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
411
self._last_block_index = None
448
412
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
414
def __repr__(self):
457
415
return "%s(%r)" % \
458
416
(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
418
def add(self, path, file_id, kind, stat, fingerprint):
492
419
"""Add a path to be tracked.
1554
1483
if basename_utf8:
1555
1484
parents.add((dirname_utf8, inv_entry.parent_id))
1556
1485
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,
1486
adds.append((None, encode(new_path), file_id,
1562
1487
inv_to_entry(inv_entry), True))
1563
1488
new_ids.add(file_id)
1564
1489
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)))
1490
deletes.append((encode(old_path), None, file_id, None, True))
1491
elif (old_path, new_path) != root_only:
1579
1493
# Because renames must preserve their children we must have
1580
1494
# processed all relocations and removes before hand. The sort
1590
1504
self._update_basis_apply_deletes(deletes)
1592
1506
# 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))
1507
adds.append((None, new_path_utf8, file_id,
1508
inv_to_entry(inv_entry), False))
1595
1509
# Expunge deletes that we've seen so that deleted/renamed
1596
1510
# children of a rename directory are handled correctly.
1597
new_deletes = reversed(list(
1598
self._iter_child_entries(1, old_path_utf8)))
1511
new_deletes = reversed(list(self._iter_child_entries(1,
1599
1513
# Remove the current contents of the tree at orig_path, and
1600
1514
# reinsert at the correct new path.
1601
1515
for entry in new_deletes:
1602
child_dirname, child_basename, child_file_id = entry[0]
1604
source_path = child_dirname + '/' + child_basename
1517
source_path = entry[0][0] + '/' + entry[0][1]
1606
source_path = child_basename
1519
source_path = entry[0][1]
1607
1520
if new_path_utf8:
1608
1521
target_path = new_path_utf8 + source_path[len(old_path):]
1610
1523
if old_path == '':
1611
1524
raise AssertionError("cannot rename directory to"
1613
1526
target_path = source_path[len(old_path) + 1:]
1614
1527
adds.append((None, target_path, entry[0][2], entry[1][1], False))
1615
1528
deletes.append(
1616
1529
(source_path, target_path, entry[0][2], None, False))
1617
deletes.append((old_path_utf8, new_path, file_id, 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)))
1618
1537
self._check_delta_ids_absent(new_ids, delta, 1)
1620
1539
# Finish expunging deletes/first half of renames.
1677
1597
# Adds are accumulated partly from renames, so can be in any input
1678
1598
# 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
1600
# adds is now in lexographic order, which places all parents before
1684
1601
# their children, so we can process it linearly.
1686
st = static_tuple.StaticTuple
1687
1603
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)
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
1786
1620
def _update_basis_apply_changes(self, changes):
1787
1621
"""Apply a sequence of changes to tree 1 during update_basis_by_delta.
1813
1653
null = DirState.NULL_PARENT_DETAILS
1814
1654
for old_path, new_path, file_id, _, real_delete in deletes:
1815
1655
if real_delete != (new_path is None):
1816
self._raise_invalid(old_path, file_id, "bad delete delta")
1656
self._changes_aborted = True
1657
raise AssertionError("bad delete delta")
1817
1658
# the entry for this file_id must be in tree 1.
1818
1659
dirname, basename = osutils.split(old_path)
1819
1660
block_index, entry_index, dir_present, file_present = \
1820
1661
self._get_block_entry_index(dirname, basename, 1)
1821
1662
if not file_present:
1822
self._raise_invalid(old_path, file_id,
1663
self._changes_aborted = True
1664
raise errors.InconsistentDelta(old_path, file_id,
1823
1665
'basis tree does not contain removed entry')
1824
1666
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
1667
if entry[0][2] != file_id:
1828
self._raise_invalid(old_path, file_id,
1668
self._changes_aborted = True
1669
raise errors.InconsistentDelta(old_path, file_id,
1829
1670
'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
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.')
1850
1677
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 "
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
1878
1695
def _after_delta_check_parents(self, parents, index):
1879
1696
"""Check that parents required by the delta are all intact.
2331
2143
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.
2144
"""Get an id index of self._dirblocks."""
2337
2145
if self._id_index is None:
2339
2147
for key, tree_details in self._iter_entries():
2340
self._add_to_id_index(id_index, key)
2148
id_index.setdefault(key[2], set()).add(key)
2341
2149
self._id_index = id_index
2342
2150
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
2152
def _get_output_lines(self, lines):
2374
2153
"""Format lines for final output.
2508
2283
trace.mutter('Not saving DirState because '
2509
2284
'_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():
2286
if (self._header_state == DirState.IN_MEMORY_MODIFIED or
2287
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
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.
2542
2293
# 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:
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.
2571
2316
def _set_data(self, parent_ids, dirblocks):
2572
2317
"""Set the full dirstate data in memory.
2737
2465
new_details = []
2738
2466
for lookup_index in xrange(tree_index):
2739
2467
# boundary case: this is the first occurence of file_id
2740
# so there are no id_indexes, possibly take this out of
2468
# so there are no id_indexs, possibly take this out of
2742
if not len(entry_keys):
2470
if not len(id_index[file_id]):
2743
2471
new_details.append(DirState.NULL_PARENT_DETAILS)
2745
2473
# grab any one entry, use it to find the right path.
2746
a_key = iter(entry_keys).next()
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()
2747
2478
if by_path[a_key][lookup_index][0] in ('r', 'a'):
2748
# its a pointer or missing statement, use it as
2479
# its a pointer or missing statement, use it as is.
2750
2480
new_details.append(by_path[a_key][lookup_index])
2752
2482
# we have the right key, make a pointer to it.
2753
2483
real_path = ('/'.join(a_key[0:2])).strip('/')
2754
new_details.append(st('r', real_path, 0, False,
2484
new_details.append(('r', real_path, 0, False, ''))
2756
2485
new_details.append(self._inv_entry_to_details(entry))
2757
2486
new_details.extend(new_location_suffix)
2758
2487
by_path[new_entry_key] = new_details
2759
self._add_to_id_index(id_index, new_entry_key)
2488
id_index[file_id].add(new_entry_key)
2760
2489
# --- end generation of full tree mappings
2762
2491
# sort and output all the entries
3487
3159
entry[1][0] = ('l', '', stat_value.st_size,
3488
3160
False, DirState.NULLSTAT)
3490
state._mark_modified([entry])
3161
state._dirblock_state = DirState.IN_MEMORY_MODIFIED
3491
3162
return link_or_sha1
3494
3165
class ProcessEntryPython(object):
3496
__slots__ = ["old_dirname_to_file_id", "new_dirname_to_file_id",
3167
__slots__ = ["old_dirname_to_file_id", "new_dirname_to_file_id", "uninteresting",
3497
3168
"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"]
3169
"use_filesystem_for_exec", "utf8_decode", "searched_specific_files",
3170
"search_specific_files", "state", "source_index", "target_index",
3171
"want_unversioned", "tree"]
3503
3173
def __init__(self, include_unchanged, use_filesystem_for_exec,
3504
3174
search_specific_files, state, source_index, target_index,
3505
3175
want_unversioned, tree):
3506
3176
self.old_dirname_to_file_id = {}
3507
3177
self.new_dirname_to_file_id = {}
3508
# Are we doing a partial iter_changes?
3509
self.partial = search_specific_files != set([''])
3178
# Just a sentry, so that _process_entry can say that this
3179
# record is handled, but isn't interesting to process (unchanged)
3180
self.uninteresting = object()
3510
3181
# Using a list so that we can access the values and change them in
3511
3182
# nested scope. Each one is [path, file_id, entry]
3512
3183
self.last_source_parent = [None, None]
4168
3796
current_dir_info = dir_iterator.next()
4169
3797
except StopIteration:
4170
3798
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:]
4291
3801
# Try to load the compiled form if possible
added
removed
bzrlib/dirstate.py
