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
251
ERROR_DIRECTORY = 267
234
if not getattr(struct, '_compile', None):
235
# Cannot pre-compile the dirstate pack_stat
236
def pack_stat(st, _encode=binascii.b2a_base64, _pack=struct.pack):
237
"""Convert stat values into a packed representation."""
238
return _encode(_pack('>LLLLLL', st.st_size, int(st.st_mtime),
239
int(st.st_ctime), st.st_dev, st.st_ino & 0xFFFFFFFF,
242
# compile the struct compiler we need, so as to only do it once
243
from _struct import Struct
244
_compiled_pack = Struct('>LLLLLL').pack
245
def pack_stat(st, _encode=binascii.b2a_base64, _pack=_compiled_pack):
246
"""Convert stat values into a packed representation."""
247
# jam 20060614 it isn't really worth removing more entries if we
248
# are going to leave it in packed form.
249
# With only st_mtime and st_mode filesize is 5.5M and read time is 275ms
250
# With all entries, filesize is 5.9M and read time is maybe 280ms
251
# well within the noise margin
253
# base64 encoding always adds a final newline, so strip it off
254
# The current version
255
return _encode(_pack(st.st_size, int(st.st_mtime), int(st.st_ctime),
256
st.st_dev, st.st_ino & 0xFFFFFFFF, st.st_mode))[:-1]
257
# This is 0.060s / 1.520s faster by not encoding as much information
258
# return _encode(_pack('>LL', int(st.st_mtime), st.st_mode))[:-1]
259
# This is not strictly faster than _encode(_pack())[:-1]
260
# return '%X.%X.%X.%X.%X.%X' % (
261
# st.st_size, int(st.st_mtime), int(st.st_ctime),
262
# st.st_dev, st.st_ino, st.st_mode)
263
# Similar to the _encode(_pack('>LL'))
264
# return '%X.%X' % (int(st.st_mtime), st.st_mode)
267
254
class SHA1Provider(object):
268
255
"""An interface for getting sha1s of a file."""
411
403
self._last_block_index = None
412
404
self._last_entry_index = None
405
# The set of known hash changes
406
self._known_hash_changes = set()
407
# How many hash changed entries can we have without saving
408
self._worth_saving_limit = worth_saving_limit
409
self._config_stack = config.LocationStack(urlutils.local_path_to_url(
414
412
def __repr__(self):
415
413
return "%s(%r)" % \
416
414
(self.__class__.__name__, self._filename)
416
def _mark_modified(self, hash_changed_entries=None, header_modified=False):
417
"""Mark this dirstate as modified.
419
:param hash_changed_entries: if non-None, mark just these entries as
420
having their hash modified.
421
:param header_modified: mark the header modified as well, not just the
424
#trace.mutter_callsite(3, "modified hash entries: %s", hash_changed_entries)
425
if hash_changed_entries:
426
self._known_hash_changes.update([e[0] for e in hash_changed_entries])
427
if self._dirblock_state in (DirState.NOT_IN_MEMORY,
428
DirState.IN_MEMORY_UNMODIFIED):
429
# If the dirstate is already marked a IN_MEMORY_MODIFIED, then
430
# that takes precedence.
431
self._dirblock_state = DirState.IN_MEMORY_HASH_MODIFIED
433
# TODO: Since we now have a IN_MEMORY_HASH_MODIFIED state, we
434
# should fail noisily if someone tries to set
435
# IN_MEMORY_MODIFIED but we don't have a write-lock!
436
# We don't know exactly what changed so disable smart saving
437
self._dirblock_state = DirState.IN_MEMORY_MODIFIED
439
self._header_state = DirState.IN_MEMORY_MODIFIED
441
def _mark_unmodified(self):
442
"""Mark this dirstate as unmodified."""
443
self._header_state = DirState.IN_MEMORY_UNMODIFIED
444
self._dirblock_state = DirState.IN_MEMORY_UNMODIFIED
445
self._known_hash_changes = set()
418
447
def add(self, path, file_id, kind, stat, fingerprint):
419
448
"""Add a path to be tracked.
1483
1510
if basename_utf8:
1484
1511
parents.add((dirname_utf8, inv_entry.parent_id))
1485
1512
if old_path is None:
1486
adds.append((None, encode(new_path), file_id,
1513
old_path_utf8 = None
1515
old_path_utf8 = encode(old_path)
1516
if old_path is None:
1517
adds.append((None, new_path_utf8, file_id,
1487
1518
inv_to_entry(inv_entry), True))
1488
1519
new_ids.add(file_id)
1489
1520
elif new_path is None:
1490
deletes.append((encode(old_path), None, file_id, None, True))
1491
elif (old_path, new_path) != root_only:
1521
deletes.append((old_path_utf8, None, file_id, None, True))
1522
elif (old_path, new_path) == root_only:
1523
# change things in-place
1524
# Note: the case of a parent directory changing its file_id
1525
# tends to break optimizations here, because officially
1526
# the file has actually been moved, it just happens to
1527
# end up at the same path. If we can figure out how to
1528
# handle that case, we can avoid a lot of add+delete
1529
# pairs for objects that stay put.
1530
# elif old_path == new_path:
1531
changes.append((old_path_utf8, new_path_utf8, file_id,
1532
inv_to_entry(inv_entry)))
1493
1535
# Because renames must preserve their children we must have
1494
1536
# processed all relocations and removes before hand. The sort
1504
1546
self._update_basis_apply_deletes(deletes)
1506
1548
# Split into an add/delete pair recursively.
1507
adds.append((None, new_path_utf8, file_id,
1508
inv_to_entry(inv_entry), False))
1549
adds.append((old_path_utf8, new_path_utf8, file_id,
1550
inv_to_entry(inv_entry), False))
1509
1551
# Expunge deletes that we've seen so that deleted/renamed
1510
1552
# children of a rename directory are handled correctly.
1511
new_deletes = reversed(list(self._iter_child_entries(1,
1553
new_deletes = reversed(list(
1554
self._iter_child_entries(1, old_path_utf8)))
1513
1555
# Remove the current contents of the tree at orig_path, and
1514
1556
# reinsert at the correct new path.
1515
1557
for entry in new_deletes:
1517
source_path = entry[0][0] + '/' + entry[0][1]
1558
child_dirname, child_basename, child_file_id = entry[0]
1560
source_path = child_dirname + '/' + child_basename
1519
source_path = entry[0][1]
1562
source_path = child_basename
1520
1563
if new_path_utf8:
1521
target_path = new_path_utf8 + source_path[len(old_path):]
1565
new_path_utf8 + source_path[len(old_path_utf8):]
1567
if old_path_utf8 == '':
1524
1568
raise AssertionError("cannot rename directory to"
1526
target_path = source_path[len(old_path) + 1:]
1570
target_path = source_path[len(old_path_utf8) + 1:]
1527
1571
adds.append((None, target_path, entry[0][2], entry[1][1], False))
1528
1572
deletes.append(
1529
1573
(source_path, target_path, entry[0][2], None, False))
1530
1574
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)))
1575
(old_path_utf8, new_path_utf8, file_id, None, False))
1537
1577
self._check_delta_ids_absent(new_ids, delta, 1)
1539
1579
# Finish expunging deletes/first half of renames.
1597
1636
# Adds are accumulated partly from renames, so can be in any input
1598
1637
# order - sort it.
1638
# TODO: we may want to sort in dirblocks order. That way each entry
1639
# will end up in the same directory, allowing the _get_entry
1640
# fast-path for looking up 2 items in the same dir work.
1641
adds.sort(key=lambda x: x[1])
1600
1642
# adds is now in lexographic order, which places all parents before
1601
1643
# their children, so we can process it linearly.
1645
st = static_tuple.StaticTuple
1603
1646
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
1647
dirname, basename = osutils.split(new_path)
1648
entry_key = st(dirname, basename, file_id)
1649
block_index, present = self._find_block_index_from_key(entry_key)
1651
# The block where we want to put the file is not present.
1652
# However, it might have just been an empty directory. Look for
1653
# the parent in the basis-so-far before throwing an error.
1654
parent_dir, parent_base = osutils.split(dirname)
1655
parent_block_idx, parent_entry_idx, _, parent_present = \
1656
self._get_block_entry_index(parent_dir, parent_base, 1)
1657
if not parent_present:
1658
self._raise_invalid(new_path, file_id,
1659
"Unable to find block for this record."
1660
" Was the parent added?")
1661
self._ensure_block(parent_block_idx, parent_entry_idx, dirname)
1663
block = self._dirblocks[block_index][1]
1664
entry_index, present = self._find_entry_index(entry_key, block)
1666
if old_path is not None:
1667
self._raise_invalid(new_path, file_id,
1668
'considered a real add but still had old_path at %s'
1671
entry = block[entry_index]
1672
basis_kind = entry[1][1][0]
1673
if basis_kind == 'a':
1674
entry[1][1] = new_details
1675
elif basis_kind == 'r':
1676
raise NotImplementedError()
1678
self._raise_invalid(new_path, file_id,
1679
"An entry was marked as a new add"
1680
" but the basis target already existed")
1682
# The exact key was not found in the block. However, we need to
1683
# check if there is a key next to us that would have matched.
1684
# We only need to check 2 locations, because there are only 2
1686
for maybe_index in range(entry_index-1, entry_index+1):
1687
if maybe_index < 0 or maybe_index >= len(block):
1689
maybe_entry = block[maybe_index]
1690
if maybe_entry[0][:2] != (dirname, basename):
1691
# Just a random neighbor
1693
if maybe_entry[0][2] == file_id:
1694
raise AssertionError(
1695
'_find_entry_index didnt find a key match'
1696
' but walking the data did, for %s'
1698
basis_kind = maybe_entry[1][1][0]
1699
if basis_kind not in 'ar':
1700
self._raise_invalid(new_path, file_id,
1701
"we have an add record for path, but the path"
1702
" is already present with another file_id %s"
1703
% (maybe_entry[0][2],))
1705
entry = (entry_key, [DirState.NULL_PARENT_DETAILS,
1707
block.insert(entry_index, entry)
1709
active_kind = entry[1][0][0]
1710
if active_kind == 'a':
1711
# The active record shows up as absent, this could be genuine,
1712
# or it could be present at some other location. We need to
1714
id_index = self._get_id_index()
1715
# The id_index may not be perfectly accurate for tree1, because
1716
# we haven't been keeping it updated. However, it should be
1717
# fine for tree0, and that gives us enough info for what we
1719
keys = id_index.get(file_id, ())
1721
block_i, entry_i, d_present, f_present = \
1722
self._get_block_entry_index(key[0], key[1], 0)
1725
active_entry = self._dirblocks[block_i][1][entry_i]
1726
if (active_entry[0][2] != file_id):
1727
# Some other file is at this path, we don't need to
1730
real_active_kind = active_entry[1][0][0]
1731
if real_active_kind in 'ar':
1732
# We found a record, which was not *this* record,
1733
# which matches the file_id, but is not actually
1734
# present. Something seems *really* wrong.
1735
self._raise_invalid(new_path, file_id,
1736
"We found a tree0 entry that doesnt make sense")
1737
# Now, we've found a tree0 entry which matches the file_id
1738
# but is at a different location. So update them to be
1740
active_dir, active_name = active_entry[0][:2]
1742
active_path = active_dir + '/' + active_name
1744
active_path = active_name
1745
active_entry[1][1] = st('r', new_path, 0, False, '')
1746
entry[1][0] = st('r', active_path, 0, False, '')
1747
elif active_kind == 'r':
1748
raise NotImplementedError()
1750
new_kind = new_details[0]
1752
self._ensure_block(block_index, entry_index, new_path)
1620
1754
def _update_basis_apply_changes(self, changes):
1621
1755
"""Apply a sequence of changes to tree 1 during update_basis_by_delta.
1653
1781
null = DirState.NULL_PARENT_DETAILS
1654
1782
for old_path, new_path, file_id, _, real_delete in deletes:
1655
1783
if real_delete != (new_path is None):
1656
self._changes_aborted = True
1657
raise AssertionError("bad delete delta")
1784
self._raise_invalid(old_path, file_id, "bad delete delta")
1658
1785
# the entry for this file_id must be in tree 1.
1659
1786
dirname, basename = osutils.split(old_path)
1660
1787
block_index, entry_index, dir_present, file_present = \
1661
1788
self._get_block_entry_index(dirname, basename, 1)
1662
1789
if not file_present:
1663
self._changes_aborted = True
1664
raise errors.InconsistentDelta(old_path, file_id,
1790
self._raise_invalid(old_path, file_id,
1665
1791
'basis tree does not contain removed entry')
1666
1792
entry = self._dirblocks[block_index][1][entry_index]
1793
# The state of the entry in the 'active' WT
1794
active_kind = entry[1][0][0]
1667
1795
if entry[0][2] != file_id:
1668
self._changes_aborted = True
1669
raise errors.InconsistentDelta(old_path, file_id,
1796
self._raise_invalid(old_path, file_id,
1670
1797
'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.')
1799
old_kind = entry[1][1][0]
1800
if active_kind in 'ar':
1801
# The active tree doesn't have this file_id.
1802
# The basis tree is changing this record. If this is a
1803
# rename, then we don't want the record here at all
1804
# anymore. If it is just an in-place change, we want the
1805
# record here, but we'll add it if we need to. So we just
1807
if active_kind == 'r':
1808
active_path = entry[1][0][1]
1809
active_entry = self._get_entry(0, file_id, active_path)
1810
if active_entry[1][1][0] != 'r':
1811
self._raise_invalid(old_path, file_id,
1812
"Dirstate did not have matching rename entries")
1813
elif active_entry[1][0][0] in 'ar':
1814
self._raise_invalid(old_path, file_id,
1815
"Dirstate had a rename pointing at an inactive"
1817
active_entry[1][1] = null
1677
1818
del self._dirblocks[block_index][1][entry_index]
1820
# This was a directory, and the active tree says it
1821
# doesn't exist, and now the basis tree says it doesn't
1822
# exist. Remove its dirblock if present
1824
present) = self._find_block_index_from_key(
1827
dir_block = self._dirblocks[dir_block_index][1]
1829
# This entry is empty, go ahead and just remove it
1830
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
1832
# There is still an active record, so just mark this
1835
block_i, entry_i, d_present, f_present = \
1836
self._get_block_entry_index(old_path, '', 1)
1838
dir_block = self._dirblocks[block_i][1]
1839
for child_entry in dir_block:
1840
child_basis_kind = child_entry[1][1][0]
1841
if child_basis_kind not in 'ar':
1842
self._raise_invalid(old_path, file_id,
1843
"The file id was deleted but its children were "
1695
1846
def _after_delta_check_parents(self, parents, index):
1696
1847
"""Check that parents required by the delta are all intact.
2143
2298
def _get_id_index(self):
2144
"""Get an id index of self._dirblocks."""
2299
"""Get an id index of self._dirblocks.
2301
This maps from file_id => [(directory, name, file_id)] entries where
2302
that file_id appears in one of the trees.
2145
2304
if self._id_index is None:
2147
2306
for key, tree_details in self._iter_entries():
2148
id_index.setdefault(key[2], set()).add(key)
2307
self._add_to_id_index(id_index, key)
2149
2308
self._id_index = id_index
2150
2309
return self._id_index
2311
def _add_to_id_index(self, id_index, entry_key):
2312
"""Add this entry to the _id_index mapping."""
2313
# This code used to use a set for every entry in the id_index. However,
2314
# it is *rare* to have more than one entry. So a set is a large
2315
# overkill. And even when we do, we won't ever have more than the
2316
# number of parent trees. Which is still a small number (rarely >2). As
2317
# such, we use a simple tuple, and do our own uniqueness checks. While
2318
# the 'in' check is O(N) since N is nicely bounded it shouldn't ever
2319
# cause quadratic failure.
2320
file_id = entry_key[2]
2321
entry_key = static_tuple.StaticTuple.from_sequence(entry_key)
2322
if file_id not in id_index:
2323
id_index[file_id] = static_tuple.StaticTuple(entry_key,)
2325
entry_keys = id_index[file_id]
2326
if entry_key not in entry_keys:
2327
id_index[file_id] = entry_keys + (entry_key,)
2329
def _remove_from_id_index(self, id_index, entry_key):
2330
"""Remove this entry from the _id_index mapping.
2332
It is an programming error to call this when the entry_key is not
2335
file_id = entry_key[2]
2336
entry_keys = list(id_index[file_id])
2337
entry_keys.remove(entry_key)
2338
id_index[file_id] = static_tuple.StaticTuple.from_sequence(entry_keys)
2152
2340
def _get_output_lines(self, lines):
2153
2341
"""Format lines for final output.
2283
2475
trace.mutter('Not saving DirState because '
2284
2476
'_changes_aborted is set.')
2286
if (self._header_state == DirState.IN_MEMORY_MODIFIED or
2287
self._dirblock_state == DirState.IN_MEMORY_MODIFIED):
2478
# TODO: Since we now distinguish IN_MEMORY_MODIFIED from
2479
# IN_MEMORY_HASH_MODIFIED, we should only fail quietly if we fail
2480
# to save an IN_MEMORY_HASH_MODIFIED, and fail *noisily* if we
2481
# fail to save IN_MEMORY_MODIFIED
2482
if not self._worth_saving():
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.
2485
grabbed_write_lock = False
2486
if self._lock_state != 'w':
2487
grabbed_write_lock, new_lock = self._lock_token.temporary_write_lock()
2488
# Switch over to the new lock, as the old one may be closed.
2489
# TODO: jam 20070315 We should validate the disk file has
2490
# not changed contents, since temporary_write_lock may
2491
# not be an atomic operation.
2492
self._lock_token = new_lock
2493
self._state_file = new_lock.f
2494
if not grabbed_write_lock:
2495
# We couldn't grab a write lock, so we switch back to a read one
2498
lines = self.get_lines()
2499
self._state_file.seek(0)
2500
self._state_file.writelines(lines)
2501
self._state_file.truncate()
2502
self._state_file.flush()
2503
self._maybe_fdatasync()
2504
self._mark_unmodified()
2506
if grabbed_write_lock:
2507
self._lock_token = self._lock_token.restore_read_lock()
2508
self._state_file = self._lock_token.f
2293
2509
# TODO: jam 20070315 We should validate the disk file has
2294
# not changed contents. Since temporary_write_lock may
2295
# not be an atomic operation.
2296
self._lock_token = new_lock
2297
self._state_file = new_lock.f
2298
if not grabbed_write_lock:
2299
# We couldn't grab a write lock, so we switch back to a read one
2302
self._state_file.seek(0)
2303
self._state_file.writelines(self.get_lines())
2304
self._state_file.truncate()
2305
self._state_file.flush()
2306
self._header_state = DirState.IN_MEMORY_UNMODIFIED
2307
self._dirblock_state = DirState.IN_MEMORY_UNMODIFIED
2309
if grabbed_write_lock:
2310
self._lock_token = self._lock_token.restore_read_lock()
2311
self._state_file = self._lock_token.f
2312
# TODO: jam 20070315 We should validate the disk file has
2313
# not changed contents. Since restore_read_lock may
2314
# not be an atomic operation.
2510
# not changed contents. Since restore_read_lock may
2511
# not be an atomic operation.
2513
def _maybe_fdatasync(self):
2514
"""Flush to disk if possible and if not configured off."""
2515
if self._config_stack.get('dirstate.fdatasync'):
2516
osutils.fdatasync(self._state_file.fileno())
2518
def _worth_saving(self):
2519
"""Is it worth saving the dirstate or not?"""
2520
if (self._header_state == DirState.IN_MEMORY_MODIFIED
2521
or self._dirblock_state == DirState.IN_MEMORY_MODIFIED):
2523
if self._dirblock_state == DirState.IN_MEMORY_HASH_MODIFIED:
2524
if self._worth_saving_limit == -1:
2525
# We never save hash changes when the limit is -1
2527
# If we're using smart saving and only a small number of
2528
# entries have changed their hash, don't bother saving. John has
2529
# suggested using a heuristic here based on the size of the
2530
# changed files and/or tree. For now, we go with a configurable
2531
# number of changes, keeping the calculation time
2532
# as low overhead as possible. (This also keeps all existing
2533
# tests passing as the default is 0, i.e. always save.)
2534
if len(self._known_hash_changes) >= self._worth_saving_limit:
2316
2538
def _set_data(self, parent_ids, dirblocks):
2317
2539
"""Set the full dirstate data in memory.
2465
2697
new_details = []
2466
2698
for lookup_index in xrange(tree_index):
2467
2699
# boundary case: this is the first occurence of file_id
2468
# so there are no id_indexs, possibly take this out of
2700
# so there are no id_indexes, possibly take this out of
2470
if not len(id_index[file_id]):
2702
if not len(entry_keys):
2471
2703
new_details.append(DirState.NULL_PARENT_DETAILS)
2473
2705
# 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()
2706
a_key = iter(entry_keys).next()
2478
2707
if by_path[a_key][lookup_index][0] in ('r', 'a'):
2479
# its a pointer or missing statement, use it as is.
2708
# its a pointer or missing statement, use it as
2480
2710
new_details.append(by_path[a_key][lookup_index])
2482
2712
# we have the right key, make a pointer to it.
2483
2713
real_path = ('/'.join(a_key[0:2])).strip('/')
2484
new_details.append(('r', real_path, 0, False, ''))
2714
new_details.append(st('r', real_path, 0, False,
2485
2716
new_details.append(self._inv_entry_to_details(entry))
2486
2717
new_details.extend(new_location_suffix)
2487
2718
by_path[new_entry_key] = new_details
2488
id_index[file_id].add(new_entry_key)
2719
self._add_to_id_index(id_index, new_entry_key)
2489
2720
# --- end generation of full tree mappings
2491
2722
# sort and output all the entries
3167
3465
__slots__ = ["old_dirname_to_file_id", "new_dirname_to_file_id",
3168
3466
"last_source_parent", "last_target_parent", "include_unchanged",
3169
"use_filesystem_for_exec", "utf8_decode", "searched_specific_files",
3170
"search_specific_files", "state", "source_index", "target_index",
3171
"want_unversioned", "tree"]
3467
"partial", "use_filesystem_for_exec", "utf8_decode",
3468
"searched_specific_files", "search_specific_files",
3469
"searched_exact_paths", "search_specific_file_parents", "seen_ids",
3470
"state", "source_index", "target_index", "want_unversioned", "tree"]
3173
3472
def __init__(self, include_unchanged, use_filesystem_for_exec,
3174
3473
search_specific_files, state, source_index, target_index,
3175
3474
want_unversioned, tree):
3176
3475
self.old_dirname_to_file_id = {}
3177
3476
self.new_dirname_to_file_id = {}
3477
# Are we doing a partial iter_changes?
3478
self.partial = search_specific_files != set([''])
3178
3479
# Using a list so that we can access the values and change them in
3179
3480
# nested scope. Each one is [path, file_id, entry]
3180
3481
self.last_source_parent = [None, None]
3795
4137
current_dir_info = dir_iterator.next()
3796
4138
except StopIteration:
3797
4139
current_dir_info = None
4140
for result in self._iter_specific_file_parents():
4143
def _iter_specific_file_parents(self):
4144
"""Iter over the specific file parents."""
4145
while self.search_specific_file_parents:
4146
# Process the parent directories for the paths we were iterating.
4147
# Even in extremely large trees this should be modest, so currently
4148
# no attempt is made to optimise.
4149
path_utf8 = self.search_specific_file_parents.pop()
4150
if osutils.is_inside_any(self.searched_specific_files, path_utf8):
4151
# We've examined this path.
4153
if path_utf8 in self.searched_exact_paths:
4154
# We've examined this path.
4156
path_entries = self.state._entries_for_path(path_utf8)
4157
# We need either one or two entries. If the path in
4158
# self.target_index has moved (so the entry in source_index is in
4159
# 'ar') then we need to also look for the entry for this path in
4160
# self.source_index, to output the appropriate delete-or-rename.
4161
selected_entries = []
4163
for candidate_entry in path_entries:
4164
# Find entries present in target at this path:
4165
if candidate_entry[1][self.target_index][0] not in 'ar':
4167
selected_entries.append(candidate_entry)
4168
# Find entries present in source at this path:
4169
elif (self.source_index is not None and
4170
candidate_entry[1][self.source_index][0] not in 'ar'):
4172
if candidate_entry[1][self.target_index][0] == 'a':
4173
# Deleted, emit it here.
4174
selected_entries.append(candidate_entry)
4176
# renamed, emit it when we process the directory it
4178
self.search_specific_file_parents.add(
4179
candidate_entry[1][self.target_index][1])
4181
raise AssertionError(
4182
"Missing entry for specific path parent %r, %r" % (
4183
path_utf8, path_entries))
4184
path_info = self._path_info(path_utf8, path_utf8.decode('utf8'))
4185
for entry in selected_entries:
4186
if entry[0][2] in self.seen_ids:
4188
result, changed = self._process_entry(entry, path_info)
4190
raise AssertionError(
4191
"Got entry<->path mismatch for specific path "
4192
"%r entry %r path_info %r " % (
4193
path_utf8, entry, path_info))
4194
# Only include changes - we're outside the users requested
4197
self._gather_result_for_consistency(result)
4198
if (result[6][0] == 'directory' and
4199
result[6][1] != 'directory'):
4200
# This stopped being a directory, the old children have
4202
if entry[1][self.source_index][0] == 'r':
4203
# renamed, take the source path
4204
entry_path_utf8 = entry[1][self.source_index][1]
4206
entry_path_utf8 = path_utf8
4207
initial_key = (entry_path_utf8, '', '')
4208
block_index, _ = self.state._find_block_index_from_key(
4210
if block_index == 0:
4211
# The children of the root are in block index 1.
4213
current_block = None
4214
if block_index < len(self.state._dirblocks):
4215
current_block = self.state._dirblocks[block_index]
4216
if not osutils.is_inside(
4217
entry_path_utf8, current_block[0]):
4218
# No entries for this directory at all.
4219
current_block = None
4220
if current_block is not None:
4221
for entry in current_block[1]:
4222
if entry[1][self.source_index][0] in 'ar':
4223
# Not in the source tree, so doesn't have to be
4226
# Path of the entry itself.
4228
self.search_specific_file_parents.add(
4229
osutils.pathjoin(*entry[0][:2]))
4230
if changed or self.include_unchanged:
4232
self.searched_exact_paths.add(path_utf8)
4234
def _path_info(self, utf8_path, unicode_path):
4235
"""Generate path_info for unicode_path.
4237
:return: None if unicode_path does not exist, or a path_info tuple.
4239
abspath = self.tree.abspath(unicode_path)
4241
stat = os.lstat(abspath)
4243
if e.errno == errno.ENOENT:
4244
# the path does not exist.
4248
utf8_basename = utf8_path.rsplit('/', 1)[-1]
4249
dir_info = (utf8_path, utf8_basename,
4250
osutils.file_kind_from_stat_mode(stat.st_mode), stat,
4252
if dir_info[2] == 'directory':
4253
if self.tree._directory_is_tree_reference(
4255
self.root_dir_info = self.root_dir_info[:2] + \
4256
('tree-reference',) + self.root_dir_info[3:]
3800
4260
# Try to load the compiled form if possible
added
removed
bzrlib/dirstate.py
