20
20
lines by NL. The field delimiters are ommitted in the grammar, line delimiters
21
21
are not - this is done for clarity of reading. All string data is in utf8.
25
MINIKIND = "f" | "d" | "l" | "a" | "r" | "t";
28
WHOLE_NUMBER = {digit}, digit;
30
REVISION_ID = a non-empty utf8 string;
32
dirstate format = header line, full checksum, row count, parent details,
33
ghost_details, entries;
34
header line = "#bazaar dirstate flat format 3", NL;
35
full checksum = "crc32: ", ["-"], WHOLE_NUMBER, NL;
36
row count = "num_entries: ", WHOLE_NUMBER, NL;
37
parent_details = WHOLE NUMBER, {REVISION_ID}* NL;
38
ghost_details = WHOLE NUMBER, {REVISION_ID}*, NL;
40
entry = entry_key, current_entry_details, {parent_entry_details};
41
entry_key = dirname, basename, fileid;
42
current_entry_details = common_entry_details, working_entry_details;
43
parent_entry_details = common_entry_details, history_entry_details;
44
common_entry_details = MINIKIND, fingerprint, size, executable
45
working_entry_details = packed_stat
46
history_entry_details = REVISION_ID;
49
fingerprint = a nonempty utf8 sequence with meaning defined by minikind.
51
Given this definition, the following is useful to know::
53
entry (aka row) - all the data for a given key.
54
entry[0]: The key (dirname, basename, fileid)
58
entry[1]: The tree(s) data for this path and id combination.
59
entry[1][0]: The current tree
60
entry[1][1]: The second tree
62
For an entry for a tree, we have (using tree 0 - current tree) to demonstrate::
64
entry[1][0][0]: minikind
65
entry[1][0][1]: fingerprint
67
entry[1][0][3]: executable
68
entry[1][0][4]: packed_stat
72
entry[1][1][4]: revision_id
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
74
68
There may be multiple rows at the root, one per id present in the root, so the
75
in memory root row is now::
77
self._dirblocks[0] -> ('', [entry ...]),
79
and the entries in there are::
83
entries[0][2]: file_id
84
entries[1][0]: The tree data for the current tree for this fileid at /
89
'r' is a relocated entry: This path is not present in this tree with this
90
id, but the id can be found at another location. The fingerprint is
91
used to point to the target location.
92
'a' is an absent entry: In that tree the id is not present at this path.
93
'd' is a directory entry: This path in this tree is a directory with the
94
current file id. There is no fingerprint for directories.
95
'f' is a file entry: As for directory, but it's a file. The fingerprint is
96
the sha1 value of the file's canonical form, i.e. after any read
97
filters have been applied to the convenience form stored in the working
99
'l' is a symlink entry: As for directory, but a symlink. The fingerprint is
101
't' is a reference to a nested subtree; the fingerprint is the referenced
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
106
The entries on disk and in memory are ordered according to the following keys::
95
The entries on disk and in memory are ordered according to the following keys:
108
97
directory, as a list of components
112
101
--- Format 1 had the following different definition: ---
116
rows = dirname, NULL, basename, NULL, MINIKIND, NULL, fileid_utf8, NULL,
117
WHOLE NUMBER (* size *), NULL, packed stat, NULL, sha1|symlink target,
119
PARENT ROW = NULL, revision_utf8, NULL, MINIKIND, NULL, dirname, NULL,
120
basename, NULL, WHOLE NUMBER (* size *), NULL, "y" | "n", NULL,
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,
123
109
PARENT ROW's are emitted for every parent that is not in the ghosts details
124
110
line. That is, if the parents are foo, bar, baz, and the ghosts are bar, then
447
410
self._last_block_index = None
448
411
self._last_entry_index = None
449
# The set of known hash changes
450
self._known_hash_changes = set()
451
# How many hash changed entries can we have without saving
452
self._worth_saving_limit = worth_saving_limit
453
self._config_stack = config.LocationStack(urlutils.local_path_to_url(
456
413
def __repr__(self):
457
414
return "%s(%r)" % \
458
415
(self.__class__.__name__, self._filename)
460
def _mark_modified(self, hash_changed_entries=None, header_modified=False):
461
"""Mark this dirstate as modified.
463
:param hash_changed_entries: if non-None, mark just these entries as
464
having their hash modified.
465
:param header_modified: mark the header modified as well, not just the
468
#trace.mutter_callsite(3, "modified hash entries: %s", hash_changed_entries)
469
if hash_changed_entries:
470
self._known_hash_changes.update([e[0] for e in hash_changed_entries])
471
if self._dirblock_state in (DirState.NOT_IN_MEMORY,
472
DirState.IN_MEMORY_UNMODIFIED):
473
# If the dirstate is already marked a IN_MEMORY_MODIFIED, then
474
# that takes precedence.
475
self._dirblock_state = DirState.IN_MEMORY_HASH_MODIFIED
477
# TODO: Since we now have a IN_MEMORY_HASH_MODIFIED state, we
478
# should fail noisily if someone tries to set
479
# IN_MEMORY_MODIFIED but we don't have a write-lock!
480
# We don't know exactly what changed so disable smart saving
481
self._dirblock_state = DirState.IN_MEMORY_MODIFIED
483
self._header_state = DirState.IN_MEMORY_MODIFIED
485
def _mark_unmodified(self):
486
"""Mark this dirstate as unmodified."""
487
self._header_state = DirState.IN_MEMORY_UNMODIFIED
488
self._dirblock_state = DirState.IN_MEMORY_UNMODIFIED
489
self._known_hash_changes = set()
491
417
def add(self, path, file_id, kind, stat, fingerprint):
492
418
"""Add a path to be tracked.
1351
def _check_delta_is_valid(self, delta):
1352
return list(inventory._check_delta_unique_ids(
1353
inventory._check_delta_unique_old_paths(
1354
inventory._check_delta_unique_new_paths(
1355
inventory._check_delta_ids_match_entry(
1356
inventory._check_delta_ids_are_valid(
1357
inventory._check_delta_new_path_entry_both_or_None(delta)))))))
1359
1277
def update_by_delta(self, delta):
1360
1278
"""Apply an inventory delta to the dirstate for tree 0
1362
This is the workhorse for apply_inventory_delta in dirstate based
1365
1280
:param delta: An inventory delta. See Inventory.apply_delta for
1368
1283
self._read_dirblocks_if_needed()
1369
encode = cache_utf8.encode
1370
1284
insertions = {}
1372
# Accumulate parent references (path_utf8, id), to check for parentless
1373
# items or items placed under files/links/tree-references. We get
1374
# references from every item in the delta that is not a deletion and
1375
# is not itself the root.
1377
# Added ids must not be in the dirstate already. This set holds those
1380
# This loop transforms the delta to single atomic operations that can
1381
# be executed and validated.
1382
delta = sorted(self._check_delta_is_valid(delta), reverse=True)
1383
for old_path, new_path, file_id, inv_entry in delta:
1286
for old_path, new_path, file_id, inv_entry in sorted(delta, reverse=True):
1384
1287
if (file_id in insertions) or (file_id in removals):
1385
self._raise_invalid(old_path or new_path, file_id,
1288
raise AssertionError("repeated file id in delta %r" % (file_id,))
1387
1289
if old_path is not None:
1388
1290
old_path = old_path.encode('utf-8')
1389
1291
removals[file_id] = old_path
1391
new_ids.add(file_id)
1392
1292
if new_path is not None:
1393
if inv_entry is None:
1394
self._raise_invalid(new_path, file_id,
1395
"new_path with no entry")
1396
1293
new_path = new_path.encode('utf-8')
1397
dirname_utf8, basename = osutils.split(new_path)
1399
parents.add((dirname_utf8, inv_entry.parent_id))
1400
key = (dirname_utf8, basename, file_id)
1294
dirname, basename = osutils.split(new_path)
1295
key = (dirname, basename, file_id)
1401
1296
minikind = DirState._kind_to_minikind[inv_entry.kind]
1402
1297
if minikind == 't':
1403
fingerprint = inv_entry.reference_revision or ''
1298
fingerprint = inv_entry.reference_revision
1405
1300
fingerprint = ''
1406
1301
insertions[file_id] = (key, minikind, inv_entry.executable,
1415
1310
minikind = child[1][0][0]
1416
1311
fingerprint = child[1][0][4]
1417
1312
executable = child[1][0][3]
1418
old_child_path = osutils.pathjoin(child_dirname,
1313
old_child_path = osutils.pathjoin(child[0][0],
1420
1315
removals[child[0][2]] = old_child_path
1421
1316
child_suffix = child_dirname[len(old_path):]
1422
1317
new_child_dirname = (new_path + child_suffix)
1423
1318
key = (new_child_dirname, child_basename, child[0][2])
1424
new_child_path = osutils.pathjoin(new_child_dirname,
1319
new_child_path = os.path.join(new_child_dirname,
1426
1321
insertions[child[0][2]] = (key, minikind, executable,
1427
1322
fingerprint, new_child_path)
1428
self._check_delta_ids_absent(new_ids, delta, 0)
1430
self._apply_removals(removals.iteritems())
1431
self._apply_insertions(insertions.values())
1433
self._after_delta_check_parents(parents, 0)
1434
except errors.BzrError, e:
1435
self._changes_aborted = True
1436
if 'integrity error' not in str(e):
1438
# _get_entry raises BzrError when a request is inconsistent; we
1439
# want such errors to be shown as InconsistentDelta - and that
1440
# fits the behaviour we trigger.
1441
raise errors.InconsistentDeltaDelta(delta,
1442
"error from _get_entry. %s" % (e,))
1323
self._apply_removals(removals.values())
1324
self._apply_insertions(insertions.values())
1444
1326
def _apply_removals(self, removals):
1445
for file_id, path in sorted(removals, reverse=True,
1446
key=operator.itemgetter(1)):
1327
for path in sorted(removals, reverse=True):
1447
1328
dirname, basename = osutils.split(path)
1448
1329
block_i, entry_i, d_present, f_present = \
1449
1330
self._get_block_entry_index(dirname, basename, 0)
1451
entry = self._dirblocks[block_i][1][entry_i]
1453
self._raise_invalid(path, file_id,
1454
"Wrong path for old path.")
1455
if not f_present or entry[1][0][0] in 'ar':
1456
self._raise_invalid(path, file_id,
1457
"Wrong path for old path.")
1458
if file_id != entry[0][2]:
1459
self._raise_invalid(path, file_id,
1460
"Attempt to remove path has wrong id - found %r."
1331
entry = self._dirblocks[block_i][1][entry_i]
1462
1332
self._make_absent(entry)
1463
1333
# See if we have a malformed delta: deleting a directory must not
1464
1334
# leave crud behind. This increases the number of bisects needed
1530
1399
# At the same time, to reduce interface friction we convert the input
1531
1400
# inventory entries to dirstate.
1532
1401
root_only = ('', '')
1533
# Accumulate parent references (path_utf8, id), to check for parentless
1534
# items or items placed under files/links/tree-references. We get
1535
# references from every item in the delta that is not a deletion and
1536
# is not itself the root.
1538
# Added ids must not be in the dirstate already. This set holds those
1541
1402
for old_path, new_path, file_id, inv_entry in delta:
1542
if inv_entry is not None and file_id != inv_entry.file_id:
1543
self._raise_invalid(new_path, file_id,
1544
"mismatched entry file_id %r" % inv_entry)
1545
if new_path is None:
1546
new_path_utf8 = None
1548
if inv_entry is None:
1549
self._raise_invalid(new_path, file_id,
1550
"new_path with no entry")
1551
new_path_utf8 = encode(new_path)
1552
# note the parent for validation
1553
dirname_utf8, basename_utf8 = osutils.split(new_path_utf8)
1555
parents.add((dirname_utf8, inv_entry.parent_id))
1556
if old_path is None:
1557
old_path_utf8 = None
1559
old_path_utf8 = encode(old_path)
1560
if old_path is None:
1561
adds.append((None, new_path_utf8, file_id,
1403
if old_path is None:
1404
adds.append((None, encode(new_path), file_id,
1562
1405
inv_to_entry(inv_entry), True))
1563
new_ids.add(file_id)
1564
1406
elif new_path is None:
1565
deletes.append((old_path_utf8, None, file_id, None, True))
1566
elif (old_path, new_path) == root_only:
1567
# change things in-place
1568
# Note: the case of a parent directory changing its file_id
1569
# tends to break optimizations here, because officially
1570
# the file has actually been moved, it just happens to
1571
# end up at the same path. If we can figure out how to
1572
# handle that case, we can avoid a lot of add+delete
1573
# pairs for objects that stay put.
1574
# elif old_path == new_path:
1575
changes.append((old_path_utf8, new_path_utf8, file_id,
1576
inv_to_entry(inv_entry)))
1407
deletes.append((encode(old_path), None, file_id, None, True))
1408
elif (old_path, new_path) != root_only:
1579
1410
# Because renames must preserve their children we must have
1580
1411
# processed all relocations and removes before hand. The sort
1589
1420
# for 'r' items on every pass.
1590
1421
self._update_basis_apply_deletes(deletes)
1423
new_path_utf8 = encode(new_path)
1592
1424
# Split into an add/delete pair recursively.
1593
adds.append((old_path_utf8, new_path_utf8, file_id,
1594
inv_to_entry(inv_entry), False))
1425
adds.append((None, new_path_utf8, file_id,
1426
inv_to_entry(inv_entry), False))
1595
1427
# Expunge deletes that we've seen so that deleted/renamed
1596
1428
# children of a rename directory are handled correctly.
1597
new_deletes = reversed(list(
1598
self._iter_child_entries(1, old_path_utf8)))
1429
new_deletes = reversed(list(self._iter_child_entries(1,
1599
1431
# Remove the current contents of the tree at orig_path, and
1600
1432
# reinsert at the correct new path.
1601
1433
for entry in new_deletes:
1602
child_dirname, child_basename, child_file_id = entry[0]
1604
source_path = child_dirname + '/' + child_basename
1435
source_path = entry[0][0] + '/' + entry[0][1]
1606
source_path = child_basename
1437
source_path = entry[0][1]
1607
1438
if new_path_utf8:
1608
1439
target_path = new_path_utf8 + source_path[len(old_path):]
1610
1441
if old_path == '':
1611
1442
raise AssertionError("cannot rename directory to"
1613
1444
target_path = source_path[len(old_path) + 1:]
1614
1445
adds.append((None, target_path, entry[0][2], entry[1][1], False))
1615
1446
deletes.append(
1616
1447
(source_path, target_path, entry[0][2], None, False))
1617
deletes.append((old_path_utf8, new_path, file_id, None, False))
1618
self._check_delta_ids_absent(new_ids, delta, 1)
1620
# Finish expunging deletes/first half of renames.
1621
self._update_basis_apply_deletes(deletes)
1622
# Reinstate second half of renames and new paths.
1623
self._update_basis_apply_adds(adds)
1624
# Apply in-situ changes.
1625
self._update_basis_apply_changes(changes)
1627
self._after_delta_check_parents(parents, 1)
1628
except errors.BzrError, e:
1629
self._changes_aborted = True
1630
if 'integrity error' not in str(e):
1632
# _get_entry raises BzrError when a request is inconsistent; we
1633
# want such errors to be shown as InconsistentDelta - and that
1634
# fits the behaviour we trigger.
1635
raise errors.InconsistentDeltaDelta(delta,
1636
"error from _get_entry. %s" % (e,))
1638
self._mark_modified(header_modified=True)
1449
(encode(old_path), new_path, file_id, None, False))
1451
# changes to just the root should not require remove/insertion
1453
changes.append((encode(old_path), encode(new_path), file_id,
1454
inv_to_entry(inv_entry)))
1456
# Finish expunging deletes/first half of renames.
1457
self._update_basis_apply_deletes(deletes)
1458
# Reinstate second half of renames and new paths.
1459
self._update_basis_apply_adds(adds)
1460
# Apply in-situ changes.
1461
self._update_basis_apply_changes(changes)
1463
self._dirblock_state = DirState.IN_MEMORY_MODIFIED
1464
self._header_state = DirState.IN_MEMORY_MODIFIED
1639
1465
self._id_index = None
1642
def _check_delta_ids_absent(self, new_ids, delta, tree_index):
1643
"""Check that none of the file_ids in new_ids are present in a tree."""
1646
id_index = self._get_id_index()
1647
for file_id in new_ids:
1648
for key in id_index.get(file_id, ()):
1649
block_i, entry_i, d_present, f_present = \
1650
self._get_block_entry_index(key[0], key[1], tree_index)
1652
# In a different tree
1654
entry = self._dirblocks[block_i][1][entry_i]
1655
if entry[0][2] != file_id:
1656
# Different file_id, so not what we want.
1658
self._raise_invalid(("%s/%s" % key[0:2]).decode('utf8'), file_id,
1659
"This file_id is new in the delta but already present in "
1662
def _raise_invalid(self, path, file_id, reason):
1663
self._changes_aborted = True
1664
raise errors.InconsistentDelta(path, file_id, reason)
1666
1468
def _update_basis_apply_adds(self, adds):
1667
1469
"""Apply a sequence of adds to tree 1 during update_basis_by_delta.
1677
1479
# Adds are accumulated partly from renames, so can be in any input
1678
1480
# order - sort it.
1679
# TODO: we may want to sort in dirblocks order. That way each entry
1680
# will end up in the same directory, allowing the _get_entry
1681
# fast-path for looking up 2 items in the same dir work.
1682
adds.sort(key=lambda x: x[1])
1683
1482
# adds is now in lexographic order, which places all parents before
1684
1483
# their children, so we can process it linearly.
1686
st = static_tuple.StaticTuple
1687
1485
for old_path, new_path, file_id, new_details, real_add in adds:
1688
dirname, basename = osutils.split(new_path)
1689
entry_key = st(dirname, basename, file_id)
1690
block_index, present = self._find_block_index_from_key(entry_key)
1692
self._raise_invalid(new_path, file_id,
1693
"Unable to find block for this record."
1694
" Was the parent added?")
1695
block = self._dirblocks[block_index][1]
1696
entry_index, present = self._find_entry_index(entry_key, block)
1698
if old_path is not None:
1699
self._raise_invalid(new_path, file_id,
1700
'considered a real add but still had old_path at %s'
1703
entry = block[entry_index]
1704
basis_kind = entry[1][1][0]
1705
if basis_kind == 'a':
1706
entry[1][1] = new_details
1707
elif basis_kind == 'r':
1708
raise NotImplementedError()
1710
self._raise_invalid(new_path, file_id,
1711
"An entry was marked as a new add"
1712
" but the basis target already existed")
1714
# The exact key was not found in the block. However, we need to
1715
# check if there is a key next to us that would have matched.
1716
# We only need to check 2 locations, because there are only 2
1718
for maybe_index in range(entry_index-1, entry_index+1):
1719
if maybe_index < 0 or maybe_index >= len(block):
1721
maybe_entry = block[maybe_index]
1722
if maybe_entry[0][:2] != (dirname, basename):
1723
# Just a random neighbor
1725
if maybe_entry[0][2] == file_id:
1726
raise AssertionError(
1727
'_find_entry_index didnt find a key match'
1728
' but walking the data did, for %s'
1730
basis_kind = maybe_entry[1][1][0]
1731
if basis_kind not in 'ar':
1732
self._raise_invalid(new_path, file_id,
1733
"we have an add record for path, but the path"
1734
" is already present with another file_id %s"
1735
% (maybe_entry[0][2],))
1737
entry = (entry_key, [DirState.NULL_PARENT_DETAILS,
1739
block.insert(entry_index, entry)
1741
active_kind = entry[1][0][0]
1742
if active_kind == 'a':
1743
# The active record shows up as absent, this could be genuine,
1744
# or it could be present at some other location. We need to
1746
id_index = self._get_id_index()
1747
# The id_index may not be perfectly accurate for tree1, because
1748
# we haven't been keeping it updated. However, it should be
1749
# fine for tree0, and that gives us enough info for what we
1751
keys = id_index.get(file_id, ())
1753
block_i, entry_i, d_present, f_present = \
1754
self._get_block_entry_index(key[0], key[1], 0)
1757
active_entry = self._dirblocks[block_i][1][entry_i]
1758
if (active_entry[0][2] != file_id):
1759
# Some other file is at this path, we don't need to
1762
real_active_kind = active_entry[1][0][0]
1763
if real_active_kind in 'ar':
1764
# We found a record, which was not *this* record,
1765
# which matches the file_id, but is not actually
1766
# present. Something seems *really* wrong.
1767
self._raise_invalid(new_path, file_id,
1768
"We found a tree0 entry that doesnt make sense")
1769
# Now, we've found a tree0 entry which matches the file_id
1770
# but is at a different location. So update them to be
1772
active_dir, active_name = active_entry[0][:2]
1774
active_path = active_dir + '/' + active_name
1776
active_path = active_name
1777
active_entry[1][1] = st('r', new_path, 0, False, '')
1778
entry[1][0] = st('r', active_path, 0, False, '')
1779
elif active_kind == 'r':
1780
raise NotImplementedError()
1782
new_kind = new_details[0]
1784
self._ensure_block(block_index, entry_index, new_path)
1486
# the entry for this file_id must be in tree 0.
1487
entry = self._get_entry(0, file_id, new_path)
1488
if entry[0] is None or entry[0][2] != file_id:
1489
self._changes_aborted = True
1490
raise errors.InconsistentDelta(new_path, file_id,
1491
'working tree does not contain new entry')
1492
if real_add and entry[1][1][0] not in absent:
1493
self._changes_aborted = True
1494
raise errors.InconsistentDelta(new_path, file_id,
1495
'The entry was considered to be a genuinely new record,'
1496
' but there was already an old record for it.')
1497
# We don't need to update the target of an 'r' because the handling
1498
# of renames turns all 'r' situations into a delete at the original
1500
entry[1][1] = new_details
1786
1502
def _update_basis_apply_changes(self, changes):
1787
1503
"""Apply a sequence of changes to tree 1 during update_basis_by_delta.
1813
1535
null = DirState.NULL_PARENT_DETAILS
1814
1536
for old_path, new_path, file_id, _, real_delete in deletes:
1815
1537
if real_delete != (new_path is None):
1816
self._raise_invalid(old_path, file_id, "bad delete delta")
1538
raise AssertionError("bad delete delta")
1817
1539
# the entry for this file_id must be in tree 1.
1818
1540
dirname, basename = osutils.split(old_path)
1819
1541
block_index, entry_index, dir_present, file_present = \
1820
1542
self._get_block_entry_index(dirname, basename, 1)
1821
1543
if not file_present:
1822
self._raise_invalid(old_path, file_id,
1544
self._changes_aborted = True
1545
raise errors.InconsistentDelta(old_path, file_id,
1823
1546
'basis tree does not contain removed entry')
1824
1547
entry = self._dirblocks[block_index][1][entry_index]
1825
# The state of the entry in the 'active' WT
1826
active_kind = entry[1][0][0]
1827
1548
if entry[0][2] != file_id:
1828
self._raise_invalid(old_path, file_id,
1549
self._changes_aborted = True
1550
raise errors.InconsistentDelta(old_path, file_id,
1829
1551
'mismatched file_id in tree 1')
1831
old_kind = entry[1][1][0]
1832
if active_kind in 'ar':
1833
# The active tree doesn't have this file_id.
1834
# The basis tree is changing this record. If this is a
1835
# rename, then we don't want the record here at all
1836
# anymore. If it is just an in-place change, we want the
1837
# record here, but we'll add it if we need to. So we just
1839
if active_kind == 'r':
1840
active_path = entry[1][0][1]
1841
active_entry = self._get_entry(0, file_id, active_path)
1842
if active_entry[1][1][0] != 'r':
1843
self._raise_invalid(old_path, file_id,
1844
"Dirstate did not have matching rename entries")
1845
elif active_entry[1][0][0] in 'ar':
1846
self._raise_invalid(old_path, file_id,
1847
"Dirstate had a rename pointing at an inactive"
1849
active_entry[1][1] = null
1553
if entry[1][0][0] != 'a':
1554
self._changes_aborted = True
1555
raise errors.InconsistentDelta(old_path, file_id,
1556
'This was marked as a real delete, but the WT state'
1557
' claims that it still exists and is versioned.')
1850
1558
del self._dirblocks[block_index][1][entry_index]
1852
# This was a directory, and the active tree says it
1853
# doesn't exist, and now the basis tree says it doesn't
1854
# exist. Remove its dirblock if present
1856
present) = self._find_block_index_from_key(
1859
dir_block = self._dirblocks[dir_block_index][1]
1861
# This entry is empty, go ahead and just remove it
1862
del self._dirblocks[dir_block_index]
1864
# There is still an active record, so just mark this
1867
block_i, entry_i, d_present, f_present = \
1868
self._get_block_entry_index(old_path, '', 1)
1870
dir_block = self._dirblocks[block_i][1]
1871
for child_entry in dir_block:
1872
child_basis_kind = child_entry[1][1][0]
1873
if child_basis_kind not in 'ar':
1874
self._raise_invalid(old_path, file_id,
1875
"The file id was deleted but its children were "
1878
def _after_delta_check_parents(self, parents, index):
1879
"""Check that parents required by the delta are all intact.
1881
:param parents: An iterable of (path_utf8, file_id) tuples which are
1882
required to be present in tree 'index' at path_utf8 with id file_id
1884
:param index: The column in the dirstate to check for parents in.
1886
for dirname_utf8, file_id in parents:
1887
# Get the entry - the ensures that file_id, dirname_utf8 exists and
1888
# has the right file id.
1889
entry = self._get_entry(index, file_id, dirname_utf8)
1890
if entry[1] is None:
1891
self._raise_invalid(dirname_utf8.decode('utf8'),
1892
file_id, "This parent is not present.")
1893
# Parents of things must be directories
1894
if entry[1][index][0] != 'd':
1895
self._raise_invalid(dirname_utf8.decode('utf8'),
1896
file_id, "This parent is not a directory.")
1560
if entry[1][0][0] == 'a':
1561
self._changes_aborted = True
1562
raise errors.InconsistentDelta(old_path, file_id,
1563
'The entry was considered a rename, but the source path'
1564
' is marked as absent.')
1565
# For whatever reason, we were asked to rename an entry
1566
# that was originally marked as deleted. This could be
1567
# because we are renaming the parent directory, and the WT
1568
# current state has the file marked as deleted.
1569
elif entry[1][0][0] == 'r':
1570
# implement the rename
1571
del self._dirblocks[block_index][1][entry_index]
1573
# it is being resurrected here, so blank it out temporarily.
1574
self._dirblocks[block_index][1][entry_index][1][1] = null
1898
1576
def _observed_sha1(self, entry, sha1, stat_value,
1899
1577
_stat_to_minikind=_stat_to_minikind, _pack_stat=pack_stat):
2331
2002
def _get_id_index(self):
2332
"""Get an id index of self._dirblocks.
2334
This maps from file_id => [(directory, name, file_id)] entries where
2335
that file_id appears in one of the trees.
2003
"""Get an id index of self._dirblocks."""
2337
2004
if self._id_index is None:
2339
2006
for key, tree_details in self._iter_entries():
2340
self._add_to_id_index(id_index, key)
2007
id_index.setdefault(key[2], set()).add(key)
2341
2008
self._id_index = id_index
2342
2009
return self._id_index
2344
def _add_to_id_index(self, id_index, entry_key):
2345
"""Add this entry to the _id_index mapping."""
2346
# This code used to use a set for every entry in the id_index. However,
2347
# it is *rare* to have more than one entry. So a set is a large
2348
# overkill. And even when we do, we won't ever have more than the
2349
# number of parent trees. Which is still a small number (rarely >2). As
2350
# such, we use a simple tuple, and do our own uniqueness checks. While
2351
# the 'in' check is O(N) since N is nicely bounded it shouldn't ever
2352
# cause quadratic failure.
2353
file_id = entry_key[2]
2354
entry_key = static_tuple.StaticTuple.from_sequence(entry_key)
2355
if file_id not in id_index:
2356
id_index[file_id] = static_tuple.StaticTuple(entry_key,)
2358
entry_keys = id_index[file_id]
2359
if entry_key not in entry_keys:
2360
id_index[file_id] = entry_keys + (entry_key,)
2362
def _remove_from_id_index(self, id_index, entry_key):
2363
"""Remove this entry from the _id_index mapping.
2365
It is an programming error to call this when the entry_key is not
2368
file_id = entry_key[2]
2369
entry_keys = list(id_index[file_id])
2370
entry_keys.remove(entry_key)
2371
id_index[file_id] = static_tuple.StaticTuple.from_sequence(entry_keys)
2373
2011
def _get_output_lines(self, lines):
2374
2012
"""Format lines for final output.
2508
2142
trace.mutter('Not saving DirState because '
2509
2143
'_changes_aborted is set.')
2511
# TODO: Since we now distinguish IN_MEMORY_MODIFIED from
2512
# IN_MEMORY_HASH_MODIFIED, we should only fail quietly if we fail
2513
# to save an IN_MEMORY_HASH_MODIFIED, and fail *noisily* if we
2514
# fail to save IN_MEMORY_MODIFIED
2515
if not self._worth_saving():
2145
if (self._header_state == DirState.IN_MEMORY_MODIFIED or
2146
self._dirblock_state == DirState.IN_MEMORY_MODIFIED):
2518
grabbed_write_lock = False
2519
if self._lock_state != 'w':
2520
grabbed_write_lock, new_lock = self._lock_token.temporary_write_lock()
2521
# Switch over to the new lock, as the old one may be closed.
2522
# TODO: jam 20070315 We should validate the disk file has
2523
# not changed contents, since temporary_write_lock may
2524
# not be an atomic operation.
2525
self._lock_token = new_lock
2526
self._state_file = new_lock.f
2527
if not grabbed_write_lock:
2528
# We couldn't grab a write lock, so we switch back to a read one
2531
lines = self.get_lines()
2532
self._state_file.seek(0)
2533
self._state_file.writelines(lines)
2534
self._state_file.truncate()
2535
self._state_file.flush()
2536
self._maybe_fdatasync()
2537
self._mark_unmodified()
2539
if grabbed_write_lock:
2540
self._lock_token = self._lock_token.restore_read_lock()
2541
self._state_file = self._lock_token.f
2148
grabbed_write_lock = False
2149
if self._lock_state != 'w':
2150
grabbed_write_lock, new_lock = self._lock_token.temporary_write_lock()
2151
# Switch over to the new lock, as the old one may be closed.
2542
2152
# TODO: jam 20070315 We should validate the disk file has
2543
# not changed contents. Since restore_read_lock may
2544
# not be an atomic operation.
2546
def _maybe_fdatasync(self):
2547
"""Flush to disk if possible and if not configured off."""
2548
if self._config_stack.get('dirstate.fdatasync'):
2549
osutils.fdatasync(self._state_file.fileno())
2551
def _worth_saving(self):
2552
"""Is it worth saving the dirstate or not?"""
2553
if (self._header_state == DirState.IN_MEMORY_MODIFIED
2554
or self._dirblock_state == DirState.IN_MEMORY_MODIFIED):
2556
if self._dirblock_state == DirState.IN_MEMORY_HASH_MODIFIED:
2557
if self._worth_saving_limit == -1:
2558
# We never save hash changes when the limit is -1
2560
# If we're using smart saving and only a small number of
2561
# entries have changed their hash, don't bother saving. John has
2562
# suggested using a heuristic here based on the size of the
2563
# changed files and/or tree. For now, we go with a configurable
2564
# number of changes, keeping the calculation time
2565
# as low overhead as possible. (This also keeps all existing
2566
# tests passing as the default is 0, i.e. always save.)
2567
if len(self._known_hash_changes) >= self._worth_saving_limit:
2153
# not changed contents. Since temporary_write_lock may
2154
# not be an atomic operation.
2155
self._lock_token = new_lock
2156
self._state_file = new_lock.f
2157
if not grabbed_write_lock:
2158
# We couldn't grab a write lock, so we switch back to a read one
2161
self._state_file.seek(0)
2162
self._state_file.writelines(self.get_lines())
2163
self._state_file.truncate()
2164
self._state_file.flush()
2165
self._header_state = DirState.IN_MEMORY_UNMODIFIED
2166
self._dirblock_state = DirState.IN_MEMORY_UNMODIFIED
2168
if grabbed_write_lock:
2169
self._lock_token = self._lock_token.restore_read_lock()
2170
self._state_file = self._lock_token.f
2171
# TODO: jam 20070315 We should validate the disk file has
2172
# not changed contents. Since restore_read_lock may
2173
# not be an atomic operation.
2571
2175
def _set_data(self, parent_ids, dirblocks):
2572
2176
"""Set the full dirstate data in memory.
2737
2324
new_details = []
2738
2325
for lookup_index in xrange(tree_index):
2739
2326
# boundary case: this is the first occurence of file_id
2740
# so there are no id_indexes, possibly take this out of
2327
# so there are no id_indexs, possibly take this out of
2742
if not len(entry_keys):
2329
if not len(id_index[file_id]):
2743
2330
new_details.append(DirState.NULL_PARENT_DETAILS)
2745
2332
# grab any one entry, use it to find the right path.
2746
a_key = iter(entry_keys).next()
2333
# TODO: optimise this to reduce memory use in highly
2334
# fragmented situations by reusing the relocation
2336
a_key = iter(id_index[file_id]).next()
2747
2337
if by_path[a_key][lookup_index][0] in ('r', 'a'):
2748
# its a pointer or missing statement, use it as
2338
# its a pointer or missing statement, use it as is.
2750
2339
new_details.append(by_path[a_key][lookup_index])
2752
2341
# we have the right key, make a pointer to it.
2753
2342
real_path = ('/'.join(a_key[0:2])).strip('/')
2754
new_details.append(st('r', real_path, 0, False,
2343
new_details.append(('r', real_path, 0, False, ''))
2756
2344
new_details.append(self._inv_entry_to_details(entry))
2757
2345
new_details.extend(new_location_suffix)
2758
2346
by_path[new_entry_key] = new_details
2759
self._add_to_id_index(id_index, new_entry_key)
2347
id_index[file_id].add(new_entry_key)
2760
2348
# --- end generation of full tree mappings
2762
2350
# sort and output all the entries
2901
2462
and new_entry_key[1:] < current_old[0][1:])):
2902
2463
# new comes before:
2903
2464
# add a entry for this and advance new
2905
trace.mutter("Inserting from new '%s'.",
2906
new_path_utf8.decode('utf8'))
2907
2465
self.update_minimal(new_entry_key, current_new_minikind,
2908
2466
executable=current_new[1].executable,
2909
path_utf8=new_path_utf8, fingerprint=fingerprint,
2467
path_utf8=new_path_utf8, fingerprint=fingerprint)
2911
2468
current_new = advance(new_iterator)
2913
2470
# we've advanced past the place where the old key would be,
2914
2471
# without seeing it in the new list. so it must be gone.
2916
trace.mutter("Deleting from old '%s/%s'.",
2917
current_old[0][0].decode('utf8'),
2918
current_old[0][1].decode('utf8'))
2919
2472
self._make_absent(current_old)
2920
2473
current_old = advance(old_iterator)
2921
self._mark_modified()
2474
self._dirblock_state = DirState.IN_MEMORY_MODIFIED
2922
2475
self._id_index = None
2923
2476
self._packed_stat_index = None
2925
trace.mutter("set_state_from_inventory complete.")
2927
def set_state_from_scratch(self, working_inv, parent_trees, parent_ghosts):
2928
"""Wipe the currently stored state and set it to something new.
2930
This is a hard-reset for the data we are working with.
2932
# Technically, we really want a write lock, but until we write, we
2933
# don't really need it.
2934
self._requires_lock()
2935
# root dir and root dir contents with no children. We have to have a
2936
# root for set_state_from_inventory to work correctly.
2937
empty_root = (('', '', inventory.ROOT_ID),
2938
[('d', '', 0, False, DirState.NULLSTAT)])
2939
empty_tree_dirblocks = [('', [empty_root]), ('', [])]
2940
self._set_data([], empty_tree_dirblocks)
2941
self.set_state_from_inventory(working_inv)
2942
self.set_parent_trees(parent_trees, parent_ghosts)
2944
2478
def _make_absent(self, current_old):
2945
2479
"""Mark current_old - an entry - as absent for tree 0.
3055
2569
# grab one of them and use it to generate parent
3056
2570
# relocation/absent entries.
3057
2571
new_entry = key, [new_details]
3058
# existing_keys can be changed as we iterate.
3059
for other_key in tuple(existing_keys):
2572
for other_key in existing_keys:
3060
2573
# change the record at other to be a pointer to this new
3061
2574
# record. The loop looks similar to the change to
3062
2575
# relocations when updating an existing record but its not:
3063
2576
# the test for existing kinds is different: this can be
3064
2577
# factored out to a helper though.
3065
other_block_index, present = self._find_block_index_from_key(
3068
raise AssertionError('could not find block for %s' % (
3070
other_block = self._dirblocks[other_block_index][1]
3071
other_entry_index, present = self._find_entry_index(
3072
other_key, other_block)
3074
raise AssertionError(
3075
'update_minimal: could not find other entry for %s'
2578
other_block_index, present = self._find_block_index_from_key(other_key)
2580
raise AssertionError('could not find block for %s' % (other_key,))
2581
other_entry_index, present = self._find_entry_index(other_key,
2582
self._dirblocks[other_block_index][1])
2584
raise AssertionError('could not find entry for %s' % (other_key,))
3077
2585
if path_utf8 is None:
3078
2586
raise AssertionError('no path')
3079
# Turn this other location into a reference to the new
3080
# location. This also updates the aliased iterator
3081
# (current_old in set_state_from_inventory) so that the old
3082
# entry, if not already examined, is skipped over by that
3084
other_entry = other_block[other_entry_index]
3085
other_entry[1][0] = ('r', path_utf8, 0, False, '')
3086
if self._maybe_remove_row(other_block, other_entry_index,
3088
# If the row holding this was removed, we need to
3089
# recompute where this entry goes
3090
entry_index, _ = self._find_entry_index(key, block)
2587
self._dirblocks[other_block_index][1][other_entry_index][1][0] = \
2588
('r', path_utf8, 0, False, '')
3093
# adds a tuple to the new details for each column
3094
# - either by copying an existing relocation pointer inside that column
3095
# - or by creating a new pointer to the right row inside that column
3096
2590
num_present_parents = self._num_present_parents()
3097
if num_present_parents:
3098
# TODO: This re-evaluates the existing_keys set, do we need
3099
# to do that ourselves?
3100
other_key = list(existing_keys)[0]
3101
2591
for lookup_index in xrange(1, num_present_parents + 1):
3102
2592
# grab any one entry, use it to find the right path.
3103
2593
# TODO: optimise this to reduce memory use in highly
3487
2937
entry[1][0] = ('l', '', stat_value.st_size,
3488
2938
False, DirState.NULLSTAT)
3490
state._mark_modified([entry])
2939
state._dirblock_state = DirState.IN_MEMORY_MODIFIED
3491
2940
return link_or_sha1
2941
update_entry = py_update_entry
3494
2944
class ProcessEntryPython(object):
3496
__slots__ = ["old_dirname_to_file_id", "new_dirname_to_file_id",
2946
__slots__ = ["old_dirname_to_file_id", "new_dirname_to_file_id", "uninteresting",
3497
2947
"last_source_parent", "last_target_parent", "include_unchanged",
3498
"partial", "use_filesystem_for_exec", "utf8_decode",
3499
"searched_specific_files", "search_specific_files",
3500
"searched_exact_paths", "search_specific_file_parents", "seen_ids",
3501
"state", "source_index", "target_index", "want_unversioned", "tree"]
2948
"use_filesystem_for_exec", "utf8_decode", "searched_specific_files",
2949
"search_specific_files", "state", "source_index", "target_index",
2950
"want_unversioned", "tree"]
3503
2952
def __init__(self, include_unchanged, use_filesystem_for_exec,
3504
2953
search_specific_files, state, source_index, target_index,
3505
2954
want_unversioned, tree):
3506
2955
self.old_dirname_to_file_id = {}
3507
2956
self.new_dirname_to_file_id = {}
3508
# Are we doing a partial iter_changes?
3509
self.partial = search_specific_files != set([''])
2957
# Just a sentry, so that _process_entry can say that this
2958
# record is handled, but isn't interesting to process (unchanged)
2959
self.uninteresting = object()
3510
2960
# Using a list so that we can access the values and change them in
3511
2961
# nested scope. Each one is [path, file_id, entry]
3512
2962
self.last_source_parent = [None, None]
4168
3577
current_dir_info = dir_iterator.next()
4169
3578
except StopIteration:
4170
3579
current_dir_info = None
4171
for result in self._iter_specific_file_parents():
4174
def _iter_specific_file_parents(self):
4175
"""Iter over the specific file parents."""
4176
while self.search_specific_file_parents:
4177
# Process the parent directories for the paths we were iterating.
4178
# Even in extremely large trees this should be modest, so currently
4179
# no attempt is made to optimise.
4180
path_utf8 = self.search_specific_file_parents.pop()
4181
if osutils.is_inside_any(self.searched_specific_files, path_utf8):
4182
# We've examined this path.
4184
if path_utf8 in self.searched_exact_paths:
4185
# We've examined this path.
4187
path_entries = self.state._entries_for_path(path_utf8)
4188
# We need either one or two entries. If the path in
4189
# self.target_index has moved (so the entry in source_index is in
4190
# 'ar') then we need to also look for the entry for this path in
4191
# self.source_index, to output the appropriate delete-or-rename.
4192
selected_entries = []
4194
for candidate_entry in path_entries:
4195
# Find entries present in target at this path:
4196
if candidate_entry[1][self.target_index][0] not in 'ar':
4198
selected_entries.append(candidate_entry)
4199
# Find entries present in source at this path:
4200
elif (self.source_index is not None and
4201
candidate_entry[1][self.source_index][0] not in 'ar'):
4203
if candidate_entry[1][self.target_index][0] == 'a':
4204
# Deleted, emit it here.
4205
selected_entries.append(candidate_entry)
4207
# renamed, emit it when we process the directory it
4209
self.search_specific_file_parents.add(
4210
candidate_entry[1][self.target_index][1])
4212
raise AssertionError(
4213
"Missing entry for specific path parent %r, %r" % (
4214
path_utf8, path_entries))
4215
path_info = self._path_info(path_utf8, path_utf8.decode('utf8'))
4216
for entry in selected_entries:
4217
if entry[0][2] in self.seen_ids:
4219
result, changed = self._process_entry(entry, path_info)
4221
raise AssertionError(
4222
"Got entry<->path mismatch for specific path "
4223
"%r entry %r path_info %r " % (
4224
path_utf8, entry, path_info))
4225
# Only include changes - we're outside the users requested
4228
self._gather_result_for_consistency(result)
4229
if (result[6][0] == 'directory' and
4230
result[6][1] != 'directory'):
4231
# This stopped being a directory, the old children have
4233
if entry[1][self.source_index][0] == 'r':
4234
# renamed, take the source path
4235
entry_path_utf8 = entry[1][self.source_index][1]
4237
entry_path_utf8 = path_utf8
4238
initial_key = (entry_path_utf8, '', '')
4239
block_index, _ = self.state._find_block_index_from_key(
4241
if block_index == 0:
4242
# The children of the root are in block index 1.
4244
current_block = None
4245
if block_index < len(self.state._dirblocks):
4246
current_block = self.state._dirblocks[block_index]
4247
if not osutils.is_inside(
4248
entry_path_utf8, current_block[0]):
4249
# No entries for this directory at all.
4250
current_block = None
4251
if current_block is not None:
4252
for entry in current_block[1]:
4253
if entry[1][self.source_index][0] in 'ar':
4254
# Not in the source tree, so doesn't have to be
4257
# Path of the entry itself.
4259
self.search_specific_file_parents.add(
4260
osutils.pathjoin(*entry[0][:2]))
4261
if changed or self.include_unchanged:
4263
self.searched_exact_paths.add(path_utf8)
4265
def _path_info(self, utf8_path, unicode_path):
4266
"""Generate path_info for unicode_path.
4268
:return: None if unicode_path does not exist, or a path_info tuple.
4270
abspath = self.tree.abspath(unicode_path)
4272
stat = os.lstat(abspath)
4274
if e.errno == errno.ENOENT:
4275
# the path does not exist.
4279
utf8_basename = utf8_path.rsplit('/', 1)[-1]
4280
dir_info = (utf8_path, utf8_basename,
4281
osutils.file_kind_from_stat_mode(stat.st_mode), stat,
4283
if dir_info[2] == 'directory':
4284
if self.tree._directory_is_tree_reference(
4286
self.root_dir_info = self.root_dir_info[:2] + \
4287
('tree-reference',) + self.root_dir_info[3:]
3580
_process_entry = ProcessEntryPython
4291
3583
# Try to load the compiled form if possible
4293
from bzrlib._dirstate_helpers_pyx import (
3585
from bzrlib._dirstate_helpers_c import (
3586
_read_dirblocks_c as _read_dirblocks,
3587
bisect_dirblock_c as bisect_dirblock,
3588
_bisect_path_left_c as _bisect_path_left,
3589
_bisect_path_right_c as _bisect_path_right,
3590
cmp_by_dirs_c as cmp_by_dirs,
4299
3591
ProcessEntryC as _process_entry,
4300
3592
update_entry as update_entry,
4302
except ImportError, e:
4303
osutils.failed_to_load_extension(e)
4304
3595
from bzrlib._dirstate_helpers_py import (
3596
_read_dirblocks_py as _read_dirblocks,
3597
bisect_dirblock_py as bisect_dirblock,
3598
_bisect_path_left_py as _bisect_path_left,
3599
_bisect_path_right_py as _bisect_path_right,
3600
cmp_by_dirs_py as cmp_by_dirs,
4311
# FIXME: It would be nice to be able to track moved lines so that the
4312
# corresponding python code can be moved to the _dirstate_helpers_py
4313
# module. I don't want to break the history for this important piece of
4314
# code so I left the code here -- vila 20090622
4315
update_entry = py_update_entry
4316
_process_entry = ProcessEntryPython
added
removed
bzrlib/dirstate.py
