.
A helper function for _new_root_data_stream.
"""
# Include direct parents of the revision, but only if they used the same
# root_id and are heads.
rev_parents = parent_map[rev_id]
parent_ids = []
for parent_id in rev_parents:
if parent_id == NULL_REVISION:
continue
if parent_id not in rev_id_to_root_id_map:
# We probably didn't read this revision, go spend the extra effort
# to actually check
try:
tree = repo.revision_tree(parent_id)
except errors.NoSuchRevision:
# Ghost, fill out rev_id_to_root_id in case we encounter this
# again.
# But set parent_root_id to None since we don't really know
parent_root_id = None
else:
parent_root_id = tree.get_root_id()
rev_id_to_root_id_map[parent_id] = None
# XXX: why not:
# rev_id_to_root_id_map[parent_id] = parent_root_id
# memory consumption maybe?
else:
parent_root_id = rev_id_to_root_id_map[parent_id]
if root_id == parent_root_id:
# With stacking we _might_ want to refer to a non-local revision,
# but this code path only applies when we have the full content
# available, so ghosts really are ghosts, not just the edge of
# local data.
parent_ids.append(parent_id)
else:
# root_id may be in the parent anyway.
try:
tree = repo.revision_tree(parent_id)
except errors.NoSuchRevision:
# ghost, can't refer to it.
pass
else:
try:
parent_ids.append(tree.inventory[root_id].revision)
except errors.NoSuchId:
# not in the tree
pass
# Drop non-head parents
if graph is None:
graph = repo.get_graph()
heads = graph.heads(parent_ids)
selected_ids = []
for parent_id in parent_ids:
if parent_id in heads and parent_id not in selected_ids:
selected_ids.append(parent_id)
parent_keys = [(root_id, parent_id) for parent_id in selected_ids]
return parent_keys
|