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
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
|
# Copyright (C) 2009, 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
"""Implementation of Graph algorithms when we have already loaded everything.
"""
from collections import deque
from bzrlib import (
errors,
revision,
)
class _KnownGraphNode(object):
"""Represents a single object in the known graph."""
__slots__ = ('key', 'parent_keys', 'child_keys', 'gdfo')
def __init__(self, key, parent_keys):
self.key = key
self.parent_keys = parent_keys
self.child_keys = []
# Greatest distance from origin
self.gdfo = None
def __repr__(self):
return '%s(%s gdfo:%s par:%s child:%s)' % (
self.__class__.__name__, self.key, self.gdfo,
self.parent_keys, self.child_keys)
class _MergeSortNode(object):
"""Information about a specific node in the merge graph."""
__slots__ = ('key', 'merge_depth', 'revno', 'end_of_merge')
def __init__(self, key, merge_depth, revno, end_of_merge):
self.key = key
self.merge_depth = merge_depth
self.revno = revno
self.end_of_merge = end_of_merge
class KnownGraph(object):
"""This is a class which assumes we already know the full graph."""
def __init__(self, parent_map, do_cache=True):
"""Create a new KnownGraph instance.
:param parent_map: A dictionary mapping key => parent_keys
"""
self._nodes = {}
# Maps {frozenset(revision_id, revision_id): heads}
self._known_heads = {}
self.do_cache = do_cache
self._initialize_nodes(parent_map)
self._find_gdfo()
def _initialize_nodes(self, parent_map):
"""Populate self._nodes.
After this has finished:
- self._nodes will have an entry for every entry in parent_map.
- ghosts will have a parent_keys = None,
- all nodes found will also have .child_keys populated with all known
child_keys,
"""
nodes = self._nodes
for key, parent_keys in parent_map.iteritems():
if key in nodes:
node = nodes[key]
node.parent_keys = parent_keys
else:
node = _KnownGraphNode(key, parent_keys)
nodes[key] = node
for parent_key in parent_keys:
try:
parent_node = nodes[parent_key]
except KeyError:
parent_node = _KnownGraphNode(parent_key, None)
nodes[parent_key] = parent_node
parent_node.child_keys.append(key)
def _find_tails(self):
return [node for node in self._nodes.itervalues()
if not node.parent_keys]
def _find_tips(self):
return [node for node in self._nodes.itervalues()
if not node.child_keys]
def _find_gdfo(self):
nodes = self._nodes
known_parent_gdfos = {}
pending = []
for node in self._find_tails():
node.gdfo = 1
pending.append(node)
while pending:
node = pending.pop()
for child_key in node.child_keys:
child = nodes[child_key]
if child_key in known_parent_gdfos:
known_gdfo = known_parent_gdfos[child_key] + 1
present = True
else:
known_gdfo = 1
present = False
if child.gdfo is None or node.gdfo + 1 > child.gdfo:
child.gdfo = node.gdfo + 1
if known_gdfo == len(child.parent_keys):
# We are the last parent updating that node, we can
# continue from there
pending.append(child)
if present:
del known_parent_gdfos[child_key]
else:
# Update known_parent_gdfos for a key we couldn't process
known_parent_gdfos[child_key] = known_gdfo
def add_node(self, key, parent_keys):
"""Add a new node to the graph.
If this fills in a ghost, then the gdfos of all children will be
updated accordingly.
:param key: The node being added. If this is a duplicate, this is a
no-op.
:param parent_keys: The parents of the given node.
:return: None (should we return if this was a ghost, etc?)
"""
nodes = self._nodes
if key in nodes:
node = nodes[key]
if node.parent_keys is None:
node.parent_keys = parent_keys
# A ghost is being added, we can no-longer trust the heads
# cache, so clear it
self._known_heads.clear()
else:
# Make sure we compare a list to a list, as tuple != list.
parent_keys = list(parent_keys)
existing_parent_keys = list(node.parent_keys)
if parent_keys == existing_parent_keys:
return # Identical content
else:
raise ValueError('Parent key mismatch, existing node %s'
' has parents of %s not %s'
% (key, existing_parent_keys, parent_keys))
else:
node = _KnownGraphNode(key, parent_keys)
nodes[key] = node
parent_gdfo = 0
for parent_key in parent_keys:
try:
parent_node = nodes[parent_key]
except KeyError:
parent_node = _KnownGraphNode(parent_key, None)
# Ghosts and roots have gdfo 1
parent_node.gdfo = 1
nodes[parent_key] = parent_node
if parent_gdfo < parent_node.gdfo:
parent_gdfo = parent_node.gdfo
parent_node.child_keys.append(key)
node.gdfo = parent_gdfo + 1
# Now fill the gdfo to all children
# Note that this loop is slightly inefficient, in that we may visit the
# same child (and its decendents) more than once, however, it is
# 'efficient' in that we only walk to nodes that would be updated,
# rather than all nodes
# We use a deque rather than a simple list stack, to go for BFD rather
# than DFD. So that if a longer path is possible, we walk it before we
# get to the final child
pending = deque([node])
while pending:
node = pending.popleft()
next_gdfo = node.gdfo + 1
for child_key in node.child_keys:
child = nodes[child_key]
if child.gdfo < next_gdfo:
# This child is being updated, we need to check its
# children
child.gdfo = next_gdfo
pending.append(child)
def heads(self, keys):
"""Return the heads from amongst keys.
This is done by searching the ancestries of each key. Any key that is
reachable from another key is not returned; all the others are.
This operation scales with the relative depth between any two keys. It
uses gdfo to avoid walking all ancestry.
:param keys: An iterable of keys.
:return: A set of the heads. Note that as a set there is no ordering
information. Callers will need to filter their input to create
order if they need it.
"""
candidate_nodes = dict((key, self._nodes[key]) for key in keys)
if revision.NULL_REVISION in candidate_nodes:
# NULL_REVISION is only a head if it is the only entry
candidate_nodes.pop(revision.NULL_REVISION)
if not candidate_nodes:
return frozenset([revision.NULL_REVISION])
if len(candidate_nodes) < 2:
# No or only one candidate
return frozenset(candidate_nodes)
heads_key = frozenset(candidate_nodes)
# Do we have a cached result ?
try:
heads = self._known_heads[heads_key]
return heads
except KeyError:
pass
# Let's compute the heads
seen = set()
pending = []
min_gdfo = None
for node in candidate_nodes.values():
if node.parent_keys:
pending.extend(node.parent_keys)
if min_gdfo is None or node.gdfo < min_gdfo:
min_gdfo = node.gdfo
nodes = self._nodes
while pending:
node_key = pending.pop()
if node_key in seen:
# node already appears in some ancestry
continue
seen.add(node_key)
node = nodes[node_key]
if node.gdfo <= min_gdfo:
continue
if node.parent_keys:
pending.extend(node.parent_keys)
heads = heads_key.difference(seen)
if self.do_cache:
self._known_heads[heads_key] = heads
return heads
def topo_sort(self):
"""Return the nodes in topological order.
All parents must occur before all children.
"""
for node in self._nodes.itervalues():
if node.gdfo is None:
raise errors.GraphCycleError(self._nodes)
pending = self._find_tails()
pending_pop = pending.pop
pending_append = pending.append
topo_order = []
topo_order_append = topo_order.append
num_seen_parents = dict.fromkeys(self._nodes, 0)
while pending:
node = pending_pop()
if node.parent_keys is not None:
# We don't include ghost parents
topo_order_append(node.key)
for child_key in node.child_keys:
child_node = self._nodes[child_key]
seen_parents = num_seen_parents[child_key] + 1
if seen_parents == len(child_node.parent_keys):
# All parents have been processed, enqueue this child
pending_append(child_node)
# This has been queued up, stop tracking it
del num_seen_parents[child_key]
else:
num_seen_parents[child_key] = seen_parents
# We started from the parents, so we don't need to do anymore work
return topo_order
def gc_sort(self):
"""Return a reverse topological ordering which is 'stable'.
There are a few constraints:
1) Reverse topological (all children before all parents)
2) Grouped by prefix
3) 'stable' sorting, so that we get the same result, independent of
machine, or extra data.
To do this, we use the same basic algorithm as topo_sort, but when we
aren't sure what node to access next, we sort them lexicographically.
"""
tips = self._find_tips()
# Split the tips based on prefix
prefix_tips = {}
for node in tips:
if node.key.__class__ is str or len(node.key) == 1:
prefix = ''
else:
prefix = node.key[0]
prefix_tips.setdefault(prefix, []).append(node)
num_seen_children = dict.fromkeys(self._nodes, 0)
result = []
for prefix in sorted(prefix_tips):
pending = sorted(prefix_tips[prefix], key=lambda n:n.key,
reverse=True)
while pending:
node = pending.pop()
if node.parent_keys is None:
# Ghost node, skip it
continue
result.append(node.key)
for parent_key in sorted(node.parent_keys, reverse=True):
parent_node = self._nodes[parent_key]
seen_children = num_seen_children[parent_key] + 1
if seen_children == len(parent_node.child_keys):
# All children have been processed, enqueue this parent
pending.append(parent_node)
# This has been queued up, stop tracking it
del num_seen_children[parent_key]
else:
num_seen_children[parent_key] = seen_children
return result
def merge_sort(self, tip_key):
"""Compute the merge sorted graph output."""
from bzrlib import tsort
as_parent_map = dict((node.key, node.parent_keys)
for node in self._nodes.itervalues()
if node.parent_keys is not None)
# We intentionally always generate revnos and never force the
# mainline_revisions
# Strip the sequence_number that merge_sort generates
return [_MergeSortNode(key, merge_depth, revno, end_of_merge)
for _, key, merge_depth, revno, end_of_merge
in tsort.merge_sort(as_parent_map, tip_key,
mainline_revisions=None,
generate_revno=True)]
def get_parent_keys(self, key):
"""Get the parents for a key
Returns a list containg the parents keys. If the key is a ghost,
None is returned. A KeyError will be raised if the key is not in
the graph.
:param keys: Key to check (eg revision_id)
:return: A list of parents
"""
return self._nodes[key].parent_keys
def get_child_keys(self, key):
"""Get the children for a key
Returns a list containg the children keys. A KeyError will be raised
if the key is not in the graph.
:param keys: Key to check (eg revision_id)
:return: A list of children
"""
return self._nodes[key].child_keys
|