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.
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
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
68
74
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
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
95
The entries on disk and in memory are ordered according to the following keys:
106
The entries on disk and in memory are ordered according to the following keys::
97
108
directory, as a list of components
101
112
--- 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,
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,
109
123
PARENT ROW's are emitted for every parent that is not in the ghosts details
110
124
line. That is, if the parents are foo, bar, baz, and the ghosts are bar, then
231
259
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)
262
class DirstateCorrupt(errors.BzrError):
264
_fmt = "The dirstate file (%(state)s) appears to be corrupt: %(msg)s"
266
def __init__(self, state, msg):
267
errors.BzrError.__init__(self)
267
272
class SHA1Provider(object):
411
418
self._last_block_index = None
412
419
self._last_entry_index = None
420
# The set of known hash changes
421
self._known_hash_changes = set()
422
# How many hash changed entries can we have without saving
423
self._worth_saving_limit = worth_saving_limit
424
self._config_stack = config.LocationStack(urlutils.local_path_to_url(
414
427
def __repr__(self):
415
428
return "%s(%r)" % \
416
429
(self.__class__.__name__, self._filename)
431
def _mark_modified(self, hash_changed_entries=None, header_modified=False):
432
"""Mark this dirstate as modified.
434
:param hash_changed_entries: if non-None, mark just these entries as
435
having their hash modified.
436
:param header_modified: mark the header modified as well, not just the
439
#trace.mutter_callsite(3, "modified hash entries: %s", hash_changed_entries)
440
if hash_changed_entries:
441
self._known_hash_changes.update([e[0] for e in hash_changed_entries])
442
if self._dirblock_state in (DirState.NOT_IN_MEMORY,
443
DirState.IN_MEMORY_UNMODIFIED):
444
# If the dirstate is already marked a IN_MEMORY_MODIFIED, then
445
# that takes precedence.
446
self._dirblock_state = DirState.IN_MEMORY_HASH_MODIFIED
448
# TODO: Since we now have a IN_MEMORY_HASH_MODIFIED state, we
449
# should fail noisily if someone tries to set
450
# IN_MEMORY_MODIFIED but we don't have a write-lock!
451
# We don't know exactly what changed so disable smart saving
452
self._dirblock_state = DirState.IN_MEMORY_MODIFIED
454
self._header_state = DirState.IN_MEMORY_MODIFIED
456
def _mark_unmodified(self):
457
"""Mark this dirstate as unmodified."""
458
self._header_state = DirState.IN_MEMORY_UNMODIFIED
459
self._dirblock_state = DirState.IN_MEMORY_UNMODIFIED
460
self._known_hash_changes = set()
418
462
def add(self, path, file_id, kind, stat, fingerprint):
419
463
"""Add a path to be tracked.
1483
1530
if basename_utf8:
1484
1531
parents.add((dirname_utf8, inv_entry.parent_id))
1485
1532
if old_path is None:
1486
adds.append((None, encode(new_path), file_id,
1533
old_path_utf8 = None
1535
old_path_utf8 = encode(old_path)
1536
if old_path is None:
1537
adds.append((None, new_path_utf8, file_id,
1487
1538
inv_to_entry(inv_entry), True))
1488
1539
new_ids.add(file_id)
1489
1540
elif new_path is None:
1490
deletes.append((encode(old_path), None, file_id, None, True))
1491
elif (old_path, new_path) != root_only:
1541
deletes.append((old_path_utf8, None, file_id, None, True))
1542
elif (old_path, new_path) == root_only:
1543
# change things in-place
1544
# Note: the case of a parent directory changing its file_id
1545
# tends to break optimizations here, because officially
1546
# the file has actually been moved, it just happens to
1547
# end up at the same path. If we can figure out how to
1548
# handle that case, we can avoid a lot of add+delete
1549
# pairs for objects that stay put.
1550
# elif old_path == new_path:
1551
changes.append((old_path_utf8, new_path_utf8, file_id,
1552
inv_to_entry(inv_entry)))
1493
1555
# Because renames must preserve their children we must have
1494
1556
# processed all relocations and removes before hand. The sort
1504
1566
self._update_basis_apply_deletes(deletes)
1506
1568
# Split into an add/delete pair recursively.
1507
adds.append((None, new_path_utf8, file_id,
1508
inv_to_entry(inv_entry), False))
1569
adds.append((old_path_utf8, new_path_utf8, file_id,
1570
inv_to_entry(inv_entry), False))
1509
1571
# Expunge deletes that we've seen so that deleted/renamed
1510
1572
# children of a rename directory are handled correctly.
1511
new_deletes = reversed(list(self._iter_child_entries(1,
1573
new_deletes = reversed(list(
1574
self._iter_child_entries(1, old_path_utf8)))
1513
1575
# Remove the current contents of the tree at orig_path, and
1514
1576
# reinsert at the correct new path.
1515
1577
for entry in new_deletes:
1517
source_path = entry[0][0] + '/' + entry[0][1]
1578
child_dirname, child_basename, child_file_id = entry[0]
1580
source_path = child_dirname + b'/' + child_basename
1519
source_path = entry[0][1]
1582
source_path = child_basename
1520
1583
if new_path_utf8:
1521
target_path = new_path_utf8 + source_path[len(old_path):]
1585
new_path_utf8 + source_path[len(old_path_utf8):]
1587
if old_path_utf8 == b'':
1524
1588
raise AssertionError("cannot rename directory to"
1526
target_path = source_path[len(old_path) + 1:]
1590
target_path = source_path[len(old_path_utf8) + 1:]
1527
1591
adds.append((None, target_path, entry[0][2], entry[1][1], False))
1528
1592
deletes.append(
1529
1593
(source_path, target_path, entry[0][2], None, False))
1530
1594
deletes.append(
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)))
1595
(old_path_utf8, new_path_utf8, file_id, None, False))
1537
1597
self._check_delta_ids_absent(new_ids, delta, 1)
1539
1599
# Finish expunging deletes/first half of renames.
1597
1656
# Adds are accumulated partly from renames, so can be in any input
1598
1657
# order - sort it.
1658
# TODO: we may want to sort in dirblocks order. That way each entry
1659
# will end up in the same directory, allowing the _get_entry
1660
# fast-path for looking up 2 items in the same dir work.
1661
adds.sort(key=lambda x: x[1])
1600
1662
# adds is now in lexographic order, which places all parents before
1601
1663
# their children, so we can process it linearly.
1664
st = static_tuple.StaticTuple
1603
1665
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
1666
dirname, basename = osutils.split(new_path)
1667
entry_key = st(dirname, basename, file_id)
1668
block_index, present = self._find_block_index_from_key(entry_key)
1670
# The block where we want to put the file is not present.
1671
# However, it might have just been an empty directory. Look for
1672
# the parent in the basis-so-far before throwing an error.
1673
parent_dir, parent_base = osutils.split(dirname)
1674
parent_block_idx, parent_entry_idx, _, parent_present = \
1675
self._get_block_entry_index(parent_dir, parent_base, 1)
1676
if not parent_present:
1677
self._raise_invalid(new_path, file_id,
1678
"Unable to find block for this record."
1679
" Was the parent added?")
1680
self._ensure_block(parent_block_idx, parent_entry_idx, dirname)
1682
block = self._dirblocks[block_index][1]
1683
entry_index, present = self._find_entry_index(entry_key, block)
1685
if old_path is not None:
1686
self._raise_invalid(new_path, file_id,
1687
'considered a real add but still had old_path at %s'
1690
entry = block[entry_index]
1691
basis_kind = entry[1][1][0]
1692
if basis_kind == b'a':
1693
entry[1][1] = new_details
1694
elif basis_kind == b'r':
1695
raise NotImplementedError()
1697
self._raise_invalid(new_path, file_id,
1698
"An entry was marked as a new add"
1699
" but the basis target already existed")
1701
# The exact key was not found in the block. However, we need to
1702
# check if there is a key next to us that would have matched.
1703
# We only need to check 2 locations, because there are only 2
1705
for maybe_index in range(entry_index-1, entry_index+1):
1706
if maybe_index < 0 or maybe_index >= len(block):
1708
maybe_entry = block[maybe_index]
1709
if maybe_entry[0][:2] != (dirname, basename):
1710
# Just a random neighbor
1712
if maybe_entry[0][2] == file_id:
1713
raise AssertionError(
1714
'_find_entry_index didnt find a key match'
1715
' but walking the data did, for %s'
1717
basis_kind = maybe_entry[1][1][0]
1718
if basis_kind not in (b'a', b'r'):
1719
self._raise_invalid(new_path, file_id,
1720
"we have an add record for path, but the path"
1721
" is already present with another file_id %s"
1722
% (maybe_entry[0][2],))
1724
entry = (entry_key, [DirState.NULL_PARENT_DETAILS,
1726
block.insert(entry_index, entry)
1728
active_kind = entry[1][0][0]
1729
if active_kind == b'a':
1730
# The active record shows up as absent, this could be genuine,
1731
# or it could be present at some other location. We need to
1733
id_index = self._get_id_index()
1734
# The id_index may not be perfectly accurate for tree1, because
1735
# we haven't been keeping it updated. However, it should be
1736
# fine for tree0, and that gives us enough info for what we
1738
keys = id_index.get(file_id, ())
1740
block_i, entry_i, d_present, f_present = \
1741
self._get_block_entry_index(key[0], key[1], 0)
1744
active_entry = self._dirblocks[block_i][1][entry_i]
1745
if (active_entry[0][2] != file_id):
1746
# Some other file is at this path, we don't need to
1749
real_active_kind = active_entry[1][0][0]
1750
if real_active_kind in (b'a', b'r'):
1751
# We found a record, which was not *this* record,
1752
# which matches the file_id, but is not actually
1753
# present. Something seems *really* wrong.
1754
self._raise_invalid(new_path, file_id,
1755
"We found a tree0 entry that doesnt make sense")
1756
# Now, we've found a tree0 entry which matches the file_id
1757
# but is at a different location. So update them to be
1759
active_dir, active_name = active_entry[0][:2]
1761
active_path = active_dir + '/' + active_name
1763
active_path = active_name
1764
active_entry[1][1] = st('r', new_path, 0, False, '')
1765
entry[1][0] = st('r', active_path, 0, False, '')
1766
elif active_kind == 'r':
1767
raise NotImplementedError()
1769
new_kind = new_details[0]
1771
self._ensure_block(block_index, entry_index, new_path)
1620
1773
def _update_basis_apply_changes(self, changes):
1621
1774
"""Apply a sequence of changes to tree 1 during update_basis_by_delta.
1653
1799
null = DirState.NULL_PARENT_DETAILS
1654
1800
for old_path, new_path, file_id, _, real_delete in deletes:
1655
1801
if real_delete != (new_path is None):
1656
self._changes_aborted = True
1657
raise AssertionError("bad delete delta")
1802
self._raise_invalid(old_path, file_id, "bad delete delta")
1658
1803
# the entry for this file_id must be in tree 1.
1659
1804
dirname, basename = osutils.split(old_path)
1660
1805
block_index, entry_index, dir_present, file_present = \
1661
1806
self._get_block_entry_index(dirname, basename, 1)
1662
1807
if not file_present:
1663
self._changes_aborted = True
1664
raise errors.InconsistentDelta(old_path, file_id,
1808
self._raise_invalid(old_path, file_id,
1665
1809
'basis tree does not contain removed entry')
1666
1810
entry = self._dirblocks[block_index][1][entry_index]
1811
# The state of the entry in the 'active' WT
1812
active_kind = entry[1][0][0]
1667
1813
if entry[0][2] != file_id:
1668
self._changes_aborted = True
1669
raise errors.InconsistentDelta(old_path, file_id,
1814
self._raise_invalid(old_path, file_id,
1670
1815
'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.')
1817
old_kind = entry[1][1][0]
1818
if active_kind in b'ar':
1819
# The active tree doesn't have this file_id.
1820
# The basis tree is changing this record. If this is a
1821
# rename, then we don't want the record here at all
1822
# anymore. If it is just an in-place change, we want the
1823
# record here, but we'll add it if we need to. So we just
1825
if active_kind == b'r':
1826
active_path = entry[1][0][1]
1827
active_entry = self._get_entry(0, file_id, active_path)
1828
if active_entry[1][1][0] != b'r':
1829
self._raise_invalid(old_path, file_id,
1830
"Dirstate did not have matching rename entries")
1831
elif active_entry[1][0][0] in 'ar':
1832
self._raise_invalid(old_path, file_id,
1833
"Dirstate had a rename pointing at an inactive"
1835
active_entry[1][1] = null
1677
1836
del self._dirblocks[block_index][1][entry_index]
1837
if old_kind == b'd':
1838
# This was a directory, and the active tree says it
1839
# doesn't exist, and now the basis tree says it doesn't
1840
# exist. Remove its dirblock if present
1842
present) = self._find_block_index_from_key(
1845
dir_block = self._dirblocks[dir_block_index][1]
1847
# This entry is empty, go ahead and just remove it
1848
del self._dirblocks[dir_block_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
1850
# There is still an active record, so just mark this
1853
block_i, entry_i, d_present, f_present = \
1854
self._get_block_entry_index(old_path, '', 1)
1856
dir_block = self._dirblocks[block_i][1]
1857
for child_entry in dir_block:
1858
child_basis_kind = child_entry[1][1][0]
1859
if child_basis_kind not in 'ar':
1860
self._raise_invalid(old_path, file_id,
1861
"The file id was deleted but its children were "
1695
1864
def _after_delta_check_parents(self, parents, index):
1696
1865
"""Check that parents required by the delta are all intact.
2145
2317
def _get_id_index(self):
2146
"""Get an id index of self._dirblocks."""
2318
"""Get an id index of self._dirblocks.
2320
This maps from file_id => [(directory, name, file_id)] entries where
2321
that file_id appears in one of the trees.
2147
2323
if self._id_index is None:
2149
2325
for key, tree_details in self._iter_entries():
2150
id_index.setdefault(key[2], set()).add(key)
2326
self._add_to_id_index(id_index, key)
2151
2327
self._id_index = id_index
2152
2328
return self._id_index
2330
def _add_to_id_index(self, id_index, entry_key):
2331
"""Add this entry to the _id_index mapping."""
2332
# This code used to use a set for every entry in the id_index. However,
2333
# it is *rare* to have more than one entry. So a set is a large
2334
# overkill. And even when we do, we won't ever have more than the
2335
# number of parent trees. Which is still a small number (rarely >2). As
2336
# such, we use a simple tuple, and do our own uniqueness checks. While
2337
# the 'in' check is O(N) since N is nicely bounded it shouldn't ever
2338
# cause quadratic failure.
2339
file_id = entry_key[2]
2340
entry_key = static_tuple.StaticTuple.from_sequence(entry_key)
2341
if file_id not in id_index:
2342
id_index[file_id] = static_tuple.StaticTuple(entry_key,)
2344
entry_keys = id_index[file_id]
2345
if entry_key not in entry_keys:
2346
id_index[file_id] = entry_keys + (entry_key,)
2348
def _remove_from_id_index(self, id_index, entry_key):
2349
"""Remove this entry from the _id_index mapping.
2351
It is an programming error to call this when the entry_key is not
2354
file_id = entry_key[2]
2355
entry_keys = list(id_index[file_id])
2356
entry_keys.remove(entry_key)
2357
id_index[file_id] = static_tuple.StaticTuple.from_sequence(entry_keys)
2154
2359
def _get_output_lines(self, lines):
2155
2360
"""Format lines for final output.
2160
2365
output_lines = [DirState.HEADER_FORMAT_3]
2161
lines.append('') # a final newline
2162
inventory_text = '\0\n\0'.join(lines)
2163
output_lines.append('crc32: %s\n' % (zlib.crc32(inventory_text),))
2366
lines.append(b'') # a final newline
2367
inventory_text = b'\0\n\0'.join(lines)
2368
output_lines.append(b'crc32: %d\n' % (zlib.crc32(inventory_text),))
2164
2369
# -3, 1 for num parents, 1 for ghosts, 1 for final newline
2165
2370
num_entries = len(lines)-3
2166
output_lines.append('num_entries: %s\n' % (num_entries,))
2371
output_lines.append(b'num_entries: %d\n' % (num_entries,))
2167
2372
output_lines.append(inventory_text)
2168
2373
return output_lines
2170
2375
def _make_deleted_row(self, fileid_utf8, parents):
2171
2376
"""Return a deleted row for fileid_utf8."""
2172
return ('/', 'RECYCLED.BIN', 'file', fileid_utf8, 0, DirState.NULLSTAT,
2377
return (b'/', b'RECYCLED.BIN', b'file', fileid_utf8, 0, DirState.NULLSTAT,
2175
2380
def _num_present_parents(self):
2176
2381
"""The number of parent entries in each record row."""
2177
2382
return len(self._parents) - len(self._ghosts)
2180
def on_file(path, sha1_provider=None):
2385
def on_file(cls, path, sha1_provider=None, worth_saving_limit=0):
2181
2386
"""Construct a DirState on the file at path "path".
2183
2388
:param path: The path at which the dirstate file on disk should live.
2184
2389
:param sha1_provider: an object meeting the SHA1Provider interface.
2185
2390
If None, a DefaultSHA1Provider is used.
2391
:param worth_saving_limit: when the exact number of hash changed
2392
entries is known, only bother saving the dirstate if more than
2393
this count of entries have changed. -1 means never save.
2186
2394
:return: An unlocked DirState object, associated with the given path.
2188
2396
if sha1_provider is None:
2189
2397
sha1_provider = DefaultSHA1Provider()
2190
result = DirState(path, sha1_provider)
2398
result = cls(path, sha1_provider,
2399
worth_saving_limit=worth_saving_limit)
2193
2402
def _read_dirblocks_if_needed(self):
2243
2452
raise errors.BzrError(
2244
2453
'invalid header line: %r' % (header,))
2245
2454
crc_line = self._state_file.readline()
2246
if not crc_line.startswith('crc32: '):
2455
if not crc_line.startswith(b'crc32: '):
2247
2456
raise errors.BzrError('missing crc32 checksum: %r' % crc_line)
2248
self.crc_expected = int(crc_line[len('crc32: '):-1])
2457
self.crc_expected = int(crc_line[len(b'crc32: '):-1])
2249
2458
num_entries_line = self._state_file.readline()
2250
if not num_entries_line.startswith('num_entries: '):
2459
if not num_entries_line.startswith(b'num_entries: '):
2251
2460
raise errors.BzrError('missing num_entries line')
2252
self._num_entries = int(num_entries_line[len('num_entries: '):-1])
2461
self._num_entries = int(num_entries_line[len(b'num_entries: '):-1])
2254
def sha1_from_stat(self, path, stat_result, _pack_stat=pack_stat):
2463
def sha1_from_stat(self, path, stat_result):
2255
2464
"""Find a sha1 given a stat lookup."""
2256
return self._get_packed_stat_index().get(_pack_stat(stat_result), None)
2465
return self._get_packed_stat_index().get(pack_stat(stat_result), None)
2258
2467
def _get_packed_stat_index(self):
2259
2468
"""Get a packed_stat index of self._dirblocks."""
2260
2469
if self._packed_stat_index is None:
2262
2471
for key, tree_details in self._iter_entries():
2263
if tree_details[0][0] == 'f':
2472
if tree_details[0][0] == b'f':
2264
2473
index[tree_details[0][4]] = tree_details[0][1]
2265
2474
self._packed_stat_index = index
2266
2475
return self._packed_stat_index
2285
2494
trace.mutter('Not saving DirState because '
2286
2495
'_changes_aborted is set.')
2288
if (self._header_state == DirState.IN_MEMORY_MODIFIED or
2289
self._dirblock_state == DirState.IN_MEMORY_MODIFIED):
2497
# TODO: Since we now distinguish IN_MEMORY_MODIFIED from
2498
# IN_MEMORY_HASH_MODIFIED, we should only fail quietly if we fail
2499
# to save an IN_MEMORY_HASH_MODIFIED, and fail *noisily* if we
2500
# fail to save IN_MEMORY_MODIFIED
2501
if not self._worth_saving():
2291
grabbed_write_lock = False
2292
if self._lock_state != 'w':
2293
grabbed_write_lock, new_lock = self._lock_token.temporary_write_lock()
2294
# Switch over to the new lock, as the old one may be closed.
2504
grabbed_write_lock = False
2505
if self._lock_state != 'w':
2506
grabbed_write_lock, new_lock = self._lock_token.temporary_write_lock()
2507
# Switch over to the new lock, as the old one may be closed.
2508
# TODO: jam 20070315 We should validate the disk file has
2509
# not changed contents, since temporary_write_lock may
2510
# not be an atomic operation.
2511
self._lock_token = new_lock
2512
self._state_file = new_lock.f
2513
if not grabbed_write_lock:
2514
# We couldn't grab a write lock, so we switch back to a read one
2517
lines = self.get_lines()
2518
self._state_file.seek(0)
2519
self._state_file.writelines(lines)
2520
self._state_file.truncate()
2521
self._state_file.flush()
2522
self._maybe_fdatasync()
2523
self._mark_unmodified()
2525
if grabbed_write_lock:
2526
self._lock_token = self._lock_token.restore_read_lock()
2527
self._state_file = self._lock_token.f
2295
2528
# TODO: jam 20070315 We should validate the disk file has
2296
# not changed contents. Since temporary_write_lock may
2297
# not be an atomic operation.
2298
self._lock_token = new_lock
2299
self._state_file = new_lock.f
2300
if not grabbed_write_lock:
2301
# We couldn't grab a write lock, so we switch back to a read one
2304
self._state_file.seek(0)
2305
self._state_file.writelines(self.get_lines())
2306
self._state_file.truncate()
2307
self._state_file.flush()
2308
self._header_state = DirState.IN_MEMORY_UNMODIFIED
2309
self._dirblock_state = DirState.IN_MEMORY_UNMODIFIED
2311
if grabbed_write_lock:
2312
self._lock_token = self._lock_token.restore_read_lock()
2313
self._state_file = self._lock_token.f
2314
# TODO: jam 20070315 We should validate the disk file has
2315
# not changed contents. Since restore_read_lock may
2316
# not be an atomic operation.
2529
# not changed contents. Since restore_read_lock may
2530
# not be an atomic operation.
2532
def _maybe_fdatasync(self):
2533
"""Flush to disk if possible and if not configured off."""
2534
if self._config_stack.get('dirstate.fdatasync'):
2535
osutils.fdatasync(self._state_file.fileno())
2537
def _worth_saving(self):
2538
"""Is it worth saving the dirstate or not?"""
2539
if (self._header_state == DirState.IN_MEMORY_MODIFIED
2540
or self._dirblock_state == DirState.IN_MEMORY_MODIFIED):
2542
if self._dirblock_state == DirState.IN_MEMORY_HASH_MODIFIED:
2543
if self._worth_saving_limit == -1:
2544
# We never save hash changes when the limit is -1
2546
# If we're using smart saving and only a small number of
2547
# entries have changed their hash, don't bother saving. John has
2548
# suggested using a heuristic here based on the size of the
2549
# changed files and/or tree. For now, we go with a configurable
2550
# number of changes, keeping the calculation time
2551
# as low overhead as possible. (This also keeps all existing
2552
# tests passing as the default is 0, i.e. always save.)
2553
if len(self._known_hash_changes) >= self._worth_saving_limit:
2318
2557
def _set_data(self, parent_ids, dirblocks):
2319
2558
"""Set the full dirstate data in memory.
2463
2717
# mapping from path,id. We need to look up the correct path
2464
2718
# for the indexes from 0 to tree_index -1
2465
2719
new_details = []
2466
for lookup_index in xrange(tree_index):
2720
for lookup_index in range(tree_index):
2467
2721
# boundary case: this is the first occurence of file_id
2468
# so there are no id_indexs, possibly take this out of
2722
# so there are no id_indexes, possibly take this out of
2470
if not len(id_index[file_id]):
2724
if not len(entry_keys):
2471
2725
new_details.append(DirState.NULL_PARENT_DETAILS)
2473
2727
# 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.
2728
a_key = next(iter(entry_keys))
2729
if by_path[a_key][lookup_index][0] in (b'r', b'a'):
2730
# its a pointer or missing statement, use it as
2480
2732
new_details.append(by_path[a_key][lookup_index])
2482
2734
# 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, ''))
2735
real_path = (b'/'.join(a_key[0:2])).strip(b'/')
2736
new_details.append(st(b'r', real_path, 0, False,
2485
2738
new_details.append(self._inv_entry_to_details(entry))
2486
2739
new_details.extend(new_location_suffix)
2487
2740
by_path[new_entry_key] = new_details
2488
id_index[file_id].add(new_entry_key)
2741
self._add_to_id_index(id_index, new_entry_key)
2489
2742
# --- end generation of full tree mappings
2491
2744
# sort and output all the entries
2492
new_entries = self._sort_entries(by_path.items())
2745
new_entries = self._sort_entries(viewitems(by_path))
2493
2746
self._entries_to_current_state(new_entries)
2494
2747
self._parents = [rev_id for rev_id, tree in trees]
2495
2748
self._ghosts = list(ghosts)
2496
self._header_state = DirState.IN_MEMORY_MODIFIED
2497
self._dirblock_state = DirState.IN_MEMORY_MODIFIED
2749
self._mark_modified(header_modified=True)
2498
2750
self._id_index = id_index
2500
2752
def _sort_entries(self, entry_list):
2849
3139
if not present:
2850
3140
raise AssertionError('not present: %r', entry_key)
2851
3141
self._dirblocks[block_index][1][entry_index][1][0] = \
2852
('r', path_utf8, 0, False, '')
3142
(b'r', path_utf8, 0, False, b'')
2853
3143
# add a containing dirblock if needed.
2854
if new_details[0] == 'd':
2855
subdir_key = (osutils.pathjoin(*key[0:2]), '', '')
3144
if new_details[0] == b'd':
3145
# GZ 2017-06-09: Using pathjoin why?
3146
subdir_key = (osutils.pathjoin(*key[0:2]), b'', b'')
2856
3147
block_index, present = self._find_block_index_from_key(subdir_key)
2857
3148
if not present:
2858
3149
self._dirblocks.insert(block_index, (subdir_key[0], []))
2860
self._dirblock_state = DirState.IN_MEMORY_MODIFIED
3151
self._mark_modified()
2862
3153
def _maybe_remove_row(self, block, index, id_index):
2863
3154
"""Remove index if it is absent or relocated across the row.
2865
3156
id_index is updated accordingly.
3157
:return: True if we removed the row, False otherwise
2867
3159
present_in_row = False
2868
3160
entry = block[index]
2869
3161
for column in entry[1]:
2870
if column[0] not in 'ar':
3162
if column[0] not in (b'a', b'r'):
2871
3163
present_in_row = True
2873
3165
if not present_in_row:
2874
3166
block.pop(index)
2875
id_index[entry[0][2]].remove(entry[0])
3167
self._remove_from_id_index(id_index, entry[0])
2877
3171
def _validate(self):
2878
3172
"""Check that invariants on the dirblock are correct.
added
removed
breezy/bzr/dirstate.py
