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
256
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
259
class SHA1Provider(object):
268
260
"""An interface for getting sha1s of a file."""
411
408
self._last_block_index = None
412
409
self._last_entry_index = None
410
# The set of known hash changes
411
self._known_hash_changes = set()
412
# How many hash changed entries can we have without saving
413
self._worth_saving_limit = worth_saving_limit
414
self._config_stack = config.LocationStack(urlutils.local_path_to_url(
414
417
def __repr__(self):
415
418
return "%s(%r)" % \
416
419
(self.__class__.__name__, self._filename)
421
def _mark_modified(self, hash_changed_entries=None, header_modified=False):
422
"""Mark this dirstate as modified.
424
:param hash_changed_entries: if non-None, mark just these entries as
425
having their hash modified.
426
:param header_modified: mark the header modified as well, not just the
429
#trace.mutter_callsite(3, "modified hash entries: %s", hash_changed_entries)
430
if hash_changed_entries:
431
self._known_hash_changes.update([e[0] for e in hash_changed_entries])
432
if self._dirblock_state in (DirState.NOT_IN_MEMORY,
433
DirState.IN_MEMORY_UNMODIFIED):
434
# If the dirstate is already marked a IN_MEMORY_MODIFIED, then
435
# that takes precedence.
436
self._dirblock_state = DirState.IN_MEMORY_HASH_MODIFIED
438
# TODO: Since we now have a IN_MEMORY_HASH_MODIFIED state, we
439
# should fail noisily if someone tries to set
440
# IN_MEMORY_MODIFIED but we don't have a write-lock!
441
# We don't know exactly what changed so disable smart saving
442
self._dirblock_state = DirState.IN_MEMORY_MODIFIED
444
self._header_state = DirState.IN_MEMORY_MODIFIED
446
def _mark_unmodified(self):
447
"""Mark this dirstate as unmodified."""
448
self._header_state = DirState.IN_MEMORY_UNMODIFIED
449
self._dirblock_state = DirState.IN_MEMORY_UNMODIFIED
450
self._known_hash_changes = set()
418
452
def add(self, path, file_id, kind, stat, fingerprint):
419
453
"""Add a path to be tracked.
1483
1515
if basename_utf8:
1484
1516
parents.add((dirname_utf8, inv_entry.parent_id))
1485
1517
if old_path is None:
1486
adds.append((None, encode(new_path), file_id,
1518
old_path_utf8 = None
1520
old_path_utf8 = encode(old_path)
1521
if old_path is None:
1522
adds.append((None, new_path_utf8, file_id,
1487
1523
inv_to_entry(inv_entry), True))
1488
1524
new_ids.add(file_id)
1489
1525
elif new_path is None:
1490
deletes.append((encode(old_path), None, file_id, None, True))
1491
elif (old_path, new_path) != root_only:
1526
deletes.append((old_path_utf8, None, file_id, None, True))
1527
elif (old_path, new_path) == root_only:
1528
# change things in-place
1529
# Note: the case of a parent directory changing its file_id
1530
# tends to break optimizations here, because officially
1531
# the file has actually been moved, it just happens to
1532
# end up at the same path. If we can figure out how to
1533
# handle that case, we can avoid a lot of add+delete
1534
# pairs for objects that stay put.
1535
# elif old_path == new_path:
1536
changes.append((old_path_utf8, new_path_utf8, file_id,
1537
inv_to_entry(inv_entry)))
1493
1540
# Because renames must preserve their children we must have
1494
1541
# processed all relocations and removes before hand. The sort
1504
1551
self._update_basis_apply_deletes(deletes)
1506
1553
# Split into an add/delete pair recursively.
1507
adds.append((None, new_path_utf8, file_id,
1508
inv_to_entry(inv_entry), False))
1554
adds.append((old_path_utf8, new_path_utf8, file_id,
1555
inv_to_entry(inv_entry), False))
1509
1556
# Expunge deletes that we've seen so that deleted/renamed
1510
1557
# children of a rename directory are handled correctly.
1511
new_deletes = reversed(list(self._iter_child_entries(1,
1558
new_deletes = reversed(list(
1559
self._iter_child_entries(1, old_path_utf8)))
1513
1560
# Remove the current contents of the tree at orig_path, and
1514
1561
# reinsert at the correct new path.
1515
1562
for entry in new_deletes:
1517
source_path = entry[0][0] + '/' + entry[0][1]
1563
child_dirname, child_basename, child_file_id = entry[0]
1565
source_path = child_dirname + '/' + child_basename
1519
source_path = entry[0][1]
1567
source_path = child_basename
1520
1568
if new_path_utf8:
1521
target_path = new_path_utf8 + source_path[len(old_path):]
1570
new_path_utf8 + source_path[len(old_path_utf8):]
1572
if old_path_utf8 == '':
1524
1573
raise AssertionError("cannot rename directory to"
1526
target_path = source_path[len(old_path) + 1:]
1575
target_path = source_path[len(old_path_utf8) + 1:]
1527
1576
adds.append((None, target_path, entry[0][2], entry[1][1], False))
1528
1577
deletes.append(
1529
1578
(source_path, target_path, entry[0][2], None, False))
1530
1579
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)))
1580
(old_path_utf8, new_path_utf8, file_id, None, False))
1537
1582
self._check_delta_ids_absent(new_ids, delta, 1)
1539
1584
# Finish expunging deletes/first half of renames.
1597
1641
# Adds are accumulated partly from renames, so can be in any input
1598
1642
# order - sort it.
1643
# TODO: we may want to sort in dirblocks order. That way each entry
1644
# will end up in the same directory, allowing the _get_entry
1645
# fast-path for looking up 2 items in the same dir work.
1646
adds.sort(key=lambda x: x[1])
1600
1647
# adds is now in lexographic order, which places all parents before
1601
1648
# their children, so we can process it linearly.
1650
st = static_tuple.StaticTuple
1603
1651
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
1652
dirname, basename = osutils.split(new_path)
1653
entry_key = st(dirname, basename, file_id)
1654
block_index, present = self._find_block_index_from_key(entry_key)
1656
# The block where we want to put the file is not present.
1657
# However, it might have just been an empty directory. Look for
1658
# the parent in the basis-so-far before throwing an error.
1659
parent_dir, parent_base = osutils.split(dirname)
1660
parent_block_idx, parent_entry_idx, _, parent_present = \
1661
self._get_block_entry_index(parent_dir, parent_base, 1)
1662
if not parent_present:
1663
self._raise_invalid(new_path, file_id,
1664
"Unable to find block for this record."
1665
" Was the parent added?")
1666
self._ensure_block(parent_block_idx, parent_entry_idx, dirname)
1668
block = self._dirblocks[block_index][1]
1669
entry_index, present = self._find_entry_index(entry_key, block)
1671
if old_path is not None:
1672
self._raise_invalid(new_path, file_id,
1673
'considered a real add but still had old_path at %s'
1676
entry = block[entry_index]
1677
basis_kind = entry[1][1][0]
1678
if basis_kind == 'a':
1679
entry[1][1] = new_details
1680
elif basis_kind == 'r':
1681
raise NotImplementedError()
1683
self._raise_invalid(new_path, file_id,
1684
"An entry was marked as a new add"
1685
" but the basis target already existed")
1687
# The exact key was not found in the block. However, we need to
1688
# check if there is a key next to us that would have matched.
1689
# We only need to check 2 locations, because there are only 2
1691
for maybe_index in range(entry_index-1, entry_index+1):
1692
if maybe_index < 0 or maybe_index >= len(block):
1694
maybe_entry = block[maybe_index]
1695
if maybe_entry[0][:2] != (dirname, basename):
1696
# Just a random neighbor
1698
if maybe_entry[0][2] == file_id:
1699
raise AssertionError(
1700
'_find_entry_index didnt find a key match'
1701
' but walking the data did, for %s'
1703
basis_kind = maybe_entry[1][1][0]
1704
if basis_kind not in 'ar':
1705
self._raise_invalid(new_path, file_id,
1706
"we have an add record for path, but the path"
1707
" is already present with another file_id %s"
1708
% (maybe_entry[0][2],))
1710
entry = (entry_key, [DirState.NULL_PARENT_DETAILS,
1712
block.insert(entry_index, entry)
1714
active_kind = entry[1][0][0]
1715
if active_kind == 'a':
1716
# The active record shows up as absent, this could be genuine,
1717
# or it could be present at some other location. We need to
1719
id_index = self._get_id_index()
1720
# The id_index may not be perfectly accurate for tree1, because
1721
# we haven't been keeping it updated. However, it should be
1722
# fine for tree0, and that gives us enough info for what we
1724
keys = id_index.get(file_id, ())
1726
block_i, entry_i, d_present, f_present = \
1727
self._get_block_entry_index(key[0], key[1], 0)
1730
active_entry = self._dirblocks[block_i][1][entry_i]
1731
if (active_entry[0][2] != file_id):
1732
# Some other file is at this path, we don't need to
1735
real_active_kind = active_entry[1][0][0]
1736
if real_active_kind in 'ar':
1737
# We found a record, which was not *this* record,
1738
# which matches the file_id, but is not actually
1739
# present. Something seems *really* wrong.
1740
self._raise_invalid(new_path, file_id,
1741
"We found a tree0 entry that doesnt make sense")
1742
# Now, we've found a tree0 entry which matches the file_id
1743
# but is at a different location. So update them to be
1745
active_dir, active_name = active_entry[0][:2]
1747
active_path = active_dir + '/' + active_name
1749
active_path = active_name
1750
active_entry[1][1] = st('r', new_path, 0, False, '')
1751
entry[1][0] = st('r', active_path, 0, False, '')
1752
elif active_kind == 'r':
1753
raise NotImplementedError()
1755
new_kind = new_details[0]
1757
self._ensure_block(block_index, entry_index, new_path)
1620
1759
def _update_basis_apply_changes(self, changes):
1621
1760
"""Apply a sequence of changes to tree 1 during update_basis_by_delta.
1653
1786
null = DirState.NULL_PARENT_DETAILS
1654
1787
for old_path, new_path, file_id, _, real_delete in deletes:
1655
1788
if real_delete != (new_path is None):
1656
self._changes_aborted = True
1657
raise AssertionError("bad delete delta")
1789
self._raise_invalid(old_path, file_id, "bad delete delta")
1658
1790
# the entry for this file_id must be in tree 1.
1659
1791
dirname, basename = osutils.split(old_path)
1660
1792
block_index, entry_index, dir_present, file_present = \
1661
1793
self._get_block_entry_index(dirname, basename, 1)
1662
1794
if not file_present:
1663
self._changes_aborted = True
1664
raise errors.InconsistentDelta(old_path, file_id,
1795
self._raise_invalid(old_path, file_id,
1665
1796
'basis tree does not contain removed entry')
1666
1797
entry = self._dirblocks[block_index][1][entry_index]
1798
# The state of the entry in the 'active' WT
1799
active_kind = entry[1][0][0]
1667
1800
if entry[0][2] != file_id:
1668
self._changes_aborted = True
1669
raise errors.InconsistentDelta(old_path, file_id,
1801
self._raise_invalid(old_path, file_id,
1670
1802
'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.')
1804
old_kind = entry[1][1][0]
1805
if active_kind in 'ar':
1806
# The active tree doesn't have this file_id.
1807
# The basis tree is changing this record. If this is a
1808
# rename, then we don't want the record here at all
1809
# anymore. If it is just an in-place change, we want the
1810
# record here, but we'll add it if we need to. So we just
1812
if active_kind == 'r':
1813
active_path = entry[1][0][1]
1814
active_entry = self._get_entry(0, file_id, active_path)
1815
if active_entry[1][1][0] != 'r':
1816
self._raise_invalid(old_path, file_id,
1817
"Dirstate did not have matching rename entries")
1818
elif active_entry[1][0][0] in 'ar':
1819
self._raise_invalid(old_path, file_id,
1820
"Dirstate had a rename pointing at an inactive"
1822
active_entry[1][1] = null
1677
1823
del self._dirblocks[block_index][1][entry_index]
1825
# This was a directory, and the active tree says it
1826
# doesn't exist, and now the basis tree says it doesn't
1827
# exist. Remove its dirblock if present
1829
present) = self._find_block_index_from_key(
1832
dir_block = self._dirblocks[dir_block_index][1]
1834
# This entry is empty, go ahead and just remove it
1835
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
1837
# There is still an active record, so just mark this
1840
block_i, entry_i, d_present, f_present = \
1841
self._get_block_entry_index(old_path, '', 1)
1843
dir_block = self._dirblocks[block_i][1]
1844
for child_entry in dir_block:
1845
child_basis_kind = child_entry[1][1][0]
1846
if child_basis_kind not in 'ar':
1847
self._raise_invalid(old_path, file_id,
1848
"The file id was deleted but its children were "
1695
1851
def _after_delta_check_parents(self, parents, index):
1696
1852
"""Check that parents required by the delta are all intact.
2145
2303
def _get_id_index(self):
2146
"""Get an id index of self._dirblocks."""
2304
"""Get an id index of self._dirblocks.
2306
This maps from file_id => [(directory, name, file_id)] entries where
2307
that file_id appears in one of the trees.
2147
2309
if self._id_index is None:
2149
2311
for key, tree_details in self._iter_entries():
2150
id_index.setdefault(key[2], set()).add(key)
2312
self._add_to_id_index(id_index, key)
2151
2313
self._id_index = id_index
2152
2314
return self._id_index
2316
def _add_to_id_index(self, id_index, entry_key):
2317
"""Add this entry to the _id_index mapping."""
2318
# This code used to use a set for every entry in the id_index. However,
2319
# it is *rare* to have more than one entry. So a set is a large
2320
# overkill. And even when we do, we won't ever have more than the
2321
# number of parent trees. Which is still a small number (rarely >2). As
2322
# such, we use a simple tuple, and do our own uniqueness checks. While
2323
# the 'in' check is O(N) since N is nicely bounded it shouldn't ever
2324
# cause quadratic failure.
2325
file_id = entry_key[2]
2326
entry_key = static_tuple.StaticTuple.from_sequence(entry_key)
2327
if file_id not in id_index:
2328
id_index[file_id] = static_tuple.StaticTuple(entry_key,)
2330
entry_keys = id_index[file_id]
2331
if entry_key not in entry_keys:
2332
id_index[file_id] = entry_keys + (entry_key,)
2334
def _remove_from_id_index(self, id_index, entry_key):
2335
"""Remove this entry from the _id_index mapping.
2337
It is an programming error to call this when the entry_key is not
2340
file_id = entry_key[2]
2341
entry_keys = list(id_index[file_id])
2342
entry_keys.remove(entry_key)
2343
id_index[file_id] = static_tuple.StaticTuple.from_sequence(entry_keys)
2154
2345
def _get_output_lines(self, lines):
2155
2346
"""Format lines for final output.
2285
2480
trace.mutter('Not saving DirState because '
2286
2481
'_changes_aborted is set.')
2288
if (self._header_state == DirState.IN_MEMORY_MODIFIED or
2289
self._dirblock_state == DirState.IN_MEMORY_MODIFIED):
2483
# TODO: Since we now distinguish IN_MEMORY_MODIFIED from
2484
# IN_MEMORY_HASH_MODIFIED, we should only fail quietly if we fail
2485
# to save an IN_MEMORY_HASH_MODIFIED, and fail *noisily* if we
2486
# fail to save IN_MEMORY_MODIFIED
2487
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.
2490
grabbed_write_lock = False
2491
if self._lock_state != 'w':
2492
grabbed_write_lock, new_lock = self._lock_token.temporary_write_lock()
2493
# Switch over to the new lock, as the old one may be closed.
2494
# TODO: jam 20070315 We should validate the disk file has
2495
# not changed contents, since temporary_write_lock may
2496
# not be an atomic operation.
2497
self._lock_token = new_lock
2498
self._state_file = new_lock.f
2499
if not grabbed_write_lock:
2500
# We couldn't grab a write lock, so we switch back to a read one
2503
lines = self.get_lines()
2504
self._state_file.seek(0)
2505
self._state_file.writelines(lines)
2506
self._state_file.truncate()
2507
self._state_file.flush()
2508
self._maybe_fdatasync()
2509
self._mark_unmodified()
2511
if grabbed_write_lock:
2512
self._lock_token = self._lock_token.restore_read_lock()
2513
self._state_file = self._lock_token.f
2295
2514
# 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.
2515
# not changed contents. Since restore_read_lock may
2516
# not be an atomic operation.
2518
def _maybe_fdatasync(self):
2519
"""Flush to disk if possible and if not configured off."""
2520
if self._config_stack.get('dirstate.fdatasync'):
2521
osutils.fdatasync(self._state_file.fileno())
2523
def _worth_saving(self):
2524
"""Is it worth saving the dirstate or not?"""
2525
if (self._header_state == DirState.IN_MEMORY_MODIFIED
2526
or self._dirblock_state == DirState.IN_MEMORY_MODIFIED):
2528
if self._dirblock_state == DirState.IN_MEMORY_HASH_MODIFIED:
2529
if self._worth_saving_limit == -1:
2530
# We never save hash changes when the limit is -1
2532
# If we're using smart saving and only a small number of
2533
# entries have changed their hash, don't bother saving. John has
2534
# suggested using a heuristic here based on the size of the
2535
# changed files and/or tree. For now, we go with a configurable
2536
# number of changes, keeping the calculation time
2537
# as low overhead as possible. (This also keeps all existing
2538
# tests passing as the default is 0, i.e. always save.)
2539
if len(self._known_hash_changes) >= self._worth_saving_limit:
2318
2543
def _set_data(self, parent_ids, dirblocks):
2319
2544
"""Set the full dirstate data in memory.
2463
2700
# mapping from path,id. We need to look up the correct path
2464
2701
# for the indexes from 0 to tree_index -1
2465
2702
new_details = []
2466
for lookup_index in xrange(tree_index):
2703
for lookup_index in range(tree_index):
2467
2704
# boundary case: this is the first occurence of file_id
2468
# so there are no id_indexs, possibly take this out of
2705
# so there are no id_indexes, possibly take this out of
2470
if not len(id_index[file_id]):
2707
if not len(entry_keys):
2471
2708
new_details.append(DirState.NULL_PARENT_DETAILS)
2473
2710
# 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()
2711
a_key = next(iter(entry_keys))
2478
2712
if by_path[a_key][lookup_index][0] in ('r', 'a'):
2479
# its a pointer or missing statement, use it as is.
2713
# its a pointer or missing statement, use it as
2480
2715
new_details.append(by_path[a_key][lookup_index])
2482
2717
# we have the right key, make a pointer to it.
2483
2718
real_path = ('/'.join(a_key[0:2])).strip('/')
2484
new_details.append(('r', real_path, 0, False, ''))
2719
new_details.append(st('r', real_path, 0, False,
2485
2721
new_details.append(self._inv_entry_to_details(entry))
2486
2722
new_details.extend(new_location_suffix)
2487
2723
by_path[new_entry_key] = new_details
2488
id_index[file_id].add(new_entry_key)
2724
self._add_to_id_index(id_index, new_entry_key)
2489
2725
# --- end generation of full tree mappings
2491
2727
# sort and output all the entries
2492
new_entries = self._sort_entries(by_path.items())
2728
new_entries = self._sort_entries(viewitems(by_path))
2493
2729
self._entries_to_current_state(new_entries)
2494
2730
self._parents = [rev_id for rev_id, tree in trees]
2495
2731
self._ghosts = list(ghosts)
2496
self._header_state = DirState.IN_MEMORY_MODIFIED
2497
self._dirblock_state = DirState.IN_MEMORY_MODIFIED
2732
self._mark_modified(header_modified=True)
2498
2733
self._id_index = id_index
2500
2735
def _sort_entries(self, entry_list):
added
removed
breezy/dirstate.py
