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., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 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 it's a file. The fingerprint is the
86
sha1 value of the file's canonical form, i.e. after any read filters have
87
been applied to the convenience form stored in the working tree.
88
'l' is a symlink entry: As for directory, but a symlink. The fingerprint is the
90
't' is a reference to a nested subtree; the fingerprint is the referenced
95
The entries on disk and in memory are ordered according to the following keys:
97
directory, as a list of components
101
--- Format 1 had the following different definition: ---
102
rows = dirname, NULL, basename, NULL, MINIKIND, NULL, fileid_utf8, NULL,
103
WHOLE NUMBER (* size *), NULL, packed stat, NULL, sha1|symlink target,
105
PARENT ROW = NULL, revision_utf8, NULL, MINIKIND, NULL, dirname, NULL,
106
basename, NULL, WHOLE NUMBER (* size *), NULL, "y" | "n", NULL,
109
PARENT ROW's are emitted for every parent that is not in the ghosts details
110
line. That is, if the parents are foo, bar, baz, and the ghosts are bar, then
111
each row will have a PARENT ROW for foo and baz, but not for bar.
114
In any tree, a kind of 'moved' indicates that the fingerprint field
115
(which we treat as opaque data specific to the 'kind' anyway) has the
116
details for the id of this row in that tree.
118
I'm strongly tempted to add a id->path index as well, but I think that
119
where we need id->path mapping; we also usually read the whole file, so
120
I'm going to skip that for the moment, as we have the ability to locate
121
via bisect any path in any tree, and if we lookup things by path, we can
122
accumulate an id->path mapping as we go, which will tend to match what we
125
I plan to implement this asap, so please speak up now to alter/tweak the
126
design - and once we stabilise on this, I'll update the wiki page for
129
The rationale for all this is that we want fast operations for the
130
common case (diff/status/commit/merge on all files) and extremely fast
131
operations for the less common but still occurs a lot status/diff/commit
132
on specific files). Operations on specific files involve a scan for all
133
the children of a path, *in every involved tree*, which the current
134
format did not accommodate.
138
1) Fast end to end use for bzr's top 5 uses cases. (commmit/diff/status/merge/???)
139
2) fall back current object model as needed.
140
3) scale usably to the largest trees known today - say 50K entries. (mozilla
141
is an example of this)
145
Eventually reuse dirstate objects across locks IFF the dirstate file has not
146
been modified, but will require that we flush/ignore cached stat-hit data
147
because we won't want to restat all files on disk just because a lock was
148
acquired, yet we cannot trust the data after the previous lock was released.
150
Memory representation:
151
vector of all directories, and vector of the childen ?
153
root_entrie = (direntry for root, [parent_direntries_for_root]),
155
('', ['data for achild', 'data for bchild', 'data for cchild'])
156
('dir', ['achild', 'cchild', 'echild'])
158
- single bisect to find N subtrees from a path spec
159
- in-order for serialisation - this is 'dirblock' grouping.
160
- insertion of a file '/a' affects only the '/' child-vector, that is, to
161
insert 10K elements from scratch does not generates O(N^2) memoves of a
162
single vector, rather each individual, which tends to be limited to a
163
manageable number. Will scale badly on trees with 10K entries in a
164
single directory. compare with Inventory.InventoryDirectory which has
165
a dictionary for the children. No bisect capability, can only probe for
166
exact matches, or grab all elements and sort.
167
- What's the risk of error here? Once we have the base format being processed
168
we should have a net win regardless of optimality. So we are going to
169
go with what seems reasonable.
172
Maybe we should do a test profile of the core structure - 10K simulated
173
searches/lookups/etc?
175
Objects for each row?
176
The lifetime of Dirstate objects is current per lock, but see above for
177
possible extensions. The lifetime of a row from a dirstate is expected to be
178
very short in the optimistic case: which we are optimising for. For instance,
179
subtree status will determine from analysis of the disk data what rows need to
180
be examined at all, and will be able to determine from a single row whether
181
that file has altered or not, so we are aiming to process tens of thousands of
182
entries each second within the dirstate context, before exposing anything to
183
the larger codebase. This suggests we want the time for a single file
184
comparison to be < 0.1 milliseconds. That would give us 10000 paths per second
185
processed, and to scale to 100 thousand we'll another order of magnitude to do
186
that. Now, as the lifetime for all unchanged entries is the time to parse, stat
187
the file on disk, and then immediately discard, the overhead of object creation
188
becomes a significant cost.
190
Figures: Creating a tuple from 3 elements was profiled at 0.0625
191
microseconds, whereas creating a object which is subclassed from tuple was
192
0.500 microseconds, and creating an object with 3 elements and slots was 3
193
microseconds long. 0.1 milliseconds is 100 microseconds, and ideally we'll get
194
down to 10 microseconds for the total processing - having 33% of that be object
195
creation is a huge overhead. There is a potential cost in using tuples within
196
each row which is that the conditional code to do comparisons may be slower
197
than method invocation, but method invocation is known to be slow due to stack
198
frame creation, so avoiding methods in these tight inner loops in unfortunately
199
desirable. We can consider a pyrex version of this with objects in future if
208
from stat import S_IEXEC
226
# This is the Windows equivalent of ENOTDIR
227
# It is defined in pywin32.winerror, but we don't want a strong dependency for
228
# just an error code.
229
ERROR_PATH_NOT_FOUND = 3
230
ERROR_DIRECTORY = 267
233
if not getattr(struct, '_compile', None):
234
# Cannot pre-compile the dirstate pack_stat
235
def pack_stat(st, _encode=binascii.b2a_base64, _pack=struct.pack):
236
"""Convert stat values into a packed representation."""
237
return _encode(_pack('>LLLLLL', st.st_size, int(st.st_mtime),
238
int(st.st_ctime), st.st_dev, st.st_ino & 0xFFFFFFFF,
241
# compile the struct compiler we need, so as to only do it once
242
from _struct import Struct
243
_compiled_pack = Struct('>LLLLLL').pack
244
def pack_stat(st, _encode=binascii.b2a_base64, _pack=_compiled_pack):
245
"""Convert stat values into a packed representation."""
246
# jam 20060614 it isn't really worth removing more entries if we
247
# are going to leave it in packed form.
248
# With only st_mtime and st_mode filesize is 5.5M and read time is 275ms
249
# With all entries, filesize is 5.9M and read time is maybe 280ms
250
# well within the noise margin
252
# base64 encoding always adds a final newline, so strip it off
253
# The current version
254
return _encode(_pack(st.st_size, int(st.st_mtime), int(st.st_ctime),
255
st.st_dev, st.st_ino & 0xFFFFFFFF, st.st_mode))[:-1]
256
# This is 0.060s / 1.520s faster by not encoding as much information
257
# return _encode(_pack('>LL', int(st.st_mtime), st.st_mode))[:-1]
258
# This is not strictly faster than _encode(_pack())[:-1]
259
# return '%X.%X.%X.%X.%X.%X' % (
260
# st.st_size, int(st.st_mtime), int(st.st_ctime),
261
# st.st_dev, st.st_ino, st.st_mode)
262
# Similar to the _encode(_pack('>LL'))
263
# return '%X.%X' % (int(st.st_mtime), st.st_mode)
266
class SHA1Provider(object):
267
"""An interface for getting sha1s of a file."""
269
def sha1(self, abspath):
270
"""Return the sha1 of a file given its absolute path.
272
:param abspath: May be a filesystem encoded absolute path
275
raise NotImplementedError(self.sha1)
277
def stat_and_sha1(self, abspath):
278
"""Return the stat and sha1 of a file given its absolute path.
280
:param abspath: May be a filesystem encoded absolute path
283
Note: the stat should be the stat of the physical file
284
while the sha may be the sha of its canonical content.
286
raise NotImplementedError(self.stat_and_sha1)
289
class DefaultSHA1Provider(SHA1Provider):
290
"""A SHA1Provider that reads directly from the filesystem."""
292
def sha1(self, abspath):
293
"""Return the sha1 of a file given its absolute path."""
294
return osutils.sha_file_by_name(abspath)
296
def stat_and_sha1(self, abspath):
297
"""Return the stat and sha1 of a file given its absolute path."""
298
file_obj = file(abspath, 'rb')
300
statvalue = os.fstat(file_obj.fileno())
301
sha1 = osutils.sha_file(file_obj)
304
return statvalue, sha1
307
class DirState(object):
308
"""Record directory and metadata state for fast access.
310
A dirstate is a specialised data structure for managing local working
311
tree state information. Its not yet well defined whether it is platform
312
specific, and if it is how we detect/parameterize that.
314
Dirstates use the usual lock_write, lock_read and unlock mechanisms.
315
Unlike most bzr disk formats, DirStates must be locked for reading, using
316
lock_read. (This is an os file lock internally.) This is necessary
317
because the file can be rewritten in place.
319
DirStates must be explicitly written with save() to commit changes; just
320
unlocking them does not write the changes to disk.
323
_kind_to_minikind = {
329
'tree-reference': 't',
331
_minikind_to_kind = {
337
't': 'tree-reference',
339
_stat_to_minikind = {
344
_to_yesno = {True:'y', False: 'n'} # TODO profile the performance gain
345
# of using int conversion rather than a dict here. AND BLAME ANDREW IF
348
# TODO: jam 20070221 Figure out what to do if we have a record that exceeds
349
# the BISECT_PAGE_SIZE. For now, we just have to make it large enough
350
# that we are sure a single record will always fit.
351
BISECT_PAGE_SIZE = 4096
354
IN_MEMORY_UNMODIFIED = 1
355
IN_MEMORY_MODIFIED = 2
357
# A pack_stat (the x's) that is just noise and will never match the output
360
NULL_PARENT_DETAILS = ('a', '', 0, False, '')
362
HEADER_FORMAT_2 = '#bazaar dirstate flat format 2\n'
363
HEADER_FORMAT_3 = '#bazaar dirstate flat format 3\n'
365
def __init__(self, path, sha1_provider):
366
"""Create a DirState object.
368
:param path: The path at which the dirstate file on disk should live.
369
:param sha1_provider: an object meeting the SHA1Provider interface.
371
# _header_state and _dirblock_state represent the current state
372
# of the dirstate metadata and the per-row data respectiely.
373
# NOT_IN_MEMORY indicates that no data is in memory
374
# IN_MEMORY_UNMODIFIED indicates that what we have in memory
375
# is the same as is on disk
376
# IN_MEMORY_MODIFIED indicates that we have a modified version
377
# of what is on disk.
378
# In future we will add more granularity, for instance _dirblock_state
379
# will probably support partially-in-memory as a separate variable,
380
# allowing for partially-in-memory unmodified and partially-in-memory
382
self._header_state = DirState.NOT_IN_MEMORY
383
self._dirblock_state = DirState.NOT_IN_MEMORY
384
# If true, an error has been detected while updating the dirstate, and
385
# for safety we're not going to commit to disk.
386
self._changes_aborted = False
390
self._state_file = None
391
self._filename = path
392
self._lock_token = None
393
self._lock_state = None
394
self._id_index = None
395
# a map from packed_stat to sha's.
396
self._packed_stat_index = None
397
self._end_of_header = None
398
self._cutoff_time = None
399
self._split_path_cache = {}
400
self._bisect_page_size = DirState.BISECT_PAGE_SIZE
401
self._sha1_provider = sha1_provider
402
if 'hashcache' in debug.debug_flags:
403
self._sha1_file = self._sha1_file_and_mutter
405
self._sha1_file = self._sha1_provider.sha1
406
# These two attributes provide a simple cache for lookups into the
407
# dirstate in-memory vectors. By probing respectively for the last
408
# block, and for the next entry, we save nearly 2 bisections per path
410
self._last_block_index = None
411
self._last_entry_index = None
415
(self.__class__.__name__, self._filename)
417
def add(self, path, file_id, kind, stat, fingerprint):
418
"""Add a path to be tracked.
420
:param path: The path within the dirstate - '' is the root, 'foo' is the
421
path foo within the root, 'foo/bar' is the path bar within foo
423
:param file_id: The file id of the path being added.
424
:param kind: The kind of the path, as a string like 'file',
426
:param stat: The output of os.lstat for the path.
427
:param fingerprint: The sha value of the file's canonical form (i.e.
428
after any read filters have been applied),
429
or the target of a symlink,
430
or the referenced revision id for tree-references,
431
or '' for directories.
434
# find the block its in.
435
# find the location in the block.
436
# check its not there
438
#------- copied from inventory.ensure_normalized_name - keep synced.
439
# --- normalized_filename wants a unicode basename only, so get one.
440
dirname, basename = osutils.split(path)
441
# we dont import normalized_filename directly because we want to be
442
# able to change the implementation at runtime for tests.
443
norm_name, can_access = osutils.normalized_filename(basename)
444
if norm_name != basename:
448
raise errors.InvalidNormalization(path)
449
# you should never have files called . or ..; just add the directory
450
# in the parent, or according to the special treatment for the root
451
if basename == '.' or basename == '..':
452
raise errors.InvalidEntryName(path)
453
# now that we've normalised, we need the correct utf8 path and
454
# dirname and basename elements. This single encode and split should be
455
# faster than three separate encodes.
456
utf8path = (dirname + '/' + basename).strip('/').encode('utf8')
457
dirname, basename = osutils.split(utf8path)
458
# uses __class__ for speed; the check is needed for safety
459
if file_id.__class__ is not str:
460
raise AssertionError(
461
"must be a utf8 file_id not %s" % (type(file_id), ))
462
# Make sure the file_id does not exist in this tree
464
file_id_entry = self._get_entry(0, fileid_utf8=file_id, include_deleted=True)
465
if file_id_entry != (None, None):
466
if file_id_entry[1][0][0] == 'a':
467
if file_id_entry[0] != (dirname, basename, file_id):
468
# set the old name's current operation to rename
469
self.update_minimal(file_id_entry[0],
475
rename_from = file_id_entry[0][0:2]
477
path = osutils.pathjoin(file_id_entry[0][0], file_id_entry[0][1])
478
kind = DirState._minikind_to_kind[file_id_entry[1][0][0]]
479
info = '%s:%s' % (kind, path)
480
raise errors.DuplicateFileId(file_id, info)
481
first_key = (dirname, basename, '')
482
block_index, present = self._find_block_index_from_key(first_key)
484
# check the path is not in the tree
485
block = self._dirblocks[block_index][1]
486
entry_index, _ = self._find_entry_index(first_key, block)
487
while (entry_index < len(block) and
488
block[entry_index][0][0:2] == first_key[0:2]):
489
if block[entry_index][1][0][0] not in 'ar':
490
# this path is in the dirstate in the current tree.
491
raise Exception, "adding already added path!"
494
# The block where we want to put the file is not present. But it
495
# might be because the directory was empty, or not loaded yet. Look
496
# for a parent entry, if not found, raise NotVersionedError
497
parent_dir, parent_base = osutils.split(dirname)
498
parent_block_idx, parent_entry_idx, _, parent_present = \
499
self._get_block_entry_index(parent_dir, parent_base, 0)
500
if not parent_present:
501
raise errors.NotVersionedError(path, str(self))
502
self._ensure_block(parent_block_idx, parent_entry_idx, dirname)
503
block = self._dirblocks[block_index][1]
504
entry_key = (dirname, basename, file_id)
507
packed_stat = DirState.NULLSTAT
510
packed_stat = pack_stat(stat)
511
parent_info = self._empty_parent_info()
512
minikind = DirState._kind_to_minikind[kind]
513
if rename_from is not None:
515
old_path_utf8 = '%s/%s' % rename_from
517
old_path_utf8 = rename_from[1]
518
parent_info[0] = ('r', old_path_utf8, 0, False, '')
520
entry_data = entry_key, [
521
(minikind, fingerprint, size, False, packed_stat),
523
elif kind == 'directory':
524
entry_data = entry_key, [
525
(minikind, '', 0, False, packed_stat),
527
elif kind == 'symlink':
528
entry_data = entry_key, [
529
(minikind, fingerprint, size, False, packed_stat),
531
elif kind == 'tree-reference':
532
entry_data = entry_key, [
533
(minikind, fingerprint, 0, False, packed_stat),
536
raise errors.BzrError('unknown kind %r' % kind)
537
entry_index, present = self._find_entry_index(entry_key, block)
539
block.insert(entry_index, entry_data)
541
if block[entry_index][1][0][0] != 'a':
542
raise AssertionError(" %r(%r) already added" % (basename, file_id))
543
block[entry_index][1][0] = entry_data[1][0]
545
if kind == 'directory':
546
# insert a new dirblock
547
self._ensure_block(block_index, entry_index, utf8path)
548
self._dirblock_state = DirState.IN_MEMORY_MODIFIED
550
self._id_index.setdefault(entry_key[2], set()).add(entry_key)
552
def _bisect(self, paths):
553
"""Bisect through the disk structure for specific rows.
555
:param paths: A list of paths to find
556
:return: A dict mapping path => entries for found entries. Missing
557
entries will not be in the map.
558
The list is not sorted, and entries will be populated
559
based on when they were read.
561
self._requires_lock()
562
# We need the file pointer to be right after the initial header block
563
self._read_header_if_needed()
564
# If _dirblock_state was in memory, we should just return info from
565
# there, this function is only meant to handle when we want to read
567
if self._dirblock_state != DirState.NOT_IN_MEMORY:
568
raise AssertionError("bad dirblock state %r" % self._dirblock_state)
570
# The disk representation is generally info + '\0\n\0' at the end. But
571
# for bisecting, it is easier to treat this as '\0' + info + '\0\n'
572
# Because it means we can sync on the '\n'
573
state_file = self._state_file
574
file_size = os.fstat(state_file.fileno()).st_size
575
# We end up with 2 extra fields, we should have a trailing '\n' to
576
# ensure that we read the whole record, and we should have a precursur
577
# '' which ensures that we start after the previous '\n'
578
entry_field_count = self._fields_per_entry() + 1
580
low = self._end_of_header
581
high = file_size - 1 # Ignore the final '\0'
582
# Map from (dir, name) => entry
585
# Avoid infinite seeking
586
max_count = 30*len(paths)
588
# pending is a list of places to look.
589
# each entry is a tuple of low, high, dir_names
590
# low -> the first byte offset to read (inclusive)
591
# high -> the last byte offset (inclusive)
592
# dir_names -> The list of (dir, name) pairs that should be found in
593
# the [low, high] range
594
pending = [(low, high, paths)]
596
page_size = self._bisect_page_size
598
fields_to_entry = self._get_fields_to_entry()
601
low, high, cur_files = pending.pop()
603
if not cur_files or low >= high:
608
if count > max_count:
609
raise errors.BzrError('Too many seeks, most likely a bug.')
611
mid = max(low, (low+high-page_size)/2)
614
# limit the read size, so we don't end up reading data that we have
616
read_size = min(page_size, (high-mid)+1)
617
block = state_file.read(read_size)
620
entries = block.split('\n')
623
# We didn't find a '\n', so we cannot have found any records.
624
# So put this range back and try again. But we know we have to
625
# increase the page size, because a single read did not contain
626
# a record break (so records must be larger than page_size)
628
pending.append((low, high, cur_files))
631
# Check the first and last entries, in case they are partial, or if
632
# we don't care about the rest of this page
634
first_fields = entries[0].split('\0')
635
if len(first_fields) < entry_field_count:
636
# We didn't get the complete first entry
637
# so move start, and grab the next, which
638
# should be a full entry
639
start += len(entries[0])+1
640
first_fields = entries[1].split('\0')
643
if len(first_fields) <= 2:
644
# We didn't even get a filename here... what do we do?
645
# Try a large page size and repeat this query
647
pending.append((low, high, cur_files))
650
# Find what entries we are looking for, which occur before and
651
# after this first record.
654
first_path = first_fields[1] + '/' + first_fields[2]
656
first_path = first_fields[2]
657
first_loc = _bisect_path_left(cur_files, first_path)
659
# These exist before the current location
660
pre = cur_files[:first_loc]
661
# These occur after the current location, which may be in the
662
# data we read, or might be after the last entry
663
post = cur_files[first_loc:]
665
if post and len(first_fields) >= entry_field_count:
666
# We have files after the first entry
668
# Parse the last entry
669
last_entry_num = len(entries)-1
670
last_fields = entries[last_entry_num].split('\0')
671
if len(last_fields) < entry_field_count:
672
# The very last hunk was not complete,
673
# read the previous hunk
674
after = mid + len(block) - len(entries[-1])
676
last_fields = entries[last_entry_num].split('\0')
678
after = mid + len(block)
681
last_path = last_fields[1] + '/' + last_fields[2]
683
last_path = last_fields[2]
684
last_loc = _bisect_path_right(post, last_path)
686
middle_files = post[:last_loc]
687
post = post[last_loc:]
690
# We have files that should occur in this block
691
# (>= first, <= last)
692
# Either we will find them here, or we can mark them as
695
if middle_files[0] == first_path:
696
# We might need to go before this location
697
pre.append(first_path)
698
if middle_files[-1] == last_path:
699
post.insert(0, last_path)
701
# Find out what paths we have
702
paths = {first_path:[first_fields]}
703
# last_path might == first_path so we need to be
704
# careful if we should append rather than overwrite
705
if last_entry_num != first_entry_num:
706
paths.setdefault(last_path, []).append(last_fields)
707
for num in xrange(first_entry_num+1, last_entry_num):
708
# TODO: jam 20070223 We are already splitting here, so
709
# shouldn't we just split the whole thing rather
710
# than doing the split again in add_one_record?
711
fields = entries[num].split('\0')
713
path = fields[1] + '/' + fields[2]
716
paths.setdefault(path, []).append(fields)
718
for path in middle_files:
719
for fields in paths.get(path, []):
720
# offset by 1 because of the opening '\0'
721
# consider changing fields_to_entry to avoid the
723
entry = fields_to_entry(fields[1:])
724
found.setdefault(path, []).append(entry)
726
# Now we have split up everything into pre, middle, and post, and
727
# we have handled everything that fell in 'middle'.
728
# We add 'post' first, so that we prefer to seek towards the
729
# beginning, so that we will tend to go as early as we need, and
730
# then only seek forward after that.
732
pending.append((after, high, post))
734
pending.append((low, start-1, pre))
736
# Consider that we may want to return the directory entries in sorted
737
# order. For now, we just return them in whatever order we found them,
738
# and leave it up to the caller if they care if it is ordered or not.
741
def _bisect_dirblocks(self, dir_list):
742
"""Bisect through the disk structure to find entries in given dirs.
744
_bisect_dirblocks is meant to find the contents of directories, which
745
differs from _bisect, which only finds individual entries.
747
:param dir_list: A sorted list of directory names ['', 'dir', 'foo'].
748
:return: A map from dir => entries_for_dir
750
# TODO: jam 20070223 A lot of the bisecting logic could be shared
751
# between this and _bisect. It would require parameterizing the
752
# inner loop with a function, though. We should evaluate the
753
# performance difference.
754
self._requires_lock()
755
# We need the file pointer to be right after the initial header block
756
self._read_header_if_needed()
757
# If _dirblock_state was in memory, we should just return info from
758
# there, this function is only meant to handle when we want to read
760
if self._dirblock_state != DirState.NOT_IN_MEMORY:
761
raise AssertionError("bad dirblock state %r" % self._dirblock_state)
762
# The disk representation is generally info + '\0\n\0' at the end. But
763
# for bisecting, it is easier to treat this as '\0' + info + '\0\n'
764
# Because it means we can sync on the '\n'
765
state_file = self._state_file
766
file_size = os.fstat(state_file.fileno()).st_size
767
# We end up with 2 extra fields, we should have a trailing '\n' to
768
# ensure that we read the whole record, and we should have a precursur
769
# '' which ensures that we start after the previous '\n'
770
entry_field_count = self._fields_per_entry() + 1
772
low = self._end_of_header
773
high = file_size - 1 # Ignore the final '\0'
774
# Map from dir => entry
777
# Avoid infinite seeking
778
max_count = 30*len(dir_list)
780
# pending is a list of places to look.
781
# each entry is a tuple of low, high, dir_names
782
# low -> the first byte offset to read (inclusive)
783
# high -> the last byte offset (inclusive)
784
# dirs -> The list of directories that should be found in
785
# the [low, high] range
786
pending = [(low, high, dir_list)]
788
page_size = self._bisect_page_size
790
fields_to_entry = self._get_fields_to_entry()
793
low, high, cur_dirs = pending.pop()
795
if not cur_dirs or low >= high:
800
if count > max_count:
801
raise errors.BzrError('Too many seeks, most likely a bug.')
803
mid = max(low, (low+high-page_size)/2)
806
# limit the read size, so we don't end up reading data that we have
808
read_size = min(page_size, (high-mid)+1)
809
block = state_file.read(read_size)
812
entries = block.split('\n')
815
# We didn't find a '\n', so we cannot have found any records.
816
# So put this range back and try again. But we know we have to
817
# increase the page size, because a single read did not contain
818
# a record break (so records must be larger than page_size)
820
pending.append((low, high, cur_dirs))
823
# Check the first and last entries, in case they are partial, or if
824
# we don't care about the rest of this page
826
first_fields = entries[0].split('\0')
827
if len(first_fields) < entry_field_count:
828
# We didn't get the complete first entry
829
# so move start, and grab the next, which
830
# should be a full entry
831
start += len(entries[0])+1
832
first_fields = entries[1].split('\0')
835
if len(first_fields) <= 1:
836
# We didn't even get a dirname here... what do we do?
837
# Try a large page size and repeat this query
839
pending.append((low, high, cur_dirs))
842
# Find what entries we are looking for, which occur before and
843
# after this first record.
845
first_dir = first_fields[1]
846
first_loc = bisect.bisect_left(cur_dirs, first_dir)
848
# These exist before the current location
849
pre = cur_dirs[:first_loc]
850
# These occur after the current location, which may be in the
851
# data we read, or might be after the last entry
852
post = cur_dirs[first_loc:]
854
if post and len(first_fields) >= entry_field_count:
855
# We have records to look at after the first entry
857
# Parse the last entry
858
last_entry_num = len(entries)-1
859
last_fields = entries[last_entry_num].split('\0')
860
if len(last_fields) < entry_field_count:
861
# The very last hunk was not complete,
862
# read the previous hunk
863
after = mid + len(block) - len(entries[-1])
865
last_fields = entries[last_entry_num].split('\0')
867
after = mid + len(block)
869
last_dir = last_fields[1]
870
last_loc = bisect.bisect_right(post, last_dir)
872
middle_files = post[:last_loc]
873
post = post[last_loc:]
876
# We have files that should occur in this block
877
# (>= first, <= last)
878
# Either we will find them here, or we can mark them as
881
if middle_files[0] == first_dir:
882
# We might need to go before this location
883
pre.append(first_dir)
884
if middle_files[-1] == last_dir:
885
post.insert(0, last_dir)
887
# Find out what paths we have
888
paths = {first_dir:[first_fields]}
889
# last_dir might == first_dir so we need to be
890
# careful if we should append rather than overwrite
891
if last_entry_num != first_entry_num:
892
paths.setdefault(last_dir, []).append(last_fields)
893
for num in xrange(first_entry_num+1, last_entry_num):
894
# TODO: jam 20070223 We are already splitting here, so
895
# shouldn't we just split the whole thing rather
896
# than doing the split again in add_one_record?
897
fields = entries[num].split('\0')
898
paths.setdefault(fields[1], []).append(fields)
900
for cur_dir in middle_files:
901
for fields in paths.get(cur_dir, []):
902
# offset by 1 because of the opening '\0'
903
# consider changing fields_to_entry to avoid the
905
entry = fields_to_entry(fields[1:])
906
found.setdefault(cur_dir, []).append(entry)
908
# Now we have split up everything into pre, middle, and post, and
909
# we have handled everything that fell in 'middle'.
910
# We add 'post' first, so that we prefer to seek towards the
911
# beginning, so that we will tend to go as early as we need, and
912
# then only seek forward after that.
914
pending.append((after, high, post))
916
pending.append((low, start-1, pre))
920
def _bisect_recursive(self, paths):
921
"""Bisect for entries for all paths and their children.
923
This will use bisect to find all records for the supplied paths. It
924
will then continue to bisect for any records which are marked as
925
directories. (and renames?)
927
:param paths: A sorted list of (dir, name) pairs
928
eg: [('', 'a'), ('', 'f'), ('a/b', 'c')]
929
:return: A dictionary mapping (dir, name, file_id) => [tree_info]
931
# Map from (dir, name, file_id) => [tree_info]
934
found_dir_names = set()
936
# Directories that have been read
937
processed_dirs = set()
938
# Get the ball rolling with the first bisect for all entries.
939
newly_found = self._bisect(paths)
942
# Directories that need to be read
944
paths_to_search = set()
945
for entry_list in newly_found.itervalues():
946
for dir_name_id, trees_info in entry_list:
947
found[dir_name_id] = trees_info
948
found_dir_names.add(dir_name_id[:2])
950
for tree_info in trees_info:
951
minikind = tree_info[0]
954
# We already processed this one as a directory,
955
# we don't need to do the extra work again.
957
subdir, name, file_id = dir_name_id
958
path = osutils.pathjoin(subdir, name)
960
if path not in processed_dirs:
961
pending_dirs.add(path)
962
elif minikind == 'r':
963
# Rename, we need to directly search the target
964
# which is contained in the fingerprint column
965
dir_name = osutils.split(tree_info[1])
966
if dir_name[0] in pending_dirs:
967
# This entry will be found in the dir search
969
if dir_name not in found_dir_names:
970
paths_to_search.add(tree_info[1])
971
# Now we have a list of paths to look for directly, and
972
# directory blocks that need to be read.
973
# newly_found is mixing the keys between (dir, name) and path
974
# entries, but that is okay, because we only really care about the
976
newly_found = self._bisect(sorted(paths_to_search))
977
newly_found.update(self._bisect_dirblocks(sorted(pending_dirs)))
978
processed_dirs.update(pending_dirs)
981
def _discard_merge_parents(self):
982
"""Discard any parents trees beyond the first.
984
Note that if this fails the dirstate is corrupted.
986
After this function returns the dirstate contains 2 trees, neither of
989
self._read_header_if_needed()
990
parents = self.get_parent_ids()
993
# only require all dirblocks if we are doing a full-pass removal.
994
self._read_dirblocks_if_needed()
995
dead_patterns = set([('a', 'r'), ('a', 'a'), ('r', 'r'), ('r', 'a')])
996
def iter_entries_removable():
997
for block in self._dirblocks:
998
deleted_positions = []
999
for pos, entry in enumerate(block[1]):
1001
if (entry[1][0][0], entry[1][1][0]) in dead_patterns:
1002
deleted_positions.append(pos)
1003
if deleted_positions:
1004
if len(deleted_positions) == len(block[1]):
1007
for pos in reversed(deleted_positions):
1009
# if the first parent is a ghost:
1010
if parents[0] in self.get_ghosts():
1011
empty_parent = [DirState.NULL_PARENT_DETAILS]
1012
for entry in iter_entries_removable():
1013
entry[1][1:] = empty_parent
1015
for entry in iter_entries_removable():
1019
self._parents = [parents[0]]
1020
self._dirblock_state = DirState.IN_MEMORY_MODIFIED
1021
self._header_state = DirState.IN_MEMORY_MODIFIED
1023
def _empty_parent_info(self):
1024
return [DirState.NULL_PARENT_DETAILS] * (len(self._parents) -
1027
def _ensure_block(self, parent_block_index, parent_row_index, dirname):
1028
"""Ensure a block for dirname exists.
1030
This function exists to let callers which know that there is a
1031
directory dirname ensure that the block for it exists. This block can
1032
fail to exist because of demand loading, or because a directory had no
1033
children. In either case it is not an error. It is however an error to
1034
call this if there is no parent entry for the directory, and thus the
1035
function requires the coordinates of such an entry to be provided.
1037
The root row is special cased and can be indicated with a parent block
1040
:param parent_block_index: The index of the block in which dirname's row
1042
:param parent_row_index: The index in the parent block where the row
1044
:param dirname: The utf8 dirname to ensure there is a block for.
1045
:return: The index for the block.
1047
if dirname == '' and parent_row_index == 0 and parent_block_index == 0:
1048
# This is the signature of the root row, and the
1049
# contents-of-root row is always index 1
1051
# the basename of the directory must be the end of its full name.
1052
if not (parent_block_index == -1 and
1053
parent_block_index == -1 and dirname == ''):
1054
if not dirname.endswith(
1055
self._dirblocks[parent_block_index][1][parent_row_index][0][1]):
1056
raise AssertionError("bad dirname %r" % dirname)
1057
block_index, present = self._find_block_index_from_key((dirname, '', ''))
1059
## In future, when doing partial parsing, this should load and
1060
# populate the entire block.
1061
self._dirblocks.insert(block_index, (dirname, []))
1064
def _entries_to_current_state(self, new_entries):
1065
"""Load new_entries into self.dirblocks.
1067
Process new_entries into the current state object, making them the active
1068
state. The entries are grouped together by directory to form dirblocks.
1070
:param new_entries: A sorted list of entries. This function does not sort
1071
to prevent unneeded overhead when callers have a sorted list already.
1074
if new_entries[0][0][0:2] != ('', ''):
1075
raise AssertionError(
1076
"Missing root row %r" % (new_entries[0][0],))
1077
# The two blocks here are deliberate: the root block and the
1078
# contents-of-root block.
1079
self._dirblocks = [('', []), ('', [])]
1080
current_block = self._dirblocks[0][1]
1081
current_dirname = ''
1083
append_entry = current_block.append
1084
for entry in new_entries:
1085
if entry[0][0] != current_dirname:
1086
# new block - different dirname
1088
current_dirname = entry[0][0]
1089
self._dirblocks.append((current_dirname, current_block))
1090
append_entry = current_block.append
1091
# append the entry to the current block
1093
self._split_root_dirblock_into_contents()
1095
def _split_root_dirblock_into_contents(self):
1096
"""Split the root dirblocks into root and contents-of-root.
1098
After parsing by path, we end up with root entries and contents-of-root
1099
entries in the same block. This loop splits them out again.
1101
# The above loop leaves the "root block" entries mixed with the
1102
# "contents-of-root block". But we don't want an if check on
1103
# all entries, so instead we just fix it up here.
1104
if self._dirblocks[1] != ('', []):
1105
raise ValueError("bad dirblock start %r" % (self._dirblocks[1],))
1107
contents_of_root_block = []
1108
for entry in self._dirblocks[0][1]:
1109
if not entry[0][1]: # This is a root entry
1110
root_block.append(entry)
1112
contents_of_root_block.append(entry)
1113
self._dirblocks[0] = ('', root_block)
1114
self._dirblocks[1] = ('', contents_of_root_block)
1116
def _entries_for_path(self, path):
1117
"""Return a list with all the entries that match path for all ids."""
1118
dirname, basename = os.path.split(path)
1119
key = (dirname, basename, '')
1120
block_index, present = self._find_block_index_from_key(key)
1122
# the block which should contain path is absent.
1125
block = self._dirblocks[block_index][1]
1126
entry_index, _ = self._find_entry_index(key, block)
1127
# we may need to look at multiple entries at this path: walk while the specific_files match.
1128
while (entry_index < len(block) and
1129
block[entry_index][0][0:2] == key[0:2]):
1130
result.append(block[entry_index])
1134
def _entry_to_line(self, entry):
1135
"""Serialize entry to a NULL delimited line ready for _get_output_lines.
1137
:param entry: An entry_tuple as defined in the module docstring.
1139
entire_entry = list(entry[0])
1140
for tree_number, tree_data in enumerate(entry[1]):
1141
# (minikind, fingerprint, size, executable, tree_specific_string)
1142
entire_entry.extend(tree_data)
1143
# 3 for the key, 5 for the fields per tree.
1144
tree_offset = 3 + tree_number * 5
1146
entire_entry[tree_offset + 0] = tree_data[0]
1148
entire_entry[tree_offset + 2] = str(tree_data[2])
1150
entire_entry[tree_offset + 3] = DirState._to_yesno[tree_data[3]]
1151
return '\0'.join(entire_entry)
1153
def _fields_per_entry(self):
1154
"""How many null separated fields should be in each entry row.
1156
Each line now has an extra '\n' field which is not used
1157
so we just skip over it
1159
3 fields for the key
1160
+ number of fields per tree_data (5) * tree count
1163
tree_count = 1 + self._num_present_parents()
1164
return 3 + 5 * tree_count + 1
1166
def _find_block(self, key, add_if_missing=False):
1167
"""Return the block that key should be present in.
1169
:param key: A dirstate entry key.
1170
:return: The block tuple.
1172
block_index, present = self._find_block_index_from_key(key)
1174
if not add_if_missing:
1175
# check to see if key is versioned itself - we might want to
1176
# add it anyway, because dirs with no entries dont get a
1177
# dirblock at parse time.
1178
# This is an uncommon branch to take: most dirs have children,
1179
# and most code works with versioned paths.
1180
parent_base, parent_name = osutils.split(key[0])
1181
if not self._get_block_entry_index(parent_base, parent_name, 0)[3]:
1182
# some parent path has not been added - its an error to add
1184
raise errors.NotVersionedError(key[0:2], str(self))
1185
self._dirblocks.insert(block_index, (key[0], []))
1186
return self._dirblocks[block_index]
1188
def _find_block_index_from_key(self, key):
1189
"""Find the dirblock index for a key.
1191
:return: The block index, True if the block for the key is present.
1193
if key[0:2] == ('', ''):
1196
if (self._last_block_index is not None and
1197
self._dirblocks[self._last_block_index][0] == key[0]):
1198
return self._last_block_index, True
1201
block_index = bisect_dirblock(self._dirblocks, key[0], 1,
1202
cache=self._split_path_cache)
1203
# _right returns one-past-where-key is so we have to subtract
1204
# one to use it. we use _right here because there are two
1205
# '' blocks - the root, and the contents of root
1206
# we always have a minimum of 2 in self._dirblocks: root and
1207
# root-contents, and for '', we get 2 back, so this is
1208
# simple and correct:
1209
present = (block_index < len(self._dirblocks) and
1210
self._dirblocks[block_index][0] == key[0])
1211
self._last_block_index = block_index
1212
# Reset the entry index cache to the beginning of the block.
1213
self._last_entry_index = -1
1214
return block_index, present
1216
def _find_entry_index(self, key, block):
1217
"""Find the entry index for a key in a block.
1219
:return: The entry index, True if the entry for the key is present.
1221
len_block = len(block)
1223
if self._last_entry_index is not None:
1225
entry_index = self._last_entry_index + 1
1226
# A hit is when the key is after the last slot, and before or
1227
# equal to the next slot.
1228
if ((entry_index > 0 and block[entry_index - 1][0] < key) and
1229
key <= block[entry_index][0]):
1230
self._last_entry_index = entry_index
1231
present = (block[entry_index][0] == key)
1232
return entry_index, present
1235
entry_index = bisect.bisect_left(block, (key, []))
1236
present = (entry_index < len_block and
1237
block[entry_index][0] == key)
1238
self._last_entry_index = entry_index
1239
return entry_index, present
1242
def from_tree(tree, dir_state_filename, sha1_provider=None):
1243
"""Create a dirstate from a bzr Tree.
1245
:param tree: The tree which should provide parent information and
1247
:param sha1_provider: an object meeting the SHA1Provider interface.
1248
If None, a DefaultSHA1Provider is used.
1249
:return: a DirState object which is currently locked for writing.
1250
(it was locked by DirState.initialize)
1252
result = DirState.initialize(dir_state_filename,
1253
sha1_provider=sha1_provider)
1257
parent_ids = tree.get_parent_ids()
1258
num_parents = len(parent_ids)
1260
for parent_id in parent_ids:
1261
parent_tree = tree.branch.repository.revision_tree(parent_id)
1262
parent_trees.append((parent_id, parent_tree))
1263
parent_tree.lock_read()
1264
result.set_parent_trees(parent_trees, [])
1265
result.set_state_from_inventory(tree.inventory)
1267
for revid, parent_tree in parent_trees:
1268
parent_tree.unlock()
1271
# The caller won't have a chance to unlock this, so make sure we
1277
def update_by_delta(self, delta):
1278
"""Apply an inventory delta to the dirstate for tree 0
1280
:param delta: An inventory delta. See Inventory.apply_delta for
1283
self._read_dirblocks_if_needed()
1286
for old_path, new_path, file_id, inv_entry in sorted(delta, reverse=True):
1287
if (file_id in insertions) or (file_id in removals):
1288
raise AssertionError("repeated file id in delta %r" % (file_id,))
1289
if old_path is not None:
1290
old_path = old_path.encode('utf-8')
1291
removals[file_id] = old_path
1292
if new_path is not None:
1293
new_path = new_path.encode('utf-8')
1294
dirname, basename = osutils.split(new_path)
1295
key = (dirname, basename, file_id)
1296
minikind = DirState._kind_to_minikind[inv_entry.kind]
1298
fingerprint = inv_entry.reference_revision
1301
insertions[file_id] = (key, minikind, inv_entry.executable,
1302
fingerprint, new_path)
1303
# Transform moves into delete+add pairs
1304
if None not in (old_path, new_path):
1305
for child in self._iter_child_entries(0, old_path):
1306
if child[0][2] in insertions or child[0][2] in removals:
1308
child_dirname = child[0][0]
1309
child_basename = child[0][1]
1310
minikind = child[1][0][0]
1311
fingerprint = child[1][0][4]
1312
executable = child[1][0][3]
1313
old_child_path = osutils.pathjoin(child[0][0],
1315
removals[child[0][2]] = old_child_path
1316
child_suffix = child_dirname[len(old_path):]
1317
new_child_dirname = (new_path + child_suffix)
1318
key = (new_child_dirname, child_basename, child[0][2])
1319
new_child_path = os.path.join(new_child_dirname,
1321
insertions[child[0][2]] = (key, minikind, executable,
1322
fingerprint, new_child_path)
1323
self._apply_removals(removals.values())
1324
self._apply_insertions(insertions.values())
1326
def _apply_removals(self, removals):
1327
for path in sorted(removals, reverse=True):
1328
dirname, basename = osutils.split(path)
1329
block_i, entry_i, d_present, f_present = \
1330
self._get_block_entry_index(dirname, basename, 0)
1331
entry = self._dirblocks[block_i][1][entry_i]
1332
self._make_absent(entry)
1333
# See if we have a malformed delta: deleting a directory must not
1334
# leave crud behind. This increases the number of bisects needed
1335
# substantially, but deletion or renames of large numbers of paths
1336
# is rare enough it shouldn't be an issue (famous last words?) RBC
1338
block_i, entry_i, d_present, f_present = \
1339
self._get_block_entry_index(path, '', 0)
1341
# The dir block is still present in the dirstate; this could
1342
# be due to it being in a parent tree, or a corrupt delta.
1343
for child_entry in self._dirblocks[block_i][1]:
1344
if child_entry[1][0][0] not in ('r', 'a'):
1345
raise errors.InconsistentDelta(path, entry[0][2],
1346
"The file id was deleted but its children were "
1349
def _apply_insertions(self, adds):
1350
for key, minikind, executable, fingerprint, path_utf8 in sorted(adds):
1351
self.update_minimal(key, minikind, executable, fingerprint,
1352
path_utf8=path_utf8)
1354
def update_basis_by_delta(self, delta, new_revid):
1355
"""Update the parents of this tree after a commit.
1357
This gives the tree one parent, with revision id new_revid. The
1358
inventory delta is applied to the current basis tree to generate the
1359
inventory for the parent new_revid, and all other parent trees are
1362
Note that an exception during the operation of this method will leave
1363
the dirstate in a corrupt state where it should not be saved.
1365
Finally, we expect all changes to be synchronising the basis tree with
1368
:param new_revid: The new revision id for the trees parent.
1369
:param delta: An inventory delta (see apply_inventory_delta) describing
1370
the changes from the current left most parent revision to new_revid.
1372
self._read_dirblocks_if_needed()
1373
self._discard_merge_parents()
1374
if self._ghosts != []:
1375
raise NotImplementedError(self.update_basis_by_delta)
1376
if len(self._parents) == 0:
1377
# setup a blank tree, the most simple way.
1378
empty_parent = DirState.NULL_PARENT_DETAILS
1379
for entry in self._iter_entries():
1380
entry[1].append(empty_parent)
1381
self._parents.append(new_revid)
1383
self._parents[0] = new_revid
1385
delta = sorted(delta, reverse=True)
1389
# The paths this function accepts are unicode and must be encoded as we
1391
encode = cache_utf8.encode
1392
inv_to_entry = self._inv_entry_to_details
1393
# delta is now (deletes, changes), (adds) in reverse lexographical
1395
# deletes in reverse lexographic order are safe to process in situ.
1396
# renames are not, as a rename from any path could go to a path
1397
# lexographically lower, so we transform renames into delete, add pairs,
1398
# expanding them recursively as needed.
1399
# At the same time, to reduce interface friction we convert the input
1400
# inventory entries to dirstate.
1401
root_only = ('', '')
1402
for old_path, new_path, file_id, inv_entry in delta:
1403
if old_path is None:
1404
adds.append((None, encode(new_path), file_id,
1405
inv_to_entry(inv_entry), True))
1406
elif new_path is None:
1407
deletes.append((encode(old_path), None, file_id, None, True))
1408
elif (old_path, new_path) != root_only:
1410
# Because renames must preserve their children we must have
1411
# processed all relocations and removes before hand. The sort
1412
# order ensures we've examined the child paths, but we also
1413
# have to execute the removals, or the split to an add/delete
1414
# pair will result in the deleted item being reinserted, or
1415
# renamed items being reinserted twice - and possibly at the
1416
# wrong place. Splitting into a delete/add pair also simplifies
1417
# the handling of entries with ('f', ...), ('r' ...) because
1418
# the target of the 'r' is old_path here, and we add that to
1419
# deletes, meaning that the add handler does not need to check
1420
# for 'r' items on every pass.
1421
self._update_basis_apply_deletes(deletes)
1423
new_path_utf8 = encode(new_path)
1424
# Split into an add/delete pair recursively.
1425
adds.append((None, new_path_utf8, file_id,
1426
inv_to_entry(inv_entry), False))
1427
# Expunge deletes that we've seen so that deleted/renamed
1428
# children of a rename directory are handled correctly.
1429
new_deletes = reversed(list(self._iter_child_entries(1,
1431
# Remove the current contents of the tree at orig_path, and
1432
# reinsert at the correct new path.
1433
for entry in new_deletes:
1435
source_path = entry[0][0] + '/' + entry[0][1]
1437
source_path = entry[0][1]
1439
target_path = new_path_utf8 + source_path[len(old_path):]
1442
raise AssertionError("cannot rename directory to"
1444
target_path = source_path[len(old_path) + 1:]
1445
adds.append((None, target_path, entry[0][2], entry[1][1], False))
1447
(source_path, target_path, entry[0][2], None, False))
1449
(encode(old_path), new_path, file_id, None, False))
1451
# changes to just the root should not require remove/insertion
1453
changes.append((encode(old_path), encode(new_path), file_id,
1454
inv_to_entry(inv_entry)))
1456
# Finish expunging deletes/first half of renames.
1457
self._update_basis_apply_deletes(deletes)
1458
# Reinstate second half of renames and new paths.
1459
self._update_basis_apply_adds(adds)
1460
# Apply in-situ changes.
1461
self._update_basis_apply_changes(changes)
1463
self._dirblock_state = DirState.IN_MEMORY_MODIFIED
1464
self._header_state = DirState.IN_MEMORY_MODIFIED
1465
self._id_index = None
1468
def _update_basis_apply_adds(self, adds):
1469
"""Apply a sequence of adds to tree 1 during update_basis_by_delta.
1471
They may be adds, or renames that have been split into add/delete
1474
:param adds: A sequence of adds. Each add is a tuple:
1475
(None, new_path_utf8, file_id, (entry_details), real_add). real_add
1476
is False when the add is the second half of a remove-and-reinsert
1477
pair created to handle renames and deletes.
1479
# Adds are accumulated partly from renames, so can be in any input
1482
# adds is now in lexographic order, which places all parents before
1483
# their children, so we can process it linearly.
1485
for old_path, new_path, file_id, new_details, real_add in adds:
1486
# the entry for this file_id must be in tree 0.
1487
entry = self._get_entry(0, file_id, new_path)
1488
if entry[0] is None or entry[0][2] != file_id:
1489
self._changes_aborted = True
1490
raise errors.InconsistentDelta(new_path, file_id,
1491
'working tree does not contain new entry')
1492
if real_add and entry[1][1][0] not in absent:
1493
self._changes_aborted = True
1494
raise errors.InconsistentDelta(new_path, file_id,
1495
'The entry was considered to be a genuinely new record,'
1496
' but there was already an old record for it.')
1497
# We don't need to update the target of an 'r' because the handling
1498
# of renames turns all 'r' situations into a delete at the original
1500
entry[1][1] = new_details
1502
def _update_basis_apply_changes(self, changes):
1503
"""Apply a sequence of changes to tree 1 during update_basis_by_delta.
1505
:param adds: A sequence of changes. Each change is a tuple:
1506
(path_utf8, path_utf8, file_id, (entry_details))
1509
for old_path, new_path, file_id, new_details in changes:
1510
# the entry for this file_id must be in tree 0.
1511
entry = self._get_entry(0, file_id, new_path)
1512
if entry[0] is None or entry[0][2] != file_id:
1513
self._changes_aborted = True
1514
raise errors.InconsistentDelta(new_path, file_id,
1515
'working tree does not contain new entry')
1516
if (entry[1][0][0] in absent or
1517
entry[1][1][0] in absent):
1518
self._changes_aborted = True
1519
raise errors.InconsistentDelta(new_path, file_id,
1520
'changed considered absent')
1521
entry[1][1] = new_details
1523
def _update_basis_apply_deletes(self, deletes):
1524
"""Apply a sequence of deletes to tree 1 during update_basis_by_delta.
1526
They may be deletes, or renames that have been split into add/delete
1529
:param deletes: A sequence of deletes. Each delete is a tuple:
1530
(old_path_utf8, new_path_utf8, file_id, None, real_delete).
1531
real_delete is True when the desired outcome is an actual deletion
1532
rather than the rename handling logic temporarily deleting a path
1533
during the replacement of a parent.
1535
null = DirState.NULL_PARENT_DETAILS
1536
for old_path, new_path, file_id, _, real_delete in deletes:
1537
if real_delete != (new_path is None):
1538
raise AssertionError("bad delete delta")
1539
# the entry for this file_id must be in tree 1.
1540
dirname, basename = osutils.split(old_path)
1541
block_index, entry_index, dir_present, file_present = \
1542
self._get_block_entry_index(dirname, basename, 1)
1543
if not file_present:
1544
self._changes_aborted = True
1545
raise errors.InconsistentDelta(old_path, file_id,
1546
'basis tree does not contain removed entry')
1547
entry = self._dirblocks[block_index][1][entry_index]
1548
if entry[0][2] != file_id:
1549
self._changes_aborted = True
1550
raise errors.InconsistentDelta(old_path, file_id,
1551
'mismatched file_id in tree 1')
1553
if entry[1][0][0] != 'a':
1554
self._changes_aborted = True
1555
raise errors.InconsistentDelta(old_path, file_id,
1556
'This was marked as a real delete, but the WT state'
1557
' claims that it still exists and is versioned.')
1558
del self._dirblocks[block_index][1][entry_index]
1560
if entry[1][0][0] == 'a':
1561
self._changes_aborted = True
1562
raise errors.InconsistentDelta(old_path, file_id,
1563
'The entry was considered a rename, but the source path'
1564
' is marked as absent.')
1565
# For whatever reason, we were asked to rename an entry
1566
# that was originally marked as deleted. This could be
1567
# because we are renaming the parent directory, and the WT
1568
# current state has the file marked as deleted.
1569
elif entry[1][0][0] == 'r':
1570
# implement the rename
1571
del self._dirblocks[block_index][1][entry_index]
1573
# it is being resurrected here, so blank it out temporarily.
1574
self._dirblocks[block_index][1][entry_index][1][1] = null
1576
def _observed_sha1(self, entry, sha1, stat_value,
1577
_stat_to_minikind=_stat_to_minikind, _pack_stat=pack_stat):
1578
"""Note the sha1 of a file.
1580
:param entry: The entry the sha1 is for.
1581
:param sha1: The observed sha1.
1582
:param stat_value: The os.lstat for the file.
1585
minikind = _stat_to_minikind[stat_value.st_mode & 0170000]
1589
packed_stat = _pack_stat(stat_value)
1591
if self._cutoff_time is None:
1592
self._sha_cutoff_time()
1593
if (stat_value.st_mtime < self._cutoff_time
1594
and stat_value.st_ctime < self._cutoff_time):
1595
entry[1][0] = ('f', sha1, entry[1][0][2], entry[1][0][3],
1597
self._dirblock_state = DirState.IN_MEMORY_MODIFIED
1599
def _sha_cutoff_time(self):
1600
"""Return cutoff time.
1602
Files modified more recently than this time are at risk of being
1603
undetectably modified and so can't be cached.
1605
# Cache the cutoff time as long as we hold a lock.
1606
# time.time() isn't super expensive (approx 3.38us), but
1607
# when you call it 50,000 times it adds up.
1608
# For comparison, os.lstat() costs 7.2us if it is hot.
1609
self._cutoff_time = int(time.time()) - 3
1610
return self._cutoff_time
1612
def _lstat(self, abspath, entry):
1613
"""Return the os.lstat value for this path."""
1614
return os.lstat(abspath)
1616
def _sha1_file_and_mutter(self, abspath):
1617
# when -Dhashcache is turned on, this is monkey-patched in to log
1619
trace.mutter("dirstate sha1 " + abspath)
1620
return self._sha1_provider.sha1(abspath)
1622
def _is_executable(self, mode, old_executable):
1623
"""Is this file executable?"""
1624
return bool(S_IEXEC & mode)
1626
def _is_executable_win32(self, mode, old_executable):
1627
"""On win32 the executable bit is stored in the dirstate."""
1628
return old_executable
1630
if sys.platform == 'win32':
1631
_is_executable = _is_executable_win32
1633
def _read_link(self, abspath, old_link):
1634
"""Read the target of a symlink"""
1635
# TODO: jam 200700301 On Win32, this could just return the value
1636
# already in memory. However, this really needs to be done at a
1637
# higher level, because there either won't be anything on disk,
1638
# or the thing on disk will be a file.
1639
fs_encoding = osutils._fs_enc
1640
if isinstance(abspath, unicode):
1641
# abspath is defined as the path to pass to lstat. readlink is
1642
# buggy in python < 2.6 (it doesn't encode unicode path into FS
1643
# encoding), so we need to encode ourselves knowing that unicode
1644
# paths are produced by UnicodeDirReader on purpose.
1645
abspath = abspath.encode(fs_encoding)
1646
target = os.readlink(abspath)
1647
if fs_encoding not in ('UTF-8', 'US-ASCII', 'ANSI_X3.4-1968'):
1648
# Change encoding if needed
1649
target = target.decode(fs_encoding).encode('UTF-8')
1652
def get_ghosts(self):
1653
"""Return a list of the parent tree revision ids that are ghosts."""
1654
self._read_header_if_needed()
1657
def get_lines(self):
1658
"""Serialise the entire dirstate to a sequence of lines."""
1659
if (self._header_state == DirState.IN_MEMORY_UNMODIFIED and
1660
self._dirblock_state == DirState.IN_MEMORY_UNMODIFIED):
1661
# read whats on disk.
1662
self._state_file.seek(0)
1663
return self._state_file.readlines()
1665
lines.append(self._get_parents_line(self.get_parent_ids()))
1666
lines.append(self._get_ghosts_line(self._ghosts))
1667
# append the root line which is special cased
1668
lines.extend(map(self._entry_to_line, self._iter_entries()))
1669
return self._get_output_lines(lines)
1671
def _get_ghosts_line(self, ghost_ids):
1672
"""Create a line for the state file for ghost information."""
1673
return '\0'.join([str(len(ghost_ids))] + ghost_ids)
1675
def _get_parents_line(self, parent_ids):
1676
"""Create a line for the state file for parents information."""
1677
return '\0'.join([str(len(parent_ids))] + parent_ids)
1679
def _get_fields_to_entry(self):
1680
"""Get a function which converts entry fields into a entry record.
1682
This handles size and executable, as well as parent records.
1684
:return: A function which takes a list of fields, and returns an
1685
appropriate record for storing in memory.
1687
# This is intentionally unrolled for performance
1688
num_present_parents = self._num_present_parents()
1689
if num_present_parents == 0:
1690
def fields_to_entry_0_parents(fields, _int=int):
1691
path_name_file_id_key = (fields[0], fields[1], fields[2])
1692
return (path_name_file_id_key, [
1694
fields[3], # minikind
1695
fields[4], # fingerprint
1696
_int(fields[5]), # size
1697
fields[6] == 'y', # executable
1698
fields[7], # packed_stat or revision_id
1700
return fields_to_entry_0_parents
1701
elif num_present_parents == 1:
1702
def fields_to_entry_1_parent(fields, _int=int):
1703
path_name_file_id_key = (fields[0], fields[1], fields[2])
1704
return (path_name_file_id_key, [
1706
fields[3], # minikind
1707
fields[4], # fingerprint
1708
_int(fields[5]), # size
1709
fields[6] == 'y', # executable
1710
fields[7], # packed_stat or revision_id
1713
fields[8], # minikind
1714
fields[9], # fingerprint
1715
_int(fields[10]), # size
1716
fields[11] == 'y', # executable
1717
fields[12], # packed_stat or revision_id
1720
return fields_to_entry_1_parent
1721
elif num_present_parents == 2:
1722
def fields_to_entry_2_parents(fields, _int=int):
1723
path_name_file_id_key = (fields[0], fields[1], fields[2])
1724
return (path_name_file_id_key, [
1726
fields[3], # minikind
1727
fields[4], # fingerprint
1728
_int(fields[5]), # size
1729
fields[6] == 'y', # executable
1730
fields[7], # packed_stat or revision_id
1733
fields[8], # minikind
1734
fields[9], # fingerprint
1735
_int(fields[10]), # size
1736
fields[11] == 'y', # executable
1737
fields[12], # packed_stat or revision_id
1740
fields[13], # minikind
1741
fields[14], # fingerprint
1742
_int(fields[15]), # size
1743
fields[16] == 'y', # executable
1744
fields[17], # packed_stat or revision_id
1747
return fields_to_entry_2_parents
1749
def fields_to_entry_n_parents(fields, _int=int):
1750
path_name_file_id_key = (fields[0], fields[1], fields[2])
1751
trees = [(fields[cur], # minikind
1752
fields[cur+1], # fingerprint
1753
_int(fields[cur+2]), # size
1754
fields[cur+3] == 'y', # executable
1755
fields[cur+4], # stat or revision_id
1756
) for cur in xrange(3, len(fields)-1, 5)]
1757
return path_name_file_id_key, trees
1758
return fields_to_entry_n_parents
1760
def get_parent_ids(self):
1761
"""Return a list of the parent tree ids for the directory state."""
1762
self._read_header_if_needed()
1763
return list(self._parents)
1765
def _get_block_entry_index(self, dirname, basename, tree_index):
1766
"""Get the coordinates for a path in the state structure.
1768
:param dirname: The utf8 dirname to lookup.
1769
:param basename: The utf8 basename to lookup.
1770
:param tree_index: The index of the tree for which this lookup should
1772
:return: A tuple describing where the path is located, or should be
1773
inserted. The tuple contains four fields: the block index, the row
1774
index, the directory is present (boolean), the entire path is
1775
present (boolean). There is no guarantee that either
1776
coordinate is currently reachable unless the found field for it is
1777
True. For instance, a directory not present in the searched tree
1778
may be returned with a value one greater than the current highest
1779
block offset. The directory present field will always be True when
1780
the path present field is True. The directory present field does
1781
NOT indicate that the directory is present in the searched tree,
1782
rather it indicates that there are at least some files in some
1785
self._read_dirblocks_if_needed()
1786
key = dirname, basename, ''
1787
block_index, present = self._find_block_index_from_key(key)
1789
# no such directory - return the dir index and 0 for the row.
1790
return block_index, 0, False, False
1791
block = self._dirblocks[block_index][1] # access the entries only
1792
entry_index, present = self._find_entry_index(key, block)
1793
# linear search through entries at this path to find the one
1795
while entry_index < len(block) and block[entry_index][0][1] == basename:
1796
if block[entry_index][1][tree_index][0] not in 'ar':
1797
# neither absent or relocated
1798
return block_index, entry_index, True, True
1800
return block_index, entry_index, True, False
1802
def _get_entry(self, tree_index, fileid_utf8=None, path_utf8=None, include_deleted=False):
1803
"""Get the dirstate entry for path in tree tree_index.
1805
If either file_id or path is supplied, it is used as the key to lookup.
1806
If both are supplied, the fastest lookup is used, and an error is
1807
raised if they do not both point at the same row.
1809
:param tree_index: The index of the tree we wish to locate this path
1810
in. If the path is present in that tree, the entry containing its
1811
details is returned, otherwise (None, None) is returned
1812
0 is the working tree, higher indexes are successive parent
1814
:param fileid_utf8: A utf8 file_id to look up.
1815
:param path_utf8: An utf8 path to be looked up.
1816
:param include_deleted: If True, and performing a lookup via
1817
fileid_utf8 rather than path_utf8, return an entry for deleted
1819
:return: The dirstate entry tuple for path, or (None, None)
1821
self._read_dirblocks_if_needed()
1822
if path_utf8 is not None:
1823
if type(path_utf8) is not str:
1824
raise AssertionError('path_utf8 is not a str: %s %s'
1825
% (type(path_utf8), path_utf8))
1826
# path lookups are faster
1827
dirname, basename = osutils.split(path_utf8)
1828
block_index, entry_index, dir_present, file_present = \
1829
self._get_block_entry_index(dirname, basename, tree_index)
1830
if not file_present:
1832
entry = self._dirblocks[block_index][1][entry_index]
1833
if not (entry[0][2] and entry[1][tree_index][0] not in ('a', 'r')):
1834
raise AssertionError('unversioned entry?')
1836
if entry[0][2] != fileid_utf8:
1837
self._changes_aborted = True
1838
raise errors.BzrError('integrity error ? : mismatching'
1839
' tree_index, file_id and path')
1842
possible_keys = self._get_id_index().get(fileid_utf8, None)
1843
if not possible_keys:
1845
for key in possible_keys:
1846
block_index, present = \
1847
self._find_block_index_from_key(key)
1848
# strange, probably indicates an out of date
1849
# id index - for now, allow this.
1852
# WARNING: DO not change this code to use _get_block_entry_index
1853
# as that function is not suitable: it does not use the key
1854
# to lookup, and thus the wrong coordinates are returned.
1855
block = self._dirblocks[block_index][1]
1856
entry_index, present = self._find_entry_index(key, block)
1858
entry = self._dirblocks[block_index][1][entry_index]
1859
if entry[1][tree_index][0] in 'fdlt':
1860
# this is the result we are looking for: the
1861
# real home of this file_id in this tree.
1863
if entry[1][tree_index][0] == 'a':
1864
# there is no home for this entry in this tree
1868
if entry[1][tree_index][0] != 'r':
1869
raise AssertionError(
1870
"entry %r has invalid minikind %r for tree %r" \
1872
entry[1][tree_index][0],
1874
real_path = entry[1][tree_index][1]
1875
return self._get_entry(tree_index, fileid_utf8=fileid_utf8,
1876
path_utf8=real_path)
1880
def initialize(cls, path, sha1_provider=None):
1881
"""Create a new dirstate on path.
1883
The new dirstate will be an empty tree - that is it has no parents,
1884
and only a root node - which has id ROOT_ID.
1886
:param path: The name of the file for the dirstate.
1887
:param sha1_provider: an object meeting the SHA1Provider interface.
1888
If None, a DefaultSHA1Provider is used.
1889
:return: A write-locked DirState object.
1891
# This constructs a new DirState object on a path, sets the _state_file
1892
# to a new empty file for that path. It then calls _set_data() with our
1893
# stock empty dirstate information - a root with ROOT_ID, no children,
1894
# and no parents. Finally it calls save() to ensure that this data will
1896
if sha1_provider is None:
1897
sha1_provider = DefaultSHA1Provider()
1898
result = cls(path, sha1_provider)
1899
# root dir and root dir contents with no children.
1900
empty_tree_dirblocks = [('', []), ('', [])]
1901
# a new root directory, with a NULLSTAT.
1902
empty_tree_dirblocks[0][1].append(
1903
(('', '', inventory.ROOT_ID), [
1904
('d', '', 0, False, DirState.NULLSTAT),
1908
result._set_data([], empty_tree_dirblocks)
1916
def _inv_entry_to_details(inv_entry):
1917
"""Convert an inventory entry (from a revision tree) to state details.
1919
:param inv_entry: An inventory entry whose sha1 and link targets can be
1920
relied upon, and which has a revision set.
1921
:return: A details tuple - the details for a single tree at a path +
1924
kind = inv_entry.kind
1925
minikind = DirState._kind_to_minikind[kind]
1926
tree_data = inv_entry.revision
1927
if kind == 'directory':
1931
elif kind == 'symlink':
1932
if inv_entry.symlink_target is None:
1935
fingerprint = inv_entry.symlink_target.encode('utf8')
1938
elif kind == 'file':
1939
fingerprint = inv_entry.text_sha1 or ''
1940
size = inv_entry.text_size or 0
1941
executable = inv_entry.executable
1942
elif kind == 'tree-reference':
1943
fingerprint = inv_entry.reference_revision or ''
1947
raise Exception("can't pack %s" % inv_entry)
1948
return (minikind, fingerprint, size, executable, tree_data)
1950
def _iter_child_entries(self, tree_index, path_utf8):
1951
"""Iterate over all the entries that are children of path_utf.
1953
This only returns entries that are present (not in 'a', 'r') in
1954
tree_index. tree_index data is not refreshed, so if tree 0 is used,
1955
results may differ from that obtained if paths were statted to
1956
determine what ones were directories.
1958
Asking for the children of a non-directory will return an empty
1962
next_pending_dirs = [path_utf8]
1964
while next_pending_dirs:
1965
pending_dirs = next_pending_dirs
1966
next_pending_dirs = []
1967
for path in pending_dirs:
1968
block_index, present = self._find_block_index_from_key(
1970
if block_index == 0:
1972
if len(self._dirblocks) == 1:
1973
# asked for the children of the root with no other
1977
# children of a non-directory asked for.
1979
block = self._dirblocks[block_index]
1980
for entry in block[1]:
1981
kind = entry[1][tree_index][0]
1982
if kind not in absent:
1986
path = entry[0][0] + '/' + entry[0][1]
1989
next_pending_dirs.append(path)
1991
def _iter_entries(self):
1992
"""Iterate over all the entries in the dirstate.
1994
Each yelt item is an entry in the standard format described in the
1995
docstring of bzrlib.dirstate.
1997
self._read_dirblocks_if_needed()
1998
for directory in self._dirblocks:
1999
for entry in directory[1]:
2002
def _get_id_index(self):
2003
"""Get an id index of self._dirblocks."""
2004
if self._id_index is None:
2006
for key, tree_details in self._iter_entries():
2007
id_index.setdefault(key[2], set()).add(key)
2008
self._id_index = id_index
2009
return self._id_index
2011
def _get_output_lines(self, lines):
2012
"""Format lines for final output.
2014
:param lines: A sequence of lines containing the parents list and the
2017
output_lines = [DirState.HEADER_FORMAT_3]
2018
lines.append('') # a final newline
2019
inventory_text = '\0\n\0'.join(lines)
2020
output_lines.append('crc32: %s\n' % (zlib.crc32(inventory_text),))
2021
# -3, 1 for num parents, 1 for ghosts, 1 for final newline
2022
num_entries = len(lines)-3
2023
output_lines.append('num_entries: %s\n' % (num_entries,))
2024
output_lines.append(inventory_text)
2027
def _make_deleted_row(self, fileid_utf8, parents):
2028
"""Return a deleted row for fileid_utf8."""
2029
return ('/', 'RECYCLED.BIN', 'file', fileid_utf8, 0, DirState.NULLSTAT,
2032
def _num_present_parents(self):
2033
"""The number of parent entries in each record row."""
2034
return len(self._parents) - len(self._ghosts)
2037
def on_file(path, sha1_provider=None):
2038
"""Construct a DirState on the file at path "path".
2040
:param path: The path at which the dirstate file on disk should live.
2041
:param sha1_provider: an object meeting the SHA1Provider interface.
2042
If None, a DefaultSHA1Provider is used.
2043
:return: An unlocked DirState object, associated with the given path.
2045
if sha1_provider is None:
2046
sha1_provider = DefaultSHA1Provider()
2047
result = DirState(path, sha1_provider)
2050
def _read_dirblocks_if_needed(self):
2051
"""Read in all the dirblocks from the file if they are not in memory.
2053
This populates self._dirblocks, and sets self._dirblock_state to
2054
IN_MEMORY_UNMODIFIED. It is not currently ready for incremental block
2057
self._read_header_if_needed()
2058
if self._dirblock_state == DirState.NOT_IN_MEMORY:
2059
_read_dirblocks(self)
2061
def _read_header(self):
2062
"""This reads in the metadata header, and the parent ids.
2064
After reading in, the file should be positioned at the null
2065
just before the start of the first record in the file.
2067
:return: (expected crc checksum, number of entries, parent list)
2069
self._read_prelude()
2070
parent_line = self._state_file.readline()
2071
info = parent_line.split('\0')
2072
num_parents = int(info[0])
2073
self._parents = info[1:-1]
2074
ghost_line = self._state_file.readline()
2075
info = ghost_line.split('\0')
2076
num_ghosts = int(info[1])
2077
self._ghosts = info[2:-1]
2078
self._header_state = DirState.IN_MEMORY_UNMODIFIED
2079
self._end_of_header = self._state_file.tell()
2081
def _read_header_if_needed(self):
2082
"""Read the header of the dirstate file if needed."""
2083
# inline this as it will be called a lot
2084
if not self._lock_token:
2085
raise errors.ObjectNotLocked(self)
2086
if self._header_state == DirState.NOT_IN_MEMORY:
2089
def _read_prelude(self):
2090
"""Read in the prelude header of the dirstate file.
2092
This only reads in the stuff that is not connected to the crc
2093
checksum. The position will be correct to read in the rest of
2094
the file and check the checksum after this point.
2095
The next entry in the file should be the number of parents,
2096
and their ids. Followed by a newline.
2098
header = self._state_file.readline()
2099
if header != DirState.HEADER_FORMAT_3:
2100
raise errors.BzrError(
2101
'invalid header line: %r' % (header,))
2102
crc_line = self._state_file.readline()
2103
if not crc_line.startswith('crc32: '):
2104
raise errors.BzrError('missing crc32 checksum: %r' % crc_line)
2105
self.crc_expected = int(crc_line[len('crc32: '):-1])
2106
num_entries_line = self._state_file.readline()
2107
if not num_entries_line.startswith('num_entries: '):
2108
raise errors.BzrError('missing num_entries line')
2109
self._num_entries = int(num_entries_line[len('num_entries: '):-1])
2111
def sha1_from_stat(self, path, stat_result, _pack_stat=pack_stat):
2112
"""Find a sha1 given a stat lookup."""
2113
return self._get_packed_stat_index().get(_pack_stat(stat_result), None)
2115
def _get_packed_stat_index(self):
2116
"""Get a packed_stat index of self._dirblocks."""
2117
if self._packed_stat_index is None:
2119
for key, tree_details in self._iter_entries():
2120
if tree_details[0][0] == 'f':
2121
index[tree_details[0][4]] = tree_details[0][1]
2122
self._packed_stat_index = index
2123
return self._packed_stat_index
2126
"""Save any pending changes created during this session.
2128
We reuse the existing file, because that prevents race conditions with
2129
file creation, and use oslocks on it to prevent concurrent modification
2130
and reads - because dirstate's incremental data aggregation is not
2131
compatible with reading a modified file, and replacing a file in use by
2132
another process is impossible on Windows.
2134
A dirstate in read only mode should be smart enough though to validate
2135
that the file has not changed, and otherwise discard its cache and
2136
start over, to allow for fine grained read lock duration, so 'status'
2137
wont block 'commit' - for example.
2139
if self._changes_aborted:
2140
# Should this be a warning? For now, I'm expecting that places that
2141
# mark it inconsistent will warn, making a warning here redundant.
2142
trace.mutter('Not saving DirState because '
2143
'_changes_aborted is set.')
2145
if (self._header_state == DirState.IN_MEMORY_MODIFIED or
2146
self._dirblock_state == DirState.IN_MEMORY_MODIFIED):
2148
grabbed_write_lock = False
2149
if self._lock_state != 'w':
2150
grabbed_write_lock, new_lock = self._lock_token.temporary_write_lock()
2151
# Switch over to the new lock, as the old one may be closed.
2152
# TODO: jam 20070315 We should validate the disk file has
2153
# not changed contents. Since temporary_write_lock may
2154
# not be an atomic operation.
2155
self._lock_token = new_lock
2156
self._state_file = new_lock.f
2157
if not grabbed_write_lock:
2158
# We couldn't grab a write lock, so we switch back to a read one
2161
self._state_file.seek(0)
2162
self._state_file.writelines(self.get_lines())
2163
self._state_file.truncate()
2164
self._state_file.flush()
2165
self._header_state = DirState.IN_MEMORY_UNMODIFIED
2166
self._dirblock_state = DirState.IN_MEMORY_UNMODIFIED
2168
if grabbed_write_lock:
2169
self._lock_token = self._lock_token.restore_read_lock()
2170
self._state_file = self._lock_token.f
2171
# TODO: jam 20070315 We should validate the disk file has
2172
# not changed contents. Since restore_read_lock may
2173
# not be an atomic operation.
2175
def _set_data(self, parent_ids, dirblocks):
2176
"""Set the full dirstate data in memory.
2178
This is an internal function used to completely replace the objects
2179
in memory state. It puts the dirstate into state 'full-dirty'.
2181
:param parent_ids: A list of parent tree revision ids.
2182
:param dirblocks: A list containing one tuple for each directory in the
2183
tree. Each tuple contains the directory path and a list of entries
2184
found in that directory.
2186
# our memory copy is now authoritative.
2187
self._dirblocks = dirblocks
2188
self._header_state = DirState.IN_MEMORY_MODIFIED
2189
self._dirblock_state = DirState.IN_MEMORY_MODIFIED
2190
self._parents = list(parent_ids)
2191
self._id_index = None
2192
self._packed_stat_index = None
2194
def set_path_id(self, path, new_id):
2195
"""Change the id of path to new_id in the current working tree.
2197
:param path: The path inside the tree to set - '' is the root, 'foo'
2198
is the path foo in the root.
2199
:param new_id: The new id to assign to the path. This must be a utf8
2200
file id (not unicode, and not None).
2202
self._read_dirblocks_if_needed()
2204
# TODO: logic not written
2205
raise NotImplementedError(self.set_path_id)
2206
# TODO: check new id is unique
2207
entry = self._get_entry(0, path_utf8=path)
2208
if entry[0][2] == new_id:
2209
# Nothing to change.
2211
# mark the old path absent, and insert a new root path
2212
self._make_absent(entry)
2213
self.update_minimal(('', '', new_id), 'd',
2214
path_utf8='', packed_stat=entry[1][0][4])
2215
self._dirblock_state = DirState.IN_MEMORY_MODIFIED
2216
if self._id_index is not None:
2217
self._id_index.setdefault(new_id, set()).add(entry[0])
2219
def set_parent_trees(self, trees, ghosts):
2220
"""Set the parent trees for the dirstate.
2222
:param trees: A list of revision_id, tree tuples. tree must be provided
2223
even if the revision_id refers to a ghost: supply an empty tree in
2225
:param ghosts: A list of the revision_ids that are ghosts at the time
2228
# TODO: generate a list of parent indexes to preserve to save
2229
# processing specific parent trees. In the common case one tree will
2230
# be preserved - the left most parent.
2231
# TODO: if the parent tree is a dirstate, we might want to walk them
2232
# all by path in parallel for 'optimal' common-case performance.
2233
# generate new root row.
2234
self._read_dirblocks_if_needed()
2235
# TODO future sketch: Examine the existing parents to generate a change
2236
# map and then walk the new parent trees only, mapping them into the
2237
# dirstate. Walk the dirstate at the same time to remove unreferenced
2240
# sketch: loop over all entries in the dirstate, cherry picking
2241
# entries from the parent trees, if they are not ghost trees.
2242
# after we finish walking the dirstate, all entries not in the dirstate
2243
# are deletes, so we want to append them to the end as per the design
2244
# discussions. So do a set difference on ids with the parents to
2245
# get deletes, and add them to the end.
2246
# During the update process we need to answer the following questions:
2247
# - find other keys containing a fileid in order to create cross-path
2248
# links. We dont't trivially use the inventory from other trees
2249
# because this leads to either double touching, or to accessing
2251
# - find other keys containing a path
2252
# We accumulate each entry via this dictionary, including the root
2255
# we could do parallel iterators, but because file id data may be
2256
# scattered throughout, we dont save on index overhead: we have to look
2257
# at everything anyway. We can probably save cycles by reusing parent
2258
# data and doing an incremental update when adding an additional
2259
# parent, but for now the common cases are adding a new parent (merge),
2260
# and replacing completely (commit), and commit is more common: so
2261
# optimise merge later.
2263
# ---- start generation of full tree mapping data
2264
# what trees should we use?
2265
parent_trees = [tree for rev_id, tree in trees if rev_id not in ghosts]
2266
# how many trees do we end up with
2267
parent_count = len(parent_trees)
2269
# one: the current tree
2270
for entry in self._iter_entries():
2271
# skip entries not in the current tree
2272
if entry[1][0][0] in 'ar': # absent, relocated
2274
by_path[entry[0]] = [entry[1][0]] + \
2275
[DirState.NULL_PARENT_DETAILS] * parent_count
2276
id_index[entry[0][2]] = set([entry[0]])
2278
# now the parent trees:
2279
for tree_index, tree in enumerate(parent_trees):
2280
# the index is off by one, adjust it.
2281
tree_index = tree_index + 1
2282
# when we add new locations for a fileid we need these ranges for
2283
# any fileid in this tree as we set the by_path[id] to:
2284
# already_processed_tree_details + new_details + new_location_suffix
2285
# the suffix is from tree_index+1:parent_count+1.
2286
new_location_suffix = [DirState.NULL_PARENT_DETAILS] * (parent_count - tree_index)
2287
# now stitch in all the entries from this tree
2288
for path, entry in tree.inventory.iter_entries_by_dir():
2289
# here we process each trees details for each item in the tree.
2290
# we first update any existing entries for the id at other paths,
2291
# then we either create or update the entry for the id at the
2292
# right path, and finally we add (if needed) a mapping from
2293
# file_id to this path. We do it in this order to allow us to
2294
# avoid checking all known paths for the id when generating a
2295
# new entry at this path: by adding the id->path mapping last,
2296
# all the mappings are valid and have correct relocation
2297
# records where needed.
2298
file_id = entry.file_id
2299
path_utf8 = path.encode('utf8')
2300
dirname, basename = osutils.split(path_utf8)
2301
new_entry_key = (dirname, basename, file_id)
2302
# tree index consistency: All other paths for this id in this tree
2303
# index must point to the correct path.
2304
for entry_key in id_index.setdefault(file_id, set()):
2305
# TODO:PROFILING: It might be faster to just update
2306
# rather than checking if we need to, and then overwrite
2307
# the one we are located at.
2308
if entry_key != new_entry_key:
2309
# this file id is at a different path in one of the
2310
# other trees, so put absent pointers there
2311
# This is the vertical axis in the matrix, all pointing
2313
by_path[entry_key][tree_index] = ('r', path_utf8, 0, False, '')
2314
# by path consistency: Insert into an existing path record (trivial), or
2315
# add a new one with relocation pointers for the other tree indexes.
2316
if new_entry_key in id_index[file_id]:
2317
# there is already an entry where this data belongs, just insert it.
2318
by_path[new_entry_key][tree_index] = \
2319
self._inv_entry_to_details(entry)
2321
# add relocated entries to the horizontal axis - this row
2322
# mapping from path,id. We need to look up the correct path
2323
# for the indexes from 0 to tree_index -1
2325
for lookup_index in xrange(tree_index):
2326
# boundary case: this is the first occurence of file_id
2327
# so there are no id_indexs, possibly take this out of
2329
if not len(id_index[file_id]):
2330
new_details.append(DirState.NULL_PARENT_DETAILS)
2332
# grab any one entry, use it to find the right path.
2333
# TODO: optimise this to reduce memory use in highly
2334
# fragmented situations by reusing the relocation
2336
a_key = iter(id_index[file_id]).next()
2337
if by_path[a_key][lookup_index][0] in ('r', 'a'):
2338
# its a pointer or missing statement, use it as is.
2339
new_details.append(by_path[a_key][lookup_index])
2341
# we have the right key, make a pointer to it.
2342
real_path = ('/'.join(a_key[0:2])).strip('/')
2343
new_details.append(('r', real_path, 0, False, ''))
2344
new_details.append(self._inv_entry_to_details(entry))
2345
new_details.extend(new_location_suffix)
2346
by_path[new_entry_key] = new_details
2347
id_index[file_id].add(new_entry_key)
2348
# --- end generation of full tree mappings
2350
# sort and output all the entries
2351
new_entries = self._sort_entries(by_path.items())
2352
self._entries_to_current_state(new_entries)
2353
self._parents = [rev_id for rev_id, tree in trees]
2354
self._ghosts = list(ghosts)
2355
self._header_state = DirState.IN_MEMORY_MODIFIED
2356
self._dirblock_state = DirState.IN_MEMORY_MODIFIED
2357
self._id_index = id_index
2359
def _sort_entries(self, entry_list):
2360
"""Given a list of entries, sort them into the right order.
2362
This is done when constructing a new dirstate from trees - normally we
2363
try to keep everything in sorted blocks all the time, but sometimes
2364
it's easier to sort after the fact.
2367
# sort by: directory parts, file name, file id
2368
return entry[0][0].split('/'), entry[0][1], entry[0][2]
2369
return sorted(entry_list, key=_key)
2371
def set_state_from_inventory(self, new_inv):
2372
"""Set new_inv as the current state.
2374
This API is called by tree transform, and will usually occur with
2375
existing parent trees.
2377
:param new_inv: The inventory object to set current state from.
2379
if 'evil' in debug.debug_flags:
2380
trace.mutter_callsite(1,
2381
"set_state_from_inventory called; please mutate the tree instead")
2382
self._read_dirblocks_if_needed()
2384
# Two iterators: current data and new data, both in dirblock order.
2385
# We zip them together, which tells about entries that are new in the
2386
# inventory, or removed in the inventory, or present in both and
2389
# You might think we could just synthesize a new dirstate directly
2390
# since we're processing it in the right order. However, we need to
2391
# also consider there may be any number of parent trees and relocation
2392
# pointers, and we don't want to duplicate that here.
2393
new_iterator = new_inv.iter_entries_by_dir()
2394
# we will be modifying the dirstate, so we need a stable iterator. In
2395
# future we might write one, for now we just clone the state into a
2396
# list - which is a shallow copy.
2397
old_iterator = iter(list(self._iter_entries()))
2398
# both must have roots so this is safe:
2399
current_new = new_iterator.next()
2400
current_old = old_iterator.next()
2401
def advance(iterator):
2403
return iterator.next()
2404
except StopIteration:
2406
while current_new or current_old:
2407
# skip entries in old that are not really there
2408
if current_old and current_old[1][0][0] in 'ar':
2409
# relocated or absent
2410
current_old = advance(old_iterator)
2413
# convert new into dirblock style
2414
new_path_utf8 = current_new[0].encode('utf8')
2415
new_dirname, new_basename = osutils.split(new_path_utf8)
2416
new_id = current_new[1].file_id
2417
new_entry_key = (new_dirname, new_basename, new_id)
2418
current_new_minikind = \
2419
DirState._kind_to_minikind[current_new[1].kind]
2420
if current_new_minikind == 't':
2421
fingerprint = current_new[1].reference_revision or ''
2423
# We normally only insert or remove records, or update
2424
# them when it has significantly changed. Then we want to
2425
# erase its fingerprint. Unaffected records should
2426
# normally not be updated at all.
2429
# for safety disable variables
2430
new_path_utf8 = new_dirname = new_basename = new_id = \
2431
new_entry_key = None
2432
# 5 cases, we dont have a value that is strictly greater than everything, so
2433
# we make both end conditions explicit
2435
# old is finished: insert current_new into the state.
2436
self.update_minimal(new_entry_key, current_new_minikind,
2437
executable=current_new[1].executable,
2438
path_utf8=new_path_utf8, fingerprint=fingerprint)
2439
current_new = advance(new_iterator)
2440
elif not current_new:
2442
self._make_absent(current_old)
2443
current_old = advance(old_iterator)
2444
elif new_entry_key == current_old[0]:
2445
# same - common case
2446
# We're looking at the same path and id in both the dirstate
2447
# and inventory, so just need to update the fields in the
2448
# dirstate from the one in the inventory.
2449
# TODO: update the record if anything significant has changed.
2450
# the minimal required trigger is if the execute bit or cached
2452
if (current_old[1][0][3] != current_new[1].executable or
2453
current_old[1][0][0] != current_new_minikind):
2454
self.update_minimal(current_old[0], current_new_minikind,
2455
executable=current_new[1].executable,
2456
path_utf8=new_path_utf8, fingerprint=fingerprint)
2457
# both sides are dealt with, move on
2458
current_old = advance(old_iterator)
2459
current_new = advance(new_iterator)
2460
elif (cmp_by_dirs(new_dirname, current_old[0][0]) < 0
2461
or (new_dirname == current_old[0][0]
2462
and new_entry_key[1:] < current_old[0][1:])):
2464
# add a entry for this and advance new
2465
self.update_minimal(new_entry_key, current_new_minikind,
2466
executable=current_new[1].executable,
2467
path_utf8=new_path_utf8, fingerprint=fingerprint)
2468
current_new = advance(new_iterator)
2470
# we've advanced past the place where the old key would be,
2471
# without seeing it in the new list. so it must be gone.
2472
self._make_absent(current_old)
2473
current_old = advance(old_iterator)
2474
self._dirblock_state = DirState.IN_MEMORY_MODIFIED
2475
self._id_index = None
2476
self._packed_stat_index = None
2478
def _make_absent(self, current_old):
2479
"""Mark current_old - an entry - as absent for tree 0.
2481
:return: True if this was the last details entry for the entry key:
2482
that is, if the underlying block has had the entry removed, thus
2483
shrinking in length.
2485
# build up paths that this id will be left at after the change is made,
2486
# so we can update their cross references in tree 0
2487
all_remaining_keys = set()
2488
# Dont check the working tree, because it's going.
2489
for details in current_old[1][1:]:
2490
if details[0] not in 'ar': # absent, relocated
2491
all_remaining_keys.add(current_old[0])
2492
elif details[0] == 'r': # relocated
2493
# record the key for the real path.
2494
all_remaining_keys.add(tuple(osutils.split(details[1])) + (current_old[0][2],))
2495
# absent rows are not present at any path.
2496
last_reference = current_old[0] not in all_remaining_keys
2498
# the current row consists entire of the current item (being marked
2499
# absent), and relocated or absent entries for the other trees:
2500
# Remove it, its meaningless.
2501
block = self._find_block(current_old[0])
2502
entry_index, present = self._find_entry_index(current_old[0], block[1])
2504
raise AssertionError('could not find entry for %s' % (current_old,))
2505
block[1].pop(entry_index)
2506
# if we have an id_index in use, remove this key from it for this id.
2507
if self._id_index is not None:
2508
self._id_index[current_old[0][2]].remove(current_old[0])
2509
# update all remaining keys for this id to record it as absent. The
2510
# existing details may either be the record we are marking as deleted
2511
# (if there were other trees with the id present at this path), or may
2513
for update_key in all_remaining_keys:
2514
update_block_index, present = \
2515
self._find_block_index_from_key(update_key)
2517
raise AssertionError('could not find block for %s' % (update_key,))
2518
update_entry_index, present = \
2519
self._find_entry_index(update_key, self._dirblocks[update_block_index][1])
2521
raise AssertionError('could not find entry for %s' % (update_key,))
2522
update_tree_details = self._dirblocks[update_block_index][1][update_entry_index][1]
2523
# it must not be absent at the moment
2524
if update_tree_details[0][0] == 'a': # absent
2525
raise AssertionError('bad row %r' % (update_tree_details,))
2526
update_tree_details[0] = DirState.NULL_PARENT_DETAILS
2527
self._dirblock_state = DirState.IN_MEMORY_MODIFIED
2528
return last_reference
2530
def update_minimal(self, key, minikind, executable=False, fingerprint='',
2531
packed_stat=None, size=0, path_utf8=None):
2532
"""Update an entry to the state in tree 0.
2534
This will either create a new entry at 'key' or update an existing one.
2535
It also makes sure that any other records which might mention this are
2538
:param key: (dir, name, file_id) for the new entry
2539
:param minikind: The type for the entry ('f' == 'file', 'd' ==
2541
:param executable: Should the executable bit be set?
2542
:param fingerprint: Simple fingerprint for new entry: canonical-form
2543
sha1 for files, referenced revision id for subtrees, etc.
2544
:param packed_stat: Packed stat value for new entry.
2545
:param size: Size information for new entry
2546
:param path_utf8: key[0] + '/' + key[1], just passed in to avoid doing
2549
If packed_stat and fingerprint are not given, they're invalidated in
2552
block = self._find_block(key)[1]
2553
if packed_stat is None:
2554
packed_stat = DirState.NULLSTAT
2555
# XXX: Some callers pass '' as the packed_stat, and it seems to be
2556
# sometimes present in the dirstate - this seems oddly inconsistent.
2558
entry_index, present = self._find_entry_index(key, block)
2559
new_details = (minikind, fingerprint, size, executable, packed_stat)
2560
id_index = self._get_id_index()
2562
# new entry, synthesis cross reference here,
2563
existing_keys = id_index.setdefault(key[2], set())
2564
if not existing_keys:
2565
# not currently in the state, simplest case
2566
new_entry = key, [new_details] + self._empty_parent_info()
2568
# present at one or more existing other paths.
2569
# grab one of them and use it to generate parent
2570
# relocation/absent entries.
2571
new_entry = key, [new_details]
2572
for other_key in existing_keys:
2573
# change the record at other to be a pointer to this new
2574
# record. The loop looks similar to the change to
2575
# relocations when updating an existing record but its not:
2576
# the test for existing kinds is different: this can be
2577
# factored out to a helper though.
2578
other_block_index, present = self._find_block_index_from_key(other_key)
2580
raise AssertionError('could not find block for %s' % (other_key,))
2581
other_entry_index, present = self._find_entry_index(other_key,
2582
self._dirblocks[other_block_index][1])
2584
raise AssertionError('could not find entry for %s' % (other_key,))
2585
if path_utf8 is None:
2586
raise AssertionError('no path')
2587
self._dirblocks[other_block_index][1][other_entry_index][1][0] = \
2588
('r', path_utf8, 0, False, '')
2590
num_present_parents = self._num_present_parents()
2591
for lookup_index in xrange(1, num_present_parents + 1):
2592
# grab any one entry, use it to find the right path.
2593
# TODO: optimise this to reduce memory use in highly
2594
# fragmented situations by reusing the relocation
2596
update_block_index, present = \
2597
self._find_block_index_from_key(other_key)
2599
raise AssertionError('could not find block for %s' % (other_key,))
2600
update_entry_index, present = \
2601
self._find_entry_index(other_key, self._dirblocks[update_block_index][1])
2603
raise AssertionError('could not find entry for %s' % (other_key,))
2604
update_details = self._dirblocks[update_block_index][1][update_entry_index][1][lookup_index]
2605
if update_details[0] in 'ar': # relocated, absent
2606
# its a pointer or absent in lookup_index's tree, use
2608
new_entry[1].append(update_details)
2610
# we have the right key, make a pointer to it.
2611
pointer_path = osutils.pathjoin(*other_key[0:2])
2612
new_entry[1].append(('r', pointer_path, 0, False, ''))
2613
block.insert(entry_index, new_entry)
2614
existing_keys.add(key)
2616
# Does the new state matter?
2617
block[entry_index][1][0] = new_details
2618
# parents cannot be affected by what we do.
2619
# other occurences of this id can be found
2620
# from the id index.
2622
# tree index consistency: All other paths for this id in this tree
2623
# index must point to the correct path. We have to loop here because
2624
# we may have passed entries in the state with this file id already
2625
# that were absent - where parent entries are - and they need to be
2626
# converted to relocated.
2627
if path_utf8 is None:
2628
raise AssertionError('no path')
2629
for entry_key in id_index.setdefault(key[2], set()):
2630
# TODO:PROFILING: It might be faster to just update
2631
# rather than checking if we need to, and then overwrite
2632
# the one we are located at.
2633
if entry_key != key:
2634
# this file id is at a different path in one of the
2635
# other trees, so put absent pointers there
2636
# This is the vertical axis in the matrix, all pointing
2638
block_index, present = self._find_block_index_from_key(entry_key)
2640
raise AssertionError('not present: %r', entry_key)
2641
entry_index, present = self._find_entry_index(entry_key, self._dirblocks[block_index][1])
2643
raise AssertionError('not present: %r', entry_key)
2644
self._dirblocks[block_index][1][entry_index][1][0] = \
2645
('r', path_utf8, 0, False, '')
2646
# add a containing dirblock if needed.
2647
if new_details[0] == 'd':
2648
subdir_key = (osutils.pathjoin(*key[0:2]), '', '')
2649
block_index, present = self._find_block_index_from_key(subdir_key)
2651
self._dirblocks.insert(block_index, (subdir_key[0], []))
2653
self._dirblock_state = DirState.IN_MEMORY_MODIFIED
2655
def _validate(self):
2656
"""Check that invariants on the dirblock are correct.
2658
This can be useful in debugging; it shouldn't be necessary in
2661
This must be called with a lock held.
2663
# NOTE: This must always raise AssertionError not just assert,
2664
# otherwise it may not behave properly under python -O
2666
# TODO: All entries must have some content that's not 'a' or 'r',
2667
# otherwise it could just be removed.
2669
# TODO: All relocations must point directly to a real entry.
2671
# TODO: No repeated keys.
2674
from pprint import pformat
2675
self._read_dirblocks_if_needed()
2676
if len(self._dirblocks) > 0:
2677
if not self._dirblocks[0][0] == '':
2678
raise AssertionError(
2679
"dirblocks don't start with root block:\n" + \
2680
pformat(self._dirblocks))
2681
if len(self._dirblocks) > 1:
2682
if not self._dirblocks[1][0] == '':
2683
raise AssertionError(
2684
"dirblocks missing root directory:\n" + \
2685
pformat(self._dirblocks))
2686
# the dirblocks are sorted by their path components, name, and dir id
2687
dir_names = [d[0].split('/')
2688
for d in self._dirblocks[1:]]
2689
if dir_names != sorted(dir_names):
2690
raise AssertionError(
2691
"dir names are not in sorted order:\n" + \
2692
pformat(self._dirblocks) + \
2695
for dirblock in self._dirblocks:
2696
# within each dirblock, the entries are sorted by filename and
2698
for entry in dirblock[1]:
2699
if dirblock[0] != entry[0][0]:
2700
raise AssertionError(
2702
"doesn't match directory name in\n%r" %
2703
(entry, pformat(dirblock)))
2704
if dirblock[1] != sorted(dirblock[1]):
2705
raise AssertionError(
2706
"dirblock for %r is not sorted:\n%s" % \
2707
(dirblock[0], pformat(dirblock)))
2709
def check_valid_parent():
2710
"""Check that the current entry has a valid parent.
2712
This makes sure that the parent has a record,
2713
and that the parent isn't marked as "absent" in the
2714
current tree. (It is invalid to have a non-absent file in an absent
2717
if entry[0][0:2] == ('', ''):
2718
# There should be no parent for the root row
2720
parent_entry = self._get_entry(tree_index, path_utf8=entry[0][0])
2721
if parent_entry == (None, None):
2722
raise AssertionError(
2723
"no parent entry for: %s in tree %s"
2724
% (this_path, tree_index))
2725
if parent_entry[1][tree_index][0] != 'd':
2726
raise AssertionError(
2727
"Parent entry for %s is not marked as a valid"
2728
" directory. %s" % (this_path, parent_entry,))
2730
# For each file id, for each tree: either
2731
# the file id is not present at all; all rows with that id in the
2732
# key have it marked as 'absent'
2733
# OR the file id is present under exactly one name; any other entries
2734
# that mention that id point to the correct name.
2736
# We check this with a dict per tree pointing either to the present
2737
# name, or None if absent.
2738
tree_count = self._num_present_parents() + 1
2739
id_path_maps = [dict() for i in range(tree_count)]
2740
# Make sure that all renamed entries point to the correct location.
2741
for entry in self._iter_entries():
2742
file_id = entry[0][2]
2743
this_path = osutils.pathjoin(entry[0][0], entry[0][1])
2744
if len(entry[1]) != tree_count:
2745
raise AssertionError(
2746
"wrong number of entry details for row\n%s" \
2747
",\nexpected %d" % \
2748
(pformat(entry), tree_count))
2749
absent_positions = 0
2750
for tree_index, tree_state in enumerate(entry[1]):
2751
this_tree_map = id_path_maps[tree_index]
2752
minikind = tree_state[0]
2753
if minikind in 'ar':
2754
absent_positions += 1
2755
# have we seen this id before in this column?
2756
if file_id in this_tree_map:
2757
previous_path, previous_loc = this_tree_map[file_id]
2758
# any later mention of this file must be consistent with
2759
# what was said before
2761
if previous_path is not None:
2762
raise AssertionError(
2763
"file %s is absent in row %r but also present " \
2765
(file_id, entry, previous_path))
2766
elif minikind == 'r':
2767
target_location = tree_state[1]
2768
if previous_path != target_location:
2769
raise AssertionError(
2770
"file %s relocation in row %r but also at %r" \
2771
% (file_id, entry, previous_path))
2773
# a file, directory, etc - may have been previously
2774
# pointed to by a relocation, which must point here
2775
if previous_path != this_path:
2776
raise AssertionError(
2777
"entry %r inconsistent with previous path %r "
2779
(entry, previous_path, previous_loc))
2780
check_valid_parent()
2783
# absent; should not occur anywhere else
2784
this_tree_map[file_id] = None, this_path
2785
elif minikind == 'r':
2786
# relocation, must occur at expected location
2787
this_tree_map[file_id] = tree_state[1], this_path
2789
this_tree_map[file_id] = this_path, this_path
2790
check_valid_parent()
2791
if absent_positions == tree_count:
2792
raise AssertionError(
2793
"entry %r has no data for any tree." % (entry,))
2795
def _wipe_state(self):
2796
"""Forget all state information about the dirstate."""
2797
self._header_state = DirState.NOT_IN_MEMORY
2798
self._dirblock_state = DirState.NOT_IN_MEMORY
2799
self._changes_aborted = False
2802
self._dirblocks = []
2803
self._id_index = None
2804
self._packed_stat_index = None
2805
self._end_of_header = None
2806
self._cutoff_time = None
2807
self._split_path_cache = {}
2809
def lock_read(self):
2810
"""Acquire a read lock on the dirstate."""
2811
if self._lock_token is not None:
2812
raise errors.LockContention(self._lock_token)
2813
# TODO: jam 20070301 Rather than wiping completely, if the blocks are
2814
# already in memory, we could read just the header and check for
2815
# any modification. If not modified, we can just leave things
2817
self._lock_token = lock.ReadLock(self._filename)
2818
self._lock_state = 'r'
2819
self._state_file = self._lock_token.f
2822
def lock_write(self):
2823
"""Acquire a write lock on the dirstate."""
2824
if self._lock_token is not None:
2825
raise errors.LockContention(self._lock_token)
2826
# TODO: jam 20070301 Rather than wiping completely, if the blocks are
2827
# already in memory, we could read just the header and check for
2828
# any modification. If not modified, we can just leave things
2830
self._lock_token = lock.WriteLock(self._filename)
2831
self._lock_state = 'w'
2832
self._state_file = self._lock_token.f
2836
"""Drop any locks held on the dirstate."""
2837
if self._lock_token is None:
2838
raise errors.LockNotHeld(self)
2839
# TODO: jam 20070301 Rather than wiping completely, if the blocks are
2840
# already in memory, we could read just the header and check for
2841
# any modification. If not modified, we can just leave things
2843
self._state_file = None
2844
self._lock_state = None
2845
self._lock_token.unlock()
2846
self._lock_token = None
2847
self._split_path_cache = {}
2849
def _requires_lock(self):
2850
"""Check that a lock is currently held by someone on the dirstate."""
2851
if not self._lock_token:
2852
raise errors.ObjectNotLocked(self)
2855
def py_update_entry(state, entry, abspath, stat_value,
2856
_stat_to_minikind=DirState._stat_to_minikind,
2857
_pack_stat=pack_stat):
2858
"""Update the entry based on what is actually on disk.
2860
This function only calculates the sha if it needs to - if the entry is
2861
uncachable, or clearly different to the first parent's entry, no sha
2862
is calculated, and None is returned.
2864
:param state: The dirstate this entry is in.
2865
:param entry: This is the dirblock entry for the file in question.
2866
:param abspath: The path on disk for this file.
2867
:param stat_value: The stat value done on the path.
2868
:return: None, or The sha1 hexdigest of the file (40 bytes) or link
2869
target of a symlink.
2872
minikind = _stat_to_minikind[stat_value.st_mode & 0170000]
2876
packed_stat = _pack_stat(stat_value)
2877
(saved_minikind, saved_link_or_sha1, saved_file_size,
2878
saved_executable, saved_packed_stat) = entry[1][0]
2880
if minikind == 'd' and saved_minikind == 't':
2882
if (minikind == saved_minikind
2883
and packed_stat == saved_packed_stat):
2884
# The stat hasn't changed since we saved, so we can re-use the
2889
# size should also be in packed_stat
2890
if saved_file_size == stat_value.st_size:
2891
return saved_link_or_sha1
2893
# If we have gotten this far, that means that we need to actually
2894
# process this entry.
2897
executable = state._is_executable(stat_value.st_mode,
2899
if state._cutoff_time is None:
2900
state._sha_cutoff_time()
2901
if (stat_value.st_mtime < state._cutoff_time
2902
and stat_value.st_ctime < state._cutoff_time
2903
and len(entry[1]) > 1
2904
and entry[1][1][0] != 'a'):
2905
# Could check for size changes for further optimised
2906
# avoidance of sha1's. However the most prominent case of
2907
# over-shaing is during initial add, which this catches.
2908
# Besides, if content filtering happens, size and sha
2909
# are calculated at the same time, so checking just the size
2910
# gains nothing w.r.t. performance.
2911
link_or_sha1 = state._sha1_file(abspath)
2912
entry[1][0] = ('f', link_or_sha1, stat_value.st_size,
2913
executable, packed_stat)
2915
entry[1][0] = ('f', '', stat_value.st_size,
2916
executable, DirState.NULLSTAT)
2917
elif minikind == 'd':
2919
entry[1][0] = ('d', '', 0, False, packed_stat)
2920
if saved_minikind != 'd':
2921
# This changed from something into a directory. Make sure we
2922
# have a directory block for it. This doesn't happen very
2923
# often, so this doesn't have to be super fast.
2924
block_index, entry_index, dir_present, file_present = \
2925
state._get_block_entry_index(entry[0][0], entry[0][1], 0)
2926
state._ensure_block(block_index, entry_index,
2927
osutils.pathjoin(entry[0][0], entry[0][1]))
2928
elif minikind == 'l':
2929
link_or_sha1 = state._read_link(abspath, saved_link_or_sha1)
2930
if state._cutoff_time is None:
2931
state._sha_cutoff_time()
2932
if (stat_value.st_mtime < state._cutoff_time
2933
and stat_value.st_ctime < state._cutoff_time):
2934
entry[1][0] = ('l', link_or_sha1, stat_value.st_size,
2937
entry[1][0] = ('l', '', stat_value.st_size,
2938
False, DirState.NULLSTAT)
2939
state._dirblock_state = DirState.IN_MEMORY_MODIFIED
2941
update_entry = py_update_entry
2944
class ProcessEntryPython(object):
2946
__slots__ = ["old_dirname_to_file_id", "new_dirname_to_file_id", "uninteresting",
2947
"last_source_parent", "last_target_parent", "include_unchanged",
2948
"use_filesystem_for_exec", "utf8_decode", "searched_specific_files",
2949
"search_specific_files", "state", "source_index", "target_index",
2950
"want_unversioned", "tree"]
2952
def __init__(self, include_unchanged, use_filesystem_for_exec,
2953
search_specific_files, state, source_index, target_index,
2954
want_unversioned, tree):
2955
self.old_dirname_to_file_id = {}
2956
self.new_dirname_to_file_id = {}
2957
# Just a sentry, so that _process_entry can say that this
2958
# record is handled, but isn't interesting to process (unchanged)
2959
self.uninteresting = object()
2960
# Using a list so that we can access the values and change them in
2961
# nested scope. Each one is [path, file_id, entry]
2962
self.last_source_parent = [None, None]
2963
self.last_target_parent = [None, None]
2964
self.include_unchanged = include_unchanged
2965
self.use_filesystem_for_exec = use_filesystem_for_exec
2966
self.utf8_decode = cache_utf8._utf8_decode
2967
# for all search_indexs in each path at or under each element of
2968
# search_specific_files, if the detail is relocated: add the id, and add the
2969
# relocated path as one to search if its not searched already. If the
2970
# detail is not relocated, add the id.
2971
self.searched_specific_files = set()
2972
self.search_specific_files = search_specific_files
2974
self.source_index = source_index
2975
self.target_index = target_index
2976
self.want_unversioned = want_unversioned
2979
def _process_entry(self, entry, path_info, pathjoin=osutils.pathjoin):
2980
"""Compare an entry and real disk to generate delta information.
2982
:param path_info: top_relpath, basename, kind, lstat, abspath for
2983
the path of entry. If None, then the path is considered absent.
2984
(Perhaps we should pass in a concrete entry for this ?)
2985
Basename is returned as a utf8 string because we expect this
2986
tuple will be ignored, and don't want to take the time to
2988
:return: None if these don't match
2989
A tuple of information about the change, or
2990
the object 'uninteresting' if these match, but are
2991
basically identical.
2993
if self.source_index is None:
2994
source_details = DirState.NULL_PARENT_DETAILS
2996
source_details = entry[1][self.source_index]
2997
target_details = entry[1][self.target_index]
2998
target_minikind = target_details[0]
2999
if path_info is not None and target_minikind in 'fdlt':
3000
if not (self.target_index == 0):
3001
raise AssertionError()
3002
link_or_sha1 = update_entry(self.state, entry,
3003
abspath=path_info[4], stat_value=path_info[3])
3004
# The entry may have been modified by update_entry
3005
target_details = entry[1][self.target_index]
3006
target_minikind = target_details[0]
3009
file_id = entry[0][2]
3010
source_minikind = source_details[0]
3011
if source_minikind in 'fdltr' and target_minikind in 'fdlt':
3012
# claimed content in both: diff
3013
# r | fdlt | | add source to search, add id path move and perform
3014
# | | | diff check on source-target
3015
# r | fdlt | a | dangling file that was present in the basis.
3017
if source_minikind in 'r':
3018
# add the source to the search path to find any children it
3019
# has. TODO ? : only add if it is a container ?
3020
if not osutils.is_inside_any(self.searched_specific_files,
3022
self.search_specific_files.add(source_details[1])
3023
# generate the old path; this is needed for stating later
3025
old_path = source_details[1]
3026
old_dirname, old_basename = os.path.split(old_path)
3027
path = pathjoin(entry[0][0], entry[0][1])
3028
old_entry = self.state._get_entry(self.source_index,
3030
# update the source details variable to be the real
3032
if old_entry == (None, None):
3033
raise errors.CorruptDirstate(self.state._filename,
3034
"entry '%s/%s' is considered renamed from %r"
3035
" but source does not exist\n"
3036
"entry: %s" % (entry[0][0], entry[0][1], old_path, entry))
3037
source_details = old_entry[1][self.source_index]
3038
source_minikind = source_details[0]
3040
old_dirname = entry[0][0]
3041
old_basename = entry[0][1]
3042
old_path = path = None
3043
if path_info is None:
3044
# the file is missing on disk, show as removed.
3045
content_change = True
3049
# source and target are both versioned and disk file is present.
3050
target_kind = path_info[2]
3051
if target_kind == 'directory':
3053
old_path = path = pathjoin(old_dirname, old_basename)
3054
self.new_dirname_to_file_id[path] = file_id
3055
if source_minikind != 'd':
3056
content_change = True
3058
# directories have no fingerprint
3059
content_change = False
3061
elif target_kind == 'file':
3062
if source_minikind != 'f':
3063
content_change = True
3065
# If the size is the same, check the sha:
3066
if target_details[2] == source_details[2]:
3067
if link_or_sha1 is None:
3069
statvalue, link_or_sha1 = \
3070
self.state._sha1_provider.stat_and_sha1(
3072
self.state._observed_sha1(entry, link_or_sha1,
3074
content_change = (link_or_sha1 != source_details[1])
3076
# Size changed, so must be different
3077
content_change = True
3078
# Target details is updated at update_entry time
3079
if self.use_filesystem_for_exec:
3080
# We don't need S_ISREG here, because we are sure
3081
# we are dealing with a file.
3082
target_exec = bool(stat.S_IEXEC & path_info[3].st_mode)
3084
target_exec = target_details[3]
3085
elif target_kind == 'symlink':
3086
if source_minikind != 'l':
3087
content_change = True
3089
content_change = (link_or_sha1 != source_details[1])
3091
elif target_kind == 'tree-reference':
3092
if source_minikind != 't':
3093
content_change = True
3095
content_change = False
3098
raise Exception, "unknown kind %s" % path_info[2]
3099
if source_minikind == 'd':
3101
old_path = path = pathjoin(old_dirname, old_basename)
3102
self.old_dirname_to_file_id[old_path] = file_id
3103
# parent id is the entry for the path in the target tree
3104
if old_dirname == self.last_source_parent[0]:
3105
source_parent_id = self.last_source_parent[1]
3108
source_parent_id = self.old_dirname_to_file_id[old_dirname]
3110
source_parent_entry = self.state._get_entry(self.source_index,
3111
path_utf8=old_dirname)
3112
source_parent_id = source_parent_entry[0][2]
3113
if source_parent_id == entry[0][2]:
3114
# This is the root, so the parent is None
3115
source_parent_id = None
3117
self.last_source_parent[0] = old_dirname
3118
self.last_source_parent[1] = source_parent_id
3119
new_dirname = entry[0][0]
3120
if new_dirname == self.last_target_parent[0]:
3121
target_parent_id = self.last_target_parent[1]
3124
target_parent_id = self.new_dirname_to_file_id[new_dirname]
3126
# TODO: We don't always need to do the lookup, because the
3127
# parent entry will be the same as the source entry.
3128
target_parent_entry = self.state._get_entry(self.target_index,
3129
path_utf8=new_dirname)
3130
if target_parent_entry == (None, None):
3131
raise AssertionError(
3132
"Could not find target parent in wt: %s\nparent of: %s"
3133
% (new_dirname, entry))
3134
target_parent_id = target_parent_entry[0][2]
3135
if target_parent_id == entry[0][2]:
3136
# This is the root, so the parent is None
3137
target_parent_id = None
3139
self.last_target_parent[0] = new_dirname
3140
self.last_target_parent[1] = target_parent_id
3142
source_exec = source_details[3]
3143
if (self.include_unchanged
3145
or source_parent_id != target_parent_id
3146
or old_basename != entry[0][1]
3147
or source_exec != target_exec
3149
if old_path is None:
3150
old_path = path = pathjoin(old_dirname, old_basename)
3151
old_path_u = self.utf8_decode(old_path)[0]
3154
old_path_u = self.utf8_decode(old_path)[0]
3155
if old_path == path:
3158
path_u = self.utf8_decode(path)[0]
3159
source_kind = DirState._minikind_to_kind[source_minikind]
3160
return (entry[0][2],
3161
(old_path_u, path_u),
3164
(source_parent_id, target_parent_id),
3165
(self.utf8_decode(old_basename)[0], self.utf8_decode(entry[0][1])[0]),
3166
(source_kind, target_kind),
3167
(source_exec, target_exec))
3169
return self.uninteresting
3170
elif source_minikind in 'a' and target_minikind in 'fdlt':
3171
# looks like a new file
3172
path = pathjoin(entry[0][0], entry[0][1])
3173
# parent id is the entry for the path in the target tree
3174
# TODO: these are the same for an entire directory: cache em.
3175
parent_id = self.state._get_entry(self.target_index,
3176
path_utf8=entry[0][0])[0][2]
3177
if parent_id == entry[0][2]:
3179
if path_info is not None:
3181
if self.use_filesystem_for_exec:
3182
# We need S_ISREG here, because we aren't sure if this
3185
stat.S_ISREG(path_info[3].st_mode)
3186
and stat.S_IEXEC & path_info[3].st_mode)
3188
target_exec = target_details[3]
3189
return (entry[0][2],
3190
(None, self.utf8_decode(path)[0]),
3194
(None, self.utf8_decode(entry[0][1])[0]),
3195
(None, path_info[2]),
3196
(None, target_exec))
3198
# Its a missing file, report it as such.
3199
return (entry[0][2],
3200
(None, self.utf8_decode(path)[0]),
3204
(None, self.utf8_decode(entry[0][1])[0]),
3207
elif source_minikind in 'fdlt' and target_minikind in 'a':
3208
# unversioned, possibly, or possibly not deleted: we dont care.
3209
# if its still on disk, *and* theres no other entry at this
3210
# path [we dont know this in this routine at the moment -
3211
# perhaps we should change this - then it would be an unknown.
3212
old_path = pathjoin(entry[0][0], entry[0][1])
3213
# parent id is the entry for the path in the target tree
3214
parent_id = self.state._get_entry(self.source_index, path_utf8=entry[0][0])[0][2]
3215
if parent_id == entry[0][2]:
3217
return (entry[0][2],
3218
(self.utf8_decode(old_path)[0], None),
3222
(self.utf8_decode(entry[0][1])[0], None),
3223
(DirState._minikind_to_kind[source_minikind], None),
3224
(source_details[3], None))
3225
elif source_minikind in 'fdlt' and target_minikind in 'r':
3226
# a rename; could be a true rename, or a rename inherited from
3227
# a renamed parent. TODO: handle this efficiently. Its not
3228
# common case to rename dirs though, so a correct but slow
3229
# implementation will do.
3230
if not osutils.is_inside_any(self.searched_specific_files, target_details[1]):
3231
self.search_specific_files.add(target_details[1])
3232
elif source_minikind in 'ra' and target_minikind in 'ra':
3233
# neither of the selected trees contain this file,
3234
# so skip over it. This is not currently directly tested, but
3235
# is indirectly via test_too_much.TestCommands.test_conflicts.
3238
raise AssertionError("don't know how to compare "
3239
"source_minikind=%r, target_minikind=%r"
3240
% (source_minikind, target_minikind))
3241
## import pdb;pdb.set_trace()
3247
def iter_changes(self):
3248
"""Iterate over the changes."""
3249
utf8_decode = cache_utf8._utf8_decode
3250
_cmp_by_dirs = cmp_by_dirs
3251
_process_entry = self._process_entry
3252
uninteresting = self.uninteresting
3253
search_specific_files = self.search_specific_files
3254
searched_specific_files = self.searched_specific_files
3255
splitpath = osutils.splitpath
3257
# compare source_index and target_index at or under each element of search_specific_files.
3258
# follow the following comparison table. Note that we only want to do diff operations when
3259
# the target is fdl because thats when the walkdirs logic will have exposed the pathinfo
3263
# Source | Target | disk | action
3264
# r | fdlt | | add source to search, add id path move and perform
3265
# | | | diff check on source-target
3266
# r | fdlt | a | dangling file that was present in the basis.
3268
# r | a | | add source to search
3270
# r | r | | this path is present in a non-examined tree, skip.
3271
# r | r | a | this path is present in a non-examined tree, skip.
3272
# a | fdlt | | add new id
3273
# a | fdlt | a | dangling locally added file, skip
3274
# a | a | | not present in either tree, skip
3275
# a | a | a | not present in any tree, skip
3276
# a | r | | not present in either tree at this path, skip as it
3277
# | | | may not be selected by the users list of paths.
3278
# a | r | a | not present in either tree at this path, skip as it
3279
# | | | may not be selected by the users list of paths.
3280
# fdlt | fdlt | | content in both: diff them
3281
# fdlt | fdlt | a | deleted locally, but not unversioned - show as deleted ?
3282
# fdlt | a | | unversioned: output deleted id for now
3283
# fdlt | a | a | unversioned and deleted: output deleted id
3284
# fdlt | r | | relocated in this tree, so add target to search.
3285
# | | | Dont diff, we will see an r,fd; pair when we reach
3286
# | | | this id at the other path.
3287
# fdlt | r | a | relocated in this tree, so add target to search.
3288
# | | | Dont diff, we will see an r,fd; pair when we reach
3289
# | | | this id at the other path.
3291
# TODO: jam 20070516 - Avoid the _get_entry lookup overhead by
3292
# keeping a cache of directories that we have seen.
3294
while search_specific_files:
3295
# TODO: the pending list should be lexically sorted? the
3296
# interface doesn't require it.
3297
current_root = search_specific_files.pop()
3298
current_root_unicode = current_root.decode('utf8')
3299
searched_specific_files.add(current_root)
3300
# process the entries for this containing directory: the rest will be
3301
# found by their parents recursively.
3302
root_entries = self.state._entries_for_path(current_root)
3303
root_abspath = self.tree.abspath(current_root_unicode)
3305
root_stat = os.lstat(root_abspath)
3307
if e.errno == errno.ENOENT:
3308
# the path does not exist: let _process_entry know that.
3309
root_dir_info = None
3311
# some other random error: hand it up.
3314
root_dir_info = ('', current_root,
3315
osutils.file_kind_from_stat_mode(root_stat.st_mode), root_stat,
3317
if root_dir_info[2] == 'directory':
3318
if self.tree._directory_is_tree_reference(
3319
current_root.decode('utf8')):
3320
root_dir_info = root_dir_info[:2] + \
3321
('tree-reference',) + root_dir_info[3:]
3323
if not root_entries and not root_dir_info:
3324
# this specified path is not present at all, skip it.
3326
path_handled = False
3327
for entry in root_entries:
3328
result = _process_entry(entry, root_dir_info)
3329
if result is not None:
3331
if result is not uninteresting:
3333
if self.want_unversioned and not path_handled and root_dir_info:
3334
new_executable = bool(
3335
stat.S_ISREG(root_dir_info[3].st_mode)
3336
and stat.S_IEXEC & root_dir_info[3].st_mode)
3338
(None, current_root_unicode),
3342
(None, splitpath(current_root_unicode)[-1]),
3343
(None, root_dir_info[2]),
3344
(None, new_executable)
3346
initial_key = (current_root, '', '')
3347
block_index, _ = self.state._find_block_index_from_key(initial_key)
3348
if block_index == 0:
3349
# we have processed the total root already, but because the
3350
# initial key matched it we should skip it here.
3352
if root_dir_info and root_dir_info[2] == 'tree-reference':
3353
current_dir_info = None
3355
dir_iterator = osutils._walkdirs_utf8(root_abspath, prefix=current_root)
3357
current_dir_info = dir_iterator.next()
3359
# on win32, python2.4 has e.errno == ERROR_DIRECTORY, but
3360
# python 2.5 has e.errno == EINVAL,
3361
# and e.winerror == ERROR_DIRECTORY
3362
e_winerror = getattr(e, 'winerror', None)
3363
win_errors = (ERROR_DIRECTORY, ERROR_PATH_NOT_FOUND)
3364
# there may be directories in the inventory even though
3365
# this path is not a file on disk: so mark it as end of
3367
if e.errno in (errno.ENOENT, errno.ENOTDIR, errno.EINVAL):
3368
current_dir_info = None
3369
elif (sys.platform == 'win32'
3370
and (e.errno in win_errors
3371
or e_winerror in win_errors)):
3372
current_dir_info = None
3376
if current_dir_info[0][0] == '':
3377
# remove .bzr from iteration
3378
bzr_index = bisect.bisect_left(current_dir_info[1], ('.bzr',))
3379
if current_dir_info[1][bzr_index][0] != '.bzr':
3380
raise AssertionError()
3381
del current_dir_info[1][bzr_index]
3382
# walk until both the directory listing and the versioned metadata
3384
if (block_index < len(self.state._dirblocks) and
3385
osutils.is_inside(current_root, self.state._dirblocks[block_index][0])):
3386
current_block = self.state._dirblocks[block_index]
3388
current_block = None
3389
while (current_dir_info is not None or
3390
current_block is not None):
3391
if (current_dir_info and current_block
3392
and current_dir_info[0][0] != current_block[0]):
3393
if _cmp_by_dirs(current_dir_info[0][0], current_block[0]) < 0:
3394
# filesystem data refers to paths not covered by the dirblock.
3395
# this has two possibilities:
3396
# A) it is versioned but empty, so there is no block for it
3397
# B) it is not versioned.
3399
# if (A) then we need to recurse into it to check for
3400
# new unknown files or directories.
3401
# if (B) then we should ignore it, because we don't
3402
# recurse into unknown directories.
3404
while path_index < len(current_dir_info[1]):
3405
current_path_info = current_dir_info[1][path_index]
3406
if self.want_unversioned:
3407
if current_path_info[2] == 'directory':
3408
if self.tree._directory_is_tree_reference(
3409
current_path_info[0].decode('utf8')):
3410
current_path_info = current_path_info[:2] + \
3411
('tree-reference',) + current_path_info[3:]
3412
new_executable = bool(
3413
stat.S_ISREG(current_path_info[3].st_mode)
3414
and stat.S_IEXEC & current_path_info[3].st_mode)
3416
(None, utf8_decode(current_path_info[0])[0]),
3420
(None, utf8_decode(current_path_info[1])[0]),
3421
(None, current_path_info[2]),
3422
(None, new_executable))
3423
# dont descend into this unversioned path if it is
3425
if current_path_info[2] in ('directory',
3427
del current_dir_info[1][path_index]
3431
# This dir info has been handled, go to the next
3433
current_dir_info = dir_iterator.next()
3434
except StopIteration:
3435
current_dir_info = None
3437
# We have a dirblock entry for this location, but there
3438
# is no filesystem path for this. This is most likely
3439
# because a directory was removed from the disk.
3440
# We don't have to report the missing directory,
3441
# because that should have already been handled, but we
3442
# need to handle all of the files that are contained
3444
for current_entry in current_block[1]:
3445
# entry referring to file not present on disk.
3446
# advance the entry only, after processing.
3447
result = _process_entry(current_entry, None)
3448
if result is not None:
3449
if result is not uninteresting:
3452
if (block_index < len(self.state._dirblocks) and
3453
osutils.is_inside(current_root,
3454
self.state._dirblocks[block_index][0])):
3455
current_block = self.state._dirblocks[block_index]
3457
current_block = None
3460
if current_block and entry_index < len(current_block[1]):
3461
current_entry = current_block[1][entry_index]
3463
current_entry = None
3464
advance_entry = True
3466
if current_dir_info and path_index < len(current_dir_info[1]):
3467
current_path_info = current_dir_info[1][path_index]
3468
if current_path_info[2] == 'directory':
3469
if self.tree._directory_is_tree_reference(
3470
current_path_info[0].decode('utf8')):
3471
current_path_info = current_path_info[:2] + \
3472
('tree-reference',) + current_path_info[3:]
3474
current_path_info = None
3476
path_handled = False
3477
while (current_entry is not None or
3478
current_path_info is not None):
3479
if current_entry is None:
3480
# the check for path_handled when the path is advanced
3481
# will yield this path if needed.
3483
elif current_path_info is None:
3484
# no path is fine: the per entry code will handle it.
3485
result = _process_entry(current_entry, current_path_info)
3486
if result is not None:
3487
if result is not uninteresting:
3489
elif (current_entry[0][1] != current_path_info[1]
3490
or current_entry[1][self.target_index][0] in 'ar'):
3491
# The current path on disk doesn't match the dirblock
3492
# record. Either the dirblock is marked as absent, or
3493
# the file on disk is not present at all in the
3494
# dirblock. Either way, report about the dirblock
3495
# entry, and let other code handle the filesystem one.
3497
# Compare the basename for these files to determine
3499
if current_path_info[1] < current_entry[0][1]:
3500
# extra file on disk: pass for now, but only
3501
# increment the path, not the entry
3502
advance_entry = False
3504
# entry referring to file not present on disk.
3505
# advance the entry only, after processing.
3506
result = _process_entry(current_entry, None)
3507
if result is not None:
3508
if result is not uninteresting:
3510
advance_path = False
3512
result = _process_entry(current_entry, current_path_info)
3513
if result is not None:
3515
if result is not uninteresting:
3517
if advance_entry and current_entry is not None:
3519
if entry_index < len(current_block[1]):
3520
current_entry = current_block[1][entry_index]
3522
current_entry = None
3524
advance_entry = True # reset the advance flaga
3525
if advance_path and current_path_info is not None:
3526
if not path_handled:
3527
# unversioned in all regards
3528
if self.want_unversioned:
3529
new_executable = bool(
3530
stat.S_ISREG(current_path_info[3].st_mode)
3531
and stat.S_IEXEC & current_path_info[3].st_mode)
3533
relpath_unicode = utf8_decode(current_path_info[0])[0]
3534
except UnicodeDecodeError:
3535
raise errors.BadFilenameEncoding(
3536
current_path_info[0], osutils._fs_enc)
3538
(None, relpath_unicode),
3542
(None, utf8_decode(current_path_info[1])[0]),
3543
(None, current_path_info[2]),
3544
(None, new_executable))
3545
# dont descend into this unversioned path if it is
3547
if current_path_info[2] in ('directory'):
3548
del current_dir_info[1][path_index]
3550
# dont descend the disk iterator into any tree
3552
if current_path_info[2] == 'tree-reference':
3553
del current_dir_info[1][path_index]
3556
if path_index < len(current_dir_info[1]):
3557
current_path_info = current_dir_info[1][path_index]
3558
if current_path_info[2] == 'directory':
3559
if self.tree._directory_is_tree_reference(
3560
current_path_info[0].decode('utf8')):
3561
current_path_info = current_path_info[:2] + \
3562
('tree-reference',) + current_path_info[3:]
3564
current_path_info = None
3565
path_handled = False
3567
advance_path = True # reset the advance flagg.
3568
if current_block is not None:
3570
if (block_index < len(self.state._dirblocks) and
3571
osutils.is_inside(current_root, self.state._dirblocks[block_index][0])):
3572
current_block = self.state._dirblocks[block_index]
3574
current_block = None
3575
if current_dir_info is not None:
3577
current_dir_info = dir_iterator.next()
3578
except StopIteration:
3579
current_dir_info = None
3580
_process_entry = ProcessEntryPython
3583
# Try to load the compiled form if possible
3585
from bzrlib._dirstate_helpers_c import (
3586
_read_dirblocks_c as _read_dirblocks,
3587
bisect_dirblock_c as bisect_dirblock,
3588
_bisect_path_left_c as _bisect_path_left,
3589
_bisect_path_right_c as _bisect_path_right,
3590
cmp_by_dirs_c as cmp_by_dirs,
3591
ProcessEntryC as _process_entry,
3592
update_entry as update_entry,
3595
from bzrlib._dirstate_helpers_py import (
3596
_read_dirblocks_py as _read_dirblocks,
3597
bisect_dirblock_py as bisect_dirblock,
3598
_bisect_path_left_py as _bisect_path_left,
3599
_bisect_path_right_py as _bisect_path_right,
3600
cmp_by_dirs_py as cmp_by_dirs,
added
removed
bzrlib/dirstate.py
