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
209
from stat import S_IEXEC
227
# This is the Windows equivalent of ENOTDIR
228
# It is defined in pywin32.winerror, but we don't want a strong dependency for
229
# just an error code.
230
ERROR_PATH_NOT_FOUND = 3
231
ERROR_DIRECTORY = 267
234
if not getattr(struct, '_compile', None):
235
# Cannot pre-compile the dirstate pack_stat
236
def pack_stat(st, _encode=binascii.b2a_base64, _pack=struct.pack):
237
"""Convert stat values into a packed representation."""
238
return _encode(_pack('>LLLLLL', st.st_size, int(st.st_mtime),
239
int(st.st_ctime), st.st_dev, st.st_ino & 0xFFFFFFFF,
242
# compile the struct compiler we need, so as to only do it once
243
from _struct import Struct
244
_compiled_pack = Struct('>LLLLLL').pack
245
def pack_stat(st, _encode=binascii.b2a_base64, _pack=_compiled_pack):
246
"""Convert stat values into a packed representation."""
247
# jam 20060614 it isn't really worth removing more entries if we
248
# are going to leave it in packed form.
249
# With only st_mtime and st_mode filesize is 5.5M and read time is 275ms
250
# With all entries, filesize is 5.9M and read time is maybe 280ms
251
# well within the noise margin
253
# base64 encoding always adds a final newline, so strip it off
254
# The current version
255
return _encode(_pack(st.st_size, int(st.st_mtime), int(st.st_ctime),
256
st.st_dev, st.st_ino & 0xFFFFFFFF, st.st_mode))[:-1]
257
# This is 0.060s / 1.520s faster by not encoding as much information
258
# return _encode(_pack('>LL', int(st.st_mtime), st.st_mode))[:-1]
259
# This is not strictly faster than _encode(_pack())[:-1]
260
# return '%X.%X.%X.%X.%X.%X' % (
261
# st.st_size, int(st.st_mtime), int(st.st_ctime),
262
# st.st_dev, st.st_ino, st.st_mode)
263
# Similar to the _encode(_pack('>LL'))
264
# return '%X.%X' % (int(st.st_mtime), st.st_mode)
267
class SHA1Provider(object):
268
"""An interface for getting sha1s of a file."""
270
def sha1(self, abspath):
271
"""Return the sha1 of a file given its absolute path.
273
:param abspath: May be a filesystem encoded absolute path
276
raise NotImplementedError(self.sha1)
278
def stat_and_sha1(self, abspath):
279
"""Return the stat and sha1 of a file given its absolute path.
281
:param abspath: May be a filesystem encoded absolute path
284
Note: the stat should be the stat of the physical file
285
while the sha may be the sha of its canonical content.
287
raise NotImplementedError(self.stat_and_sha1)
290
class DefaultSHA1Provider(SHA1Provider):
291
"""A SHA1Provider that reads directly from the filesystem."""
293
def sha1(self, abspath):
294
"""Return the sha1 of a file given its absolute path."""
295
return osutils.sha_file_by_name(abspath)
297
def stat_and_sha1(self, abspath):
298
"""Return the stat and sha1 of a file given its absolute path."""
299
file_obj = file(abspath, 'rb')
301
statvalue = os.fstat(file_obj.fileno())
302
sha1 = osutils.sha_file(file_obj)
305
return statvalue, sha1
308
class DirState(object):
309
"""Record directory and metadata state for fast access.
311
A dirstate is a specialised data structure for managing local working
312
tree state information. Its not yet well defined whether it is platform
313
specific, and if it is how we detect/parameterize that.
315
Dirstates use the usual lock_write, lock_read and unlock mechanisms.
316
Unlike most bzr disk formats, DirStates must be locked for reading, using
317
lock_read. (This is an os file lock internally.) This is necessary
318
because the file can be rewritten in place.
320
DirStates must be explicitly written with save() to commit changes; just
321
unlocking them does not write the changes to disk.
324
_kind_to_minikind = {
330
'tree-reference': 't',
332
_minikind_to_kind = {
338
't': 'tree-reference',
340
_stat_to_minikind = {
345
_to_yesno = {True:'y', False: 'n'} # TODO profile the performance gain
346
# of using int conversion rather than a dict here. AND BLAME ANDREW IF
349
# TODO: jam 20070221 Figure out what to do if we have a record that exceeds
350
# the BISECT_PAGE_SIZE. For now, we just have to make it large enough
351
# that we are sure a single record will always fit.
352
BISECT_PAGE_SIZE = 4096
355
IN_MEMORY_UNMODIFIED = 1
356
IN_MEMORY_MODIFIED = 2
358
# A pack_stat (the x's) that is just noise and will never match the output
361
NULL_PARENT_DETAILS = ('a', '', 0, False, '')
363
HEADER_FORMAT_2 = '#bazaar dirstate flat format 2\n'
364
HEADER_FORMAT_3 = '#bazaar dirstate flat format 3\n'
366
def __init__(self, path, sha1_provider):
367
"""Create a DirState object.
369
:param path: The path at which the dirstate file on disk should live.
370
:param sha1_provider: an object meeting the SHA1Provider interface.
372
# _header_state and _dirblock_state represent the current state
373
# of the dirstate metadata and the per-row data respectiely.
374
# NOT_IN_MEMORY indicates that no data is in memory
375
# IN_MEMORY_UNMODIFIED indicates that what we have in memory
376
# is the same as is on disk
377
# IN_MEMORY_MODIFIED indicates that we have a modified version
378
# of what is on disk.
379
# In future we will add more granularity, for instance _dirblock_state
380
# will probably support partially-in-memory as a separate variable,
381
# allowing for partially-in-memory unmodified and partially-in-memory
383
self._header_state = DirState.NOT_IN_MEMORY
384
self._dirblock_state = DirState.NOT_IN_MEMORY
385
# If true, an error has been detected while updating the dirstate, and
386
# for safety we're not going to commit to disk.
387
self._changes_aborted = False
391
self._state_file = None
392
self._filename = path
393
self._lock_token = None
394
self._lock_state = None
395
self._id_index = None
396
# a map from packed_stat to sha's.
397
self._packed_stat_index = None
398
self._end_of_header = None
399
self._cutoff_time = None
400
self._split_path_cache = {}
401
self._bisect_page_size = DirState.BISECT_PAGE_SIZE
402
self._sha1_provider = sha1_provider
403
if 'hashcache' in debug.debug_flags:
404
self._sha1_file = self._sha1_file_and_mutter
406
self._sha1_file = self._sha1_provider.sha1
407
# These two attributes provide a simple cache for lookups into the
408
# dirstate in-memory vectors. By probing respectively for the last
409
# block, and for the next entry, we save nearly 2 bisections per path
411
self._last_block_index = None
412
self._last_entry_index = None
416
(self.__class__.__name__, self._filename)
418
def add(self, path, file_id, kind, stat, fingerprint):
419
"""Add a path to be tracked.
421
:param path: The path within the dirstate - '' is the root, 'foo' is the
422
path foo within the root, 'foo/bar' is the path bar within foo
424
:param file_id: The file id of the path being added.
425
:param kind: The kind of the path, as a string like 'file',
427
:param stat: The output of os.lstat for the path.
428
:param fingerprint: The sha value of the file's canonical form (i.e.
429
after any read filters have been applied),
430
or the target of a symlink,
431
or the referenced revision id for tree-references,
432
or '' for directories.
435
# find the block its in.
436
# find the location in the block.
437
# check its not there
439
#------- copied from inventory.ensure_normalized_name - keep synced.
440
# --- normalized_filename wants a unicode basename only, so get one.
441
dirname, basename = osutils.split(path)
442
# we dont import normalized_filename directly because we want to be
443
# able to change the implementation at runtime for tests.
444
norm_name, can_access = osutils.normalized_filename(basename)
445
if norm_name != basename:
449
raise errors.InvalidNormalization(path)
450
# you should never have files called . or ..; just add the directory
451
# in the parent, or according to the special treatment for the root
452
if basename == '.' or basename == '..':
453
raise errors.InvalidEntryName(path)
454
# now that we've normalised, we need the correct utf8 path and
455
# dirname and basename elements. This single encode and split should be
456
# faster than three separate encodes.
457
utf8path = (dirname + '/' + basename).strip('/').encode('utf8')
458
dirname, basename = osutils.split(utf8path)
459
# uses __class__ for speed; the check is needed for safety
460
if file_id.__class__ is not str:
461
raise AssertionError(
462
"must be a utf8 file_id not %s" % (type(file_id), ))
463
# Make sure the file_id does not exist in this tree
465
file_id_entry = self._get_entry(0, fileid_utf8=file_id, include_deleted=True)
466
if file_id_entry != (None, None):
467
if file_id_entry[1][0][0] == 'a':
468
if file_id_entry[0] != (dirname, basename, file_id):
469
# set the old name's current operation to rename
470
self.update_minimal(file_id_entry[0],
476
rename_from = file_id_entry[0][0:2]
478
path = osutils.pathjoin(file_id_entry[0][0], file_id_entry[0][1])
479
kind = DirState._minikind_to_kind[file_id_entry[1][0][0]]
480
info = '%s:%s' % (kind, path)
481
raise errors.DuplicateFileId(file_id, info)
482
first_key = (dirname, basename, '')
483
block_index, present = self._find_block_index_from_key(first_key)
485
# check the path is not in the tree
486
block = self._dirblocks[block_index][1]
487
entry_index, _ = self._find_entry_index(first_key, block)
488
while (entry_index < len(block) and
489
block[entry_index][0][0:2] == first_key[0:2]):
490
if block[entry_index][1][0][0] not in 'ar':
491
# this path is in the dirstate in the current tree.
492
raise Exception, "adding already added path!"
495
# The block where we want to put the file is not present. But it
496
# might be because the directory was empty, or not loaded yet. Look
497
# for a parent entry, if not found, raise NotVersionedError
498
parent_dir, parent_base = osutils.split(dirname)
499
parent_block_idx, parent_entry_idx, _, parent_present = \
500
self._get_block_entry_index(parent_dir, parent_base, 0)
501
if not parent_present:
502
raise errors.NotVersionedError(path, str(self))
503
self._ensure_block(parent_block_idx, parent_entry_idx, dirname)
504
block = self._dirblocks[block_index][1]
505
entry_key = (dirname, basename, file_id)
508
packed_stat = DirState.NULLSTAT
511
packed_stat = pack_stat(stat)
512
parent_info = self._empty_parent_info()
513
minikind = DirState._kind_to_minikind[kind]
514
if rename_from is not None:
516
old_path_utf8 = '%s/%s' % rename_from
518
old_path_utf8 = rename_from[1]
519
parent_info[0] = ('r', old_path_utf8, 0, False, '')
521
entry_data = entry_key, [
522
(minikind, fingerprint, size, False, packed_stat),
524
elif kind == 'directory':
525
entry_data = entry_key, [
526
(minikind, '', 0, False, packed_stat),
528
elif kind == 'symlink':
529
entry_data = entry_key, [
530
(minikind, fingerprint, size, False, packed_stat),
532
elif kind == 'tree-reference':
533
entry_data = entry_key, [
534
(minikind, fingerprint, 0, False, packed_stat),
537
raise errors.BzrError('unknown kind %r' % kind)
538
entry_index, present = self._find_entry_index(entry_key, block)
540
block.insert(entry_index, entry_data)
542
if block[entry_index][1][0][0] != 'a':
543
raise AssertionError(" %r(%r) already added" % (basename, file_id))
544
block[entry_index][1][0] = entry_data[1][0]
546
if kind == 'directory':
547
# insert a new dirblock
548
self._ensure_block(block_index, entry_index, utf8path)
549
self._dirblock_state = DirState.IN_MEMORY_MODIFIED
551
self._id_index.setdefault(entry_key[2], set()).add(entry_key)
553
def _bisect(self, paths):
554
"""Bisect through the disk structure for specific rows.
556
:param paths: A list of paths to find
557
:return: A dict mapping path => entries for found entries. Missing
558
entries will not be in the map.
559
The list is not sorted, and entries will be populated
560
based on when they were read.
562
self._requires_lock()
563
# We need the file pointer to be right after the initial header block
564
self._read_header_if_needed()
565
# If _dirblock_state was in memory, we should just return info from
566
# there, this function is only meant to handle when we want to read
568
if self._dirblock_state != DirState.NOT_IN_MEMORY:
569
raise AssertionError("bad dirblock state %r" % self._dirblock_state)
571
# The disk representation is generally info + '\0\n\0' at the end. But
572
# for bisecting, it is easier to treat this as '\0' + info + '\0\n'
573
# Because it means we can sync on the '\n'
574
state_file = self._state_file
575
file_size = os.fstat(state_file.fileno()).st_size
576
# We end up with 2 extra fields, we should have a trailing '\n' to
577
# ensure that we read the whole record, and we should have a precursur
578
# '' which ensures that we start after the previous '\n'
579
entry_field_count = self._fields_per_entry() + 1
581
low = self._end_of_header
582
high = file_size - 1 # Ignore the final '\0'
583
# Map from (dir, name) => entry
586
# Avoid infinite seeking
587
max_count = 30*len(paths)
589
# pending is a list of places to look.
590
# each entry is a tuple of low, high, dir_names
591
# low -> the first byte offset to read (inclusive)
592
# high -> the last byte offset (inclusive)
593
# dir_names -> The list of (dir, name) pairs that should be found in
594
# the [low, high] range
595
pending = [(low, high, paths)]
597
page_size = self._bisect_page_size
599
fields_to_entry = self._get_fields_to_entry()
602
low, high, cur_files = pending.pop()
604
if not cur_files or low >= high:
609
if count > max_count:
610
raise errors.BzrError('Too many seeks, most likely a bug.')
612
mid = max(low, (low+high-page_size)/2)
615
# limit the read size, so we don't end up reading data that we have
617
read_size = min(page_size, (high-mid)+1)
618
block = state_file.read(read_size)
621
entries = block.split('\n')
624
# We didn't find a '\n', so we cannot have found any records.
625
# So put this range back and try again. But we know we have to
626
# increase the page size, because a single read did not contain
627
# a record break (so records must be larger than page_size)
629
pending.append((low, high, cur_files))
632
# Check the first and last entries, in case they are partial, or if
633
# we don't care about the rest of this page
635
first_fields = entries[0].split('\0')
636
if len(first_fields) < entry_field_count:
637
# We didn't get the complete first entry
638
# so move start, and grab the next, which
639
# should be a full entry
640
start += len(entries[0])+1
641
first_fields = entries[1].split('\0')
644
if len(first_fields) <= 2:
645
# We didn't even get a filename here... what do we do?
646
# Try a large page size and repeat this query
648
pending.append((low, high, cur_files))
651
# Find what entries we are looking for, which occur before and
652
# after this first record.
655
first_path = first_fields[1] + '/' + first_fields[2]
657
first_path = first_fields[2]
658
first_loc = _bisect_path_left(cur_files, first_path)
660
# These exist before the current location
661
pre = cur_files[:first_loc]
662
# These occur after the current location, which may be in the
663
# data we read, or might be after the last entry
664
post = cur_files[first_loc:]
666
if post and len(first_fields) >= entry_field_count:
667
# We have files after the first entry
669
# Parse the last entry
670
last_entry_num = len(entries)-1
671
last_fields = entries[last_entry_num].split('\0')
672
if len(last_fields) < entry_field_count:
673
# The very last hunk was not complete,
674
# read the previous hunk
675
after = mid + len(block) - len(entries[-1])
677
last_fields = entries[last_entry_num].split('\0')
679
after = mid + len(block)
682
last_path = last_fields[1] + '/' + last_fields[2]
684
last_path = last_fields[2]
685
last_loc = _bisect_path_right(post, last_path)
687
middle_files = post[:last_loc]
688
post = post[last_loc:]
691
# We have files that should occur in this block
692
# (>= first, <= last)
693
# Either we will find them here, or we can mark them as
696
if middle_files[0] == first_path:
697
# We might need to go before this location
698
pre.append(first_path)
699
if middle_files[-1] == last_path:
700
post.insert(0, last_path)
702
# Find out what paths we have
703
paths = {first_path:[first_fields]}
704
# last_path might == first_path so we need to be
705
# careful if we should append rather than overwrite
706
if last_entry_num != first_entry_num:
707
paths.setdefault(last_path, []).append(last_fields)
708
for num in xrange(first_entry_num+1, last_entry_num):
709
# TODO: jam 20070223 We are already splitting here, so
710
# shouldn't we just split the whole thing rather
711
# than doing the split again in add_one_record?
712
fields = entries[num].split('\0')
714
path = fields[1] + '/' + fields[2]
717
paths.setdefault(path, []).append(fields)
719
for path in middle_files:
720
for fields in paths.get(path, []):
721
# offset by 1 because of the opening '\0'
722
# consider changing fields_to_entry to avoid the
724
entry = fields_to_entry(fields[1:])
725
found.setdefault(path, []).append(entry)
727
# Now we have split up everything into pre, middle, and post, and
728
# we have handled everything that fell in 'middle'.
729
# We add 'post' first, so that we prefer to seek towards the
730
# beginning, so that we will tend to go as early as we need, and
731
# then only seek forward after that.
733
pending.append((after, high, post))
735
pending.append((low, start-1, pre))
737
# Consider that we may want to return the directory entries in sorted
738
# order. For now, we just return them in whatever order we found them,
739
# and leave it up to the caller if they care if it is ordered or not.
742
def _bisect_dirblocks(self, dir_list):
743
"""Bisect through the disk structure to find entries in given dirs.
745
_bisect_dirblocks is meant to find the contents of directories, which
746
differs from _bisect, which only finds individual entries.
748
:param dir_list: A sorted list of directory names ['', 'dir', 'foo'].
749
:return: A map from dir => entries_for_dir
751
# TODO: jam 20070223 A lot of the bisecting logic could be shared
752
# between this and _bisect. It would require parameterizing the
753
# inner loop with a function, though. We should evaluate the
754
# performance difference.
755
self._requires_lock()
756
# We need the file pointer to be right after the initial header block
757
self._read_header_if_needed()
758
# If _dirblock_state was in memory, we should just return info from
759
# there, this function is only meant to handle when we want to read
761
if self._dirblock_state != DirState.NOT_IN_MEMORY:
762
raise AssertionError("bad dirblock state %r" % self._dirblock_state)
763
# The disk representation is generally info + '\0\n\0' at the end. But
764
# for bisecting, it is easier to treat this as '\0' + info + '\0\n'
765
# Because it means we can sync on the '\n'
766
state_file = self._state_file
767
file_size = os.fstat(state_file.fileno()).st_size
768
# We end up with 2 extra fields, we should have a trailing '\n' to
769
# ensure that we read the whole record, and we should have a precursur
770
# '' which ensures that we start after the previous '\n'
771
entry_field_count = self._fields_per_entry() + 1
773
low = self._end_of_header
774
high = file_size - 1 # Ignore the final '\0'
775
# Map from dir => entry
778
# Avoid infinite seeking
779
max_count = 30*len(dir_list)
781
# pending is a list of places to look.
782
# each entry is a tuple of low, high, dir_names
783
# low -> the first byte offset to read (inclusive)
784
# high -> the last byte offset (inclusive)
785
# dirs -> The list of directories that should be found in
786
# the [low, high] range
787
pending = [(low, high, dir_list)]
789
page_size = self._bisect_page_size
791
fields_to_entry = self._get_fields_to_entry()
794
low, high, cur_dirs = pending.pop()
796
if not cur_dirs or low >= high:
801
if count > max_count:
802
raise errors.BzrError('Too many seeks, most likely a bug.')
804
mid = max(low, (low+high-page_size)/2)
807
# limit the read size, so we don't end up reading data that we have
809
read_size = min(page_size, (high-mid)+1)
810
block = state_file.read(read_size)
813
entries = block.split('\n')
816
# We didn't find a '\n', so we cannot have found any records.
817
# So put this range back and try again. But we know we have to
818
# increase the page size, because a single read did not contain
819
# a record break (so records must be larger than page_size)
821
pending.append((low, high, cur_dirs))
824
# Check the first and last entries, in case they are partial, or if
825
# we don't care about the rest of this page
827
first_fields = entries[0].split('\0')
828
if len(first_fields) < entry_field_count:
829
# We didn't get the complete first entry
830
# so move start, and grab the next, which
831
# should be a full entry
832
start += len(entries[0])+1
833
first_fields = entries[1].split('\0')
836
if len(first_fields) <= 1:
837
# We didn't even get a dirname here... what do we do?
838
# Try a large page size and repeat this query
840
pending.append((low, high, cur_dirs))
843
# Find what entries we are looking for, which occur before and
844
# after this first record.
846
first_dir = first_fields[1]
847
first_loc = bisect.bisect_left(cur_dirs, first_dir)
849
# These exist before the current location
850
pre = cur_dirs[:first_loc]
851
# These occur after the current location, which may be in the
852
# data we read, or might be after the last entry
853
post = cur_dirs[first_loc:]
855
if post and len(first_fields) >= entry_field_count:
856
# We have records to look at after the first entry
858
# Parse the last entry
859
last_entry_num = len(entries)-1
860
last_fields = entries[last_entry_num].split('\0')
861
if len(last_fields) < entry_field_count:
862
# The very last hunk was not complete,
863
# read the previous hunk
864
after = mid + len(block) - len(entries[-1])
866
last_fields = entries[last_entry_num].split('\0')
868
after = mid + len(block)
870
last_dir = last_fields[1]
871
last_loc = bisect.bisect_right(post, last_dir)
873
middle_files = post[:last_loc]
874
post = post[last_loc:]
877
# We have files that should occur in this block
878
# (>= first, <= last)
879
# Either we will find them here, or we can mark them as
882
if middle_files[0] == first_dir:
883
# We might need to go before this location
884
pre.append(first_dir)
885
if middle_files[-1] == last_dir:
886
post.insert(0, last_dir)
888
# Find out what paths we have
889
paths = {first_dir:[first_fields]}
890
# last_dir might == first_dir so we need to be
891
# careful if we should append rather than overwrite
892
if last_entry_num != first_entry_num:
893
paths.setdefault(last_dir, []).append(last_fields)
894
for num in xrange(first_entry_num+1, last_entry_num):
895
# TODO: jam 20070223 We are already splitting here, so
896
# shouldn't we just split the whole thing rather
897
# than doing the split again in add_one_record?
898
fields = entries[num].split('\0')
899
paths.setdefault(fields[1], []).append(fields)
901
for cur_dir in middle_files:
902
for fields in paths.get(cur_dir, []):
903
# offset by 1 because of the opening '\0'
904
# consider changing fields_to_entry to avoid the
906
entry = fields_to_entry(fields[1:])
907
found.setdefault(cur_dir, []).append(entry)
909
# Now we have split up everything into pre, middle, and post, and
910
# we have handled everything that fell in 'middle'.
911
# We add 'post' first, so that we prefer to seek towards the
912
# beginning, so that we will tend to go as early as we need, and
913
# then only seek forward after that.
915
pending.append((after, high, post))
917
pending.append((low, start-1, pre))
921
def _bisect_recursive(self, paths):
922
"""Bisect for entries for all paths and their children.
924
This will use bisect to find all records for the supplied paths. It
925
will then continue to bisect for any records which are marked as
926
directories. (and renames?)
928
:param paths: A sorted list of (dir, name) pairs
929
eg: [('', 'a'), ('', 'f'), ('a/b', 'c')]
930
:return: A dictionary mapping (dir, name, file_id) => [tree_info]
932
# Map from (dir, name, file_id) => [tree_info]
935
found_dir_names = set()
937
# Directories that have been read
938
processed_dirs = set()
939
# Get the ball rolling with the first bisect for all entries.
940
newly_found = self._bisect(paths)
943
# Directories that need to be read
945
paths_to_search = set()
946
for entry_list in newly_found.itervalues():
947
for dir_name_id, trees_info in entry_list:
948
found[dir_name_id] = trees_info
949
found_dir_names.add(dir_name_id[:2])
951
for tree_info in trees_info:
952
minikind = tree_info[0]
955
# We already processed this one as a directory,
956
# we don't need to do the extra work again.
958
subdir, name, file_id = dir_name_id
959
path = osutils.pathjoin(subdir, name)
961
if path not in processed_dirs:
962
pending_dirs.add(path)
963
elif minikind == 'r':
964
# Rename, we need to directly search the target
965
# which is contained in the fingerprint column
966
dir_name = osutils.split(tree_info[1])
967
if dir_name[0] in pending_dirs:
968
# This entry will be found in the dir search
970
if dir_name not in found_dir_names:
971
paths_to_search.add(tree_info[1])
972
# Now we have a list of paths to look for directly, and
973
# directory blocks that need to be read.
974
# newly_found is mixing the keys between (dir, name) and path
975
# entries, but that is okay, because we only really care about the
977
newly_found = self._bisect(sorted(paths_to_search))
978
newly_found.update(self._bisect_dirblocks(sorted(pending_dirs)))
979
processed_dirs.update(pending_dirs)
982
def _discard_merge_parents(self):
983
"""Discard any parents trees beyond the first.
985
Note that if this fails the dirstate is corrupted.
987
After this function returns the dirstate contains 2 trees, neither of
990
self._read_header_if_needed()
991
parents = self.get_parent_ids()
994
# only require all dirblocks if we are doing a full-pass removal.
995
self._read_dirblocks_if_needed()
996
dead_patterns = set([('a', 'r'), ('a', 'a'), ('r', 'r'), ('r', 'a')])
997
def iter_entries_removable():
998
for block in self._dirblocks:
999
deleted_positions = []
1000
for pos, entry in enumerate(block[1]):
1002
if (entry[1][0][0], entry[1][1][0]) in dead_patterns:
1003
deleted_positions.append(pos)
1004
if deleted_positions:
1005
if len(deleted_positions) == len(block[1]):
1008
for pos in reversed(deleted_positions):
1010
# if the first parent is a ghost:
1011
if parents[0] in self.get_ghosts():
1012
empty_parent = [DirState.NULL_PARENT_DETAILS]
1013
for entry in iter_entries_removable():
1014
entry[1][1:] = empty_parent
1016
for entry in iter_entries_removable():
1020
self._parents = [parents[0]]
1021
self._dirblock_state = DirState.IN_MEMORY_MODIFIED
1022
self._header_state = DirState.IN_MEMORY_MODIFIED
1024
def _empty_parent_info(self):
1025
return [DirState.NULL_PARENT_DETAILS] * (len(self._parents) -
1028
def _ensure_block(self, parent_block_index, parent_row_index, dirname):
1029
"""Ensure a block for dirname exists.
1031
This function exists to let callers which know that there is a
1032
directory dirname ensure that the block for it exists. This block can
1033
fail to exist because of demand loading, or because a directory had no
1034
children. In either case it is not an error. It is however an error to
1035
call this if there is no parent entry for the directory, and thus the
1036
function requires the coordinates of such an entry to be provided.
1038
The root row is special cased and can be indicated with a parent block
1041
:param parent_block_index: The index of the block in which dirname's row
1043
:param parent_row_index: The index in the parent block where the row
1045
:param dirname: The utf8 dirname to ensure there is a block for.
1046
:return: The index for the block.
1048
if dirname == '' and parent_row_index == 0 and parent_block_index == 0:
1049
# This is the signature of the root row, and the
1050
# contents-of-root row is always index 1
1052
# the basename of the directory must be the end of its full name.
1053
if not (parent_block_index == -1 and
1054
parent_block_index == -1 and dirname == ''):
1055
if not dirname.endswith(
1056
self._dirblocks[parent_block_index][1][parent_row_index][0][1]):
1057
raise AssertionError("bad dirname %r" % dirname)
1058
block_index, present = self._find_block_index_from_key((dirname, '', ''))
1060
## In future, when doing partial parsing, this should load and
1061
# populate the entire block.
1062
self._dirblocks.insert(block_index, (dirname, []))
1065
def _entries_to_current_state(self, new_entries):
1066
"""Load new_entries into self.dirblocks.
1068
Process new_entries into the current state object, making them the active
1069
state. The entries are grouped together by directory to form dirblocks.
1071
:param new_entries: A sorted list of entries. This function does not sort
1072
to prevent unneeded overhead when callers have a sorted list already.
1075
if new_entries[0][0][0:2] != ('', ''):
1076
raise AssertionError(
1077
"Missing root row %r" % (new_entries[0][0],))
1078
# The two blocks here are deliberate: the root block and the
1079
# contents-of-root block.
1080
self._dirblocks = [('', []), ('', [])]
1081
current_block = self._dirblocks[0][1]
1082
current_dirname = ''
1084
append_entry = current_block.append
1085
for entry in new_entries:
1086
if entry[0][0] != current_dirname:
1087
# new block - different dirname
1089
current_dirname = entry[0][0]
1090
self._dirblocks.append((current_dirname, current_block))
1091
append_entry = current_block.append
1092
# append the entry to the current block
1094
self._split_root_dirblock_into_contents()
1096
def _split_root_dirblock_into_contents(self):
1097
"""Split the root dirblocks into root and contents-of-root.
1099
After parsing by path, we end up with root entries and contents-of-root
1100
entries in the same block. This loop splits them out again.
1102
# The above loop leaves the "root block" entries mixed with the
1103
# "contents-of-root block". But we don't want an if check on
1104
# all entries, so instead we just fix it up here.
1105
if self._dirblocks[1] != ('', []):
1106
raise ValueError("bad dirblock start %r" % (self._dirblocks[1],))
1108
contents_of_root_block = []
1109
for entry in self._dirblocks[0][1]:
1110
if not entry[0][1]: # This is a root entry
1111
root_block.append(entry)
1113
contents_of_root_block.append(entry)
1114
self._dirblocks[0] = ('', root_block)
1115
self._dirblocks[1] = ('', contents_of_root_block)
1117
def _entries_for_path(self, path):
1118
"""Return a list with all the entries that match path for all ids."""
1119
dirname, basename = os.path.split(path)
1120
key = (dirname, basename, '')
1121
block_index, present = self._find_block_index_from_key(key)
1123
# the block which should contain path is absent.
1126
block = self._dirblocks[block_index][1]
1127
entry_index, _ = self._find_entry_index(key, block)
1128
# we may need to look at multiple entries at this path: walk while the specific_files match.
1129
while (entry_index < len(block) and
1130
block[entry_index][0][0:2] == key[0:2]):
1131
result.append(block[entry_index])
1135
def _entry_to_line(self, entry):
1136
"""Serialize entry to a NULL delimited line ready for _get_output_lines.
1138
:param entry: An entry_tuple as defined in the module docstring.
1140
entire_entry = list(entry[0])
1141
for tree_number, tree_data in enumerate(entry[1]):
1142
# (minikind, fingerprint, size, executable, tree_specific_string)
1143
entire_entry.extend(tree_data)
1144
# 3 for the key, 5 for the fields per tree.
1145
tree_offset = 3 + tree_number * 5
1147
entire_entry[tree_offset + 0] = tree_data[0]
1149
entire_entry[tree_offset + 2] = str(tree_data[2])
1151
entire_entry[tree_offset + 3] = DirState._to_yesno[tree_data[3]]
1152
return '\0'.join(entire_entry)
1154
def _fields_per_entry(self):
1155
"""How many null separated fields should be in each entry row.
1157
Each line now has an extra '\n' field which is not used
1158
so we just skip over it
1160
3 fields for the key
1161
+ number of fields per tree_data (5) * tree count
1164
tree_count = 1 + self._num_present_parents()
1165
return 3 + 5 * tree_count + 1
1167
def _find_block(self, key, add_if_missing=False):
1168
"""Return the block that key should be present in.
1170
:param key: A dirstate entry key.
1171
:return: The block tuple.
1173
block_index, present = self._find_block_index_from_key(key)
1175
if not add_if_missing:
1176
# check to see if key is versioned itself - we might want to
1177
# add it anyway, because dirs with no entries dont get a
1178
# dirblock at parse time.
1179
# This is an uncommon branch to take: most dirs have children,
1180
# and most code works with versioned paths.
1181
parent_base, parent_name = osutils.split(key[0])
1182
if not self._get_block_entry_index(parent_base, parent_name, 0)[3]:
1183
# some parent path has not been added - its an error to add
1185
raise errors.NotVersionedError(key[0:2], str(self))
1186
self._dirblocks.insert(block_index, (key[0], []))
1187
return self._dirblocks[block_index]
1189
def _find_block_index_from_key(self, key):
1190
"""Find the dirblock index for a key.
1192
:return: The block index, True if the block for the key is present.
1194
if key[0:2] == ('', ''):
1197
if (self._last_block_index is not None and
1198
self._dirblocks[self._last_block_index][0] == key[0]):
1199
return self._last_block_index, True
1202
block_index = bisect_dirblock(self._dirblocks, key[0], 1,
1203
cache=self._split_path_cache)
1204
# _right returns one-past-where-key is so we have to subtract
1205
# one to use it. we use _right here because there are two
1206
# '' blocks - the root, and the contents of root
1207
# we always have a minimum of 2 in self._dirblocks: root and
1208
# root-contents, and for '', we get 2 back, so this is
1209
# simple and correct:
1210
present = (block_index < len(self._dirblocks) and
1211
self._dirblocks[block_index][0] == key[0])
1212
self._last_block_index = block_index
1213
# Reset the entry index cache to the beginning of the block.
1214
self._last_entry_index = -1
1215
return block_index, present
1217
def _find_entry_index(self, key, block):
1218
"""Find the entry index for a key in a block.
1220
:return: The entry index, True if the entry for the key is present.
1222
len_block = len(block)
1224
if self._last_entry_index is not None:
1226
entry_index = self._last_entry_index + 1
1227
# A hit is when the key is after the last slot, and before or
1228
# equal to the next slot.
1229
if ((entry_index > 0 and block[entry_index - 1][0] < key) and
1230
key <= block[entry_index][0]):
1231
self._last_entry_index = entry_index
1232
present = (block[entry_index][0] == key)
1233
return entry_index, present
1236
entry_index = bisect.bisect_left(block, (key, []))
1237
present = (entry_index < len_block and
1238
block[entry_index][0] == key)
1239
self._last_entry_index = entry_index
1240
return entry_index, present
1243
def from_tree(tree, dir_state_filename, sha1_provider=None):
1244
"""Create a dirstate from a bzr Tree.
1246
:param tree: The tree which should provide parent information and
1248
:param sha1_provider: an object meeting the SHA1Provider interface.
1249
If None, a DefaultSHA1Provider is used.
1250
:return: a DirState object which is currently locked for writing.
1251
(it was locked by DirState.initialize)
1253
result = DirState.initialize(dir_state_filename,
1254
sha1_provider=sha1_provider)
1258
parent_ids = tree.get_parent_ids()
1259
num_parents = len(parent_ids)
1261
for parent_id in parent_ids:
1262
parent_tree = tree.branch.repository.revision_tree(parent_id)
1263
parent_trees.append((parent_id, parent_tree))
1264
parent_tree.lock_read()
1265
result.set_parent_trees(parent_trees, [])
1266
result.set_state_from_inventory(tree.inventory)
1268
for revid, parent_tree in parent_trees:
1269
parent_tree.unlock()
1272
# The caller won't have a chance to unlock this, so make sure we
1278
def update_by_delta(self, delta):
1279
"""Apply an inventory delta to the dirstate for tree 0
1281
This is the workhorse for apply_inventory_delta in dirstate based
1284
:param delta: An inventory delta. See Inventory.apply_delta for
1287
self._read_dirblocks_if_needed()
1288
encode = cache_utf8.encode
1291
# Accumulate parent references (path_utf8, id), to check for parentless
1292
# items or items placed under files/links/tree-references. We get
1293
# references from every item in the delta that is not a deletion and
1294
# is not itself the root.
1296
# Added ids must not be in the dirstate already. This set holds those
1299
# This loop transforms the delta to single atomic operations that can
1300
# be executed and validated.
1301
for old_path, new_path, file_id, inv_entry in sorted(
1302
inventory._check_delta_unique_old_paths(
1303
inventory._check_delta_unique_new_paths(
1304
inventory._check_delta_ids_match_entry(
1305
inventory._check_delta_ids_are_valid(
1306
inventory._check_delta_new_path_entry_both_or_None(delta))))),
1308
if (file_id in insertions) or (file_id in removals):
1309
raise errors.InconsistentDelta(old_path or new_path, file_id,
1311
if old_path is not None:
1312
old_path = old_path.encode('utf-8')
1313
removals[file_id] = old_path
1315
new_ids.add(file_id)
1316
if new_path is not None:
1317
if inv_entry is None:
1318
raise errors.InconsistentDelta(new_path, file_id,
1319
"new_path with no entry")
1320
new_path = new_path.encode('utf-8')
1321
dirname_utf8, basename = osutils.split(new_path)
1323
parents.add((dirname_utf8, inv_entry.parent_id))
1324
key = (dirname_utf8, basename, file_id)
1325
minikind = DirState._kind_to_minikind[inv_entry.kind]
1327
fingerprint = inv_entry.reference_revision or ''
1330
insertions[file_id] = (key, minikind, inv_entry.executable,
1331
fingerprint, new_path)
1332
# Transform moves into delete+add pairs
1333
if None not in (old_path, new_path):
1334
for child in self._iter_child_entries(0, old_path):
1335
if child[0][2] in insertions or child[0][2] in removals:
1337
child_dirname = child[0][0]
1338
child_basename = child[0][1]
1339
minikind = child[1][0][0]
1340
fingerprint = child[1][0][4]
1341
executable = child[1][0][3]
1342
old_child_path = osutils.pathjoin(child[0][0],
1344
removals[child[0][2]] = old_child_path
1345
child_suffix = child_dirname[len(old_path):]
1346
new_child_dirname = (new_path + child_suffix)
1347
key = (new_child_dirname, child_basename, child[0][2])
1348
new_child_path = os.path.join(new_child_dirname,
1350
insertions[child[0][2]] = (key, minikind, executable,
1351
fingerprint, new_child_path)
1352
self._check_delta_ids_absent(new_ids, delta, 0)
1354
self._apply_removals(removals.iteritems())
1355
self._apply_insertions(insertions.values())
1357
self._after_delta_check_parents(parents, 0)
1358
except errors.BzrError, e:
1359
self._changes_aborted = True
1360
if 'integrity error' not in str(e):
1362
# _get_entry raises BzrError when a request is inconsistent; we
1363
# want such errors to be shown as InconsistentDelta - and that
1364
# fits the behaviour we trigger.
1365
raise errors.InconsistentDeltaDelta(delta, "error from _get_entry.")
1367
def _apply_removals(self, removals):
1368
for file_id, path in sorted(removals, reverse=True,
1369
key=operator.itemgetter(1)):
1370
dirname, basename = osutils.split(path)
1371
block_i, entry_i, d_present, f_present = \
1372
self._get_block_entry_index(dirname, basename, 0)
1374
entry = self._dirblocks[block_i][1][entry_i]
1376
self._changes_aborted = True
1377
raise errors.InconsistentDelta(path, file_id,
1378
"Wrong path for old path.")
1379
if not f_present or entry[1][0][0] in 'ar':
1380
self._changes_aborted = True
1381
raise errors.InconsistentDelta(path, file_id,
1382
"Wrong path for old path.")
1383
if file_id != entry[0][2]:
1384
self._changes_aborted = True
1385
raise errors.InconsistentDelta(path, file_id,
1386
"Attempt to remove path has wrong id - found %r."
1388
self._make_absent(entry)
1389
# See if we have a malformed delta: deleting a directory must not
1390
# leave crud behind. This increases the number of bisects needed
1391
# substantially, but deletion or renames of large numbers of paths
1392
# is rare enough it shouldn't be an issue (famous last words?) RBC
1394
block_i, entry_i, d_present, f_present = \
1395
self._get_block_entry_index(path, '', 0)
1397
# The dir block is still present in the dirstate; this could
1398
# be due to it being in a parent tree, or a corrupt delta.
1399
for child_entry in self._dirblocks[block_i][1]:
1400
if child_entry[1][0][0] not in ('r', 'a'):
1401
self._changes_aborted = True
1402
raise errors.InconsistentDelta(path, entry[0][2],
1403
"The file id was deleted but its children were "
1406
def _apply_insertions(self, adds):
1408
for key, minikind, executable, fingerprint, path_utf8 in sorted(adds):
1409
self.update_minimal(key, minikind, executable, fingerprint,
1410
path_utf8=path_utf8)
1411
except errors.NotVersionedError:
1412
self._changes_aborted = True
1413
raise errors.InconsistentDelta(path_utf8.decode('utf8'), key[2],
1416
def update_basis_by_delta(self, delta, new_revid):
1417
"""Update the parents of this tree after a commit.
1419
This gives the tree one parent, with revision id new_revid. The
1420
inventory delta is applied to the current basis tree to generate the
1421
inventory for the parent new_revid, and all other parent trees are
1424
Note that an exception during the operation of this method will leave
1425
the dirstate in a corrupt state where it should not be saved.
1427
Finally, we expect all changes to be synchronising the basis tree with
1430
:param new_revid: The new revision id for the trees parent.
1431
:param delta: An inventory delta (see apply_inventory_delta) describing
1432
the changes from the current left most parent revision to new_revid.
1434
self._read_dirblocks_if_needed()
1435
self._discard_merge_parents()
1436
if self._ghosts != []:
1437
raise NotImplementedError(self.update_basis_by_delta)
1438
if len(self._parents) == 0:
1439
# setup a blank tree, the most simple way.
1440
empty_parent = DirState.NULL_PARENT_DETAILS
1441
for entry in self._iter_entries():
1442
entry[1].append(empty_parent)
1443
self._parents.append(new_revid)
1445
self._parents[0] = new_revid
1447
delta = sorted(delta, reverse=True)
1451
# The paths this function accepts are unicode and must be encoded as we
1453
encode = cache_utf8.encode
1454
inv_to_entry = self._inv_entry_to_details
1455
# delta is now (deletes, changes), (adds) in reverse lexographical
1457
# deletes in reverse lexographic order are safe to process in situ.
1458
# renames are not, as a rename from any path could go to a path
1459
# lexographically lower, so we transform renames into delete, add pairs,
1460
# expanding them recursively as needed.
1461
# At the same time, to reduce interface friction we convert the input
1462
# inventory entries to dirstate.
1463
root_only = ('', '')
1464
# Accumulate parent references (path_utf8, id), to check for parentless
1465
# items or items placed under files/links/tree-references. We get
1466
# references from every item in the delta that is not a deletion and
1467
# is not itself the root.
1469
# Added ids must not be in the dirstate already. This set holds those
1472
for old_path, new_path, file_id, inv_entry in delta:
1473
if inv_entry is not None and file_id != inv_entry.file_id:
1474
raise errors.InconsistentDelta(new_path, file_id,
1475
"mismatched entry file_id %r" % inv_entry)
1476
if new_path is not None:
1477
if inv_entry is None:
1478
raise errors.InconsistentDelta(new_path, file_id,
1479
"new_path with no entry")
1480
new_path_utf8 = encode(new_path)
1481
# note the parent for validation
1482
dirname_utf8, basename_utf8 = osutils.split(new_path_utf8)
1484
parents.add((dirname_utf8, inv_entry.parent_id))
1485
if old_path is None:
1486
adds.append((None, encode(new_path), file_id,
1487
inv_to_entry(inv_entry), True))
1488
new_ids.add(file_id)
1489
elif new_path is None:
1490
deletes.append((encode(old_path), None, file_id, None, True))
1491
elif (old_path, new_path) != root_only:
1493
# Because renames must preserve their children we must have
1494
# processed all relocations and removes before hand. The sort
1495
# order ensures we've examined the child paths, but we also
1496
# have to execute the removals, or the split to an add/delete
1497
# pair will result in the deleted item being reinserted, or
1498
# renamed items being reinserted twice - and possibly at the
1499
# wrong place. Splitting into a delete/add pair also simplifies
1500
# the handling of entries with ('f', ...), ('r' ...) because
1501
# the target of the 'r' is old_path here, and we add that to
1502
# deletes, meaning that the add handler does not need to check
1503
# for 'r' items on every pass.
1504
self._update_basis_apply_deletes(deletes)
1506
# Split into an add/delete pair recursively.
1507
adds.append((None, new_path_utf8, file_id,
1508
inv_to_entry(inv_entry), False))
1509
# Expunge deletes that we've seen so that deleted/renamed
1510
# children of a rename directory are handled correctly.
1511
new_deletes = reversed(list(self._iter_child_entries(1,
1513
# Remove the current contents of the tree at orig_path, and
1514
# reinsert at the correct new path.
1515
for entry in new_deletes:
1517
source_path = entry[0][0] + '/' + entry[0][1]
1519
source_path = entry[0][1]
1521
target_path = new_path_utf8 + source_path[len(old_path):]
1524
raise AssertionError("cannot rename directory to"
1526
target_path = source_path[len(old_path) + 1:]
1527
adds.append((None, target_path, entry[0][2], entry[1][1], False))
1529
(source_path, target_path, entry[0][2], None, False))
1531
(encode(old_path), new_path, file_id, None, False))
1533
# changes to just the root should not require remove/insertion
1535
changes.append((encode(old_path), encode(new_path), file_id,
1536
inv_to_entry(inv_entry)))
1537
self._check_delta_ids_absent(new_ids, delta, 1)
1539
# Finish expunging deletes/first half of renames.
1540
self._update_basis_apply_deletes(deletes)
1541
# Reinstate second half of renames and new paths.
1542
self._update_basis_apply_adds(adds)
1543
# Apply in-situ changes.
1544
self._update_basis_apply_changes(changes)
1546
self._after_delta_check_parents(parents, 1)
1547
except errors.BzrError, e:
1548
self._changes_aborted = True
1549
if 'integrity error' not in str(e):
1551
# _get_entry raises BzrError when a request is inconsistent; we
1552
# want such errors to be shown as InconsistentDelta - and that
1553
# fits the behaviour we trigger. Partof this is driven by dirstate
1554
# only supporting deltas that turn the basis into a closer fit to
1556
raise errors.InconsistentDeltaDelta(delta, "error from _get_entry.")
1558
self._dirblock_state = DirState.IN_MEMORY_MODIFIED
1559
self._header_state = DirState.IN_MEMORY_MODIFIED
1560
self._id_index = None
1563
def _check_delta_ids_absent(self, new_ids, delta, tree_index):
1564
"""Check that none of the file_ids in new_ids are present in a tree."""
1567
id_index = self._get_id_index()
1568
for file_id in new_ids:
1569
for key in id_index.get(file_id, []):
1570
block_i, entry_i, d_present, f_present = \
1571
self._get_block_entry_index(key[0], key[1], tree_index)
1573
# In a different tree
1575
entry = self._dirblocks[block_i][1][entry_i]
1576
if entry[0][2] != file_id:
1577
# Different file_id, so not what we want.
1579
# NB: No changes made before this helper is called, so no need
1580
# to set the _changes_aborted flag.
1581
raise errors.InconsistentDelta(
1582
("%s/%s" % key[0:2]).decode('utf8'), file_id,
1583
"This file_id is new in the delta but already present in "
1586
def _update_basis_apply_adds(self, adds):
1587
"""Apply a sequence of adds to tree 1 during update_basis_by_delta.
1589
They may be adds, or renames that have been split into add/delete
1592
:param adds: A sequence of adds. Each add is a tuple:
1593
(None, new_path_utf8, file_id, (entry_details), real_add). real_add
1594
is False when the add is the second half of a remove-and-reinsert
1595
pair created to handle renames and deletes.
1597
# Adds are accumulated partly from renames, so can be in any input
1600
# adds is now in lexographic order, which places all parents before
1601
# their children, so we can process it linearly.
1603
for old_path, new_path, file_id, new_details, real_add in adds:
1604
# the entry for this file_id must be in tree 0.
1605
entry = self._get_entry(0, file_id, new_path)
1606
if entry[0] is None or entry[0][2] != file_id:
1607
self._changes_aborted = True
1608
raise errors.InconsistentDelta(new_path, file_id,
1609
'working tree does not contain new entry')
1610
if real_add and entry[1][1][0] not in absent:
1611
self._changes_aborted = True
1612
raise errors.InconsistentDelta(new_path, file_id,
1613
'The entry was considered to be a genuinely new record,'
1614
' but there was already an old record for it.')
1615
# We don't need to update the target of an 'r' because the handling
1616
# of renames turns all 'r' situations into a delete at the original
1618
entry[1][1] = new_details
1620
def _update_basis_apply_changes(self, changes):
1621
"""Apply a sequence of changes to tree 1 during update_basis_by_delta.
1623
:param adds: A sequence of changes. Each change is a tuple:
1624
(path_utf8, path_utf8, file_id, (entry_details))
1627
for old_path, new_path, file_id, new_details in changes:
1628
# the entry for this file_id must be in tree 0.
1629
entry = self._get_entry(0, file_id, new_path)
1630
if entry[0] is None or entry[0][2] != file_id:
1631
self._changes_aborted = True
1632
raise errors.InconsistentDelta(new_path, file_id,
1633
'working tree does not contain new entry')
1634
if (entry[1][0][0] in absent or
1635
entry[1][1][0] in absent):
1636
self._changes_aborted = True
1637
raise errors.InconsistentDelta(new_path, file_id,
1638
'changed considered absent')
1639
entry[1][1] = new_details
1641
def _update_basis_apply_deletes(self, deletes):
1642
"""Apply a sequence of deletes to tree 1 during update_basis_by_delta.
1644
They may be deletes, or renames that have been split into add/delete
1647
:param deletes: A sequence of deletes. Each delete is a tuple:
1648
(old_path_utf8, new_path_utf8, file_id, None, real_delete).
1649
real_delete is True when the desired outcome is an actual deletion
1650
rather than the rename handling logic temporarily deleting a path
1651
during the replacement of a parent.
1653
null = DirState.NULL_PARENT_DETAILS
1654
for old_path, new_path, file_id, _, real_delete in deletes:
1655
if real_delete != (new_path is None):
1656
self._changes_aborted = True
1657
raise AssertionError("bad delete delta")
1658
# the entry for this file_id must be in tree 1.
1659
dirname, basename = osutils.split(old_path)
1660
block_index, entry_index, dir_present, file_present = \
1661
self._get_block_entry_index(dirname, basename, 1)
1662
if not file_present:
1663
self._changes_aborted = True
1664
raise errors.InconsistentDelta(old_path, file_id,
1665
'basis tree does not contain removed entry')
1666
entry = self._dirblocks[block_index][1][entry_index]
1667
if entry[0][2] != file_id:
1668
self._changes_aborted = True
1669
raise errors.InconsistentDelta(old_path, file_id,
1670
'mismatched file_id in tree 1')
1672
if entry[1][0][0] != 'a':
1673
self._changes_aborted = True
1674
raise errors.InconsistentDelta(old_path, file_id,
1675
'This was marked as a real delete, but the WT state'
1676
' claims that it still exists and is versioned.')
1677
del self._dirblocks[block_index][1][entry_index]
1679
if entry[1][0][0] == 'a':
1680
self._changes_aborted = True
1681
raise errors.InconsistentDelta(old_path, file_id,
1682
'The entry was considered a rename, but the source path'
1683
' is marked as absent.')
1684
# For whatever reason, we were asked to rename an entry
1685
# that was originally marked as deleted. This could be
1686
# because we are renaming the parent directory, and the WT
1687
# current state has the file marked as deleted.
1688
elif entry[1][0][0] == 'r':
1689
# implement the rename
1690
del self._dirblocks[block_index][1][entry_index]
1692
# it is being resurrected here, so blank it out temporarily.
1693
self._dirblocks[block_index][1][entry_index][1][1] = null
1695
def _after_delta_check_parents(self, parents, index):
1696
"""Check that parents required by the delta are all intact.
1698
:param parents: An iterable of (path_utf8, file_id) tuples which are
1699
required to be present in tree 'index' at path_utf8 with id file_id
1701
:param index: The column in the dirstate to check for parents in.
1703
for dirname_utf8, file_id in parents:
1704
# Get the entry - the ensures that file_id, dirname_utf8 exists and
1705
# has the right file id.
1706
entry = self._get_entry(index, file_id, dirname_utf8)
1707
if entry[1] is None:
1708
self._changes_aborted = True
1709
raise errors.InconsistentDelta(dirname_utf8.decode('utf8'),
1710
file_id, "This parent is not present.")
1711
# Parents of things must be directories
1712
if entry[1][index][0] != 'd':
1713
self._changes_aborted = True
1714
raise errors.InconsistentDelta(dirname_utf8.decode('utf8'),
1715
file_id, "This parent is not a directory.")
1717
def _observed_sha1(self, entry, sha1, stat_value,
1718
_stat_to_minikind=_stat_to_minikind, _pack_stat=pack_stat):
1719
"""Note the sha1 of a file.
1721
:param entry: The entry the sha1 is for.
1722
:param sha1: The observed sha1.
1723
:param stat_value: The os.lstat for the file.
1726
minikind = _stat_to_minikind[stat_value.st_mode & 0170000]
1730
packed_stat = _pack_stat(stat_value)
1732
if self._cutoff_time is None:
1733
self._sha_cutoff_time()
1734
if (stat_value.st_mtime < self._cutoff_time
1735
and stat_value.st_ctime < self._cutoff_time):
1736
entry[1][0] = ('f', sha1, entry[1][0][2], entry[1][0][3],
1738
self._dirblock_state = DirState.IN_MEMORY_MODIFIED
1740
def _sha_cutoff_time(self):
1741
"""Return cutoff time.
1743
Files modified more recently than this time are at risk of being
1744
undetectably modified and so can't be cached.
1746
# Cache the cutoff time as long as we hold a lock.
1747
# time.time() isn't super expensive (approx 3.38us), but
1748
# when you call it 50,000 times it adds up.
1749
# For comparison, os.lstat() costs 7.2us if it is hot.
1750
self._cutoff_time = int(time.time()) - 3
1751
return self._cutoff_time
1753
def _lstat(self, abspath, entry):
1754
"""Return the os.lstat value for this path."""
1755
return os.lstat(abspath)
1757
def _sha1_file_and_mutter(self, abspath):
1758
# when -Dhashcache is turned on, this is monkey-patched in to log
1760
trace.mutter("dirstate sha1 " + abspath)
1761
return self._sha1_provider.sha1(abspath)
1763
def _is_executable(self, mode, old_executable):
1764
"""Is this file executable?"""
1765
return bool(S_IEXEC & mode)
1767
def _is_executable_win32(self, mode, old_executable):
1768
"""On win32 the executable bit is stored in the dirstate."""
1769
return old_executable
1771
if sys.platform == 'win32':
1772
_is_executable = _is_executable_win32
1774
def _read_link(self, abspath, old_link):
1775
"""Read the target of a symlink"""
1776
# TODO: jam 200700301 On Win32, this could just return the value
1777
# already in memory. However, this really needs to be done at a
1778
# higher level, because there either won't be anything on disk,
1779
# or the thing on disk will be a file.
1780
fs_encoding = osutils._fs_enc
1781
if isinstance(abspath, unicode):
1782
# abspath is defined as the path to pass to lstat. readlink is
1783
# buggy in python < 2.6 (it doesn't encode unicode path into FS
1784
# encoding), so we need to encode ourselves knowing that unicode
1785
# paths are produced by UnicodeDirReader on purpose.
1786
abspath = abspath.encode(fs_encoding)
1787
target = os.readlink(abspath)
1788
if fs_encoding not in ('UTF-8', 'US-ASCII', 'ANSI_X3.4-1968'):
1789
# Change encoding if needed
1790
target = target.decode(fs_encoding).encode('UTF-8')
1793
def get_ghosts(self):
1794
"""Return a list of the parent tree revision ids that are ghosts."""
1795
self._read_header_if_needed()
1798
def get_lines(self):
1799
"""Serialise the entire dirstate to a sequence of lines."""
1800
if (self._header_state == DirState.IN_MEMORY_UNMODIFIED and
1801
self._dirblock_state == DirState.IN_MEMORY_UNMODIFIED):
1802
# read whats on disk.
1803
self._state_file.seek(0)
1804
return self._state_file.readlines()
1806
lines.append(self._get_parents_line(self.get_parent_ids()))
1807
lines.append(self._get_ghosts_line(self._ghosts))
1808
# append the root line which is special cased
1809
lines.extend(map(self._entry_to_line, self._iter_entries()))
1810
return self._get_output_lines(lines)
1812
def _get_ghosts_line(self, ghost_ids):
1813
"""Create a line for the state file for ghost information."""
1814
return '\0'.join([str(len(ghost_ids))] + ghost_ids)
1816
def _get_parents_line(self, parent_ids):
1817
"""Create a line for the state file for parents information."""
1818
return '\0'.join([str(len(parent_ids))] + parent_ids)
1820
def _get_fields_to_entry(self):
1821
"""Get a function which converts entry fields into a entry record.
1823
This handles size and executable, as well as parent records.
1825
:return: A function which takes a list of fields, and returns an
1826
appropriate record for storing in memory.
1828
# This is intentionally unrolled for performance
1829
num_present_parents = self._num_present_parents()
1830
if num_present_parents == 0:
1831
def fields_to_entry_0_parents(fields, _int=int):
1832
path_name_file_id_key = (fields[0], fields[1], fields[2])
1833
return (path_name_file_id_key, [
1835
fields[3], # minikind
1836
fields[4], # fingerprint
1837
_int(fields[5]), # size
1838
fields[6] == 'y', # executable
1839
fields[7], # packed_stat or revision_id
1841
return fields_to_entry_0_parents
1842
elif num_present_parents == 1:
1843
def fields_to_entry_1_parent(fields, _int=int):
1844
path_name_file_id_key = (fields[0], fields[1], fields[2])
1845
return (path_name_file_id_key, [
1847
fields[3], # minikind
1848
fields[4], # fingerprint
1849
_int(fields[5]), # size
1850
fields[6] == 'y', # executable
1851
fields[7], # packed_stat or revision_id
1854
fields[8], # minikind
1855
fields[9], # fingerprint
1856
_int(fields[10]), # size
1857
fields[11] == 'y', # executable
1858
fields[12], # packed_stat or revision_id
1861
return fields_to_entry_1_parent
1862
elif num_present_parents == 2:
1863
def fields_to_entry_2_parents(fields, _int=int):
1864
path_name_file_id_key = (fields[0], fields[1], fields[2])
1865
return (path_name_file_id_key, [
1867
fields[3], # minikind
1868
fields[4], # fingerprint
1869
_int(fields[5]), # size
1870
fields[6] == 'y', # executable
1871
fields[7], # packed_stat or revision_id
1874
fields[8], # minikind
1875
fields[9], # fingerprint
1876
_int(fields[10]), # size
1877
fields[11] == 'y', # executable
1878
fields[12], # packed_stat or revision_id
1881
fields[13], # minikind
1882
fields[14], # fingerprint
1883
_int(fields[15]), # size
1884
fields[16] == 'y', # executable
1885
fields[17], # packed_stat or revision_id
1888
return fields_to_entry_2_parents
1890
def fields_to_entry_n_parents(fields, _int=int):
1891
path_name_file_id_key = (fields[0], fields[1], fields[2])
1892
trees = [(fields[cur], # minikind
1893
fields[cur+1], # fingerprint
1894
_int(fields[cur+2]), # size
1895
fields[cur+3] == 'y', # executable
1896
fields[cur+4], # stat or revision_id
1897
) for cur in xrange(3, len(fields)-1, 5)]
1898
return path_name_file_id_key, trees
1899
return fields_to_entry_n_parents
1901
def get_parent_ids(self):
1902
"""Return a list of the parent tree ids for the directory state."""
1903
self._read_header_if_needed()
1904
return list(self._parents)
1906
def _get_block_entry_index(self, dirname, basename, tree_index):
1907
"""Get the coordinates for a path in the state structure.
1909
:param dirname: The utf8 dirname to lookup.
1910
:param basename: The utf8 basename to lookup.
1911
:param tree_index: The index of the tree for which this lookup should
1913
:return: A tuple describing where the path is located, or should be
1914
inserted. The tuple contains four fields: the block index, the row
1915
index, the directory is present (boolean), the entire path is
1916
present (boolean). There is no guarantee that either
1917
coordinate is currently reachable unless the found field for it is
1918
True. For instance, a directory not present in the searched tree
1919
may be returned with a value one greater than the current highest
1920
block offset. The directory present field will always be True when
1921
the path present field is True. The directory present field does
1922
NOT indicate that the directory is present in the searched tree,
1923
rather it indicates that there are at least some files in some
1926
self._read_dirblocks_if_needed()
1927
key = dirname, basename, ''
1928
block_index, present = self._find_block_index_from_key(key)
1930
# no such directory - return the dir index and 0 for the row.
1931
return block_index, 0, False, False
1932
block = self._dirblocks[block_index][1] # access the entries only
1933
entry_index, present = self._find_entry_index(key, block)
1934
# linear search through entries at this path to find the one
1936
while entry_index < len(block) and block[entry_index][0][1] == basename:
1937
if block[entry_index][1][tree_index][0] not in 'ar':
1938
# neither absent or relocated
1939
return block_index, entry_index, True, True
1941
return block_index, entry_index, True, False
1943
def _get_entry(self, tree_index, fileid_utf8=None, path_utf8=None, include_deleted=False):
1944
"""Get the dirstate entry for path in tree tree_index.
1946
If either file_id or path is supplied, it is used as the key to lookup.
1947
If both are supplied, the fastest lookup is used, and an error is
1948
raised if they do not both point at the same row.
1950
:param tree_index: The index of the tree we wish to locate this path
1951
in. If the path is present in that tree, the entry containing its
1952
details is returned, otherwise (None, None) is returned
1953
0 is the working tree, higher indexes are successive parent
1955
:param fileid_utf8: A utf8 file_id to look up.
1956
:param path_utf8: An utf8 path to be looked up.
1957
:param include_deleted: If True, and performing a lookup via
1958
fileid_utf8 rather than path_utf8, return an entry for deleted
1960
:return: The dirstate entry tuple for path, or (None, None)
1962
self._read_dirblocks_if_needed()
1963
if path_utf8 is not None:
1964
if type(path_utf8) is not str:
1965
raise errors.BzrError('path_utf8 is not a str: %s %r'
1966
% (type(path_utf8), path_utf8))
1967
# path lookups are faster
1968
dirname, basename = osutils.split(path_utf8)
1969
block_index, entry_index, dir_present, file_present = \
1970
self._get_block_entry_index(dirname, basename, tree_index)
1971
if not file_present:
1973
entry = self._dirblocks[block_index][1][entry_index]
1974
if not (entry[0][2] and entry[1][tree_index][0] not in ('a', 'r')):
1975
raise AssertionError('unversioned entry?')
1977
if entry[0][2] != fileid_utf8:
1978
self._changes_aborted = True
1979
raise errors.BzrError('integrity error ? : mismatching'
1980
' tree_index, file_id and path')
1983
possible_keys = self._get_id_index().get(fileid_utf8, None)
1984
if not possible_keys:
1986
for key in possible_keys:
1987
block_index, present = \
1988
self._find_block_index_from_key(key)
1989
# strange, probably indicates an out of date
1990
# id index - for now, allow this.
1993
# WARNING: DO not change this code to use _get_block_entry_index
1994
# as that function is not suitable: it does not use the key
1995
# to lookup, and thus the wrong coordinates are returned.
1996
block = self._dirblocks[block_index][1]
1997
entry_index, present = self._find_entry_index(key, block)
1999
entry = self._dirblocks[block_index][1][entry_index]
2000
if entry[1][tree_index][0] in 'fdlt':
2001
# this is the result we are looking for: the
2002
# real home of this file_id in this tree.
2004
if entry[1][tree_index][0] == 'a':
2005
# there is no home for this entry in this tree
2009
if entry[1][tree_index][0] != 'r':
2010
raise AssertionError(
2011
"entry %r has invalid minikind %r for tree %r" \
2013
entry[1][tree_index][0],
2015
real_path = entry[1][tree_index][1]
2016
return self._get_entry(tree_index, fileid_utf8=fileid_utf8,
2017
path_utf8=real_path)
2021
def initialize(cls, path, sha1_provider=None):
2022
"""Create a new dirstate on path.
2024
The new dirstate will be an empty tree - that is it has no parents,
2025
and only a root node - which has id ROOT_ID.
2027
:param path: The name of the file for the dirstate.
2028
:param sha1_provider: an object meeting the SHA1Provider interface.
2029
If None, a DefaultSHA1Provider is used.
2030
:return: A write-locked DirState object.
2032
# This constructs a new DirState object on a path, sets the _state_file
2033
# to a new empty file for that path. It then calls _set_data() with our
2034
# stock empty dirstate information - a root with ROOT_ID, no children,
2035
# and no parents. Finally it calls save() to ensure that this data will
2037
if sha1_provider is None:
2038
sha1_provider = DefaultSHA1Provider()
2039
result = cls(path, sha1_provider)
2040
# root dir and root dir contents with no children.
2041
empty_tree_dirblocks = [('', []), ('', [])]
2042
# a new root directory, with a NULLSTAT.
2043
empty_tree_dirblocks[0][1].append(
2044
(('', '', inventory.ROOT_ID), [
2045
('d', '', 0, False, DirState.NULLSTAT),
2049
result._set_data([], empty_tree_dirblocks)
2057
def _inv_entry_to_details(inv_entry):
2058
"""Convert an inventory entry (from a revision tree) to state details.
2060
:param inv_entry: An inventory entry whose sha1 and link targets can be
2061
relied upon, and which has a revision set.
2062
:return: A details tuple - the details for a single tree at a path +
2065
kind = inv_entry.kind
2066
minikind = DirState._kind_to_minikind[kind]
2067
tree_data = inv_entry.revision
2068
if kind == 'directory':
2072
elif kind == 'symlink':
2073
if inv_entry.symlink_target is None:
2076
fingerprint = inv_entry.symlink_target.encode('utf8')
2079
elif kind == 'file':
2080
fingerprint = inv_entry.text_sha1 or ''
2081
size = inv_entry.text_size or 0
2082
executable = inv_entry.executable
2083
elif kind == 'tree-reference':
2084
fingerprint = inv_entry.reference_revision or ''
2088
raise Exception("can't pack %s" % inv_entry)
2089
return (minikind, fingerprint, size, executable, tree_data)
2091
def _iter_child_entries(self, tree_index, path_utf8):
2092
"""Iterate over all the entries that are children of path_utf.
2094
This only returns entries that are present (not in 'a', 'r') in
2095
tree_index. tree_index data is not refreshed, so if tree 0 is used,
2096
results may differ from that obtained if paths were statted to
2097
determine what ones were directories.
2099
Asking for the children of a non-directory will return an empty
2103
next_pending_dirs = [path_utf8]
2105
while next_pending_dirs:
2106
pending_dirs = next_pending_dirs
2107
next_pending_dirs = []
2108
for path in pending_dirs:
2109
block_index, present = self._find_block_index_from_key(
2111
if block_index == 0:
2113
if len(self._dirblocks) == 1:
2114
# asked for the children of the root with no other
2118
# children of a non-directory asked for.
2120
block = self._dirblocks[block_index]
2121
for entry in block[1]:
2122
kind = entry[1][tree_index][0]
2123
if kind not in absent:
2127
path = entry[0][0] + '/' + entry[0][1]
2130
next_pending_dirs.append(path)
2132
def _iter_entries(self):
2133
"""Iterate over all the entries in the dirstate.
2135
Each yelt item is an entry in the standard format described in the
2136
docstring of bzrlib.dirstate.
2138
self._read_dirblocks_if_needed()
2139
for directory in self._dirblocks:
2140
for entry in directory[1]:
2143
def _get_id_index(self):
2144
"""Get an id index of self._dirblocks."""
2145
if self._id_index is None:
2147
for key, tree_details in self._iter_entries():
2148
id_index.setdefault(key[2], set()).add(key)
2149
self._id_index = id_index
2150
return self._id_index
2152
def _get_output_lines(self, lines):
2153
"""Format lines for final output.
2155
:param lines: A sequence of lines containing the parents list and the
2158
output_lines = [DirState.HEADER_FORMAT_3]
2159
lines.append('') # a final newline
2160
inventory_text = '\0\n\0'.join(lines)
2161
output_lines.append('crc32: %s\n' % (zlib.crc32(inventory_text),))
2162
# -3, 1 for num parents, 1 for ghosts, 1 for final newline
2163
num_entries = len(lines)-3
2164
output_lines.append('num_entries: %s\n' % (num_entries,))
2165
output_lines.append(inventory_text)
2168
def _make_deleted_row(self, fileid_utf8, parents):
2169
"""Return a deleted row for fileid_utf8."""
2170
return ('/', 'RECYCLED.BIN', 'file', fileid_utf8, 0, DirState.NULLSTAT,
2173
def _num_present_parents(self):
2174
"""The number of parent entries in each record row."""
2175
return len(self._parents) - len(self._ghosts)
2178
def on_file(path, sha1_provider=None):
2179
"""Construct a DirState on the file at path "path".
2181
:param path: The path at which the dirstate file on disk should live.
2182
:param sha1_provider: an object meeting the SHA1Provider interface.
2183
If None, a DefaultSHA1Provider is used.
2184
:return: An unlocked DirState object, associated with the given path.
2186
if sha1_provider is None:
2187
sha1_provider = DefaultSHA1Provider()
2188
result = DirState(path, sha1_provider)
2191
def _read_dirblocks_if_needed(self):
2192
"""Read in all the dirblocks from the file if they are not in memory.
2194
This populates self._dirblocks, and sets self._dirblock_state to
2195
IN_MEMORY_UNMODIFIED. It is not currently ready for incremental block
2198
self._read_header_if_needed()
2199
if self._dirblock_state == DirState.NOT_IN_MEMORY:
2200
_read_dirblocks(self)
2202
def _read_header(self):
2203
"""This reads in the metadata header, and the parent ids.
2205
After reading in, the file should be positioned at the null
2206
just before the start of the first record in the file.
2208
:return: (expected crc checksum, number of entries, parent list)
2210
self._read_prelude()
2211
parent_line = self._state_file.readline()
2212
info = parent_line.split('\0')
2213
num_parents = int(info[0])
2214
self._parents = info[1:-1]
2215
ghost_line = self._state_file.readline()
2216
info = ghost_line.split('\0')
2217
num_ghosts = int(info[1])
2218
self._ghosts = info[2:-1]
2219
self._header_state = DirState.IN_MEMORY_UNMODIFIED
2220
self._end_of_header = self._state_file.tell()
2222
def _read_header_if_needed(self):
2223
"""Read the header of the dirstate file if needed."""
2224
# inline this as it will be called a lot
2225
if not self._lock_token:
2226
raise errors.ObjectNotLocked(self)
2227
if self._header_state == DirState.NOT_IN_MEMORY:
2230
def _read_prelude(self):
2231
"""Read in the prelude header of the dirstate file.
2233
This only reads in the stuff that is not connected to the crc
2234
checksum. The position will be correct to read in the rest of
2235
the file and check the checksum after this point.
2236
The next entry in the file should be the number of parents,
2237
and their ids. Followed by a newline.
2239
header = self._state_file.readline()
2240
if header != DirState.HEADER_FORMAT_3:
2241
raise errors.BzrError(
2242
'invalid header line: %r' % (header,))
2243
crc_line = self._state_file.readline()
2244
if not crc_line.startswith('crc32: '):
2245
raise errors.BzrError('missing crc32 checksum: %r' % crc_line)
2246
self.crc_expected = int(crc_line[len('crc32: '):-1])
2247
num_entries_line = self._state_file.readline()
2248
if not num_entries_line.startswith('num_entries: '):
2249
raise errors.BzrError('missing num_entries line')
2250
self._num_entries = int(num_entries_line[len('num_entries: '):-1])
2252
def sha1_from_stat(self, path, stat_result, _pack_stat=pack_stat):
2253
"""Find a sha1 given a stat lookup."""
2254
return self._get_packed_stat_index().get(_pack_stat(stat_result), None)
2256
def _get_packed_stat_index(self):
2257
"""Get a packed_stat index of self._dirblocks."""
2258
if self._packed_stat_index is None:
2260
for key, tree_details in self._iter_entries():
2261
if tree_details[0][0] == 'f':
2262
index[tree_details[0][4]] = tree_details[0][1]
2263
self._packed_stat_index = index
2264
return self._packed_stat_index
2267
"""Save any pending changes created during this session.
2269
We reuse the existing file, because that prevents race conditions with
2270
file creation, and use oslocks on it to prevent concurrent modification
2271
and reads - because dirstate's incremental data aggregation is not
2272
compatible with reading a modified file, and replacing a file in use by
2273
another process is impossible on Windows.
2275
A dirstate in read only mode should be smart enough though to validate
2276
that the file has not changed, and otherwise discard its cache and
2277
start over, to allow for fine grained read lock duration, so 'status'
2278
wont block 'commit' - for example.
2280
if self._changes_aborted:
2281
# Should this be a warning? For now, I'm expecting that places that
2282
# mark it inconsistent will warn, making a warning here redundant.
2283
trace.mutter('Not saving DirState because '
2284
'_changes_aborted is set.')
2286
if (self._header_state == DirState.IN_MEMORY_MODIFIED or
2287
self._dirblock_state == DirState.IN_MEMORY_MODIFIED):
2289
grabbed_write_lock = False
2290
if self._lock_state != 'w':
2291
grabbed_write_lock, new_lock = self._lock_token.temporary_write_lock()
2292
# Switch over to the new lock, as the old one may be closed.
2293
# TODO: jam 20070315 We should validate the disk file has
2294
# not changed contents. Since temporary_write_lock may
2295
# not be an atomic operation.
2296
self._lock_token = new_lock
2297
self._state_file = new_lock.f
2298
if not grabbed_write_lock:
2299
# We couldn't grab a write lock, so we switch back to a read one
2302
self._state_file.seek(0)
2303
self._state_file.writelines(self.get_lines())
2304
self._state_file.truncate()
2305
self._state_file.flush()
2306
self._header_state = DirState.IN_MEMORY_UNMODIFIED
2307
self._dirblock_state = DirState.IN_MEMORY_UNMODIFIED
2309
if grabbed_write_lock:
2310
self._lock_token = self._lock_token.restore_read_lock()
2311
self._state_file = self._lock_token.f
2312
# TODO: jam 20070315 We should validate the disk file has
2313
# not changed contents. Since restore_read_lock may
2314
# not be an atomic operation.
2316
def _set_data(self, parent_ids, dirblocks):
2317
"""Set the full dirstate data in memory.
2319
This is an internal function used to completely replace the objects
2320
in memory state. It puts the dirstate into state 'full-dirty'.
2322
:param parent_ids: A list of parent tree revision ids.
2323
:param dirblocks: A list containing one tuple for each directory in the
2324
tree. Each tuple contains the directory path and a list of entries
2325
found in that directory.
2327
# our memory copy is now authoritative.
2328
self._dirblocks = dirblocks
2329
self._header_state = DirState.IN_MEMORY_MODIFIED
2330
self._dirblock_state = DirState.IN_MEMORY_MODIFIED
2331
self._parents = list(parent_ids)
2332
self._id_index = None
2333
self._packed_stat_index = None
2335
def set_path_id(self, path, new_id):
2336
"""Change the id of path to new_id in the current working tree.
2338
:param path: The path inside the tree to set - '' is the root, 'foo'
2339
is the path foo in the root.
2340
:param new_id: The new id to assign to the path. This must be a utf8
2341
file id (not unicode, and not None).
2343
self._read_dirblocks_if_needed()
2345
# TODO: logic not written
2346
raise NotImplementedError(self.set_path_id)
2347
# TODO: check new id is unique
2348
entry = self._get_entry(0, path_utf8=path)
2349
if entry[0][2] == new_id:
2350
# Nothing to change.
2352
# mark the old path absent, and insert a new root path
2353
self._make_absent(entry)
2354
self.update_minimal(('', '', new_id), 'd',
2355
path_utf8='', packed_stat=entry[1][0][4])
2356
self._dirblock_state = DirState.IN_MEMORY_MODIFIED
2357
if self._id_index is not None:
2358
self._id_index.setdefault(new_id, set()).add(entry[0])
2360
def set_parent_trees(self, trees, ghosts):
2361
"""Set the parent trees for the dirstate.
2363
:param trees: A list of revision_id, tree tuples. tree must be provided
2364
even if the revision_id refers to a ghost: supply an empty tree in
2366
:param ghosts: A list of the revision_ids that are ghosts at the time
2369
# TODO: generate a list of parent indexes to preserve to save
2370
# processing specific parent trees. In the common case one tree will
2371
# be preserved - the left most parent.
2372
# TODO: if the parent tree is a dirstate, we might want to walk them
2373
# all by path in parallel for 'optimal' common-case performance.
2374
# generate new root row.
2375
self._read_dirblocks_if_needed()
2376
# TODO future sketch: Examine the existing parents to generate a change
2377
# map and then walk the new parent trees only, mapping them into the
2378
# dirstate. Walk the dirstate at the same time to remove unreferenced
2381
# sketch: loop over all entries in the dirstate, cherry picking
2382
# entries from the parent trees, if they are not ghost trees.
2383
# after we finish walking the dirstate, all entries not in the dirstate
2384
# are deletes, so we want to append them to the end as per the design
2385
# discussions. So do a set difference on ids with the parents to
2386
# get deletes, and add them to the end.
2387
# During the update process we need to answer the following questions:
2388
# - find other keys containing a fileid in order to create cross-path
2389
# links. We dont't trivially use the inventory from other trees
2390
# because this leads to either double touching, or to accessing
2392
# - find other keys containing a path
2393
# We accumulate each entry via this dictionary, including the root
2396
# we could do parallel iterators, but because file id data may be
2397
# scattered throughout, we dont save on index overhead: we have to look
2398
# at everything anyway. We can probably save cycles by reusing parent
2399
# data and doing an incremental update when adding an additional
2400
# parent, but for now the common cases are adding a new parent (merge),
2401
# and replacing completely (commit), and commit is more common: so
2402
# optimise merge later.
2404
# ---- start generation of full tree mapping data
2405
# what trees should we use?
2406
parent_trees = [tree for rev_id, tree in trees if rev_id not in ghosts]
2407
# how many trees do we end up with
2408
parent_count = len(parent_trees)
2410
# one: the current tree
2411
for entry in self._iter_entries():
2412
# skip entries not in the current tree
2413
if entry[1][0][0] in 'ar': # absent, relocated
2415
by_path[entry[0]] = [entry[1][0]] + \
2416
[DirState.NULL_PARENT_DETAILS] * parent_count
2417
id_index[entry[0][2]] = set([entry[0]])
2419
# now the parent trees:
2420
for tree_index, tree in enumerate(parent_trees):
2421
# the index is off by one, adjust it.
2422
tree_index = tree_index + 1
2423
# when we add new locations for a fileid we need these ranges for
2424
# any fileid in this tree as we set the by_path[id] to:
2425
# already_processed_tree_details + new_details + new_location_suffix
2426
# the suffix is from tree_index+1:parent_count+1.
2427
new_location_suffix = [DirState.NULL_PARENT_DETAILS] * (parent_count - tree_index)
2428
# now stitch in all the entries from this tree
2429
for path, entry in tree.inventory.iter_entries_by_dir():
2430
# here we process each trees details for each item in the tree.
2431
# we first update any existing entries for the id at other paths,
2432
# then we either create or update the entry for the id at the
2433
# right path, and finally we add (if needed) a mapping from
2434
# file_id to this path. We do it in this order to allow us to
2435
# avoid checking all known paths for the id when generating a
2436
# new entry at this path: by adding the id->path mapping last,
2437
# all the mappings are valid and have correct relocation
2438
# records where needed.
2439
file_id = entry.file_id
2440
path_utf8 = path.encode('utf8')
2441
dirname, basename = osutils.split(path_utf8)
2442
new_entry_key = (dirname, basename, file_id)
2443
# tree index consistency: All other paths for this id in this tree
2444
# index must point to the correct path.
2445
for entry_key in id_index.setdefault(file_id, set()):
2446
# TODO:PROFILING: It might be faster to just update
2447
# rather than checking if we need to, and then overwrite
2448
# the one we are located at.
2449
if entry_key != new_entry_key:
2450
# this file id is at a different path in one of the
2451
# other trees, so put absent pointers there
2452
# This is the vertical axis in the matrix, all pointing
2454
by_path[entry_key][tree_index] = ('r', path_utf8, 0, False, '')
2455
# by path consistency: Insert into an existing path record (trivial), or
2456
# add a new one with relocation pointers for the other tree indexes.
2457
if new_entry_key in id_index[file_id]:
2458
# there is already an entry where this data belongs, just insert it.
2459
by_path[new_entry_key][tree_index] = \
2460
self._inv_entry_to_details(entry)
2462
# add relocated entries to the horizontal axis - this row
2463
# mapping from path,id. We need to look up the correct path
2464
# for the indexes from 0 to tree_index -1
2466
for lookup_index in xrange(tree_index):
2467
# boundary case: this is the first occurence of file_id
2468
# so there are no id_indexs, possibly take this out of
2470
if not len(id_index[file_id]):
2471
new_details.append(DirState.NULL_PARENT_DETAILS)
2473
# grab any one entry, use it to find the right path.
2474
# TODO: optimise this to reduce memory use in highly
2475
# fragmented situations by reusing the relocation
2477
a_key = iter(id_index[file_id]).next()
2478
if by_path[a_key][lookup_index][0] in ('r', 'a'):
2479
# its a pointer or missing statement, use it as is.
2480
new_details.append(by_path[a_key][lookup_index])
2482
# we have the right key, make a pointer to it.
2483
real_path = ('/'.join(a_key[0:2])).strip('/')
2484
new_details.append(('r', real_path, 0, False, ''))
2485
new_details.append(self._inv_entry_to_details(entry))
2486
new_details.extend(new_location_suffix)
2487
by_path[new_entry_key] = new_details
2488
id_index[file_id].add(new_entry_key)
2489
# --- end generation of full tree mappings
2491
# sort and output all the entries
2492
new_entries = self._sort_entries(by_path.items())
2493
self._entries_to_current_state(new_entries)
2494
self._parents = [rev_id for rev_id, tree in trees]
2495
self._ghosts = list(ghosts)
2496
self._header_state = DirState.IN_MEMORY_MODIFIED
2497
self._dirblock_state = DirState.IN_MEMORY_MODIFIED
2498
self._id_index = id_index
2500
def _sort_entries(self, entry_list):
2501
"""Given a list of entries, sort them into the right order.
2503
This is done when constructing a new dirstate from trees - normally we
2504
try to keep everything in sorted blocks all the time, but sometimes
2505
it's easier to sort after the fact.
2508
# sort by: directory parts, file name, file id
2509
return entry[0][0].split('/'), entry[0][1], entry[0][2]
2510
return sorted(entry_list, key=_key)
2512
def set_state_from_inventory(self, new_inv):
2513
"""Set new_inv as the current state.
2515
This API is called by tree transform, and will usually occur with
2516
existing parent trees.
2518
:param new_inv: The inventory object to set current state from.
2520
if 'evil' in debug.debug_flags:
2521
trace.mutter_callsite(1,
2522
"set_state_from_inventory called; please mutate the tree instead")
2523
tracing = 'dirstate' in debug.debug_flags
2525
trace.mutter("set_state_from_inventory trace:")
2526
self._read_dirblocks_if_needed()
2528
# Two iterators: current data and new data, both in dirblock order.
2529
# We zip them together, which tells about entries that are new in the
2530
# inventory, or removed in the inventory, or present in both and
2533
# You might think we could just synthesize a new dirstate directly
2534
# since we're processing it in the right order. However, we need to
2535
# also consider there may be any number of parent trees and relocation
2536
# pointers, and we don't want to duplicate that here.
2537
new_iterator = new_inv.iter_entries_by_dir()
2538
# we will be modifying the dirstate, so we need a stable iterator. In
2539
# future we might write one, for now we just clone the state into a
2540
# list using a copy so that we see every original item and don't have
2541
# to adjust the position when items are inserted or deleted in the
2542
# underlying dirstate.
2543
old_iterator = iter(list(self._iter_entries()))
2544
# both must have roots so this is safe:
2545
current_new = new_iterator.next()
2546
current_old = old_iterator.next()
2547
def advance(iterator):
2549
return iterator.next()
2550
except StopIteration:
2552
while current_new or current_old:
2553
# skip entries in old that are not really there
2554
if current_old and current_old[1][0][0] in 'ar':
2555
# relocated or absent
2556
current_old = advance(old_iterator)
2559
# convert new into dirblock style
2560
new_path_utf8 = current_new[0].encode('utf8')
2561
new_dirname, new_basename = osutils.split(new_path_utf8)
2562
new_id = current_new[1].file_id
2563
new_entry_key = (new_dirname, new_basename, new_id)
2564
current_new_minikind = \
2565
DirState._kind_to_minikind[current_new[1].kind]
2566
if current_new_minikind == 't':
2567
fingerprint = current_new[1].reference_revision or ''
2569
# We normally only insert or remove records, or update
2570
# them when it has significantly changed. Then we want to
2571
# erase its fingerprint. Unaffected records should
2572
# normally not be updated at all.
2575
# for safety disable variables
2576
new_path_utf8 = new_dirname = new_basename = new_id = \
2577
new_entry_key = None
2578
# 5 cases, we dont have a value that is strictly greater than everything, so
2579
# we make both end conditions explicit
2581
# old is finished: insert current_new into the state.
2583
trace.mutter("Appending from new '%s'.",
2584
new_path_utf8.decode('utf8'))
2585
self.update_minimal(new_entry_key, current_new_minikind,
2586
executable=current_new[1].executable,
2587
path_utf8=new_path_utf8, fingerprint=fingerprint,
2589
current_new = advance(new_iterator)
2590
elif not current_new:
2593
trace.mutter("Truncating from old '%s/%s'.",
2594
current_old[0][0].decode('utf8'),
2595
current_old[0][1].decode('utf8'))
2596
self._make_absent(current_old)
2597
current_old = advance(old_iterator)
2598
elif new_entry_key == current_old[0]:
2599
# same - common case
2600
# We're looking at the same path and id in both the dirstate
2601
# and inventory, so just need to update the fields in the
2602
# dirstate from the one in the inventory.
2603
# TODO: update the record if anything significant has changed.
2604
# the minimal required trigger is if the execute bit or cached
2606
if (current_old[1][0][3] != current_new[1].executable or
2607
current_old[1][0][0] != current_new_minikind):
2609
trace.mutter("Updating in-place change '%s'.",
2610
new_path_utf8.decode('utf8'))
2611
self.update_minimal(current_old[0], current_new_minikind,
2612
executable=current_new[1].executable,
2613
path_utf8=new_path_utf8, fingerprint=fingerprint,
2615
# both sides are dealt with, move on
2616
current_old = advance(old_iterator)
2617
current_new = advance(new_iterator)
2618
elif (cmp_by_dirs(new_dirname, current_old[0][0]) < 0
2619
or (new_dirname == current_old[0][0]
2620
and new_entry_key[1:] < current_old[0][1:])):
2622
# add a entry for this and advance new
2624
trace.mutter("Inserting from new '%s'.",
2625
new_path_utf8.decode('utf8'))
2626
self.update_minimal(new_entry_key, current_new_minikind,
2627
executable=current_new[1].executable,
2628
path_utf8=new_path_utf8, fingerprint=fingerprint,
2630
current_new = advance(new_iterator)
2632
# we've advanced past the place where the old key would be,
2633
# without seeing it in the new list. so it must be gone.
2635
trace.mutter("Deleting from old '%s/%s'.",
2636
current_old[0][0].decode('utf8'),
2637
current_old[0][1].decode('utf8'))
2638
self._make_absent(current_old)
2639
current_old = advance(old_iterator)
2640
self._dirblock_state = DirState.IN_MEMORY_MODIFIED
2641
self._id_index = None
2642
self._packed_stat_index = None
2644
trace.mutter("set_state_from_inventory complete.")
2646
def _make_absent(self, current_old):
2647
"""Mark current_old - an entry - as absent for tree 0.
2649
:return: True if this was the last details entry for the entry key:
2650
that is, if the underlying block has had the entry removed, thus
2651
shrinking in length.
2653
# build up paths that this id will be left at after the change is made,
2654
# so we can update their cross references in tree 0
2655
all_remaining_keys = set()
2656
# Dont check the working tree, because it's going.
2657
for details in current_old[1][1:]:
2658
if details[0] not in 'ar': # absent, relocated
2659
all_remaining_keys.add(current_old[0])
2660
elif details[0] == 'r': # relocated
2661
# record the key for the real path.
2662
all_remaining_keys.add(tuple(osutils.split(details[1])) + (current_old[0][2],))
2663
# absent rows are not present at any path.
2664
last_reference = current_old[0] not in all_remaining_keys
2666
# the current row consists entire of the current item (being marked
2667
# absent), and relocated or absent entries for the other trees:
2668
# Remove it, its meaningless.
2669
block = self._find_block(current_old[0])
2670
entry_index, present = self._find_entry_index(current_old[0], block[1])
2672
raise AssertionError('could not find entry for %s' % (current_old,))
2673
block[1].pop(entry_index)
2674
# if we have an id_index in use, remove this key from it for this id.
2675
if self._id_index is not None:
2676
self._id_index[current_old[0][2]].remove(current_old[0])
2677
# update all remaining keys for this id to record it as absent. The
2678
# existing details may either be the record we are marking as deleted
2679
# (if there were other trees with the id present at this path), or may
2681
for update_key in all_remaining_keys:
2682
update_block_index, present = \
2683
self._find_block_index_from_key(update_key)
2685
raise AssertionError('could not find block for %s' % (update_key,))
2686
update_entry_index, present = \
2687
self._find_entry_index(update_key, self._dirblocks[update_block_index][1])
2689
raise AssertionError('could not find entry for %s' % (update_key,))
2690
update_tree_details = self._dirblocks[update_block_index][1][update_entry_index][1]
2691
# it must not be absent at the moment
2692
if update_tree_details[0][0] == 'a': # absent
2693
raise AssertionError('bad row %r' % (update_tree_details,))
2694
update_tree_details[0] = DirState.NULL_PARENT_DETAILS
2695
self._dirblock_state = DirState.IN_MEMORY_MODIFIED
2696
return last_reference
2698
def update_minimal(self, key, minikind, executable=False, fingerprint='',
2699
packed_stat=None, size=0, path_utf8=None, fullscan=False):
2700
"""Update an entry to the state in tree 0.
2702
This will either create a new entry at 'key' or update an existing one.
2703
It also makes sure that any other records which might mention this are
2706
:param key: (dir, name, file_id) for the new entry
2707
:param minikind: The type for the entry ('f' == 'file', 'd' ==
2709
:param executable: Should the executable bit be set?
2710
:param fingerprint: Simple fingerprint for new entry: canonical-form
2711
sha1 for files, referenced revision id for subtrees, etc.
2712
:param packed_stat: Packed stat value for new entry.
2713
:param size: Size information for new entry
2714
:param path_utf8: key[0] + '/' + key[1], just passed in to avoid doing
2716
:param fullscan: If True then a complete scan of the dirstate is being
2717
done and checking for duplicate rows should not be done. This
2718
should only be set by set_state_from_inventory and similar methods.
2720
If packed_stat and fingerprint are not given, they're invalidated in
2723
block = self._find_block(key)[1]
2724
if packed_stat is None:
2725
packed_stat = DirState.NULLSTAT
2726
# XXX: Some callers pass '' as the packed_stat, and it seems to be
2727
# sometimes present in the dirstate - this seems oddly inconsistent.
2729
entry_index, present = self._find_entry_index(key, block)
2730
new_details = (minikind, fingerprint, size, executable, packed_stat)
2731
id_index = self._get_id_index()
2733
# New record. Check there isn't a entry at this path already.
2735
low_index, _ = self._find_entry_index(key[0:2] + ('',), block)
2736
while low_index < len(block):
2737
entry = block[low_index]
2738
if entry[0][0:2] == key[0:2]:
2739
if entry[1][0][0] not in 'ar':
2740
# This entry has the same path (but a different id) as
2741
# the new entry we're adding, and is present in ths
2743
raise errors.InconsistentDelta(
2744
("%s/%s" % key[0:2]).decode('utf8'), key[2],
2745
"Attempt to add item at path already occupied by "
2746
"id %r" % entry[0][2])
2750
# new entry, synthesis cross reference here,
2751
existing_keys = id_index.setdefault(key[2], set())
2752
if not existing_keys:
2753
# not currently in the state, simplest case
2754
new_entry = key, [new_details] + self._empty_parent_info()
2756
# present at one or more existing other paths.
2757
# grab one of them and use it to generate parent
2758
# relocation/absent entries.
2759
new_entry = key, [new_details]
2760
# existing_keys can be changed as we iterate.
2761
for other_key in tuple(existing_keys):
2762
# change the record at other to be a pointer to this new
2763
# record. The loop looks similar to the change to
2764
# relocations when updating an existing record but its not:
2765
# the test for existing kinds is different: this can be
2766
# factored out to a helper though.
2767
other_block_index, present = self._find_block_index_from_key(
2770
raise AssertionError('could not find block for %s' % (
2772
other_block = self._dirblocks[other_block_index][1]
2773
other_entry_index, present = self._find_entry_index(
2774
other_key, other_block)
2776
raise AssertionError(
2777
'update_minimal: could not find other entry for %s'
2779
if path_utf8 is None:
2780
raise AssertionError('no path')
2781
# Turn this other location into a reference to the new
2782
# location. This also updates the aliased iterator
2783
# (current_old in set_state_from_inventory) so that the old
2784
# entry, if not already examined, is skipped over by that
2786
other_entry = other_block[other_entry_index]
2787
other_entry[1][0] = ('r', path_utf8, 0, False, '')
2788
self._maybe_remove_row(other_block, other_entry_index,
2792
# adds a tuple to the new details for each column
2793
# - either by copying an existing relocation pointer inside that column
2794
# - or by creating a new pointer to the right row inside that column
2795
num_present_parents = self._num_present_parents()
2796
if num_present_parents:
2797
other_key = list(existing_keys)[0]
2798
for lookup_index in xrange(1, num_present_parents + 1):
2799
# grab any one entry, use it to find the right path.
2800
# TODO: optimise this to reduce memory use in highly
2801
# fragmented situations by reusing the relocation
2803
update_block_index, present = \
2804
self._find_block_index_from_key(other_key)
2806
raise AssertionError('could not find block for %s' % (other_key,))
2807
update_entry_index, present = \
2808
self._find_entry_index(other_key, self._dirblocks[update_block_index][1])
2810
raise AssertionError('update_minimal: could not find entry for %s' % (other_key,))
2811
update_details = self._dirblocks[update_block_index][1][update_entry_index][1][lookup_index]
2812
if update_details[0] in 'ar': # relocated, absent
2813
# its a pointer or absent in lookup_index's tree, use
2815
new_entry[1].append(update_details)
2817
# we have the right key, make a pointer to it.
2818
pointer_path = osutils.pathjoin(*other_key[0:2])
2819
new_entry[1].append(('r', pointer_path, 0, False, ''))
2820
block.insert(entry_index, new_entry)
2821
existing_keys.add(key)
2823
# Does the new state matter?
2824
block[entry_index][1][0] = new_details
2825
# parents cannot be affected by what we do.
2826
# other occurences of this id can be found
2827
# from the id index.
2829
# tree index consistency: All other paths for this id in this tree
2830
# index must point to the correct path. We have to loop here because
2831
# we may have passed entries in the state with this file id already
2832
# that were absent - where parent entries are - and they need to be
2833
# converted to relocated.
2834
if path_utf8 is None:
2835
raise AssertionError('no path')
2836
for entry_key in id_index.setdefault(key[2], set()):
2837
# TODO:PROFILING: It might be faster to just update
2838
# rather than checking if we need to, and then overwrite
2839
# the one we are located at.
2840
if entry_key != key:
2841
# this file id is at a different path in one of the
2842
# other trees, so put absent pointers there
2843
# This is the vertical axis in the matrix, all pointing
2845
block_index, present = self._find_block_index_from_key(entry_key)
2847
raise AssertionError('not present: %r', entry_key)
2848
entry_index, present = self._find_entry_index(entry_key, self._dirblocks[block_index][1])
2850
raise AssertionError('not present: %r', entry_key)
2851
self._dirblocks[block_index][1][entry_index][1][0] = \
2852
('r', path_utf8, 0, False, '')
2853
# add a containing dirblock if needed.
2854
if new_details[0] == 'd':
2855
subdir_key = (osutils.pathjoin(*key[0:2]), '', '')
2856
block_index, present = self._find_block_index_from_key(subdir_key)
2858
self._dirblocks.insert(block_index, (subdir_key[0], []))
2860
self._dirblock_state = DirState.IN_MEMORY_MODIFIED
2862
def _maybe_remove_row(self, block, index, id_index):
2863
"""Remove index if it is absent or relocated across the row.
2865
id_index is updated accordingly.
2867
present_in_row = False
2868
entry = block[index]
2869
for column in entry[1]:
2870
if column[0] not in 'ar':
2871
present_in_row = True
2873
if not present_in_row:
2875
id_index[entry[0][2]].remove(entry[0])
2877
def _validate(self):
2878
"""Check that invariants on the dirblock are correct.
2880
This can be useful in debugging; it shouldn't be necessary in
2883
This must be called with a lock held.
2885
# NOTE: This must always raise AssertionError not just assert,
2886
# otherwise it may not behave properly under python -O
2888
# TODO: All entries must have some content that's not 'a' or 'r',
2889
# otherwise it could just be removed.
2891
# TODO: All relocations must point directly to a real entry.
2893
# TODO: No repeated keys.
2896
from pprint import pformat
2897
self._read_dirblocks_if_needed()
2898
if len(self._dirblocks) > 0:
2899
if not self._dirblocks[0][0] == '':
2900
raise AssertionError(
2901
"dirblocks don't start with root block:\n" + \
2902
pformat(self._dirblocks))
2903
if len(self._dirblocks) > 1:
2904
if not self._dirblocks[1][0] == '':
2905
raise AssertionError(
2906
"dirblocks missing root directory:\n" + \
2907
pformat(self._dirblocks))
2908
# the dirblocks are sorted by their path components, name, and dir id
2909
dir_names = [d[0].split('/')
2910
for d in self._dirblocks[1:]]
2911
if dir_names != sorted(dir_names):
2912
raise AssertionError(
2913
"dir names are not in sorted order:\n" + \
2914
pformat(self._dirblocks) + \
2917
for dirblock in self._dirblocks:
2918
# within each dirblock, the entries are sorted by filename and
2920
for entry in dirblock[1]:
2921
if dirblock[0] != entry[0][0]:
2922
raise AssertionError(
2924
"doesn't match directory name in\n%r" %
2925
(entry, pformat(dirblock)))
2926
if dirblock[1] != sorted(dirblock[1]):
2927
raise AssertionError(
2928
"dirblock for %r is not sorted:\n%s" % \
2929
(dirblock[0], pformat(dirblock)))
2931
def check_valid_parent():
2932
"""Check that the current entry has a valid parent.
2934
This makes sure that the parent has a record,
2935
and that the parent isn't marked as "absent" in the
2936
current tree. (It is invalid to have a non-absent file in an absent
2939
if entry[0][0:2] == ('', ''):
2940
# There should be no parent for the root row
2942
parent_entry = self._get_entry(tree_index, path_utf8=entry[0][0])
2943
if parent_entry == (None, None):
2944
raise AssertionError(
2945
"no parent entry for: %s in tree %s"
2946
% (this_path, tree_index))
2947
if parent_entry[1][tree_index][0] != 'd':
2948
raise AssertionError(
2949
"Parent entry for %s is not marked as a valid"
2950
" directory. %s" % (this_path, parent_entry,))
2952
# For each file id, for each tree: either
2953
# the file id is not present at all; all rows with that id in the
2954
# key have it marked as 'absent'
2955
# OR the file id is present under exactly one name; any other entries
2956
# that mention that id point to the correct name.
2958
# We check this with a dict per tree pointing either to the present
2959
# name, or None if absent.
2960
tree_count = self._num_present_parents() + 1
2961
id_path_maps = [dict() for i in range(tree_count)]
2962
# Make sure that all renamed entries point to the correct location.
2963
for entry in self._iter_entries():
2964
file_id = entry[0][2]
2965
this_path = osutils.pathjoin(entry[0][0], entry[0][1])
2966
if len(entry[1]) != tree_count:
2967
raise AssertionError(
2968
"wrong number of entry details for row\n%s" \
2969
",\nexpected %d" % \
2970
(pformat(entry), tree_count))
2971
absent_positions = 0
2972
for tree_index, tree_state in enumerate(entry[1]):
2973
this_tree_map = id_path_maps[tree_index]
2974
minikind = tree_state[0]
2975
if minikind in 'ar':
2976
absent_positions += 1
2977
# have we seen this id before in this column?
2978
if file_id in this_tree_map:
2979
previous_path, previous_loc = this_tree_map[file_id]
2980
# any later mention of this file must be consistent with
2981
# what was said before
2983
if previous_path is not None:
2984
raise AssertionError(
2985
"file %s is absent in row %r but also present " \
2987
(file_id, entry, previous_path))
2988
elif minikind == 'r':
2989
target_location = tree_state[1]
2990
if previous_path != target_location:
2991
raise AssertionError(
2992
"file %s relocation in row %r but also at %r" \
2993
% (file_id, entry, previous_path))
2995
# a file, directory, etc - may have been previously
2996
# pointed to by a relocation, which must point here
2997
if previous_path != this_path:
2998
raise AssertionError(
2999
"entry %r inconsistent with previous path %r "
3001
(entry, previous_path, previous_loc))
3002
check_valid_parent()
3005
# absent; should not occur anywhere else
3006
this_tree_map[file_id] = None, this_path
3007
elif minikind == 'r':
3008
# relocation, must occur at expected location
3009
this_tree_map[file_id] = tree_state[1], this_path
3011
this_tree_map[file_id] = this_path, this_path
3012
check_valid_parent()
3013
if absent_positions == tree_count:
3014
raise AssertionError(
3015
"entry %r has no data for any tree." % (entry,))
3017
def _wipe_state(self):
3018
"""Forget all state information about the dirstate."""
3019
self._header_state = DirState.NOT_IN_MEMORY
3020
self._dirblock_state = DirState.NOT_IN_MEMORY
3021
self._changes_aborted = False
3024
self._dirblocks = []
3025
self._id_index = None
3026
self._packed_stat_index = None
3027
self._end_of_header = None
3028
self._cutoff_time = None
3029
self._split_path_cache = {}
3031
def lock_read(self):
3032
"""Acquire a read lock on the dirstate."""
3033
if self._lock_token is not None:
3034
raise errors.LockContention(self._lock_token)
3035
# TODO: jam 20070301 Rather than wiping completely, if the blocks are
3036
# already in memory, we could read just the header and check for
3037
# any modification. If not modified, we can just leave things
3039
self._lock_token = lock.ReadLock(self._filename)
3040
self._lock_state = 'r'
3041
self._state_file = self._lock_token.f
3044
def lock_write(self):
3045
"""Acquire a write lock on the dirstate."""
3046
if self._lock_token is not None:
3047
raise errors.LockContention(self._lock_token)
3048
# TODO: jam 20070301 Rather than wiping completely, if the blocks are
3049
# already in memory, we could read just the header and check for
3050
# any modification. If not modified, we can just leave things
3052
self._lock_token = lock.WriteLock(self._filename)
3053
self._lock_state = 'w'
3054
self._state_file = self._lock_token.f
3058
"""Drop any locks held on the dirstate."""
3059
if self._lock_token is None:
3060
raise errors.LockNotHeld(self)
3061
# TODO: jam 20070301 Rather than wiping completely, if the blocks are
3062
# already in memory, we could read just the header and check for
3063
# any modification. If not modified, we can just leave things
3065
self._state_file = None
3066
self._lock_state = None
3067
self._lock_token.unlock()
3068
self._lock_token = None
3069
self._split_path_cache = {}
3071
def _requires_lock(self):
3072
"""Check that a lock is currently held by someone on the dirstate."""
3073
if not self._lock_token:
3074
raise errors.ObjectNotLocked(self)
3077
def py_update_entry(state, entry, abspath, stat_value,
3078
_stat_to_minikind=DirState._stat_to_minikind,
3079
_pack_stat=pack_stat):
3080
"""Update the entry based on what is actually on disk.
3082
This function only calculates the sha if it needs to - if the entry is
3083
uncachable, or clearly different to the first parent's entry, no sha
3084
is calculated, and None is returned.
3086
:param state: The dirstate this entry is in.
3087
:param entry: This is the dirblock entry for the file in question.
3088
:param abspath: The path on disk for this file.
3089
:param stat_value: The stat value done on the path.
3090
:return: None, or The sha1 hexdigest of the file (40 bytes) or link
3091
target of a symlink.
3094
minikind = _stat_to_minikind[stat_value.st_mode & 0170000]
3098
packed_stat = _pack_stat(stat_value)
3099
(saved_minikind, saved_link_or_sha1, saved_file_size,
3100
saved_executable, saved_packed_stat) = entry[1][0]
3102
if minikind == 'd' and saved_minikind == 't':
3104
if (minikind == saved_minikind
3105
and packed_stat == saved_packed_stat):
3106
# The stat hasn't changed since we saved, so we can re-use the
3111
# size should also be in packed_stat
3112
if saved_file_size == stat_value.st_size:
3113
return saved_link_or_sha1
3115
# If we have gotten this far, that means that we need to actually
3116
# process this entry.
3119
executable = state._is_executable(stat_value.st_mode,
3121
if state._cutoff_time is None:
3122
state._sha_cutoff_time()
3123
if (stat_value.st_mtime < state._cutoff_time
3124
and stat_value.st_ctime < state._cutoff_time
3125
and len(entry[1]) > 1
3126
and entry[1][1][0] != 'a'):
3127
# Could check for size changes for further optimised
3128
# avoidance of sha1's. However the most prominent case of
3129
# over-shaing is during initial add, which this catches.
3130
# Besides, if content filtering happens, size and sha
3131
# are calculated at the same time, so checking just the size
3132
# gains nothing w.r.t. performance.
3133
link_or_sha1 = state._sha1_file(abspath)
3134
entry[1][0] = ('f', link_or_sha1, stat_value.st_size,
3135
executable, packed_stat)
3137
entry[1][0] = ('f', '', stat_value.st_size,
3138
executable, DirState.NULLSTAT)
3139
elif minikind == 'd':
3141
entry[1][0] = ('d', '', 0, False, packed_stat)
3142
if saved_minikind != 'd':
3143
# This changed from something into a directory. Make sure we
3144
# have a directory block for it. This doesn't happen very
3145
# often, so this doesn't have to be super fast.
3146
block_index, entry_index, dir_present, file_present = \
3147
state._get_block_entry_index(entry[0][0], entry[0][1], 0)
3148
state._ensure_block(block_index, entry_index,
3149
osutils.pathjoin(entry[0][0], entry[0][1]))
3150
elif minikind == 'l':
3151
link_or_sha1 = state._read_link(abspath, saved_link_or_sha1)
3152
if state._cutoff_time is None:
3153
state._sha_cutoff_time()
3154
if (stat_value.st_mtime < state._cutoff_time
3155
and stat_value.st_ctime < state._cutoff_time):
3156
entry[1][0] = ('l', link_or_sha1, stat_value.st_size,
3159
entry[1][0] = ('l', '', stat_value.st_size,
3160
False, DirState.NULLSTAT)
3161
state._dirblock_state = DirState.IN_MEMORY_MODIFIED
3165
class ProcessEntryPython(object):
3167
__slots__ = ["old_dirname_to_file_id", "new_dirname_to_file_id",
3168
"last_source_parent", "last_target_parent", "include_unchanged",
3169
"partial", "use_filesystem_for_exec", "utf8_decode",
3170
"searched_specific_files", "search_specific_files",
3171
"searched_exact_paths", "search_specific_file_parents", "seen_ids",
3172
"state", "source_index", "target_index", "want_unversioned", "tree"]
3174
def __init__(self, include_unchanged, use_filesystem_for_exec,
3175
search_specific_files, state, source_index, target_index,
3176
want_unversioned, tree):
3177
self.old_dirname_to_file_id = {}
3178
self.new_dirname_to_file_id = {}
3179
# Are we doing a partial iter_changes?
3180
self.partial = search_specific_files != set([''])
3181
# Using a list so that we can access the values and change them in
3182
# nested scope. Each one is [path, file_id, entry]
3183
self.last_source_parent = [None, None]
3184
self.last_target_parent = [None, None]
3185
self.include_unchanged = include_unchanged
3186
self.use_filesystem_for_exec = use_filesystem_for_exec
3187
self.utf8_decode = cache_utf8._utf8_decode
3188
# for all search_indexs in each path at or under each element of
3189
# search_specific_files, if the detail is relocated: add the id, and
3190
# add the relocated path as one to search if its not searched already.
3191
# If the detail is not relocated, add the id.
3192
self.searched_specific_files = set()
3193
# When we search exact paths without expanding downwards, we record
3195
self.searched_exact_paths = set()
3196
self.search_specific_files = search_specific_files
3197
# The parents up to the root of the paths we are searching.
3198
# After all normal paths are returned, these specific items are returned.
3199
self.search_specific_file_parents = set()
3200
# The ids we've sent out in the delta.
3201
self.seen_ids = set()
3203
self.source_index = source_index
3204
self.target_index = target_index
3205
if target_index != 0:
3206
# A lot of code in here depends on target_index == 0
3207
raise errors.BzrError('unsupported target index')
3208
self.want_unversioned = want_unversioned
3211
def _process_entry(self, entry, path_info, pathjoin=osutils.pathjoin):
3212
"""Compare an entry and real disk to generate delta information.
3214
:param path_info: top_relpath, basename, kind, lstat, abspath for
3215
the path of entry. If None, then the path is considered absent in
3216
the target (Perhaps we should pass in a concrete entry for this ?)
3217
Basename is returned as a utf8 string because we expect this
3218
tuple will be ignored, and don't want to take the time to
3220
:return: (iter_changes_result, changed). If the entry has not been
3221
handled then changed is None. Otherwise it is False if no content
3222
or metadata changes have occurred, and True if any content or
3223
metadata change has occurred. If self.include_unchanged is True then
3224
if changed is not None, iter_changes_result will always be a result
3225
tuple. Otherwise, iter_changes_result is None unless changed is
3228
if self.source_index is None:
3229
source_details = DirState.NULL_PARENT_DETAILS
3231
source_details = entry[1][self.source_index]
3232
target_details = entry[1][self.target_index]
3233
target_minikind = target_details[0]
3234
if path_info is not None and target_minikind in 'fdlt':
3235
if not (self.target_index == 0):
3236
raise AssertionError()
3237
link_or_sha1 = update_entry(self.state, entry,
3238
abspath=path_info[4], stat_value=path_info[3])
3239
# The entry may have been modified by update_entry
3240
target_details = entry[1][self.target_index]
3241
target_minikind = target_details[0]
3244
file_id = entry[0][2]
3245
source_minikind = source_details[0]
3246
if source_minikind in 'fdltr' and target_minikind in 'fdlt':
3247
# claimed content in both: diff
3248
# r | fdlt | | add source to search, add id path move and perform
3249
# | | | diff check on source-target
3250
# r | fdlt | a | dangling file that was present in the basis.
3252
if source_minikind in 'r':
3253
# add the source to the search path to find any children it
3254
# has. TODO ? : only add if it is a container ?
3255
if not osutils.is_inside_any(self.searched_specific_files,
3257
self.search_specific_files.add(source_details[1])
3258
# generate the old path; this is needed for stating later
3260
old_path = source_details[1]
3261
old_dirname, old_basename = os.path.split(old_path)
3262
path = pathjoin(entry[0][0], entry[0][1])
3263
old_entry = self.state._get_entry(self.source_index,
3265
# update the source details variable to be the real
3267
if old_entry == (None, None):
3268
raise errors.CorruptDirstate(self.state._filename,
3269
"entry '%s/%s' is considered renamed from %r"
3270
" but source does not exist\n"
3271
"entry: %s" % (entry[0][0], entry[0][1], old_path, entry))
3272
source_details = old_entry[1][self.source_index]
3273
source_minikind = source_details[0]
3275
old_dirname = entry[0][0]
3276
old_basename = entry[0][1]
3277
old_path = path = None
3278
if path_info is None:
3279
# the file is missing on disk, show as removed.
3280
content_change = True
3284
# source and target are both versioned and disk file is present.
3285
target_kind = path_info[2]
3286
if target_kind == 'directory':
3288
old_path = path = pathjoin(old_dirname, old_basename)
3289
self.new_dirname_to_file_id[path] = file_id
3290
if source_minikind != 'd':
3291
content_change = True
3293
# directories have no fingerprint
3294
content_change = False
3296
elif target_kind == 'file':
3297
if source_minikind != 'f':
3298
content_change = True
3300
# Check the sha. We can't just rely on the size as
3301
# content filtering may mean differ sizes actually
3302
# map to the same content
3303
if link_or_sha1 is None:
3305
statvalue, link_or_sha1 = \
3306
self.state._sha1_provider.stat_and_sha1(
3308
self.state._observed_sha1(entry, link_or_sha1,
3310
content_change = (link_or_sha1 != source_details[1])
3311
# Target details is updated at update_entry time
3312
if self.use_filesystem_for_exec:
3313
# We don't need S_ISREG here, because we are sure
3314
# we are dealing with a file.
3315
target_exec = bool(stat.S_IEXEC & path_info[3].st_mode)
3317
target_exec = target_details[3]
3318
elif target_kind == 'symlink':
3319
if source_minikind != 'l':
3320
content_change = True
3322
content_change = (link_or_sha1 != source_details[1])
3324
elif target_kind == 'tree-reference':
3325
if source_minikind != 't':
3326
content_change = True
3328
content_change = False
3332
path = pathjoin(old_dirname, old_basename)
3333
raise errors.BadFileKindError(path, path_info[2])
3334
if source_minikind == 'd':
3336
old_path = path = pathjoin(old_dirname, old_basename)
3337
self.old_dirname_to_file_id[old_path] = file_id
3338
# parent id is the entry for the path in the target tree
3339
if old_basename and old_dirname == self.last_source_parent[0]:
3340
source_parent_id = self.last_source_parent[1]
3343
source_parent_id = self.old_dirname_to_file_id[old_dirname]
3345
source_parent_entry = self.state._get_entry(self.source_index,
3346
path_utf8=old_dirname)
3347
source_parent_id = source_parent_entry[0][2]
3348
if source_parent_id == entry[0][2]:
3349
# This is the root, so the parent is None
3350
source_parent_id = None
3352
self.last_source_parent[0] = old_dirname
3353
self.last_source_parent[1] = source_parent_id
3354
new_dirname = entry[0][0]
3355
if entry[0][1] and new_dirname == self.last_target_parent[0]:
3356
target_parent_id = self.last_target_parent[1]
3359
target_parent_id = self.new_dirname_to_file_id[new_dirname]
3361
# TODO: We don't always need to do the lookup, because the
3362
# parent entry will be the same as the source entry.
3363
target_parent_entry = self.state._get_entry(self.target_index,
3364
path_utf8=new_dirname)
3365
if target_parent_entry == (None, None):
3366
raise AssertionError(
3367
"Could not find target parent in wt: %s\nparent of: %s"
3368
% (new_dirname, entry))
3369
target_parent_id = target_parent_entry[0][2]
3370
if target_parent_id == entry[0][2]:
3371
# This is the root, so the parent is None
3372
target_parent_id = None
3374
self.last_target_parent[0] = new_dirname
3375
self.last_target_parent[1] = target_parent_id
3377
source_exec = source_details[3]
3378
changed = (content_change
3379
or source_parent_id != target_parent_id
3380
or old_basename != entry[0][1]
3381
or source_exec != target_exec
3383
if not changed and not self.include_unchanged:
3386
if old_path is None:
3387
old_path = path = pathjoin(old_dirname, old_basename)
3388
old_path_u = self.utf8_decode(old_path)[0]
3391
old_path_u = self.utf8_decode(old_path)[0]
3392
if old_path == path:
3395
path_u = self.utf8_decode(path)[0]
3396
source_kind = DirState._minikind_to_kind[source_minikind]
3397
return (entry[0][2],
3398
(old_path_u, path_u),
3401
(source_parent_id, target_parent_id),
3402
(self.utf8_decode(old_basename)[0], self.utf8_decode(entry[0][1])[0]),
3403
(source_kind, target_kind),
3404
(source_exec, target_exec)), changed
3405
elif source_minikind in 'a' and target_minikind in 'fdlt':
3406
# looks like a new file
3407
path = pathjoin(entry[0][0], entry[0][1])
3408
# parent id is the entry for the path in the target tree
3409
# TODO: these are the same for an entire directory: cache em.
3410
parent_id = self.state._get_entry(self.target_index,
3411
path_utf8=entry[0][0])[0][2]
3412
if parent_id == entry[0][2]:
3414
if path_info is not None:
3416
if self.use_filesystem_for_exec:
3417
# We need S_ISREG here, because we aren't sure if this
3420
stat.S_ISREG(path_info[3].st_mode)
3421
and stat.S_IEXEC & path_info[3].st_mode)
3423
target_exec = target_details[3]
3424
return (entry[0][2],
3425
(None, self.utf8_decode(path)[0]),
3429
(None, self.utf8_decode(entry[0][1])[0]),
3430
(None, path_info[2]),
3431
(None, target_exec)), True
3433
# Its a missing file, report it as such.
3434
return (entry[0][2],
3435
(None, self.utf8_decode(path)[0]),
3439
(None, self.utf8_decode(entry[0][1])[0]),
3441
(None, False)), True
3442
elif source_minikind in 'fdlt' and target_minikind in 'a':
3443
# unversioned, possibly, or possibly not deleted: we dont care.
3444
# if its still on disk, *and* theres no other entry at this
3445
# path [we dont know this in this routine at the moment -
3446
# perhaps we should change this - then it would be an unknown.
3447
old_path = pathjoin(entry[0][0], entry[0][1])
3448
# parent id is the entry for the path in the target tree
3449
parent_id = self.state._get_entry(self.source_index, path_utf8=entry[0][0])[0][2]
3450
if parent_id == entry[0][2]:
3452
return (entry[0][2],
3453
(self.utf8_decode(old_path)[0], None),
3457
(self.utf8_decode(entry[0][1])[0], None),
3458
(DirState._minikind_to_kind[source_minikind], None),
3459
(source_details[3], None)), True
3460
elif source_minikind in 'fdlt' and target_minikind in 'r':
3461
# a rename; could be a true rename, or a rename inherited from
3462
# a renamed parent. TODO: handle this efficiently. Its not
3463
# common case to rename dirs though, so a correct but slow
3464
# implementation will do.
3465
if not osutils.is_inside_any(self.searched_specific_files, target_details[1]):
3466
self.search_specific_files.add(target_details[1])
3467
elif source_minikind in 'ra' and target_minikind in 'ra':
3468
# neither of the selected trees contain this file,
3469
# so skip over it. This is not currently directly tested, but
3470
# is indirectly via test_too_much.TestCommands.test_conflicts.
3473
raise AssertionError("don't know how to compare "
3474
"source_minikind=%r, target_minikind=%r"
3475
% (source_minikind, target_minikind))
3476
## import pdb;pdb.set_trace()
3482
def _gather_result_for_consistency(self, result):
3483
"""Check a result we will yield to make sure we are consistent later.
3485
This gathers result's parents into a set to output later.
3487
:param result: A result tuple.
3489
if not self.partial or not result[0]:
3491
self.seen_ids.add(result[0])
3492
new_path = result[1][1]
3494
# Not the root and not a delete: queue up the parents of the path.
3495
self.search_specific_file_parents.update(
3496
osutils.parent_directories(new_path.encode('utf8')))
3497
# Add the root directory which parent_directories does not
3499
self.search_specific_file_parents.add('')
3501
def iter_changes(self):
3502
"""Iterate over the changes."""
3503
utf8_decode = cache_utf8._utf8_decode
3504
_cmp_by_dirs = cmp_by_dirs
3505
_process_entry = self._process_entry
3506
search_specific_files = self.search_specific_files
3507
searched_specific_files = self.searched_specific_files
3508
splitpath = osutils.splitpath
3510
# compare source_index and target_index at or under each element of search_specific_files.
3511
# follow the following comparison table. Note that we only want to do diff operations when
3512
# the target is fdl because thats when the walkdirs logic will have exposed the pathinfo
3516
# Source | Target | disk | action
3517
# r | fdlt | | add source to search, add id path move and perform
3518
# | | | diff check on source-target
3519
# r | fdlt | a | dangling file that was present in the basis.
3521
# r | a | | add source to search
3523
# r | r | | this path is present in a non-examined tree, skip.
3524
# r | r | a | this path is present in a non-examined tree, skip.
3525
# a | fdlt | | add new id
3526
# a | fdlt | a | dangling locally added file, skip
3527
# a | a | | not present in either tree, skip
3528
# a | a | a | not present in any tree, skip
3529
# a | r | | not present in either tree at this path, skip as it
3530
# | | | may not be selected by the users list of paths.
3531
# a | r | a | not present in either tree at this path, skip as it
3532
# | | | may not be selected by the users list of paths.
3533
# fdlt | fdlt | | content in both: diff them
3534
# fdlt | fdlt | a | deleted locally, but not unversioned - show as deleted ?
3535
# fdlt | a | | unversioned: output deleted id for now
3536
# fdlt | a | a | unversioned and deleted: output deleted id
3537
# fdlt | r | | relocated in this tree, so add target to search.
3538
# | | | Dont diff, we will see an r,fd; pair when we reach
3539
# | | | this id at the other path.
3540
# fdlt | r | a | relocated in this tree, so add target to search.
3541
# | | | Dont diff, we will see an r,fd; pair when we reach
3542
# | | | this id at the other path.
3544
# TODO: jam 20070516 - Avoid the _get_entry lookup overhead by
3545
# keeping a cache of directories that we have seen.
3547
while search_specific_files:
3548
# TODO: the pending list should be lexically sorted? the
3549
# interface doesn't require it.
3550
current_root = search_specific_files.pop()
3551
current_root_unicode = current_root.decode('utf8')
3552
searched_specific_files.add(current_root)
3553
# process the entries for this containing directory: the rest will be
3554
# found by their parents recursively.
3555
root_entries = self.state._entries_for_path(current_root)
3556
root_abspath = self.tree.abspath(current_root_unicode)
3558
root_stat = os.lstat(root_abspath)
3560
if e.errno == errno.ENOENT:
3561
# the path does not exist: let _process_entry know that.
3562
root_dir_info = None
3564
# some other random error: hand it up.
3567
root_dir_info = ('', current_root,
3568
osutils.file_kind_from_stat_mode(root_stat.st_mode), root_stat,
3570
if root_dir_info[2] == 'directory':
3571
if self.tree._directory_is_tree_reference(
3572
current_root.decode('utf8')):
3573
root_dir_info = root_dir_info[:2] + \
3574
('tree-reference',) + root_dir_info[3:]
3576
if not root_entries and not root_dir_info:
3577
# this specified path is not present at all, skip it.
3579
path_handled = False
3580
for entry in root_entries:
3581
result, changed = _process_entry(entry, root_dir_info)
3582
if changed is not None:
3585
self._gather_result_for_consistency(result)
3586
if changed or self.include_unchanged:
3588
if self.want_unversioned and not path_handled and root_dir_info:
3589
new_executable = bool(
3590
stat.S_ISREG(root_dir_info[3].st_mode)
3591
and stat.S_IEXEC & root_dir_info[3].st_mode)
3593
(None, current_root_unicode),
3597
(None, splitpath(current_root_unicode)[-1]),
3598
(None, root_dir_info[2]),
3599
(None, new_executable)
3601
initial_key = (current_root, '', '')
3602
block_index, _ = self.state._find_block_index_from_key(initial_key)
3603
if block_index == 0:
3604
# we have processed the total root already, but because the
3605
# initial key matched it we should skip it here.
3607
if root_dir_info and root_dir_info[2] == 'tree-reference':
3608
current_dir_info = None
3610
dir_iterator = osutils._walkdirs_utf8(root_abspath, prefix=current_root)
3612
current_dir_info = dir_iterator.next()
3614
# on win32, python2.4 has e.errno == ERROR_DIRECTORY, but
3615
# python 2.5 has e.errno == EINVAL,
3616
# and e.winerror == ERROR_DIRECTORY
3617
e_winerror = getattr(e, 'winerror', None)
3618
win_errors = (ERROR_DIRECTORY, ERROR_PATH_NOT_FOUND)
3619
# there may be directories in the inventory even though
3620
# this path is not a file on disk: so mark it as end of
3622
if e.errno in (errno.ENOENT, errno.ENOTDIR, errno.EINVAL):
3623
current_dir_info = None
3624
elif (sys.platform == 'win32'
3625
and (e.errno in win_errors
3626
or e_winerror in win_errors)):
3627
current_dir_info = None
3631
if current_dir_info[0][0] == '':
3632
# remove .bzr from iteration
3633
bzr_index = bisect.bisect_left(current_dir_info[1], ('.bzr',))
3634
if current_dir_info[1][bzr_index][0] != '.bzr':
3635
raise AssertionError()
3636
del current_dir_info[1][bzr_index]
3637
# walk until both the directory listing and the versioned metadata
3639
if (block_index < len(self.state._dirblocks) and
3640
osutils.is_inside(current_root, self.state._dirblocks[block_index][0])):
3641
current_block = self.state._dirblocks[block_index]
3643
current_block = None
3644
while (current_dir_info is not None or
3645
current_block is not None):
3646
if (current_dir_info and current_block
3647
and current_dir_info[0][0] != current_block[0]):
3648
if _cmp_by_dirs(current_dir_info[0][0], current_block[0]) < 0:
3649
# filesystem data refers to paths not covered by the dirblock.
3650
# this has two possibilities:
3651
# A) it is versioned but empty, so there is no block for it
3652
# B) it is not versioned.
3654
# if (A) then we need to recurse into it to check for
3655
# new unknown files or directories.
3656
# if (B) then we should ignore it, because we don't
3657
# recurse into unknown directories.
3659
while path_index < len(current_dir_info[1]):
3660
current_path_info = current_dir_info[1][path_index]
3661
if self.want_unversioned:
3662
if current_path_info[2] == 'directory':
3663
if self.tree._directory_is_tree_reference(
3664
current_path_info[0].decode('utf8')):
3665
current_path_info = current_path_info[:2] + \
3666
('tree-reference',) + current_path_info[3:]
3667
new_executable = bool(
3668
stat.S_ISREG(current_path_info[3].st_mode)
3669
and stat.S_IEXEC & current_path_info[3].st_mode)
3671
(None, utf8_decode(current_path_info[0])[0]),
3675
(None, utf8_decode(current_path_info[1])[0]),
3676
(None, current_path_info[2]),
3677
(None, new_executable))
3678
# dont descend into this unversioned path if it is
3680
if current_path_info[2] in ('directory',
3682
del current_dir_info[1][path_index]
3686
# This dir info has been handled, go to the next
3688
current_dir_info = dir_iterator.next()
3689
except StopIteration:
3690
current_dir_info = None
3692
# We have a dirblock entry for this location, but there
3693
# is no filesystem path for this. This is most likely
3694
# because a directory was removed from the disk.
3695
# We don't have to report the missing directory,
3696
# because that should have already been handled, but we
3697
# need to handle all of the files that are contained
3699
for current_entry in current_block[1]:
3700
# entry referring to file not present on disk.
3701
# advance the entry only, after processing.
3702
result, changed = _process_entry(current_entry, None)
3703
if changed is not None:
3705
self._gather_result_for_consistency(result)
3706
if changed or self.include_unchanged:
3709
if (block_index < len(self.state._dirblocks) and
3710
osutils.is_inside(current_root,
3711
self.state._dirblocks[block_index][0])):
3712
current_block = self.state._dirblocks[block_index]
3714
current_block = None
3717
if current_block and entry_index < len(current_block[1]):
3718
current_entry = current_block[1][entry_index]
3720
current_entry = None
3721
advance_entry = True
3723
if current_dir_info and path_index < len(current_dir_info[1]):
3724
current_path_info = current_dir_info[1][path_index]
3725
if current_path_info[2] == 'directory':
3726
if self.tree._directory_is_tree_reference(
3727
current_path_info[0].decode('utf8')):
3728
current_path_info = current_path_info[:2] + \
3729
('tree-reference',) + current_path_info[3:]
3731
current_path_info = None
3733
path_handled = False
3734
while (current_entry is not None or
3735
current_path_info is not None):
3736
if current_entry is None:
3737
# the check for path_handled when the path is advanced
3738
# will yield this path if needed.
3740
elif current_path_info is None:
3741
# no path is fine: the per entry code will handle it.
3742
result, changed = _process_entry(current_entry, current_path_info)
3743
if changed is not None:
3745
self._gather_result_for_consistency(result)
3746
if changed or self.include_unchanged:
3748
elif (current_entry[0][1] != current_path_info[1]
3749
or current_entry[1][self.target_index][0] in 'ar'):
3750
# The current path on disk doesn't match the dirblock
3751
# record. Either the dirblock is marked as absent, or
3752
# the file on disk is not present at all in the
3753
# dirblock. Either way, report about the dirblock
3754
# entry, and let other code handle the filesystem one.
3756
# Compare the basename for these files to determine
3758
if current_path_info[1] < current_entry[0][1]:
3759
# extra file on disk: pass for now, but only
3760
# increment the path, not the entry
3761
advance_entry = False
3763
# entry referring to file not present on disk.
3764
# advance the entry only, after processing.
3765
result, changed = _process_entry(current_entry, None)
3766
if changed is not None:
3768
self._gather_result_for_consistency(result)
3769
if changed or self.include_unchanged:
3771
advance_path = False
3773
result, changed = _process_entry(current_entry, current_path_info)
3774
if changed is not None:
3777
self._gather_result_for_consistency(result)
3778
if changed or self.include_unchanged:
3780
if advance_entry and current_entry is not None:
3782
if entry_index < len(current_block[1]):
3783
current_entry = current_block[1][entry_index]
3785
current_entry = None
3787
advance_entry = True # reset the advance flaga
3788
if advance_path and current_path_info is not None:
3789
if not path_handled:
3790
# unversioned in all regards
3791
if self.want_unversioned:
3792
new_executable = bool(
3793
stat.S_ISREG(current_path_info[3].st_mode)
3794
and stat.S_IEXEC & current_path_info[3].st_mode)
3796
relpath_unicode = utf8_decode(current_path_info[0])[0]
3797
except UnicodeDecodeError:
3798
raise errors.BadFilenameEncoding(
3799
current_path_info[0], osutils._fs_enc)
3801
(None, relpath_unicode),
3805
(None, utf8_decode(current_path_info[1])[0]),
3806
(None, current_path_info[2]),
3807
(None, new_executable))
3808
# dont descend into this unversioned path if it is
3810
if current_path_info[2] in ('directory'):
3811
del current_dir_info[1][path_index]
3813
# dont descend the disk iterator into any tree
3815
if current_path_info[2] == 'tree-reference':
3816
del current_dir_info[1][path_index]
3819
if path_index < len(current_dir_info[1]):
3820
current_path_info = current_dir_info[1][path_index]
3821
if current_path_info[2] == 'directory':
3822
if self.tree._directory_is_tree_reference(
3823
current_path_info[0].decode('utf8')):
3824
current_path_info = current_path_info[:2] + \
3825
('tree-reference',) + current_path_info[3:]
3827
current_path_info = None
3828
path_handled = False
3830
advance_path = True # reset the advance flagg.
3831
if current_block is not None:
3833
if (block_index < len(self.state._dirblocks) and
3834
osutils.is_inside(current_root, self.state._dirblocks[block_index][0])):
3835
current_block = self.state._dirblocks[block_index]
3837
current_block = None
3838
if current_dir_info is not None:
3840
current_dir_info = dir_iterator.next()
3841
except StopIteration:
3842
current_dir_info = None
3843
for result in self._iter_specific_file_parents():
3846
def _iter_specific_file_parents(self):
3847
"""Iter over the specific file parents."""
3848
while self.search_specific_file_parents:
3849
# Process the parent directories for the paths we were iterating.
3850
# Even in extremely large trees this should be modest, so currently
3851
# no attempt is made to optimise.
3852
path_utf8 = self.search_specific_file_parents.pop()
3853
if osutils.is_inside_any(self.searched_specific_files, path_utf8):
3854
# We've examined this path.
3856
if path_utf8 in self.searched_exact_paths:
3857
# We've examined this path.
3859
path_entries = self.state._entries_for_path(path_utf8)
3860
# We need either one or two entries. If the path in
3861
# self.target_index has moved (so the entry in source_index is in
3862
# 'ar') then we need to also look for the entry for this path in
3863
# self.source_index, to output the appropriate delete-or-rename.
3864
selected_entries = []
3866
for candidate_entry in path_entries:
3867
# Find entries present in target at this path:
3868
if candidate_entry[1][self.target_index][0] not in 'ar':
3870
selected_entries.append(candidate_entry)
3871
# Find entries present in source at this path:
3872
elif (self.source_index is not None and
3873
candidate_entry[1][self.source_index][0] not in 'ar'):
3875
if candidate_entry[1][self.target_index][0] == 'a':
3876
# Deleted, emit it here.
3877
selected_entries.append(candidate_entry)
3879
# renamed, emit it when we process the directory it
3881
self.search_specific_file_parents.add(
3882
candidate_entry[1][self.target_index][1])
3884
raise AssertionError(
3885
"Missing entry for specific path parent %r, %r" % (
3886
path_utf8, path_entries))
3887
path_info = self._path_info(path_utf8, path_utf8.decode('utf8'))
3888
for entry in selected_entries:
3889
if entry[0][2] in self.seen_ids:
3891
result, changed = self._process_entry(entry, path_info)
3893
raise AssertionError(
3894
"Got entry<->path mismatch for specific path "
3895
"%r entry %r path_info %r " % (
3896
path_utf8, entry, path_info))
3897
# Only include changes - we're outside the users requested
3900
self._gather_result_for_consistency(result)
3901
if (result[6][0] == 'directory' and
3902
result[6][1] != 'directory'):
3903
# This stopped being a directory, the old children have
3905
if entry[1][self.source_index][0] == 'r':
3906
# renamed, take the source path
3907
entry_path_utf8 = entry[1][self.source_index][1]
3909
entry_path_utf8 = path_utf8
3910
initial_key = (entry_path_utf8, '', '')
3911
block_index, _ = self.state._find_block_index_from_key(
3913
if block_index == 0:
3914
# The children of the root are in block index 1.
3916
current_block = None
3917
if block_index < len(self.state._dirblocks):
3918
current_block = self.state._dirblocks[block_index]
3919
if not osutils.is_inside(
3920
entry_path_utf8, current_block[0]):
3921
# No entries for this directory at all.
3922
current_block = None
3923
if current_block is not None:
3924
for entry in current_block[1]:
3925
if entry[1][self.source_index][0] in 'ar':
3926
# Not in the source tree, so doesn't have to be
3929
# Path of the entry itself.
3931
self.search_specific_file_parents.add(
3932
osutils.pathjoin(*entry[0][:2]))
3933
if changed or self.include_unchanged:
3935
self.searched_exact_paths.add(path_utf8)
3937
def _path_info(self, utf8_path, unicode_path):
3938
"""Generate path_info for unicode_path.
3940
:return: None if unicode_path does not exist, or a path_info tuple.
3942
abspath = self.tree.abspath(unicode_path)
3944
stat = os.lstat(abspath)
3946
if e.errno == errno.ENOENT:
3947
# the path does not exist.
3951
utf8_basename = utf8_path.rsplit('/', 1)[-1]
3952
dir_info = (utf8_path, utf8_basename,
3953
osutils.file_kind_from_stat_mode(stat.st_mode), stat,
3955
if dir_info[2] == 'directory':
3956
if self.tree._directory_is_tree_reference(
3958
self.root_dir_info = self.root_dir_info[:2] + \
3959
('tree-reference',) + self.root_dir_info[3:]
3963
# Try to load the compiled form if possible
3965
from bzrlib._dirstate_helpers_pyx import (
3971
ProcessEntryC as _process_entry,
3972
update_entry as update_entry,
3974
except ImportError, e:
3975
osutils.failed_to_load_extension(e)
3976
from bzrlib._dirstate_helpers_py import (
3983
# FIXME: It would be nice to be able to track moved lines so that the
3984
# corresponding python code can be moved to the _dirstate_helpers_py
3985
# module. I don't want to break the history for this important piece of
3986
# code so I left the code here -- vila 20090622
3987
update_entry = py_update_entry
3988
_process_entry = ProcessEntryPython
added
removed
bzrlib/dirstate.py
