1
# Copyright (C) 2006, 2007, 2008 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
17
"""DirState objects record the state of a directory and its bzr metadata.
19
Pseudo EBNF grammar for the state file. Fields are separated by NULLs, and
20
lines by NL. The field delimiters are ommitted in the grammar, line delimiters
21
are not - this is done for clarity of reading. All string data is in utf8.
23
MINIKIND = "f" | "d" | "l" | "a" | "r" | "t";
26
WHOLE_NUMBER = {digit}, digit;
28
REVISION_ID = a non-empty utf8 string;
30
dirstate format = header line, full checksum, row count, parent details,
31
ghost_details, entries;
32
header line = "#bazaar dirstate flat format 3", NL;
33
full checksum = "crc32: ", ["-"], WHOLE_NUMBER, NL;
34
row count = "num_entries: ", WHOLE_NUMBER, NL;
35
parent_details = WHOLE NUMBER, {REVISION_ID}* NL;
36
ghost_details = WHOLE NUMBER, {REVISION_ID}*, NL;
38
entry = entry_key, current_entry_details, {parent_entry_details};
39
entry_key = dirname, basename, fileid;
40
current_entry_details = common_entry_details, working_entry_details;
41
parent_entry_details = common_entry_details, history_entry_details;
42
common_entry_details = MINIKIND, fingerprint, size, executable
43
working_entry_details = packed_stat
44
history_entry_details = REVISION_ID;
47
fingerprint = a nonempty utf8 sequence with meaning defined by minikind.
49
Given this definition, the following is useful to know:
50
entry (aka row) - all the data for a given key.
51
entry[0]: The key (dirname, basename, fileid)
55
entry[1]: The tree(s) data for this path and id combination.
56
entry[1][0]: The current tree
57
entry[1][1]: The second tree
59
For an entry for a tree, we have (using tree 0 - current tree) to demonstrate:
60
entry[1][0][0]: minikind
61
entry[1][0][1]: fingerprint
63
entry[1][0][3]: executable
64
entry[1][0][4]: packed_stat
66
entry[1][1][4]: revision_id
68
There may be multiple rows at the root, one per id present in the root, so the
69
in memory root row is now:
70
self._dirblocks[0] -> ('', [entry ...]),
71
and the entries in there are
74
entries[0][2]: file_id
75
entries[1][0]: The tree data for the current tree for this fileid at /
79
'r' is a relocated entry: This path is not present in this tree with this id,
80
but the id can be found at another location. The fingerprint is used to
81
point to the target location.
82
'a' is an absent entry: In that tree the id is not present at this path.
83
'd' is a directory entry: This path in this tree is a directory with the
84
current file id. There is no fingerprint for directories.
85
'f' is a file entry: As for directory, but its a file. The fingerprint is a
87
'l' is a symlink entry: As for directory, but a symlink. The fingerprint is the
89
't' is a reference to a nested subtree; the fingerprint is the referenced
94
The entries on disk and in memory are ordered according to the following keys:
96
directory, as a list of components
100
--- Format 1 had the following different definition: ---
101
rows = dirname, NULL, basename, NULL, MINIKIND, NULL, fileid_utf8, NULL,
102
WHOLE NUMBER (* size *), NULL, packed stat, NULL, sha1|symlink target,
104
PARENT ROW = NULL, revision_utf8, NULL, MINIKIND, NULL, dirname, NULL,
105
basename, NULL, WHOLE NUMBER (* size *), NULL, "y" | "n", NULL,
108
PARENT ROW's are emitted for every parent that is not in the ghosts details
109
line. That is, if the parents are foo, bar, baz, and the ghosts are bar, then
110
each row will have a PARENT ROW for foo and baz, but not for bar.
113
In any tree, a kind of 'moved' indicates that the fingerprint field
114
(which we treat as opaque data specific to the 'kind' anyway) has the
115
details for the id of this row in that tree.
117
I'm strongly tempted to add a id->path index as well, but I think that
118
where we need id->path mapping; we also usually read the whole file, so
119
I'm going to skip that for the moment, as we have the ability to locate
120
via bisect any path in any tree, and if we lookup things by path, we can
121
accumulate an id->path mapping as we go, which will tend to match what we
124
I plan to implement this asap, so please speak up now to alter/tweak the
125
design - and once we stabilise on this, I'll update the wiki page for
128
The rationale for all this is that we want fast operations for the
129
common case (diff/status/commit/merge on all files) and extremely fast
130
operations for the less common but still occurs a lot status/diff/commit
131
on specific files). Operations on specific files involve a scan for all
132
the children of a path, *in every involved tree*, which the current
133
format did not accommodate.
137
1) Fast end to end use for bzr's top 5 uses cases. (commmit/diff/status/merge/???)
138
2) fall back current object model as needed.
139
3) scale usably to the largest trees known today - say 50K entries. (mozilla
140
is an example of this)
144
Eventually reuse dirstate objects across locks IFF the dirstate file has not
145
been modified, but will require that we flush/ignore cached stat-hit data
146
because we won't want to restat all files on disk just because a lock was
147
acquired, yet we cannot trust the data after the previous lock was released.
149
Memory representation:
150
vector of all directories, and vector of the childen ?
152
root_entrie = (direntry for root, [parent_direntries_for_root]),
154
('', ['data for achild', 'data for bchild', 'data for cchild'])
155
('dir', ['achild', 'cchild', 'echild'])
157
- single bisect to find N subtrees from a path spec
158
- in-order for serialisation - this is 'dirblock' grouping.
159
- insertion of a file '/a' affects only the '/' child-vector, that is, to
160
insert 10K elements from scratch does not generates O(N^2) memoves of a
161
single vector, rather each individual, which tends to be limited to a
162
manageable number. Will scale badly on trees with 10K entries in a
163
single directory. compare with Inventory.InventoryDirectory which has
164
a dictionary for the children. No bisect capability, can only probe for
165
exact matches, or grab all elements and sort.
166
- What's the risk of error here? Once we have the base format being processed
167
we should have a net win regardless of optimality. So we are going to
168
go with what seems reasonable.
171
Maybe we should do a test profile of the core structure - 10K simulated
172
searches/lookups/etc?
174
Objects for each row?
175
The lifetime of Dirstate objects is current per lock, but see above for
176
possible extensions. The lifetime of a row from a dirstate is expected to be
177
very short in the optimistic case: which we are optimising for. For instance,
178
subtree status will determine from analysis of the disk data what rows need to
179
be examined at all, and will be able to determine from a single row whether
180
that file has altered or not, so we are aiming to process tens of thousands of
181
entries each second within the dirstate context, before exposing anything to
182
the larger codebase. This suggests we want the time for a single file
183
comparison to be < 0.1 milliseconds. That would give us 10000 paths per second
184
processed, and to scale to 100 thousand we'll another order of magnitude to do
185
that. Now, as the lifetime for all unchanged entries is the time to parse, stat
186
the file on disk, and then immediately discard, the overhead of object creation
187
becomes a significant cost.
189
Figures: Creating a tuple from from 3 elements was profiled at 0.0625
190
microseconds, whereas creating a object which is subclassed from tuple was
191
0.500 microseconds, and creating an object with 3 elements and slots was 3
192
microseconds long. 0.1 milliseconds is 100 microseconds, and ideally we'll get
193
down to 10 microseconds for the total processing - having 33% of that be object
194
creation is a huge overhead. There is a potential cost in using tuples within
195
each row which is that the conditional code to do comparisons may be slower
196
than method invocation, but method invocation is known to be slow due to stack
197
frame creation, so avoiding methods in these tight inner loops in unfortunately
198
desirable. We can consider a pyrex version of this with objects in future if
207
from stat import S_IEXEC
225
def pack_stat(st, _encode=binascii.b2a_base64, _pack=struct.pack):
226
"""Convert stat values into a packed representation."""
227
# jam 20060614 it isn't really worth removing more entries if we
228
# are going to leave it in packed form.
229
# With only st_mtime and st_mode filesize is 5.5M and read time is 275ms
230
# With all entries, filesize is 5.9M and read time is maybe 280ms
231
# well within the noise margin
233
# base64 encoding always adds a final newline, so strip it off
234
# The current version
235
return _encode(_pack('>LLLLLL'
236
, st.st_size, int(st.st_mtime), int(st.st_ctime)
237
, st.st_dev, st.st_ino & 0xFFFFFFFF, st.st_mode))[:-1]
238
# This is 0.060s / 1.520s faster by not encoding as much information
239
# return _encode(_pack('>LL', int(st.st_mtime), st.st_mode))[:-1]
240
# This is not strictly faster than _encode(_pack())[:-1]
241
# return '%X.%X.%X.%X.%X.%X' % (
242
# st.st_size, int(st.st_mtime), int(st.st_ctime),
243
# st.st_dev, st.st_ino, st.st_mode)
244
# Similar to the _encode(_pack('>LL'))
245
# return '%X.%X' % (int(st.st_mtime), st.st_mode)
248
class DirState(object):
249
"""Record directory and metadata state for fast access.
251
A dirstate is a specialised data structure for managing local working
252
tree state information. Its not yet well defined whether it is platform
253
specific, and if it is how we detect/parameterize that.
255
Dirstates use the usual lock_write, lock_read and unlock mechanisms.
256
Unlike most bzr disk formats, DirStates must be locked for reading, using
257
lock_read. (This is an os file lock internally.) This is necessary
258
because the file can be rewritten in place.
260
DirStates must be explicitly written with save() to commit changes; just
261
unlocking them does not write the changes to disk.
264
_kind_to_minikind = {
270
'tree-reference': 't',
272
_minikind_to_kind = {
278
't': 'tree-reference',
280
_stat_to_minikind = {
285
_to_yesno = {True:'y', False: 'n'} # TODO profile the performance gain
286
# of using int conversion rather than a dict here. AND BLAME ANDREW IF
289
# TODO: jam 20070221 Figure out what to do if we have a record that exceeds
290
# the BISECT_PAGE_SIZE. For now, we just have to make it large enough
291
# that we are sure a single record will always fit.
292
BISECT_PAGE_SIZE = 4096
295
IN_MEMORY_UNMODIFIED = 1
296
IN_MEMORY_MODIFIED = 2
298
# A pack_stat (the x's) that is just noise and will never match the output
301
NULL_PARENT_DETAILS = ('a', '', 0, False, '')
303
HEADER_FORMAT_2 = '#bazaar dirstate flat format 2\n'
304
HEADER_FORMAT_3 = '#bazaar dirstate flat format 3\n'
306
def __init__(self, path):
307
"""Create a DirState object.
309
:param path: The path at which the dirstate file on disk should live.
311
# _header_state and _dirblock_state represent the current state
312
# of the dirstate metadata and the per-row data respectiely.
313
# NOT_IN_MEMORY indicates that no data is in memory
314
# IN_MEMORY_UNMODIFIED indicates that what we have in memory
315
# is the same as is on disk
316
# IN_MEMORY_MODIFIED indicates that we have a modified version
317
# of what is on disk.
318
# In future we will add more granularity, for instance _dirblock_state
319
# will probably support partially-in-memory as a separate variable,
320
# allowing for partially-in-memory unmodified and partially-in-memory
322
self._header_state = DirState.NOT_IN_MEMORY
323
self._dirblock_state = DirState.NOT_IN_MEMORY
324
# If true, an error has been detected while updating the dirstate, and
325
# for safety we're not going to commit to disk.
326
self._changes_aborted = False
330
self._state_file = None
331
self._filename = path
332
self._lock_token = None
333
self._lock_state = None
334
self._id_index = None
335
# a map from packed_stat to sha's.
336
self._packed_stat_index = None
337
self._end_of_header = None
338
self._cutoff_time = None
339
self._split_path_cache = {}
340
self._bisect_page_size = DirState.BISECT_PAGE_SIZE
341
if 'hashcache' in debug.debug_flags:
342
self._sha1_file = self._sha1_file_and_mutter
344
self._sha1_file = osutils.sha_file_by_name
345
# These two attributes provide a simple cache for lookups into the
346
# dirstate in-memory vectors. By probing respectively for the last
347
# block, and for the next entry, we save nearly 2 bisections per path
349
self._last_block_index = None
350
self._last_entry_index = None
354
(self.__class__.__name__, self._filename)
356
def add(self, path, file_id, kind, stat, fingerprint):
357
"""Add a path to be tracked.
359
:param path: The path within the dirstate - '' is the root, 'foo' is the
360
path foo within the root, 'foo/bar' is the path bar within foo
362
:param file_id: The file id of the path being added.
363
:param kind: The kind of the path, as a string like 'file',
365
:param stat: The output of os.lstat for the path.
366
:param fingerprint: The sha value of the file,
367
or the target of a symlink,
368
or the referenced revision id for tree-references,
369
or '' for directories.
372
# find the block its in.
373
# find the location in the block.
374
# check its not there
376
#------- copied from inventory.ensure_normalized_name - keep synced.
377
# --- normalized_filename wants a unicode basename only, so get one.
378
dirname, basename = osutils.split(path)
379
# we dont import normalized_filename directly because we want to be
380
# able to change the implementation at runtime for tests.
381
norm_name, can_access = osutils.normalized_filename(basename)
382
if norm_name != basename:
386
raise errors.InvalidNormalization(path)
387
# you should never have files called . or ..; just add the directory
388
# in the parent, or according to the special treatment for the root
389
if basename == '.' or basename == '..':
390
raise errors.InvalidEntryName(path)
391
# now that we've normalised, we need the correct utf8 path and
392
# dirname and basename elements. This single encode and split should be
393
# faster than three separate encodes.
394
utf8path = (dirname + '/' + basename).strip('/').encode('utf8')
395
dirname, basename = osutils.split(utf8path)
396
# uses __class__ for speed; the check is needed for safety
397
if file_id.__class__ is not str:
398
raise AssertionError(
399
"must be a utf8 file_id not %s" % (type(file_id), ))
400
# Make sure the file_id does not exist in this tree
401
file_id_entry = self._get_entry(0, fileid_utf8=file_id)
402
if file_id_entry != (None, None):
403
path = osutils.pathjoin(file_id_entry[0][0], file_id_entry[0][1])
404
kind = DirState._minikind_to_kind[file_id_entry[1][0][0]]
405
info = '%s:%s' % (kind, path)
406
raise errors.DuplicateFileId(file_id, info)
407
first_key = (dirname, basename, '')
408
block_index, present = self._find_block_index_from_key(first_key)
410
# check the path is not in the tree
411
block = self._dirblocks[block_index][1]
412
entry_index, _ = self._find_entry_index(first_key, block)
413
while (entry_index < len(block) and
414
block[entry_index][0][0:2] == first_key[0:2]):
415
if block[entry_index][1][0][0] not in 'ar':
416
# this path is in the dirstate in the current tree.
417
raise Exception, "adding already added path!"
420
# The block where we want to put the file is not present. But it
421
# might be because the directory was empty, or not loaded yet. Look
422
# for a parent entry, if not found, raise NotVersionedError
423
parent_dir, parent_base = osutils.split(dirname)
424
parent_block_idx, parent_entry_idx, _, parent_present = \
425
self._get_block_entry_index(parent_dir, parent_base, 0)
426
if not parent_present:
427
raise errors.NotVersionedError(path, str(self))
428
self._ensure_block(parent_block_idx, parent_entry_idx, dirname)
429
block = self._dirblocks[block_index][1]
430
entry_key = (dirname, basename, file_id)
433
packed_stat = DirState.NULLSTAT
436
packed_stat = pack_stat(stat)
437
parent_info = self._empty_parent_info()
438
minikind = DirState._kind_to_minikind[kind]
440
entry_data = entry_key, [
441
(minikind, fingerprint, size, False, packed_stat),
443
elif kind == 'directory':
444
entry_data = entry_key, [
445
(minikind, '', 0, False, packed_stat),
447
elif kind == 'symlink':
448
entry_data = entry_key, [
449
(minikind, fingerprint, size, False, packed_stat),
451
elif kind == 'tree-reference':
452
entry_data = entry_key, [
453
(minikind, fingerprint, 0, False, packed_stat),
456
raise errors.BzrError('unknown kind %r' % kind)
457
entry_index, present = self._find_entry_index(entry_key, block)
459
block.insert(entry_index, entry_data)
461
if block[entry_index][1][0][0] != 'a':
462
raise AssertionError(" %r(%r) already added" % (basename, file_id))
463
block[entry_index][1][0] = entry_data[1][0]
465
if kind == 'directory':
466
# insert a new dirblock
467
self._ensure_block(block_index, entry_index, utf8path)
468
self._dirblock_state = DirState.IN_MEMORY_MODIFIED
470
self._id_index.setdefault(entry_key[2], set()).add(entry_key)
472
def _bisect(self, paths):
473
"""Bisect through the disk structure for specific rows.
475
:param paths: A list of paths to find
476
:return: A dict mapping path => entries for found entries. Missing
477
entries will not be in the map.
478
The list is not sorted, and entries will be populated
479
based on when they were read.
481
self._requires_lock()
482
# We need the file pointer to be right after the initial header block
483
self._read_header_if_needed()
484
# If _dirblock_state was in memory, we should just return info from
485
# there, this function is only meant to handle when we want to read
487
if self._dirblock_state != DirState.NOT_IN_MEMORY:
488
raise AssertionError("bad dirblock state %r" % self._dirblock_state)
490
# The disk representation is generally info + '\0\n\0' at the end. But
491
# for bisecting, it is easier to treat this as '\0' + info + '\0\n'
492
# Because it means we can sync on the '\n'
493
state_file = self._state_file
494
file_size = os.fstat(state_file.fileno()).st_size
495
# We end up with 2 extra fields, we should have a trailing '\n' to
496
# ensure that we read the whole record, and we should have a precursur
497
# '' which ensures that we start after the previous '\n'
498
entry_field_count = self._fields_per_entry() + 1
500
low = self._end_of_header
501
high = file_size - 1 # Ignore the final '\0'
502
# Map from (dir, name) => entry
505
# Avoid infinite seeking
506
max_count = 30*len(paths)
508
# pending is a list of places to look.
509
# each entry is a tuple of low, high, dir_names
510
# low -> the first byte offset to read (inclusive)
511
# high -> the last byte offset (inclusive)
512
# dir_names -> The list of (dir, name) pairs that should be found in
513
# the [low, high] range
514
pending = [(low, high, paths)]
516
page_size = self._bisect_page_size
518
fields_to_entry = self._get_fields_to_entry()
521
low, high, cur_files = pending.pop()
523
if not cur_files or low >= high:
528
if count > max_count:
529
raise errors.BzrError('Too many seeks, most likely a bug.')
531
mid = max(low, (low+high-page_size)/2)
534
# limit the read size, so we don't end up reading data that we have
536
read_size = min(page_size, (high-mid)+1)
537
block = state_file.read(read_size)
540
entries = block.split('\n')
543
# We didn't find a '\n', so we cannot have found any records.
544
# So put this range back and try again. But we know we have to
545
# increase the page size, because a single read did not contain
546
# a record break (so records must be larger than page_size)
548
pending.append((low, high, cur_files))
551
# Check the first and last entries, in case they are partial, or if
552
# we don't care about the rest of this page
554
first_fields = entries[0].split('\0')
555
if len(first_fields) < entry_field_count:
556
# We didn't get the complete first entry
557
# so move start, and grab the next, which
558
# should be a full entry
559
start += len(entries[0])+1
560
first_fields = entries[1].split('\0')
563
if len(first_fields) <= 2:
564
# We didn't even get a filename here... what do we do?
565
# Try a large page size and repeat this query
567
pending.append((low, high, cur_files))
570
# Find what entries we are looking for, which occur before and
571
# after this first record.
574
first_path = first_fields[1] + '/' + first_fields[2]
576
first_path = first_fields[2]
577
first_loc = _bisect_path_left(cur_files, first_path)
579
# These exist before the current location
580
pre = cur_files[:first_loc]
581
# These occur after the current location, which may be in the
582
# data we read, or might be after the last entry
583
post = cur_files[first_loc:]
585
if post and len(first_fields) >= entry_field_count:
586
# We have files after the first entry
588
# Parse the last entry
589
last_entry_num = len(entries)-1
590
last_fields = entries[last_entry_num].split('\0')
591
if len(last_fields) < entry_field_count:
592
# The very last hunk was not complete,
593
# read the previous hunk
594
after = mid + len(block) - len(entries[-1])
596
last_fields = entries[last_entry_num].split('\0')
598
after = mid + len(block)
601
last_path = last_fields[1] + '/' + last_fields[2]
603
last_path = last_fields[2]
604
last_loc = _bisect_path_right(post, last_path)
606
middle_files = post[:last_loc]
607
post = post[last_loc:]
610
# We have files that should occur in this block
611
# (>= first, <= last)
612
# Either we will find them here, or we can mark them as
615
if middle_files[0] == first_path:
616
# We might need to go before this location
617
pre.append(first_path)
618
if middle_files[-1] == last_path:
619
post.insert(0, last_path)
621
# Find out what paths we have
622
paths = {first_path:[first_fields]}
623
# last_path might == first_path so we need to be
624
# careful if we should append rather than overwrite
625
if last_entry_num != first_entry_num:
626
paths.setdefault(last_path, []).append(last_fields)
627
for num in xrange(first_entry_num+1, last_entry_num):
628
# TODO: jam 20070223 We are already splitting here, so
629
# shouldn't we just split the whole thing rather
630
# than doing the split again in add_one_record?
631
fields = entries[num].split('\0')
633
path = fields[1] + '/' + fields[2]
636
paths.setdefault(path, []).append(fields)
638
for path in middle_files:
639
for fields in paths.get(path, []):
640
# offset by 1 because of the opening '\0'
641
# consider changing fields_to_entry to avoid the
643
entry = fields_to_entry(fields[1:])
644
found.setdefault(path, []).append(entry)
646
# Now we have split up everything into pre, middle, and post, and
647
# we have handled everything that fell in 'middle'.
648
# We add 'post' first, so that we prefer to seek towards the
649
# beginning, so that we will tend to go as early as we need, and
650
# then only seek forward after that.
652
pending.append((after, high, post))
654
pending.append((low, start-1, pre))
656
# Consider that we may want to return the directory entries in sorted
657
# order. For now, we just return them in whatever order we found them,
658
# and leave it up to the caller if they care if it is ordered or not.
661
def _bisect_dirblocks(self, dir_list):
662
"""Bisect through the disk structure to find entries in given dirs.
664
_bisect_dirblocks is meant to find the contents of directories, which
665
differs from _bisect, which only finds individual entries.
667
:param dir_list: A sorted list of directory names ['', 'dir', 'foo'].
668
:return: A map from dir => entries_for_dir
670
# TODO: jam 20070223 A lot of the bisecting logic could be shared
671
# between this and _bisect. It would require parameterizing the
672
# inner loop with a function, though. We should evaluate the
673
# performance difference.
674
self._requires_lock()
675
# We need the file pointer to be right after the initial header block
676
self._read_header_if_needed()
677
# If _dirblock_state was in memory, we should just return info from
678
# there, this function is only meant to handle when we want to read
680
if self._dirblock_state != DirState.NOT_IN_MEMORY:
681
raise AssertionError("bad dirblock state %r" % self._dirblock_state)
682
# The disk representation is generally info + '\0\n\0' at the end. But
683
# for bisecting, it is easier to treat this as '\0' + info + '\0\n'
684
# Because it means we can sync on the '\n'
685
state_file = self._state_file
686
file_size = os.fstat(state_file.fileno()).st_size
687
# We end up with 2 extra fields, we should have a trailing '\n' to
688
# ensure that we read the whole record, and we should have a precursur
689
# '' which ensures that we start after the previous '\n'
690
entry_field_count = self._fields_per_entry() + 1
692
low = self._end_of_header
693
high = file_size - 1 # Ignore the final '\0'
694
# Map from dir => entry
697
# Avoid infinite seeking
698
max_count = 30*len(dir_list)
700
# pending is a list of places to look.
701
# each entry is a tuple of low, high, dir_names
702
# low -> the first byte offset to read (inclusive)
703
# high -> the last byte offset (inclusive)
704
# dirs -> The list of directories that should be found in
705
# the [low, high] range
706
pending = [(low, high, dir_list)]
708
page_size = self._bisect_page_size
710
fields_to_entry = self._get_fields_to_entry()
713
low, high, cur_dirs = pending.pop()
715
if not cur_dirs or low >= high:
720
if count > max_count:
721
raise errors.BzrError('Too many seeks, most likely a bug.')
723
mid = max(low, (low+high-page_size)/2)
726
# limit the read size, so we don't end up reading data that we have
728
read_size = min(page_size, (high-mid)+1)
729
block = state_file.read(read_size)
732
entries = block.split('\n')
735
# We didn't find a '\n', so we cannot have found any records.
736
# So put this range back and try again. But we know we have to
737
# increase the page size, because a single read did not contain
738
# a record break (so records must be larger than page_size)
740
pending.append((low, high, cur_dirs))
743
# Check the first and last entries, in case they are partial, or if
744
# we don't care about the rest of this page
746
first_fields = entries[0].split('\0')
747
if len(first_fields) < entry_field_count:
748
# We didn't get the complete first entry
749
# so move start, and grab the next, which
750
# should be a full entry
751
start += len(entries[0])+1
752
first_fields = entries[1].split('\0')
755
if len(first_fields) <= 1:
756
# We didn't even get a dirname here... what do we do?
757
# Try a large page size and repeat this query
759
pending.append((low, high, cur_dirs))
762
# Find what entries we are looking for, which occur before and
763
# after this first record.
765
first_dir = first_fields[1]
766
first_loc = bisect.bisect_left(cur_dirs, first_dir)
768
# These exist before the current location
769
pre = cur_dirs[:first_loc]
770
# These occur after the current location, which may be in the
771
# data we read, or might be after the last entry
772
post = cur_dirs[first_loc:]
774
if post and len(first_fields) >= entry_field_count:
775
# We have records to look at after the first entry
777
# Parse the last entry
778
last_entry_num = len(entries)-1
779
last_fields = entries[last_entry_num].split('\0')
780
if len(last_fields) < entry_field_count:
781
# The very last hunk was not complete,
782
# read the previous hunk
783
after = mid + len(block) - len(entries[-1])
785
last_fields = entries[last_entry_num].split('\0')
787
after = mid + len(block)
789
last_dir = last_fields[1]
790
last_loc = bisect.bisect_right(post, last_dir)
792
middle_files = post[:last_loc]
793
post = post[last_loc:]
796
# We have files that should occur in this block
797
# (>= first, <= last)
798
# Either we will find them here, or we can mark them as
801
if middle_files[0] == first_dir:
802
# We might need to go before this location
803
pre.append(first_dir)
804
if middle_files[-1] == last_dir:
805
post.insert(0, last_dir)
807
# Find out what paths we have
808
paths = {first_dir:[first_fields]}
809
# last_dir might == first_dir so we need to be
810
# careful if we should append rather than overwrite
811
if last_entry_num != first_entry_num:
812
paths.setdefault(last_dir, []).append(last_fields)
813
for num in xrange(first_entry_num+1, last_entry_num):
814
# TODO: jam 20070223 We are already splitting here, so
815
# shouldn't we just split the whole thing rather
816
# than doing the split again in add_one_record?
817
fields = entries[num].split('\0')
818
paths.setdefault(fields[1], []).append(fields)
820
for cur_dir in middle_files:
821
for fields in paths.get(cur_dir, []):
822
# offset by 1 because of the opening '\0'
823
# consider changing fields_to_entry to avoid the
825
entry = fields_to_entry(fields[1:])
826
found.setdefault(cur_dir, []).append(entry)
828
# Now we have split up everything into pre, middle, and post, and
829
# we have handled everything that fell in 'middle'.
830
# We add 'post' first, so that we prefer to seek towards the
831
# beginning, so that we will tend to go as early as we need, and
832
# then only seek forward after that.
834
pending.append((after, high, post))
836
pending.append((low, start-1, pre))
840
def _bisect_recursive(self, paths):
841
"""Bisect for entries for all paths and their children.
843
This will use bisect to find all records for the supplied paths. It
844
will then continue to bisect for any records which are marked as
845
directories. (and renames?)
847
:param paths: A sorted list of (dir, name) pairs
848
eg: [('', 'a'), ('', 'f'), ('a/b', 'c')]
849
:return: A dictionary mapping (dir, name, file_id) => [tree_info]
851
# Map from (dir, name, file_id) => [tree_info]
854
found_dir_names = set()
856
# Directories that have been read
857
processed_dirs = set()
858
# Get the ball rolling with the first bisect for all entries.
859
newly_found = self._bisect(paths)
862
# Directories that need to be read
864
paths_to_search = set()
865
for entry_list in newly_found.itervalues():
866
for dir_name_id, trees_info in entry_list:
867
found[dir_name_id] = trees_info
868
found_dir_names.add(dir_name_id[:2])
870
for tree_info in trees_info:
871
minikind = tree_info[0]
874
# We already processed this one as a directory,
875
# we don't need to do the extra work again.
877
subdir, name, file_id = dir_name_id
878
path = osutils.pathjoin(subdir, name)
880
if path not in processed_dirs:
881
pending_dirs.add(path)
882
elif minikind == 'r':
883
# Rename, we need to directly search the target
884
# which is contained in the fingerprint column
885
dir_name = osutils.split(tree_info[1])
886
if dir_name[0] in pending_dirs:
887
# This entry will be found in the dir search
889
if dir_name not in found_dir_names:
890
paths_to_search.add(tree_info[1])
891
# Now we have a list of paths to look for directly, and
892
# directory blocks that need to be read.
893
# newly_found is mixing the keys between (dir, name) and path
894
# entries, but that is okay, because we only really care about the
896
newly_found = self._bisect(sorted(paths_to_search))
897
newly_found.update(self._bisect_dirblocks(sorted(pending_dirs)))
898
processed_dirs.update(pending_dirs)
901
def _discard_merge_parents(self):
902
"""Discard any parents trees beyond the first.
904
Note that if this fails the dirstate is corrupted.
906
After this function returns the dirstate contains 2 trees, neither of
909
self._read_header_if_needed()
910
parents = self.get_parent_ids()
913
# only require all dirblocks if we are doing a full-pass removal.
914
self._read_dirblocks_if_needed()
915
dead_patterns = set([('a', 'r'), ('a', 'a'), ('r', 'r'), ('r', 'a')])
916
def iter_entries_removable():
917
for block in self._dirblocks:
918
deleted_positions = []
919
for pos, entry in enumerate(block[1]):
921
if (entry[1][0][0], entry[1][1][0]) in dead_patterns:
922
deleted_positions.append(pos)
923
if deleted_positions:
924
if len(deleted_positions) == len(block[1]):
927
for pos in reversed(deleted_positions):
929
# if the first parent is a ghost:
930
if parents[0] in self.get_ghosts():
931
empty_parent = [DirState.NULL_PARENT_DETAILS]
932
for entry in iter_entries_removable():
933
entry[1][1:] = empty_parent
935
for entry in iter_entries_removable():
939
self._parents = [parents[0]]
940
self._dirblock_state = DirState.IN_MEMORY_MODIFIED
941
self._header_state = DirState.IN_MEMORY_MODIFIED
943
def _empty_parent_info(self):
944
return [DirState.NULL_PARENT_DETAILS] * (len(self._parents) -
947
def _ensure_block(self, parent_block_index, parent_row_index, dirname):
948
"""Ensure a block for dirname exists.
950
This function exists to let callers which know that there is a
951
directory dirname ensure that the block for it exists. This block can
952
fail to exist because of demand loading, or because a directory had no
953
children. In either case it is not an error. It is however an error to
954
call this if there is no parent entry for the directory, and thus the
955
function requires the coordinates of such an entry to be provided.
957
The root row is special cased and can be indicated with a parent block
960
:param parent_block_index: The index of the block in which dirname's row
962
:param parent_row_index: The index in the parent block where the row
964
:param dirname: The utf8 dirname to ensure there is a block for.
965
:return: The index for the block.
967
if dirname == '' and parent_row_index == 0 and parent_block_index == 0:
968
# This is the signature of the root row, and the
969
# contents-of-root row is always index 1
971
# the basename of the directory must be the end of its full name.
972
if not (parent_block_index == -1 and
973
parent_block_index == -1 and dirname == ''):
974
if not dirname.endswith(
975
self._dirblocks[parent_block_index][1][parent_row_index][0][1]):
976
raise AssertionError("bad dirname %r" % dirname)
977
block_index, present = self._find_block_index_from_key((dirname, '', ''))
979
## In future, when doing partial parsing, this should load and
980
# populate the entire block.
981
self._dirblocks.insert(block_index, (dirname, []))
984
def _entries_to_current_state(self, new_entries):
985
"""Load new_entries into self.dirblocks.
987
Process new_entries into the current state object, making them the active
988
state. The entries are grouped together by directory to form dirblocks.
990
:param new_entries: A sorted list of entries. This function does not sort
991
to prevent unneeded overhead when callers have a sorted list already.
994
if new_entries[0][0][0:2] != ('', ''):
995
raise AssertionError(
996
"Missing root row %r" % (new_entries[0][0],))
997
# The two blocks here are deliberate: the root block and the
998
# contents-of-root block.
999
self._dirblocks = [('', []), ('', [])]
1000
current_block = self._dirblocks[0][1]
1001
current_dirname = ''
1003
append_entry = current_block.append
1004
for entry in new_entries:
1005
if entry[0][0] != current_dirname:
1006
# new block - different dirname
1008
current_dirname = entry[0][0]
1009
self._dirblocks.append((current_dirname, current_block))
1010
append_entry = current_block.append
1011
# append the entry to the current block
1013
self._split_root_dirblock_into_contents()
1015
def _split_root_dirblock_into_contents(self):
1016
"""Split the root dirblocks into root and contents-of-root.
1018
After parsing by path, we end up with root entries and contents-of-root
1019
entries in the same block. This loop splits them out again.
1021
# The above loop leaves the "root block" entries mixed with the
1022
# "contents-of-root block". But we don't want an if check on
1023
# all entries, so instead we just fix it up here.
1024
if self._dirblocks[1] != ('', []):
1025
raise ValueError("bad dirblock start %r" % (self._dirblocks[1],))
1027
contents_of_root_block = []
1028
for entry in self._dirblocks[0][1]:
1029
if not entry[0][1]: # This is a root entry
1030
root_block.append(entry)
1032
contents_of_root_block.append(entry)
1033
self._dirblocks[0] = ('', root_block)
1034
self._dirblocks[1] = ('', contents_of_root_block)
1036
def _entry_to_line(self, entry):
1037
"""Serialize entry to a NULL delimited line ready for _get_output_lines.
1039
:param entry: An entry_tuple as defined in the module docstring.
1041
entire_entry = list(entry[0])
1042
for tree_number, tree_data in enumerate(entry[1]):
1043
# (minikind, fingerprint, size, executable, tree_specific_string)
1044
entire_entry.extend(tree_data)
1045
# 3 for the key, 5 for the fields per tree.
1046
tree_offset = 3 + tree_number * 5
1048
entire_entry[tree_offset + 0] = tree_data[0]
1050
entire_entry[tree_offset + 2] = str(tree_data[2])
1052
entire_entry[tree_offset + 3] = DirState._to_yesno[tree_data[3]]
1053
return '\0'.join(entire_entry)
1055
def _fields_per_entry(self):
1056
"""How many null separated fields should be in each entry row.
1058
Each line now has an extra '\n' field which is not used
1059
so we just skip over it
1061
3 fields for the key
1062
+ number of fields per tree_data (5) * tree count
1065
tree_count = 1 + self._num_present_parents()
1066
return 3 + 5 * tree_count + 1
1068
def _find_block(self, key, add_if_missing=False):
1069
"""Return the block that key should be present in.
1071
:param key: A dirstate entry key.
1072
:return: The block tuple.
1074
block_index, present = self._find_block_index_from_key(key)
1076
if not add_if_missing:
1077
# check to see if key is versioned itself - we might want to
1078
# add it anyway, because dirs with no entries dont get a
1079
# dirblock at parse time.
1080
# This is an uncommon branch to take: most dirs have children,
1081
# and most code works with versioned paths.
1082
parent_base, parent_name = osutils.split(key[0])
1083
if not self._get_block_entry_index(parent_base, parent_name, 0)[3]:
1084
# some parent path has not been added - its an error to add
1086
raise errors.NotVersionedError(key[0:2], str(self))
1087
self._dirblocks.insert(block_index, (key[0], []))
1088
return self._dirblocks[block_index]
1090
def _find_block_index_from_key(self, key):
1091
"""Find the dirblock index for a key.
1093
:return: The block index, True if the block for the key is present.
1095
if key[0:2] == ('', ''):
1098
if (self._last_block_index is not None and
1099
self._dirblocks[self._last_block_index][0] == key[0]):
1100
return self._last_block_index, True
1103
block_index = bisect_dirblock(self._dirblocks, key[0], 1,
1104
cache=self._split_path_cache)
1105
# _right returns one-past-where-key is so we have to subtract
1106
# one to use it. we use _right here because there are two
1107
# '' blocks - the root, and the contents of root
1108
# we always have a minimum of 2 in self._dirblocks: root and
1109
# root-contents, and for '', we get 2 back, so this is
1110
# simple and correct:
1111
present = (block_index < len(self._dirblocks) and
1112
self._dirblocks[block_index][0] == key[0])
1113
self._last_block_index = block_index
1114
# Reset the entry index cache to the beginning of the block.
1115
self._last_entry_index = -1
1116
return block_index, present
1118
def _find_entry_index(self, key, block):
1119
"""Find the entry index for a key in a block.
1121
:return: The entry index, True if the entry for the key is present.
1123
len_block = len(block)
1125
if self._last_entry_index is not None:
1127
entry_index = self._last_entry_index + 1
1128
# A hit is when the key is after the last slot, and before or
1129
# equal to the next slot.
1130
if ((entry_index > 0 and block[entry_index - 1][0] < key) and
1131
key <= block[entry_index][0]):
1132
self._last_entry_index = entry_index
1133
present = (block[entry_index][0] == key)
1134
return entry_index, present
1137
entry_index = bisect.bisect_left(block, (key, []))
1138
present = (entry_index < len_block and
1139
block[entry_index][0] == key)
1140
self._last_entry_index = entry_index
1141
return entry_index, present
1144
def from_tree(tree, dir_state_filename):
1145
"""Create a dirstate from a bzr Tree.
1147
:param tree: The tree which should provide parent information and
1149
:return: a DirState object which is currently locked for writing.
1150
(it was locked by DirState.initialize)
1152
result = DirState.initialize(dir_state_filename)
1156
parent_ids = tree.get_parent_ids()
1157
num_parents = len(parent_ids)
1159
for parent_id in parent_ids:
1160
parent_tree = tree.branch.repository.revision_tree(parent_id)
1161
parent_trees.append((parent_id, parent_tree))
1162
parent_tree.lock_read()
1163
result.set_parent_trees(parent_trees, [])
1164
result.set_state_from_inventory(tree.inventory)
1166
for revid, parent_tree in parent_trees:
1167
parent_tree.unlock()
1170
# The caller won't have a chance to unlock this, so make sure we
1176
def update_by_delta(self, delta):
1177
"""Apply an inventory delta to the dirstate for tree 0
1179
:param delta: An inventory delta. See Inventory.apply_delta for
1182
self._read_dirblocks_if_needed()
1185
for old_path, new_path, file_id, inv_entry in sorted(delta, reverse=True):
1186
if (file_id in insertions) or (file_id in removals):
1187
raise AssertionError("repeated file id in delta %r" % (file_id,))
1188
if old_path is not None:
1189
old_path = old_path.encode('utf-8')
1190
removals[file_id] = old_path
1191
if new_path is not None:
1192
new_path = new_path.encode('utf-8')
1193
dirname, basename = osutils.split(new_path)
1194
key = (dirname, basename, file_id)
1195
minikind = DirState._kind_to_minikind[inv_entry.kind]
1197
fingerprint = inv_entry.reference_revision
1200
insertions[file_id] = (key, minikind, inv_entry.executable,
1201
fingerprint, new_path)
1202
# Transform moves into delete+add pairs
1203
if None not in (old_path, new_path):
1204
for child in self._iter_child_entries(0, old_path):
1205
if child[0][2] in insertions or child[0][2] in removals:
1207
child_dirname = child[0][0]
1208
child_basename = child[0][1]
1209
minikind = child[1][0][0]
1210
fingerprint = child[1][0][4]
1211
executable = child[1][0][3]
1212
old_child_path = osutils.pathjoin(child[0][0],
1214
removals[child[0][2]] = old_child_path
1215
child_suffix = child_dirname[len(old_path):]
1216
new_child_dirname = (new_path + child_suffix)
1217
key = (new_child_dirname, child_basename, child[0][2])
1218
new_child_path = os.path.join(new_child_dirname,
1220
insertions[child[0][2]] = (key, minikind, executable,
1221
fingerprint, new_child_path)
1222
self._apply_removals(removals.values())
1223
self._apply_insertions(insertions.values())
1225
def _apply_removals(self, removals):
1226
for path in sorted(removals, reverse=True):
1227
dirname, basename = osutils.split(path)
1228
block_i, entry_i, d_present, f_present = \
1229
self._get_block_entry_index(dirname, basename, 0)
1230
entry = self._dirblocks[block_i][1][entry_i]
1231
self._make_absent(entry)
1232
# See if we have a malformed delta: deleting a directory must not
1233
# leave crud behind. This increases the number of bisects needed
1234
# substantially, but deletion or renames of large numbers of paths
1235
# is rare enough it shouldn't be an issue (famous last words?) RBC
1237
block_i, entry_i, d_present, f_present = \
1238
self._get_block_entry_index(path, '', 0)
1240
# The dir block is still present in the dirstate; this could
1241
# be due to it being in a parent tree, or a corrupt delta.
1242
for child_entry in self._dirblocks[block_i][1]:
1243
if child_entry[1][0][0] not in ('r', 'a'):
1244
raise errors.InconsistentDelta(path, entry[0][2],
1245
"The file id was deleted but its children were "
1248
def _apply_insertions(self, adds):
1249
for key, minikind, executable, fingerprint, path_utf8 in sorted(adds):
1250
self.update_minimal(key, minikind, executable, fingerprint,
1251
path_utf8=path_utf8)
1253
def update_basis_by_delta(self, delta, new_revid):
1254
"""Update the parents of this tree after a commit.
1256
This gives the tree one parent, with revision id new_revid. The
1257
inventory delta is applied to the current basis tree to generate the
1258
inventory for the parent new_revid, and all other parent trees are
1261
Note that an exception during the operation of this method will leave
1262
the dirstate in a corrupt state where it should not be saved.
1264
Finally, we expect all changes to be synchronising the basis tree with
1267
:param new_revid: The new revision id for the trees parent.
1268
:param delta: An inventory delta (see apply_inventory_delta) describing
1269
the changes from the current left most parent revision to new_revid.
1271
self._read_dirblocks_if_needed()
1272
self._discard_merge_parents()
1273
if self._ghosts != []:
1274
raise NotImplementedError(self.update_basis_by_delta)
1275
if len(self._parents) == 0:
1276
# setup a blank tree, the most simple way.
1277
empty_parent = DirState.NULL_PARENT_DETAILS
1278
for entry in self._iter_entries():
1279
entry[1].append(empty_parent)
1280
self._parents.append(new_revid)
1282
self._parents[0] = new_revid
1284
delta = sorted(delta, reverse=True)
1288
# The paths this function accepts are unicode and must be encoded as we
1290
encode = cache_utf8.encode
1291
inv_to_entry = self._inv_entry_to_details
1292
# delta is now (deletes, changes), (adds) in reverse lexographical
1294
# deletes in reverse lexographic order are safe to process in situ.
1295
# renames are not, as a rename from any path could go to a path
1296
# lexographically lower, so we transform renames into delete, add pairs,
1297
# expanding them recursively as needed.
1298
# At the same time, to reduce interface friction we convert the input
1299
# inventory entries to dirstate.
1300
root_only = ('', '')
1301
for old_path, new_path, file_id, inv_entry in delta:
1302
if old_path is None:
1303
adds.append((None, encode(new_path), file_id,
1304
inv_to_entry(inv_entry), True))
1305
elif new_path is None:
1306
deletes.append((encode(old_path), None, file_id, None, True))
1307
elif (old_path, new_path) != root_only:
1309
# Because renames must preserve their children we must have
1310
# processed all relocations and removes before hand. The sort
1311
# order ensures we've examined the child paths, but we also
1312
# have to execute the removals, or the split to an add/delete
1313
# pair will result in the deleted item being reinserted, or
1314
# renamed items being reinserted twice - and possibly at the
1315
# wrong place. Splitting into a delete/add pair also simplifies
1316
# the handling of entries with ('f', ...), ('r' ...) because
1317
# the target of the 'r' is old_path here, and we add that to
1318
# deletes, meaning that the add handler does not need to check
1319
# for 'r' items on every pass.
1320
self._update_basis_apply_deletes(deletes)
1322
new_path_utf8 = encode(new_path)
1323
# Split into an add/delete pair recursively.
1324
adds.append((None, new_path_utf8, file_id,
1325
inv_to_entry(inv_entry), False))
1326
# Expunge deletes that we've seen so that deleted/renamed
1327
# children of a rename directory are handled correctly.
1328
new_deletes = reversed(list(self._iter_child_entries(1,
1330
# Remove the current contents of the tree at orig_path, and
1331
# reinsert at the correct new path.
1332
for entry in new_deletes:
1334
source_path = entry[0][0] + '/' + entry[0][1]
1336
source_path = entry[0][1]
1338
target_path = new_path_utf8 + source_path[len(old_path):]
1341
raise AssertionError("cannot rename directory to"
1343
target_path = source_path[len(old_path) + 1:]
1344
adds.append((None, target_path, entry[0][2], entry[1][1], False))
1346
(source_path, target_path, entry[0][2], None, False))
1348
(encode(old_path), new_path, file_id, None, False))
1350
# changes to just the root should not require remove/insertion
1352
changes.append((encode(old_path), encode(new_path), file_id,
1353
inv_to_entry(inv_entry)))
1355
# Finish expunging deletes/first half of renames.
1356
self._update_basis_apply_deletes(deletes)
1357
# Reinstate second half of renames and new paths.
1358
self._update_basis_apply_adds(adds)
1359
# Apply in-situ changes.
1360
self._update_basis_apply_changes(changes)
1362
self._dirblock_state = DirState.IN_MEMORY_MODIFIED
1363
self._header_state = DirState.IN_MEMORY_MODIFIED
1364
self._id_index = None
1367
def _update_basis_apply_adds(self, adds):
1368
"""Apply a sequence of adds to tree 1 during update_basis_by_delta.
1370
They may be adds, or renames that have been split into add/delete
1373
:param adds: A sequence of adds. Each add is a tuple:
1374
(None, new_path_utf8, file_id, (entry_details), real_add). real_add
1375
is False when the add is the second half of a remove-and-reinsert
1376
pair created to handle renames and deletes.
1378
# Adds are accumulated partly from renames, so can be in any input
1381
# adds is now in lexographic order, which places all parents before
1382
# their children, so we can process it linearly.
1384
for old_path, new_path, file_id, new_details, real_add in adds:
1385
# the entry for this file_id must be in tree 0.
1386
entry = self._get_entry(0, file_id, new_path)
1387
if entry[0] is None or entry[0][2] != file_id:
1388
self._changes_aborted = True
1389
raise errors.InconsistentDelta(new_path, file_id,
1390
'working tree does not contain new entry')
1391
if real_add and entry[1][1][0] not in absent:
1392
self._changes_aborted = True
1393
raise errors.InconsistentDelta(new_path, file_id,
1394
'The entry was considered to be a genuinely new record,'
1395
' but there was already an old record for it.')
1396
# We don't need to update the target of an 'r' because the handling
1397
# of renames turns all 'r' situations into a delete at the original
1399
entry[1][1] = new_details
1401
def _update_basis_apply_changes(self, changes):
1402
"""Apply a sequence of changes to tree 1 during update_basis_by_delta.
1404
:param adds: A sequence of changes. Each change is a tuple:
1405
(path_utf8, path_utf8, file_id, (entry_details))
1408
for old_path, new_path, file_id, new_details in changes:
1409
# the entry for this file_id must be in tree 0.
1410
entry = self._get_entry(0, file_id, new_path)
1411
if entry[0] is None or entry[0][2] != file_id:
1412
self._changes_aborted = True
1413
raise errors.InconsistentDelta(new_path, file_id,
1414
'working tree does not contain new entry')
1415
if (entry[1][0][0] in absent or
1416
entry[1][1][0] in absent):
1417
self._changes_aborted = True
1418
raise errors.InconsistentDelta(new_path, file_id,
1419
'changed considered absent')
1420
entry[1][1] = new_details
1422
def _update_basis_apply_deletes(self, deletes):
1423
"""Apply a sequence of deletes to tree 1 during update_basis_by_delta.
1425
They may be deletes, or renames that have been split into add/delete
1428
:param deletes: A sequence of deletes. Each delete is a tuple:
1429
(old_path_utf8, new_path_utf8, file_id, None, real_delete).
1430
real_delete is True when the desired outcome is an actual deletion
1431
rather than the rename handling logic temporarily deleting a path
1432
during the replacement of a parent.
1434
null = DirState.NULL_PARENT_DETAILS
1435
for old_path, new_path, file_id, _, real_delete in deletes:
1436
if real_delete != (new_path is None):
1437
raise AssertionError("bad delete delta")
1438
# the entry for this file_id must be in tree 1.
1439
dirname, basename = osutils.split(old_path)
1440
block_index, entry_index, dir_present, file_present = \
1441
self._get_block_entry_index(dirname, basename, 1)
1442
if not file_present:
1443
self._changes_aborted = True
1444
raise errors.InconsistentDelta(old_path, file_id,
1445
'basis tree does not contain removed entry')
1446
entry = self._dirblocks[block_index][1][entry_index]
1447
if entry[0][2] != file_id:
1448
self._changes_aborted = True
1449
raise errors.InconsistentDelta(old_path, file_id,
1450
'mismatched file_id in tree 1')
1452
if entry[1][0][0] != 'a':
1453
self._changes_aborted = True
1454
raise errors.InconsistentDelta(old_path, file_id,
1455
'This was marked as a real delete, but the WT state'
1456
' claims that it still exists and is versioned.')
1457
del self._dirblocks[block_index][1][entry_index]
1459
if entry[1][0][0] == 'a':
1460
self._changes_aborted = True
1461
raise errors.InconsistentDelta(old_path, file_id,
1462
'The entry was considered a rename, but the source path'
1463
' is marked as absent.')
1464
# For whatever reason, we were asked to rename an entry
1465
# that was originally marked as deleted. This could be
1466
# because we are renaming the parent directory, and the WT
1467
# current state has the file marked as deleted.
1468
elif entry[1][0][0] == 'r':
1469
# implement the rename
1470
del self._dirblocks[block_index][1][entry_index]
1472
# it is being resurrected here, so blank it out temporarily.
1473
self._dirblocks[block_index][1][entry_index][1][1] = null
1475
def _sha_cutoff_time(self):
1476
"""Return cutoff time.
1478
Files modified more recently than this time are at risk of being
1479
undetectably modified and so can't be cached.
1481
# Cache the cutoff time as long as we hold a lock.
1482
# time.time() isn't super expensive (approx 3.38us), but
1483
# when you call it 50,000 times it adds up.
1484
# For comparison, os.lstat() costs 7.2us if it is hot.
1485
self._cutoff_time = int(time.time()) - 3
1486
return self._cutoff_time
1488
def _lstat(self, abspath, entry):
1489
"""Return the os.lstat value for this path."""
1490
return os.lstat(abspath)
1492
def _sha1_file_and_mutter(self, abspath):
1493
# when -Dhashcache is turned on, this is monkey-patched in to log
1495
trace.mutter("dirstate sha1 " + abspath)
1496
return osutils.sha_file_by_name(abspath)
1498
def _is_executable(self, mode, old_executable):
1499
"""Is this file executable?"""
1500
return bool(S_IEXEC & mode)
1502
def _is_executable_win32(self, mode, old_executable):
1503
"""On win32 the executable bit is stored in the dirstate."""
1504
return old_executable
1506
if sys.platform == 'win32':
1507
_is_executable = _is_executable_win32
1509
def _read_link(self, abspath, old_link):
1510
"""Read the target of a symlink"""
1511
# TODO: jam 200700301 On Win32, this could just return the value
1512
# already in memory. However, this really needs to be done at a
1513
# higher level, because there either won't be anything on disk,
1514
# or the thing on disk will be a file.
1515
return os.readlink(abspath)
1517
def get_ghosts(self):
1518
"""Return a list of the parent tree revision ids that are ghosts."""
1519
self._read_header_if_needed()
1522
def get_lines(self):
1523
"""Serialise the entire dirstate to a sequence of lines."""
1524
if (self._header_state == DirState.IN_MEMORY_UNMODIFIED and
1525
self._dirblock_state == DirState.IN_MEMORY_UNMODIFIED):
1526
# read whats on disk.
1527
self._state_file.seek(0)
1528
return self._state_file.readlines()
1530
lines.append(self._get_parents_line(self.get_parent_ids()))
1531
lines.append(self._get_ghosts_line(self._ghosts))
1532
# append the root line which is special cased
1533
lines.extend(map(self._entry_to_line, self._iter_entries()))
1534
return self._get_output_lines(lines)
1536
def _get_ghosts_line(self, ghost_ids):
1537
"""Create a line for the state file for ghost information."""
1538
return '\0'.join([str(len(ghost_ids))] + ghost_ids)
1540
def _get_parents_line(self, parent_ids):
1541
"""Create a line for the state file for parents information."""
1542
return '\0'.join([str(len(parent_ids))] + parent_ids)
1544
def _get_fields_to_entry(self):
1545
"""Get a function which converts entry fields into a entry record.
1547
This handles size and executable, as well as parent records.
1549
:return: A function which takes a list of fields, and returns an
1550
appropriate record for storing in memory.
1552
# This is intentionally unrolled for performance
1553
num_present_parents = self._num_present_parents()
1554
if num_present_parents == 0:
1555
def fields_to_entry_0_parents(fields, _int=int):
1556
path_name_file_id_key = (fields[0], fields[1], fields[2])
1557
return (path_name_file_id_key, [
1559
fields[3], # minikind
1560
fields[4], # fingerprint
1561
_int(fields[5]), # size
1562
fields[6] == 'y', # executable
1563
fields[7], # packed_stat or revision_id
1565
return fields_to_entry_0_parents
1566
elif num_present_parents == 1:
1567
def fields_to_entry_1_parent(fields, _int=int):
1568
path_name_file_id_key = (fields[0], fields[1], fields[2])
1569
return (path_name_file_id_key, [
1571
fields[3], # minikind
1572
fields[4], # fingerprint
1573
_int(fields[5]), # size
1574
fields[6] == 'y', # executable
1575
fields[7], # packed_stat or revision_id
1578
fields[8], # minikind
1579
fields[9], # fingerprint
1580
_int(fields[10]), # size
1581
fields[11] == 'y', # executable
1582
fields[12], # packed_stat or revision_id
1585
return fields_to_entry_1_parent
1586
elif num_present_parents == 2:
1587
def fields_to_entry_2_parents(fields, _int=int):
1588
path_name_file_id_key = (fields[0], fields[1], fields[2])
1589
return (path_name_file_id_key, [
1591
fields[3], # minikind
1592
fields[4], # fingerprint
1593
_int(fields[5]), # size
1594
fields[6] == 'y', # executable
1595
fields[7], # packed_stat or revision_id
1598
fields[8], # minikind
1599
fields[9], # fingerprint
1600
_int(fields[10]), # size
1601
fields[11] == 'y', # executable
1602
fields[12], # packed_stat or revision_id
1605
fields[13], # minikind
1606
fields[14], # fingerprint
1607
_int(fields[15]), # size
1608
fields[16] == 'y', # executable
1609
fields[17], # packed_stat or revision_id
1612
return fields_to_entry_2_parents
1614
def fields_to_entry_n_parents(fields, _int=int):
1615
path_name_file_id_key = (fields[0], fields[1], fields[2])
1616
trees = [(fields[cur], # minikind
1617
fields[cur+1], # fingerprint
1618
_int(fields[cur+2]), # size
1619
fields[cur+3] == 'y', # executable
1620
fields[cur+4], # stat or revision_id
1621
) for cur in xrange(3, len(fields)-1, 5)]
1622
return path_name_file_id_key, trees
1623
return fields_to_entry_n_parents
1625
def get_parent_ids(self):
1626
"""Return a list of the parent tree ids for the directory state."""
1627
self._read_header_if_needed()
1628
return list(self._parents)
1630
def _get_block_entry_index(self, dirname, basename, tree_index):
1631
"""Get the coordinates for a path in the state structure.
1633
:param dirname: The utf8 dirname to lookup.
1634
:param basename: The utf8 basename to lookup.
1635
:param tree_index: The index of the tree for which this lookup should
1637
:return: A tuple describing where the path is located, or should be
1638
inserted. The tuple contains four fields: the block index, the row
1639
index, the directory is present (boolean), the entire path is
1640
present (boolean). There is no guarantee that either
1641
coordinate is currently reachable unless the found field for it is
1642
True. For instance, a directory not present in the searched tree
1643
may be returned with a value one greater than the current highest
1644
block offset. The directory present field will always be True when
1645
the path present field is True. The directory present field does
1646
NOT indicate that the directory is present in the searched tree,
1647
rather it indicates that there are at least some files in some
1650
self._read_dirblocks_if_needed()
1651
key = dirname, basename, ''
1652
block_index, present = self._find_block_index_from_key(key)
1654
# no such directory - return the dir index and 0 for the row.
1655
return block_index, 0, False, False
1656
block = self._dirblocks[block_index][1] # access the entries only
1657
entry_index, present = self._find_entry_index(key, block)
1658
# linear search through entries at this path to find the one
1660
while entry_index < len(block) and block[entry_index][0][1] == basename:
1661
if block[entry_index][1][tree_index][0] not in 'ar':
1662
# neither absent or relocated
1663
return block_index, entry_index, True, True
1665
return block_index, entry_index, True, False
1667
def _get_entry(self, tree_index, fileid_utf8=None, path_utf8=None):
1668
"""Get the dirstate entry for path in tree tree_index.
1670
If either file_id or path is supplied, it is used as the key to lookup.
1671
If both are supplied, the fastest lookup is used, and an error is
1672
raised if they do not both point at the same row.
1674
:param tree_index: The index of the tree we wish to locate this path
1675
in. If the path is present in that tree, the entry containing its
1676
details is returned, otherwise (None, None) is returned
1677
0 is the working tree, higher indexes are successive parent
1679
:param fileid_utf8: A utf8 file_id to look up.
1680
:param path_utf8: An utf8 path to be looked up.
1681
:return: The dirstate entry tuple for path, or (None, None)
1683
self._read_dirblocks_if_needed()
1684
if path_utf8 is not None:
1685
if type(path_utf8) is not str:
1686
raise AssertionError('path_utf8 is not a str: %s %s'
1687
% (type(path_utf8), path_utf8))
1688
# path lookups are faster
1689
dirname, basename = osutils.split(path_utf8)
1690
block_index, entry_index, dir_present, file_present = \
1691
self._get_block_entry_index(dirname, basename, tree_index)
1692
if not file_present:
1694
entry = self._dirblocks[block_index][1][entry_index]
1695
if not (entry[0][2] and entry[1][tree_index][0] not in ('a', 'r')):
1696
raise AssertionError('unversioned entry?')
1698
if entry[0][2] != fileid_utf8:
1699
self._changes_aborted = True
1700
raise errors.BzrError('integrity error ? : mismatching'
1701
' tree_index, file_id and path')
1704
possible_keys = self._get_id_index().get(fileid_utf8, None)
1705
if not possible_keys:
1707
for key in possible_keys:
1708
block_index, present = \
1709
self._find_block_index_from_key(key)
1710
# strange, probably indicates an out of date
1711
# id index - for now, allow this.
1714
# WARNING: DO not change this code to use _get_block_entry_index
1715
# as that function is not suitable: it does not use the key
1716
# to lookup, and thus the wrong coordinates are returned.
1717
block = self._dirblocks[block_index][1]
1718
entry_index, present = self._find_entry_index(key, block)
1720
entry = self._dirblocks[block_index][1][entry_index]
1721
if entry[1][tree_index][0] in 'fdlt':
1722
# this is the result we are looking for: the
1723
# real home of this file_id in this tree.
1725
if entry[1][tree_index][0] == 'a':
1726
# there is no home for this entry in this tree
1728
if entry[1][tree_index][0] != 'r':
1729
raise AssertionError(
1730
"entry %r has invalid minikind %r for tree %r" \
1732
entry[1][tree_index][0],
1734
real_path = entry[1][tree_index][1]
1735
return self._get_entry(tree_index, fileid_utf8=fileid_utf8,
1736
path_utf8=real_path)
1740
def initialize(cls, path):
1741
"""Create a new dirstate on path.
1743
The new dirstate will be an empty tree - that is it has no parents,
1744
and only a root node - which has id ROOT_ID.
1746
:param path: The name of the file for the dirstate.
1747
:return: A write-locked DirState object.
1749
# This constructs a new DirState object on a path, sets the _state_file
1750
# to a new empty file for that path. It then calls _set_data() with our
1751
# stock empty dirstate information - a root with ROOT_ID, no children,
1752
# and no parents. Finally it calls save() to ensure that this data will
1755
# root dir and root dir contents with no children.
1756
empty_tree_dirblocks = [('', []), ('', [])]
1757
# a new root directory, with a NULLSTAT.
1758
empty_tree_dirblocks[0][1].append(
1759
(('', '', inventory.ROOT_ID), [
1760
('d', '', 0, False, DirState.NULLSTAT),
1764
result._set_data([], empty_tree_dirblocks)
1772
def _inv_entry_to_details(inv_entry):
1773
"""Convert an inventory entry (from a revision tree) to state details.
1775
:param inv_entry: An inventory entry whose sha1 and link targets can be
1776
relied upon, and which has a revision set.
1777
:return: A details tuple - the details for a single tree at a path +
1780
kind = inv_entry.kind
1781
minikind = DirState._kind_to_minikind[kind]
1782
tree_data = inv_entry.revision
1783
if kind == 'directory':
1787
elif kind == 'symlink':
1788
# We don't support non-ascii targets for symlinks yet.
1789
fingerprint = str(inv_entry.symlink_target or '')
1792
elif kind == 'file':
1793
fingerprint = inv_entry.text_sha1 or ''
1794
size = inv_entry.text_size or 0
1795
executable = inv_entry.executable
1796
elif kind == 'tree-reference':
1797
fingerprint = inv_entry.reference_revision or ''
1801
raise Exception("can't pack %s" % inv_entry)
1802
return (minikind, fingerprint, size, executable, tree_data)
1804
def _iter_child_entries(self, tree_index, path_utf8):
1805
"""Iterate over all the entries that are children of path_utf.
1807
This only returns entries that are present (not in 'a', 'r') in
1808
tree_index. tree_index data is not refreshed, so if tree 0 is used,
1809
results may differ from that obtained if paths were statted to
1810
determine what ones were directories.
1812
Asking for the children of a non-directory will return an empty
1816
next_pending_dirs = [path_utf8]
1818
while next_pending_dirs:
1819
pending_dirs = next_pending_dirs
1820
next_pending_dirs = []
1821
for path in pending_dirs:
1822
block_index, present = self._find_block_index_from_key(
1824
if block_index == 0:
1826
if len(self._dirblocks) == 1:
1827
# asked for the children of the root with no other
1831
# children of a non-directory asked for.
1833
block = self._dirblocks[block_index]
1834
for entry in block[1]:
1835
kind = entry[1][tree_index][0]
1836
if kind not in absent:
1840
path = entry[0][0] + '/' + entry[0][1]
1843
next_pending_dirs.append(path)
1845
def _iter_entries(self):
1846
"""Iterate over all the entries in the dirstate.
1848
Each yelt item is an entry in the standard format described in the
1849
docstring of bzrlib.dirstate.
1851
self._read_dirblocks_if_needed()
1852
for directory in self._dirblocks:
1853
for entry in directory[1]:
1856
def _get_id_index(self):
1857
"""Get an id index of self._dirblocks."""
1858
if self._id_index is None:
1860
for key, tree_details in self._iter_entries():
1861
id_index.setdefault(key[2], set()).add(key)
1862
self._id_index = id_index
1863
return self._id_index
1865
def _get_output_lines(self, lines):
1866
"""Format lines for final output.
1868
:param lines: A sequence of lines containing the parents list and the
1871
output_lines = [DirState.HEADER_FORMAT_3]
1872
lines.append('') # a final newline
1873
inventory_text = '\0\n\0'.join(lines)
1874
output_lines.append('crc32: %s\n' % (zlib.crc32(inventory_text),))
1875
# -3, 1 for num parents, 1 for ghosts, 1 for final newline
1876
num_entries = len(lines)-3
1877
output_lines.append('num_entries: %s\n' % (num_entries,))
1878
output_lines.append(inventory_text)
1881
def _make_deleted_row(self, fileid_utf8, parents):
1882
"""Return a deleted row for fileid_utf8."""
1883
return ('/', 'RECYCLED.BIN', 'file', fileid_utf8, 0, DirState.NULLSTAT,
1886
def _num_present_parents(self):
1887
"""The number of parent entries in each record row."""
1888
return len(self._parents) - len(self._ghosts)
1892
"""Construct a DirState on the file at path path.
1894
:return: An unlocked DirState object, associated with the given path.
1896
result = DirState(path)
1899
def _read_dirblocks_if_needed(self):
1900
"""Read in all the dirblocks from the file if they are not in memory.
1902
This populates self._dirblocks, and sets self._dirblock_state to
1903
IN_MEMORY_UNMODIFIED. It is not currently ready for incremental block
1906
self._read_header_if_needed()
1907
if self._dirblock_state == DirState.NOT_IN_MEMORY:
1908
_read_dirblocks(self)
1910
def _read_header(self):
1911
"""This reads in the metadata header, and the parent ids.
1913
After reading in, the file should be positioned at the null
1914
just before the start of the first record in the file.
1916
:return: (expected crc checksum, number of entries, parent list)
1918
self._read_prelude()
1919
parent_line = self._state_file.readline()
1920
info = parent_line.split('\0')
1921
num_parents = int(info[0])
1922
self._parents = info[1:-1]
1923
ghost_line = self._state_file.readline()
1924
info = ghost_line.split('\0')
1925
num_ghosts = int(info[1])
1926
self._ghosts = info[2:-1]
1927
self._header_state = DirState.IN_MEMORY_UNMODIFIED
1928
self._end_of_header = self._state_file.tell()
1930
def _read_header_if_needed(self):
1931
"""Read the header of the dirstate file if needed."""
1932
# inline this as it will be called a lot
1933
if not self._lock_token:
1934
raise errors.ObjectNotLocked(self)
1935
if self._header_state == DirState.NOT_IN_MEMORY:
1938
def _read_prelude(self):
1939
"""Read in the prelude header of the dirstate file.
1941
This only reads in the stuff that is not connected to the crc
1942
checksum. The position will be correct to read in the rest of
1943
the file and check the checksum after this point.
1944
The next entry in the file should be the number of parents,
1945
and their ids. Followed by a newline.
1947
header = self._state_file.readline()
1948
if header != DirState.HEADER_FORMAT_3:
1949
raise errors.BzrError(
1950
'invalid header line: %r' % (header,))
1951
crc_line = self._state_file.readline()
1952
if not crc_line.startswith('crc32: '):
1953
raise errors.BzrError('missing crc32 checksum: %r' % crc_line)
1954
self.crc_expected = int(crc_line[len('crc32: '):-1])
1955
num_entries_line = self._state_file.readline()
1956
if not num_entries_line.startswith('num_entries: '):
1957
raise errors.BzrError('missing num_entries line')
1958
self._num_entries = int(num_entries_line[len('num_entries: '):-1])
1960
def sha1_from_stat(self, path, stat_result, _pack_stat=pack_stat):
1961
"""Find a sha1 given a stat lookup."""
1962
return self._get_packed_stat_index().get(_pack_stat(stat_result), None)
1964
def _get_packed_stat_index(self):
1965
"""Get a packed_stat index of self._dirblocks."""
1966
if self._packed_stat_index is None:
1968
for key, tree_details in self._iter_entries():
1969
if tree_details[0][0] == 'f':
1970
index[tree_details[0][4]] = tree_details[0][1]
1971
self._packed_stat_index = index
1972
return self._packed_stat_index
1975
"""Save any pending changes created during this session.
1977
We reuse the existing file, because that prevents race conditions with
1978
file creation, and use oslocks on it to prevent concurrent modification
1979
and reads - because dirstate's incremental data aggregation is not
1980
compatible with reading a modified file, and replacing a file in use by
1981
another process is impossible on Windows.
1983
A dirstate in read only mode should be smart enough though to validate
1984
that the file has not changed, and otherwise discard its cache and
1985
start over, to allow for fine grained read lock duration, so 'status'
1986
wont block 'commit' - for example.
1988
if self._changes_aborted:
1989
# Should this be a warning? For now, I'm expecting that places that
1990
# mark it inconsistent will warn, making a warning here redundant.
1991
trace.mutter('Not saving DirState because '
1992
'_changes_aborted is set.')
1994
if (self._header_state == DirState.IN_MEMORY_MODIFIED or
1995
self._dirblock_state == DirState.IN_MEMORY_MODIFIED):
1997
grabbed_write_lock = False
1998
if self._lock_state != 'w':
1999
grabbed_write_lock, new_lock = self._lock_token.temporary_write_lock()
2000
# Switch over to the new lock, as the old one may be closed.
2001
# TODO: jam 20070315 We should validate the disk file has
2002
# not changed contents. Since temporary_write_lock may
2003
# not be an atomic operation.
2004
self._lock_token = new_lock
2005
self._state_file = new_lock.f
2006
if not grabbed_write_lock:
2007
# We couldn't grab a write lock, so we switch back to a read one
2010
self._state_file.seek(0)
2011
self._state_file.writelines(self.get_lines())
2012
self._state_file.truncate()
2013
self._state_file.flush()
2014
self._header_state = DirState.IN_MEMORY_UNMODIFIED
2015
self._dirblock_state = DirState.IN_MEMORY_UNMODIFIED
2017
if grabbed_write_lock:
2018
self._lock_token = self._lock_token.restore_read_lock()
2019
self._state_file = self._lock_token.f
2020
# TODO: jam 20070315 We should validate the disk file has
2021
# not changed contents. Since restore_read_lock may
2022
# not be an atomic operation.
2024
def _set_data(self, parent_ids, dirblocks):
2025
"""Set the full dirstate data in memory.
2027
This is an internal function used to completely replace the objects
2028
in memory state. It puts the dirstate into state 'full-dirty'.
2030
:param parent_ids: A list of parent tree revision ids.
2031
:param dirblocks: A list containing one tuple for each directory in the
2032
tree. Each tuple contains the directory path and a list of entries
2033
found in that directory.
2035
# our memory copy is now authoritative.
2036
self._dirblocks = dirblocks
2037
self._header_state = DirState.IN_MEMORY_MODIFIED
2038
self._dirblock_state = DirState.IN_MEMORY_MODIFIED
2039
self._parents = list(parent_ids)
2040
self._id_index = None
2041
self._packed_stat_index = None
2043
def set_path_id(self, path, new_id):
2044
"""Change the id of path to new_id in the current working tree.
2046
:param path: The path inside the tree to set - '' is the root, 'foo'
2047
is the path foo in the root.
2048
:param new_id: The new id to assign to the path. This must be a utf8
2049
file id (not unicode, and not None).
2051
self._read_dirblocks_if_needed()
2053
# TODO: logic not written
2054
raise NotImplementedError(self.set_path_id)
2055
# TODO: check new id is unique
2056
entry = self._get_entry(0, path_utf8=path)
2057
if entry[0][2] == new_id:
2058
# Nothing to change.
2060
# mark the old path absent, and insert a new root path
2061
self._make_absent(entry)
2062
self.update_minimal(('', '', new_id), 'd',
2063
path_utf8='', packed_stat=entry[1][0][4])
2064
self._dirblock_state = DirState.IN_MEMORY_MODIFIED
2065
if self._id_index is not None:
2066
self._id_index.setdefault(new_id, set()).add(entry[0])
2068
def set_parent_trees(self, trees, ghosts):
2069
"""Set the parent trees for the dirstate.
2071
:param trees: A list of revision_id, tree tuples. tree must be provided
2072
even if the revision_id refers to a ghost: supply an empty tree in
2074
:param ghosts: A list of the revision_ids that are ghosts at the time
2077
# TODO: generate a list of parent indexes to preserve to save
2078
# processing specific parent trees. In the common case one tree will
2079
# be preserved - the left most parent.
2080
# TODO: if the parent tree is a dirstate, we might want to walk them
2081
# all by path in parallel for 'optimal' common-case performance.
2082
# generate new root row.
2083
self._read_dirblocks_if_needed()
2084
# TODO future sketch: Examine the existing parents to generate a change
2085
# map and then walk the new parent trees only, mapping them into the
2086
# dirstate. Walk the dirstate at the same time to remove unreferenced
2089
# sketch: loop over all entries in the dirstate, cherry picking
2090
# entries from the parent trees, if they are not ghost trees.
2091
# after we finish walking the dirstate, all entries not in the dirstate
2092
# are deletes, so we want to append them to the end as per the design
2093
# discussions. So do a set difference on ids with the parents to
2094
# get deletes, and add them to the end.
2095
# During the update process we need to answer the following questions:
2096
# - find other keys containing a fileid in order to create cross-path
2097
# links. We dont't trivially use the inventory from other trees
2098
# because this leads to either double touching, or to accessing
2100
# - find other keys containing a path
2101
# We accumulate each entry via this dictionary, including the root
2104
# we could do parallel iterators, but because file id data may be
2105
# scattered throughout, we dont save on index overhead: we have to look
2106
# at everything anyway. We can probably save cycles by reusing parent
2107
# data and doing an incremental update when adding an additional
2108
# parent, but for now the common cases are adding a new parent (merge),
2109
# and replacing completely (commit), and commit is more common: so
2110
# optimise merge later.
2112
# ---- start generation of full tree mapping data
2113
# what trees should we use?
2114
parent_trees = [tree for rev_id, tree in trees if rev_id not in ghosts]
2115
# how many trees do we end up with
2116
parent_count = len(parent_trees)
2118
# one: the current tree
2119
for entry in self._iter_entries():
2120
# skip entries not in the current tree
2121
if entry[1][0][0] in 'ar': # absent, relocated
2123
by_path[entry[0]] = [entry[1][0]] + \
2124
[DirState.NULL_PARENT_DETAILS] * parent_count
2125
id_index[entry[0][2]] = set([entry[0]])
2127
# now the parent trees:
2128
for tree_index, tree in enumerate(parent_trees):
2129
# the index is off by one, adjust it.
2130
tree_index = tree_index + 1
2131
# when we add new locations for a fileid we need these ranges for
2132
# any fileid in this tree as we set the by_path[id] to:
2133
# already_processed_tree_details + new_details + new_location_suffix
2134
# the suffix is from tree_index+1:parent_count+1.
2135
new_location_suffix = [DirState.NULL_PARENT_DETAILS] * (parent_count - tree_index)
2136
# now stitch in all the entries from this tree
2137
for path, entry in tree.inventory.iter_entries_by_dir():
2138
# here we process each trees details for each item in the tree.
2139
# we first update any existing entries for the id at other paths,
2140
# then we either create or update the entry for the id at the
2141
# right path, and finally we add (if needed) a mapping from
2142
# file_id to this path. We do it in this order to allow us to
2143
# avoid checking all known paths for the id when generating a
2144
# new entry at this path: by adding the id->path mapping last,
2145
# all the mappings are valid and have correct relocation
2146
# records where needed.
2147
file_id = entry.file_id
2148
path_utf8 = path.encode('utf8')
2149
dirname, basename = osutils.split(path_utf8)
2150
new_entry_key = (dirname, basename, file_id)
2151
# tree index consistency: All other paths for this id in this tree
2152
# index must point to the correct path.
2153
for entry_key in id_index.setdefault(file_id, set()):
2154
# TODO:PROFILING: It might be faster to just update
2155
# rather than checking if we need to, and then overwrite
2156
# the one we are located at.
2157
if entry_key != new_entry_key:
2158
# this file id is at a different path in one of the
2159
# other trees, so put absent pointers there
2160
# This is the vertical axis in the matrix, all pointing
2162
by_path[entry_key][tree_index] = ('r', path_utf8, 0, False, '')
2163
# by path consistency: Insert into an existing path record (trivial), or
2164
# add a new one with relocation pointers for the other tree indexes.
2165
if new_entry_key in id_index[file_id]:
2166
# there is already an entry where this data belongs, just insert it.
2167
by_path[new_entry_key][tree_index] = \
2168
self._inv_entry_to_details(entry)
2170
# add relocated entries to the horizontal axis - this row
2171
# mapping from path,id. We need to look up the correct path
2172
# for the indexes from 0 to tree_index -1
2174
for lookup_index in xrange(tree_index):
2175
# boundary case: this is the first occurence of file_id
2176
# so there are no id_indexs, possibly take this out of
2178
if not len(id_index[file_id]):
2179
new_details.append(DirState.NULL_PARENT_DETAILS)
2181
# grab any one entry, use it to find the right path.
2182
# TODO: optimise this to reduce memory use in highly
2183
# fragmented situations by reusing the relocation
2185
a_key = iter(id_index[file_id]).next()
2186
if by_path[a_key][lookup_index][0] in ('r', 'a'):
2187
# its a pointer or missing statement, use it as is.
2188
new_details.append(by_path[a_key][lookup_index])
2190
# we have the right key, make a pointer to it.
2191
real_path = ('/'.join(a_key[0:2])).strip('/')
2192
new_details.append(('r', real_path, 0, False, ''))
2193
new_details.append(self._inv_entry_to_details(entry))
2194
new_details.extend(new_location_suffix)
2195
by_path[new_entry_key] = new_details
2196
id_index[file_id].add(new_entry_key)
2197
# --- end generation of full tree mappings
2199
# sort and output all the entries
2200
new_entries = self._sort_entries(by_path.items())
2201
self._entries_to_current_state(new_entries)
2202
self._parents = [rev_id for rev_id, tree in trees]
2203
self._ghosts = list(ghosts)
2204
self._header_state = DirState.IN_MEMORY_MODIFIED
2205
self._dirblock_state = DirState.IN_MEMORY_MODIFIED
2206
self._id_index = id_index
2208
def _sort_entries(self, entry_list):
2209
"""Given a list of entries, sort them into the right order.
2211
This is done when constructing a new dirstate from trees - normally we
2212
try to keep everything in sorted blocks all the time, but sometimes
2213
it's easier to sort after the fact.
2216
# sort by: directory parts, file name, file id
2217
return entry[0][0].split('/'), entry[0][1], entry[0][2]
2218
return sorted(entry_list, key=_key)
2220
def set_state_from_inventory(self, new_inv):
2221
"""Set new_inv as the current state.
2223
This API is called by tree transform, and will usually occur with
2224
existing parent trees.
2226
:param new_inv: The inventory object to set current state from.
2228
if 'evil' in debug.debug_flags:
2229
trace.mutter_callsite(1,
2230
"set_state_from_inventory called; please mutate the tree instead")
2231
self._read_dirblocks_if_needed()
2233
# Two iterators: current data and new data, both in dirblock order.
2234
# We zip them together, which tells about entries that are new in the
2235
# inventory, or removed in the inventory, or present in both and
2238
# You might think we could just synthesize a new dirstate directly
2239
# since we're processing it in the right order. However, we need to
2240
# also consider there may be any number of parent trees and relocation
2241
# pointers, and we don't want to duplicate that here.
2242
new_iterator = new_inv.iter_entries_by_dir()
2243
# we will be modifying the dirstate, so we need a stable iterator. In
2244
# future we might write one, for now we just clone the state into a
2245
# list - which is a shallow copy.
2246
old_iterator = iter(list(self._iter_entries()))
2247
# both must have roots so this is safe:
2248
current_new = new_iterator.next()
2249
current_old = old_iterator.next()
2250
def advance(iterator):
2252
return iterator.next()
2253
except StopIteration:
2255
while current_new or current_old:
2256
# skip entries in old that are not really there
2257
if current_old and current_old[1][0][0] in 'ar':
2258
# relocated or absent
2259
current_old = advance(old_iterator)
2262
# convert new into dirblock style
2263
new_path_utf8 = current_new[0].encode('utf8')
2264
new_dirname, new_basename = osutils.split(new_path_utf8)
2265
new_id = current_new[1].file_id
2266
new_entry_key = (new_dirname, new_basename, new_id)
2267
current_new_minikind = \
2268
DirState._kind_to_minikind[current_new[1].kind]
2269
if current_new_minikind == 't':
2270
fingerprint = current_new[1].reference_revision or ''
2272
# We normally only insert or remove records, or update
2273
# them when it has significantly changed. Then we want to
2274
# erase its fingerprint. Unaffected records should
2275
# normally not be updated at all.
2278
# for safety disable variables
2279
new_path_utf8 = new_dirname = new_basename = new_id = \
2280
new_entry_key = None
2281
# 5 cases, we dont have a value that is strictly greater than everything, so
2282
# we make both end conditions explicit
2284
# old is finished: insert current_new into the state.
2285
self.update_minimal(new_entry_key, current_new_minikind,
2286
executable=current_new[1].executable,
2287
path_utf8=new_path_utf8, fingerprint=fingerprint)
2288
current_new = advance(new_iterator)
2289
elif not current_new:
2291
self._make_absent(current_old)
2292
current_old = advance(old_iterator)
2293
elif new_entry_key == current_old[0]:
2294
# same - common case
2295
# We're looking at the same path and id in both the dirstate
2296
# and inventory, so just need to update the fields in the
2297
# dirstate from the one in the inventory.
2298
# TODO: update the record if anything significant has changed.
2299
# the minimal required trigger is if the execute bit or cached
2301
if (current_old[1][0][3] != current_new[1].executable or
2302
current_old[1][0][0] != current_new_minikind):
2303
self.update_minimal(current_old[0], current_new_minikind,
2304
executable=current_new[1].executable,
2305
path_utf8=new_path_utf8, fingerprint=fingerprint)
2306
# both sides are dealt with, move on
2307
current_old = advance(old_iterator)
2308
current_new = advance(new_iterator)
2309
elif (cmp_by_dirs(new_dirname, current_old[0][0]) < 0
2310
or (new_dirname == current_old[0][0]
2311
and new_entry_key[1:] < current_old[0][1:])):
2313
# add a entry for this and advance new
2314
self.update_minimal(new_entry_key, current_new_minikind,
2315
executable=current_new[1].executable,
2316
path_utf8=new_path_utf8, fingerprint=fingerprint)
2317
current_new = advance(new_iterator)
2319
# we've advanced past the place where the old key would be,
2320
# without seeing it in the new list. so it must be gone.
2321
self._make_absent(current_old)
2322
current_old = advance(old_iterator)
2323
self._dirblock_state = DirState.IN_MEMORY_MODIFIED
2324
self._id_index = None
2325
self._packed_stat_index = None
2327
def _make_absent(self, current_old):
2328
"""Mark current_old - an entry - as absent for tree 0.
2330
:return: True if this was the last details entry for the entry key:
2331
that is, if the underlying block has had the entry removed, thus
2332
shrinking in length.
2334
# build up paths that this id will be left at after the change is made,
2335
# so we can update their cross references in tree 0
2336
all_remaining_keys = set()
2337
# Dont check the working tree, because it's going.
2338
for details in current_old[1][1:]:
2339
if details[0] not in 'ar': # absent, relocated
2340
all_remaining_keys.add(current_old[0])
2341
elif details[0] == 'r': # relocated
2342
# record the key for the real path.
2343
all_remaining_keys.add(tuple(osutils.split(details[1])) + (current_old[0][2],))
2344
# absent rows are not present at any path.
2345
last_reference = current_old[0] not in all_remaining_keys
2347
# the current row consists entire of the current item (being marked
2348
# absent), and relocated or absent entries for the other trees:
2349
# Remove it, its meaningless.
2350
block = self._find_block(current_old[0])
2351
entry_index, present = self._find_entry_index(current_old[0], block[1])
2353
raise AssertionError('could not find entry for %s' % (current_old,))
2354
block[1].pop(entry_index)
2355
# if we have an id_index in use, remove this key from it for this id.
2356
if self._id_index is not None:
2357
self._id_index[current_old[0][2]].remove(current_old[0])
2358
# update all remaining keys for this id to record it as absent. The
2359
# existing details may either be the record we are marking as deleted
2360
# (if there were other trees with the id present at this path), or may
2362
for update_key in all_remaining_keys:
2363
update_block_index, present = \
2364
self._find_block_index_from_key(update_key)
2366
raise AssertionError('could not find block for %s' % (update_key,))
2367
update_entry_index, present = \
2368
self._find_entry_index(update_key, self._dirblocks[update_block_index][1])
2370
raise AssertionError('could not find entry for %s' % (update_key,))
2371
update_tree_details = self._dirblocks[update_block_index][1][update_entry_index][1]
2372
# it must not be absent at the moment
2373
if update_tree_details[0][0] == 'a': # absent
2374
raise AssertionError('bad row %r' % (update_tree_details,))
2375
update_tree_details[0] = DirState.NULL_PARENT_DETAILS
2376
self._dirblock_state = DirState.IN_MEMORY_MODIFIED
2377
return last_reference
2379
def update_minimal(self, key, minikind, executable=False, fingerprint='',
2380
packed_stat=None, size=0, path_utf8=None):
2381
"""Update an entry to the state in tree 0.
2383
This will either create a new entry at 'key' or update an existing one.
2384
It also makes sure that any other records which might mention this are
2387
:param key: (dir, name, file_id) for the new entry
2388
:param minikind: The type for the entry ('f' == 'file', 'd' ==
2390
:param executable: Should the executable bit be set?
2391
:param fingerprint: Simple fingerprint for new entry: sha1 for files,
2392
referenced revision id for subtrees, etc.
2393
:param packed_stat: Packed stat value for new entry.
2394
:param size: Size information for new entry
2395
:param path_utf8: key[0] + '/' + key[1], just passed in to avoid doing
2398
If packed_stat and fingerprint are not given, they're invalidated in
2401
block = self._find_block(key)[1]
2402
if packed_stat is None:
2403
packed_stat = DirState.NULLSTAT
2404
# XXX: Some callers pass '' as the packed_stat, and it seems to be
2405
# sometimes present in the dirstate - this seems oddly inconsistent.
2407
entry_index, present = self._find_entry_index(key, block)
2408
new_details = (minikind, fingerprint, size, executable, packed_stat)
2409
id_index = self._get_id_index()
2411
# new entry, synthesis cross reference here,
2412
existing_keys = id_index.setdefault(key[2], set())
2413
if not existing_keys:
2414
# not currently in the state, simplest case
2415
new_entry = key, [new_details] + self._empty_parent_info()
2417
# present at one or more existing other paths.
2418
# grab one of them and use it to generate parent
2419
# relocation/absent entries.
2420
new_entry = key, [new_details]
2421
for other_key in existing_keys:
2422
# change the record at other to be a pointer to this new
2423
# record. The loop looks similar to the change to
2424
# relocations when updating an existing record but its not:
2425
# the test for existing kinds is different: this can be
2426
# factored out to a helper though.
2427
other_block_index, present = self._find_block_index_from_key(other_key)
2429
raise AssertionError('could not find block for %s' % (other_key,))
2430
other_entry_index, present = self._find_entry_index(other_key,
2431
self._dirblocks[other_block_index][1])
2433
raise AssertionError('could not find entry for %s' % (other_key,))
2434
if path_utf8 is None:
2435
raise AssertionError('no path')
2436
self._dirblocks[other_block_index][1][other_entry_index][1][0] = \
2437
('r', path_utf8, 0, False, '')
2439
num_present_parents = self._num_present_parents()
2440
for lookup_index in xrange(1, num_present_parents + 1):
2441
# grab any one entry, use it to find the right path.
2442
# TODO: optimise this to reduce memory use in highly
2443
# fragmented situations by reusing the relocation
2445
update_block_index, present = \
2446
self._find_block_index_from_key(other_key)
2448
raise AssertionError('could not find block for %s' % (other_key,))
2449
update_entry_index, present = \
2450
self._find_entry_index(other_key, self._dirblocks[update_block_index][1])
2452
raise AssertionError('could not find entry for %s' % (other_key,))
2453
update_details = self._dirblocks[update_block_index][1][update_entry_index][1][lookup_index]
2454
if update_details[0] in 'ar': # relocated, absent
2455
# its a pointer or absent in lookup_index's tree, use
2457
new_entry[1].append(update_details)
2459
# we have the right key, make a pointer to it.
2460
pointer_path = osutils.pathjoin(*other_key[0:2])
2461
new_entry[1].append(('r', pointer_path, 0, False, ''))
2462
block.insert(entry_index, new_entry)
2463
existing_keys.add(key)
2465
# Does the new state matter?
2466
block[entry_index][1][0] = new_details
2467
# parents cannot be affected by what we do.
2468
# other occurences of this id can be found
2469
# from the id index.
2471
# tree index consistency: All other paths for this id in this tree
2472
# index must point to the correct path. We have to loop here because
2473
# we may have passed entries in the state with this file id already
2474
# that were absent - where parent entries are - and they need to be
2475
# converted to relocated.
2476
if path_utf8 is None:
2477
raise AssertionError('no path')
2478
for entry_key in id_index.setdefault(key[2], set()):
2479
# TODO:PROFILING: It might be faster to just update
2480
# rather than checking if we need to, and then overwrite
2481
# the one we are located at.
2482
if entry_key != key:
2483
# this file id is at a different path in one of the
2484
# other trees, so put absent pointers there
2485
# This is the vertical axis in the matrix, all pointing
2487
block_index, present = self._find_block_index_from_key(entry_key)
2489
raise AssertionError('not present: %r', entry_key)
2490
entry_index, present = self._find_entry_index(entry_key, self._dirblocks[block_index][1])
2492
raise AssertionError('not present: %r', entry_key)
2493
self._dirblocks[block_index][1][entry_index][1][0] = \
2494
('r', path_utf8, 0, False, '')
2495
# add a containing dirblock if needed.
2496
if new_details[0] == 'd':
2497
subdir_key = (osutils.pathjoin(*key[0:2]), '', '')
2498
block_index, present = self._find_block_index_from_key(subdir_key)
2500
self._dirblocks.insert(block_index, (subdir_key[0], []))
2502
self._dirblock_state = DirState.IN_MEMORY_MODIFIED
2504
def _validate(self):
2505
"""Check that invariants on the dirblock are correct.
2507
This can be useful in debugging; it shouldn't be necessary in
2510
This must be called with a lock held.
2512
# NOTE: This must always raise AssertionError not just assert,
2513
# otherwise it may not behave properly under python -O
2515
# TODO: All entries must have some content that's not 'a' or 'r',
2516
# otherwise it could just be removed.
2518
# TODO: All relocations must point directly to a real entry.
2520
# TODO: No repeated keys.
2523
from pprint import pformat
2524
self._read_dirblocks_if_needed()
2525
if len(self._dirblocks) > 0:
2526
if not self._dirblocks[0][0] == '':
2527
raise AssertionError(
2528
"dirblocks don't start with root block:\n" + \
2529
pformat(self._dirblocks))
2530
if len(self._dirblocks) > 1:
2531
if not self._dirblocks[1][0] == '':
2532
raise AssertionError(
2533
"dirblocks missing root directory:\n" + \
2534
pformat(self._dirblocks))
2535
# the dirblocks are sorted by their path components, name, and dir id
2536
dir_names = [d[0].split('/')
2537
for d in self._dirblocks[1:]]
2538
if dir_names != sorted(dir_names):
2539
raise AssertionError(
2540
"dir names are not in sorted order:\n" + \
2541
pformat(self._dirblocks) + \
2544
for dirblock in self._dirblocks:
2545
# within each dirblock, the entries are sorted by filename and
2547
for entry in dirblock[1]:
2548
if dirblock[0] != entry[0][0]:
2549
raise AssertionError(
2551
"doesn't match directory name in\n%r" %
2552
(entry, pformat(dirblock)))
2553
if dirblock[1] != sorted(dirblock[1]):
2554
raise AssertionError(
2555
"dirblock for %r is not sorted:\n%s" % \
2556
(dirblock[0], pformat(dirblock)))
2558
def check_valid_parent():
2559
"""Check that the current entry has a valid parent.
2561
This makes sure that the parent has a record,
2562
and that the parent isn't marked as "absent" in the
2563
current tree. (It is invalid to have a non-absent file in an absent
2566
if entry[0][0:2] == ('', ''):
2567
# There should be no parent for the root row
2569
parent_entry = self._get_entry(tree_index, path_utf8=entry[0][0])
2570
if parent_entry == (None, None):
2571
raise AssertionError(
2572
"no parent entry for: %s in tree %s"
2573
% (this_path, tree_index))
2574
if parent_entry[1][tree_index][0] != 'd':
2575
raise AssertionError(
2576
"Parent entry for %s is not marked as a valid"
2577
" directory. %s" % (this_path, parent_entry,))
2579
# For each file id, for each tree: either
2580
# the file id is not present at all; all rows with that id in the
2581
# key have it marked as 'absent'
2582
# OR the file id is present under exactly one name; any other entries
2583
# that mention that id point to the correct name.
2585
# We check this with a dict per tree pointing either to the present
2586
# name, or None if absent.
2587
tree_count = self._num_present_parents() + 1
2588
id_path_maps = [dict() for i in range(tree_count)]
2589
# Make sure that all renamed entries point to the correct location.
2590
for entry in self._iter_entries():
2591
file_id = entry[0][2]
2592
this_path = osutils.pathjoin(entry[0][0], entry[0][1])
2593
if len(entry[1]) != tree_count:
2594
raise AssertionError(
2595
"wrong number of entry details for row\n%s" \
2596
",\nexpected %d" % \
2597
(pformat(entry), tree_count))
2598
absent_positions = 0
2599
for tree_index, tree_state in enumerate(entry[1]):
2600
this_tree_map = id_path_maps[tree_index]
2601
minikind = tree_state[0]
2602
if minikind in 'ar':
2603
absent_positions += 1
2604
# have we seen this id before in this column?
2605
if file_id in this_tree_map:
2606
previous_path, previous_loc = this_tree_map[file_id]
2607
# any later mention of this file must be consistent with
2608
# what was said before
2610
if previous_path is not None:
2611
raise AssertionError(
2612
"file %s is absent in row %r but also present " \
2614
(file_id, entry, previous_path))
2615
elif minikind == 'r':
2616
target_location = tree_state[1]
2617
if previous_path != target_location:
2618
raise AssertionError(
2619
"file %s relocation in row %r but also at %r" \
2620
% (file_id, entry, previous_path))
2622
# a file, directory, etc - may have been previously
2623
# pointed to by a relocation, which must point here
2624
if previous_path != this_path:
2625
raise AssertionError(
2626
"entry %r inconsistent with previous path %r "
2628
(entry, previous_path, previous_loc))
2629
check_valid_parent()
2632
# absent; should not occur anywhere else
2633
this_tree_map[file_id] = None, this_path
2634
elif minikind == 'r':
2635
# relocation, must occur at expected location
2636
this_tree_map[file_id] = tree_state[1], this_path
2638
this_tree_map[file_id] = this_path, this_path
2639
check_valid_parent()
2640
if absent_positions == tree_count:
2641
raise AssertionError(
2642
"entry %r has no data for any tree." % (entry,))
2644
def _wipe_state(self):
2645
"""Forget all state information about the dirstate."""
2646
self._header_state = DirState.NOT_IN_MEMORY
2647
self._dirblock_state = DirState.NOT_IN_MEMORY
2648
self._changes_aborted = False
2651
self._dirblocks = []
2652
self._id_index = None
2653
self._packed_stat_index = None
2654
self._end_of_header = None
2655
self._cutoff_time = None
2656
self._split_path_cache = {}
2658
def lock_read(self):
2659
"""Acquire a read lock on the dirstate."""
2660
if self._lock_token is not None:
2661
raise errors.LockContention(self._lock_token)
2662
# TODO: jam 20070301 Rather than wiping completely, if the blocks are
2663
# already in memory, we could read just the header and check for
2664
# any modification. If not modified, we can just leave things
2666
self._lock_token = lock.ReadLock(self._filename)
2667
self._lock_state = 'r'
2668
self._state_file = self._lock_token.f
2671
def lock_write(self):
2672
"""Acquire a write lock on the dirstate."""
2673
if self._lock_token is not None:
2674
raise errors.LockContention(self._lock_token)
2675
# TODO: jam 20070301 Rather than wiping completely, if the blocks are
2676
# already in memory, we could read just the header and check for
2677
# any modification. If not modified, we can just leave things
2679
self._lock_token = lock.WriteLock(self._filename)
2680
self._lock_state = 'w'
2681
self._state_file = self._lock_token.f
2685
"""Drop any locks held on the dirstate."""
2686
if self._lock_token is None:
2687
raise errors.LockNotHeld(self)
2688
# TODO: jam 20070301 Rather than wiping completely, if the blocks are
2689
# already in memory, we could read just the header and check for
2690
# any modification. If not modified, we can just leave things
2692
self._state_file = None
2693
self._lock_state = None
2694
self._lock_token.unlock()
2695
self._lock_token = None
2696
self._split_path_cache = {}
2698
def _requires_lock(self):
2699
"""Check that a lock is currently held by someone on the dirstate."""
2700
if not self._lock_token:
2701
raise errors.ObjectNotLocked(self)
2704
def py_update_entry(self, entry, abspath, stat_value,
2705
_stat_to_minikind=DirState._stat_to_minikind,
2706
_pack_stat=pack_stat):
2707
"""Update the entry based on what is actually on disk.
2709
:param entry: This is the dirblock entry for the file in question.
2710
:param abspath: The path on disk for this file.
2711
:param stat_value: (optional) if we already have done a stat on the
2713
:return: The sha1 hexdigest of the file (40 bytes) or link target of a
2717
minikind = _stat_to_minikind[stat_value.st_mode & 0170000]
2721
packed_stat = _pack_stat(stat_value)
2722
(saved_minikind, saved_link_or_sha1, saved_file_size,
2723
saved_executable, saved_packed_stat) = entry[1][0]
2725
if (minikind == saved_minikind
2726
and packed_stat == saved_packed_stat):
2727
# The stat hasn't changed since we saved, so we can re-use the
2732
# size should also be in packed_stat
2733
if saved_file_size == stat_value.st_size:
2734
return saved_link_or_sha1
2736
# If we have gotten this far, that means that we need to actually
2737
# process this entry.
2740
link_or_sha1 = self._sha1_file(abspath)
2741
executable = self._is_executable(stat_value.st_mode,
2743
if self._cutoff_time is None:
2744
self._sha_cutoff_time()
2745
if (stat_value.st_mtime < self._cutoff_time
2746
and stat_value.st_ctime < self._cutoff_time):
2747
entry[1][0] = ('f', link_or_sha1, stat_value.st_size,
2748
executable, packed_stat)
2750
entry[1][0] = ('f', '', stat_value.st_size,
2751
executable, DirState.NULLSTAT)
2752
elif minikind == 'd':
2754
entry[1][0] = ('d', '', 0, False, packed_stat)
2755
if saved_minikind != 'd':
2756
# This changed from something into a directory. Make sure we
2757
# have a directory block for it. This doesn't happen very
2758
# often, so this doesn't have to be super fast.
2759
block_index, entry_index, dir_present, file_present = \
2760
self._get_block_entry_index(entry[0][0], entry[0][1], 0)
2761
self._ensure_block(block_index, entry_index,
2762
osutils.pathjoin(entry[0][0], entry[0][1]))
2763
elif minikind == 'l':
2764
link_or_sha1 = self._read_link(abspath, saved_link_or_sha1)
2765
if self._cutoff_time is None:
2766
self._sha_cutoff_time()
2767
if (stat_value.st_mtime < self._cutoff_time
2768
and stat_value.st_ctime < self._cutoff_time):
2769
entry[1][0] = ('l', link_or_sha1, stat_value.st_size,
2772
entry[1][0] = ('l', '', stat_value.st_size,
2773
False, DirState.NULLSTAT)
2774
self._dirblock_state = DirState.IN_MEMORY_MODIFIED
2777
update_entry = py_update_entry
2780
# Try to load the compiled form if possible
2782
from bzrlib._dirstate_helpers_c import (
2783
_read_dirblocks_c as _read_dirblocks,
2784
bisect_dirblock_c as bisect_dirblock,
2785
_bisect_path_left_c as _bisect_path_left,
2786
_bisect_path_right_c as _bisect_path_right,
2787
cmp_by_dirs_c as cmp_by_dirs,
2788
update_entry as update_entry,
2791
from bzrlib._dirstate_helpers_py import (
2792
_read_dirblocks_py as _read_dirblocks,
2793
bisect_dirblock_py as bisect_dirblock,
2794
_bisect_path_left_py as _bisect_path_left,
2795
_bisect_path_right_py as _bisect_path_right,
2796
cmp_by_dirs_py as cmp_by_dirs,
added
removed
bzrlib/dirstate.py
