tests/simplestorerepo.py
| author |
Pierre-Yves David <pierre-yves.david@octobus.net> |
|
Mon, 14 Dec 2020 11:32:24 +0100 |
| changeset 46149 |
294d5aca4ff5 |
| parent 45811 |
a5206e71c536
|
| child 46561 |
7a93b7b3dc2d |
| permissions |
-rw-r--r-- |
copies: iterate over children directly (instead of parents)
Before this change we would gather all parent → child edges and iterate on
all parent, gathering copy information for children and aggregating them from
there.
They are not strict requirement for edges to be processed in that specific
order. We could also simply iterate over all "children" revision and aggregate
data from both parents at the same time. This patch does that.
It make various things simpler:
* since both parents are processed at the same time, we no longer need to
cache data for merge (see next changeset for details),
* we no longer need nested loop to process data,
* we no longer need to store partial merge data for a rev from distinct loop
interaction to another when processing merges,
* we no longer need to build a full parent -> children mapping (we only rely on
a simpler "parent -> number of children" map (for memory efficiency),
* the data access pattern is now simpler (from lower revisions to higher
revisions) and entirely predicable. That predictability open the way to
prefetching and parallel processing.
So that new iterations order requires simpler code and open the way to
interesting optimisation.
The effect on performance is quite good. In the worse case, we don't see any
significant negative impact. And in the best case, the reduction of roundtrip
to Python provide us with a significant speed. Some example below:
Repo Case Source-Rev Dest-Rev # of revisions old time new time Difference Factor time per rev
---------------------------------------------------------------------------------------------------------------------------------------------------------------
mozilla-try x00000_revs_x00000_added_0_copies dc8a3ca7010e d16fde900c9c : 34414 revs, 0.962867 s, 0.502584 s, -0.460283 s, × 0.5220, 14 µs/rev
mozilla-try x0000_revs_xx000_added_x_copies 156f6e2674f2 4d0f2c178e66 : 8598 revs, 0.110717 s, 0.076323 s, -0.034394 s, × 0.6894, 8 µs/rev
# full comparison between the previous changeset and this one
Repo Case Source-Rev Dest-Rev # of revisions old time new time Difference Factor time per rev
---------------------------------------------------------------------------------------------------------------------------------------------------------------
mercurial x_revs_x_added_0_copies ad6b123de1c7 39cfcef4f463 : 1 revs, 0.000048 s, 0.000041 s, -0.000007 s, × 0.8542, 41 µs/rev
mercurial x_revs_x_added_x_copies 2b1c78674230 0c1d10351869 : 6 revs, 0.000153 s, 0.000102 s, -0.000051 s, × 0.6667, 17 µs/rev
mercurial x000_revs_x000_added_x_copies 81f8ff2a9bf2 dd3267698d84 : 1032 revs, 0.004209 s, 0.004254 s, +0.000045 s, × 1.0107, 4 µs/rev
pypy x_revs_x_added_0_copies aed021ee8ae8 099ed31b181b : 9 revs, 0.000203 s, 0.000282 s, +0.000079 s, × 1.3892, 31 µs/rev
pypy x_revs_x000_added_0_copies 4aa4e1f8e19a 359343b9ac0e : 1 revs, 0.000059 s, 0.000048 s, -0.000011 s, × 0.8136, 48 µs/rev
pypy x_revs_x_added_x_copies ac52eb7bbbb0 72e022663155 : 7 revs, 0.000194 s, 0.000211 s, +0.000017 s, × 1.0876, 30 µs/rev
pypy x_revs_x00_added_x_copies c3b14617fbd7 ace7255d9a26 : 1 revs, 0.000380 s, 0.000375 s, -0.000005 s, × 0.9868, 375 µs/rev
pypy x_revs_x000_added_x000_copies df6f7a526b60 a83dc6a2d56f : 6 revs, 0.010588 s, 0.010574 s, -0.000014 s, × 0.9987, 1762 µs/rev
pypy x000_revs_xx00_added_0_copies 89a76aede314 2f22446ff07e : 4785 revs, 0.048961 s, 0.049974 s, +0.001013 s, × 1.0207, 10 µs/rev
pypy x000_revs_x000_added_x_copies 8a3b5bfd266e 2c68e87c3efe : 6780 revs, 0.083612 s, 0.084300 s, +0.000688 s, × 1.0082, 12 µs/rev
pypy x000_revs_x000_added_x000_copies 89a76aede314 7b3dda341c84 : 5441 revs, 0.058579 s, 0.060128 s, +0.001549 s, × 1.0264, 11 µs/rev
pypy x0000_revs_x_added_0_copies d1defd0dc478 c9cb1334cc78 : 43645 revs, 0.736783 s, 0.686542 s, -0.050241 s, × 0.9318, 15 µs/rev
pypy x0000_revs_xx000_added_0_copies bf2c629d0071 4ffed77c095c : 2 revs, 0.022050 s, 0.009277 s, -0.012773 s, × 0.4207, 4638 µs/rev
pypy x0000_revs_xx000_added_x000_copies 08ea3258278e d9fa043f30c0 : 11316 revs, 0.120800 s, 0.114733 s, -0.006067 s, × 0.9498, 10 µs/rev
netbeans x_revs_x_added_0_copies fb0955ffcbcd a01e9239f9e7 : 2 revs, 0.000140 s, 0.000081 s, -0.000059 s, × 0.5786, 40 µs/rev
netbeans x_revs_x000_added_0_copies 6f360122949f 20eb231cc7d0 : 2 revs, 0.000114 s, 0.000107 s, -0.000007 s, × 0.9386, 53 µs/rev
netbeans x_revs_x_added_x_copies 1ada3faf6fb6 5a39d12eecf4 : 3 revs, 0.000224 s, 0.000173 s, -0.000051 s, × 0.7723, 57 µs/rev
netbeans x_revs_x00_added_x_copies 35be93ba1e2c 9eec5e90c05f : 9 revs, 0.000723 s, 0.000698 s, -0.000025 s, × 0.9654, 77 µs/rev
netbeans x000_revs_xx00_added_0_copies eac3045b4fdd 51d4ae7f1290 : 1421 revs, 0.009665 s, 0.009248 s, -0.000417 s, × 0.9569, 6 µs/rev
netbeans x000_revs_x000_added_x_copies e2063d266acd 6081d72689dc : 1533 revs, 0.014820 s, 0.015446 s, +0.000626 s, × 1.0422, 10 µs/rev
netbeans x000_revs_x000_added_x000_copies ff453e9fee32 411350406ec2 : 5750 revs, 0.076049 s, 0.074373 s, -0.001676 s, × 0.9780, 12 µs/rev
netbeans x0000_revs_xx000_added_x000_copies 588c2d1ced70 1aad62e59ddd : 66949 revs, 0.683603 s, 0.639870 s, -0.043733 s, × 0.9360, 9 µs/rev
mozilla-central x_revs_x_added_0_copies 3697f962bb7b 7015fcdd43a2 : 2 revs, 0.000161 s, 0.000088 s, -0.000073 s, × 0.5466, 44 µs/rev
mozilla-central x_revs_x000_added_0_copies dd390860c6c9 40d0c5bed75d : 8 revs, 0.000234 s, 0.000199 s, -0.000035 s, × 0.8504, 24 µs/rev
mozilla-central x_revs_x_added_x_copies 8d198483ae3b 14207ffc2b2f : 9 revs, 0.000247 s, 0.000171 s, -0.000076 s, × 0.6923, 19 µs/rev
mozilla-central x_revs_x00_added_x_copies 98cbc58cc6bc 446a150332c3 : 7 revs, 0.000630 s, 0.000592 s, -0.000038 s, × 0.9397, 84 µs/rev
mozilla-central x_revs_x000_added_x000_copies 3c684b4b8f68 0a5e72d1b479 : 3 revs, 0.003286 s, 0.003151 s, -0.000135 s, × 0.9589, 1050 µs/rev
mozilla-central x_revs_x0000_added_x0000_copies effb563bb7e5 c07a39dc4e80 : 6 revs, 0.062441 s, 0.061612 s, -0.000829 s, × 0.9867, 10268 µs/rev
mozilla-central x000_revs_xx00_added_0_copies 6100d773079a 04a55431795e : 1593 revs, 0.005423 s, 0.005381 s, -0.000042 s, × 0.9923, 3 µs/rev
mozilla-central x000_revs_x000_added_x_copies 9f17a6fc04f9 2d37b966abed : 41 revs, 0.005919 s, 0.003742 s, -0.002177 s, × 0.6322, 91 µs/rev
mozilla-central x000_revs_x000_added_x000_copies 7c97034feb78 4407bd0c6330 : 7839 revs, 0.062597 s, 0.061983 s, -0.000614 s, × 0.9902, 7 µs/rev
mozilla-central x0000_revs_xx000_added_0_copies 9eec5917337d 67118cc6dcad : 615 revs, 0.043551 s, 0.019861 s, -0.023690 s, × 0.4560, 32 µs/rev
mozilla-central x0000_revs_xx000_added_x000_copies f78c615a656c 96a38b690156 : 30263 revs, 0.192475 s, 0.188101 s, -0.004374 s, × 0.9773, 6 µs/rev
mozilla-central x00000_revs_x0000_added_x0000_copies 6832ae71433c 4c222a1d9a00 : 153721 revs, 1.955575 s, 1.806696 s, -0.148879 s, × 0.9239, 11 µs/rev
mozilla-central x00000_revs_x00000_added_x000_copies 76caed42cf7c 1daa622bbe42 : 204976 revs, 2.886501 s, 2.682987 s, -0.203514 s, × 0.9295, 13 µs/rev
mozilla-try x_revs_x_added_0_copies aaf6dde0deb8 9790f499805a : 2 revs, 0.001181 s, 0.000852 s, -0.000329 s, × 0.7214, 426 µs/rev
mozilla-try x_revs_x000_added_0_copies d8d0222927b4 5bb8ce8c7450 : 2 revs, 0.001189 s, 0.000859 s, -0.000330 s, × 0.7225, 429 µs/rev
mozilla-try x_revs_x_added_x_copies 092fcca11bdb 936255a0384a : 4 revs, 0.000563 s, 0.000150 s, -0.000413 s, × 0.2664, 37 µs/rev
mozilla-try x_revs_x00_added_x_copies b53d2fadbdb5 017afae788ec : 2 revs, 0.001548 s, 0.001158 s, -0.000390 s, × 0.7481, 579 µs/rev
mozilla-try x_revs_x000_added_x000_copies 20408ad61ce5 6f0ee96e21ad : 1 revs, 0.027782 s, 0.027240 s, -0.000542 s, × 0.9805, 27240 µs/rev
mozilla-try x_revs_x0000_added_x0000_copies effb563bb7e5 c07a39dc4e80 : 6 revs, 0.062781 s, 0.062824 s, +0.000043 s, × 1.0007, 10470 µs/rev
mozilla-try x000_revs_xx00_added_0_copies 6100d773079a 04a55431795e : 1593 revs, 0.005778 s, 0.005463 s, -0.000315 s, × 0.9455, 3 µs/rev
mozilla-try x000_revs_x000_added_x_copies 9f17a6fc04f9 2d37b966abed : 41 revs, 0.006192 s, 0.004238 s, -0.001954 s, × 0.6844, 103 µs/rev
mozilla-try x000_revs_x000_added_x000_copies 1346fd0130e4 4c65cbdabc1f : 6657 revs, 0.065391 s, 0.064113 s, -0.001278 s, × 0.9805, 9 µs/rev
mozilla-try x0000_revs_x_added_0_copies 63519bfd42ee a36a2a865d92 : 40314 revs, 0.317216 s, 0.294063 s, -0.023153 s, × 0.9270, 7 µs/rev
mozilla-try x0000_revs_x_added_x_copies 9fe69ff0762d bcabf2a78927 : 38690 revs, 0.303119 s, 0.281493 s, -0.021626 s, × 0.9287, 7 µs/rev
mozilla-try x0000_revs_xx000_added_x_copies 156f6e2674f2 4d0f2c178e66 : 8598 revs, 0.110717 s, 0.076323 s, -0.034394 s, × 0.6894, 8 µs/rev
mozilla-try x0000_revs_xx000_added_0_copies 9eec5917337d 67118cc6dcad : 615 revs, 0.045739 s, 0.020390 s, -0.025349 s, × 0.4458, 33 µs/rev
mozilla-try x0000_revs_xx000_added_x000_copies 89294cd501d9 7ccb2fc7ccb5 : 97052 revs, 3.098021 s, 3.023879 s, -0.074142 s, × 0.9761, 31 µs/rev
mozilla-try x0000_revs_x0000_added_x0000_copies e928c65095ed e951f4ad123a : 52031 revs, 0.771480 s, 0.735549 s, -0.035931 s, × 0.9534, 14 µs/rev
mozilla-try x00000_revs_x_added_0_copies 6a320851d377 1ebb79acd503 : 363753 revs, 18.813422 s, 18.568900 s, -0.244522 s, × 0.9870, 51 µs/rev
mozilla-try x00000_revs_x00000_added_0_copies dc8a3ca7010e d16fde900c9c : 34414 revs, 0.962867 s, 0.502584 s, -0.460283 s, × 0.5220, 14 µs/rev
mozilla-try x00000_revs_x_added_x_copies 5173c4b6f97c 95d83ee7242d : 362229 revs, 18.684923 s, 18.356645 s, -0.328278 s, × 0.9824, 50 µs/rev
mozilla-try x00000_revs_x000_added_x_copies 9126823d0e9c ca82787bb23c : 359344 revs, 18.296305 s, 18.250393 s, -0.045912 s, × 0.9975, 50 µs/rev
mozilla-try x00000_revs_x0000_added_x0000_copies 8d3fafa80d4b eb884023b810 : 192665 revs, 3.061887 s, 2.792459 s, -0.269428 s, × 0.9120, 14 µs/rev
mozilla-try x00000_revs_x00000_added_x0000_copies 1b661134e2ca 1ae03d022d6d : 228985 revs, 103.869641 s, 107.697264 s, +3.827623 s, × 1.0369, 470 µs/rev
mozilla-try x00000_revs_x00000_added_x000_copies 9b2a99adc05e 8e29777b48e6 : 382065 revs, 64.262957 s, 63.961040 s, -0.301917 s, × 0.9953, 167 µs/rev
Differential Revision: https://phab.mercurial-scm.org/D9422
# simplestorerepo.py - Extension that swaps in alternate repository storage.
#
# Copyright 2018 Gregory Szorc <gregory.szorc@gmail.com>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
# To use this with the test suite:
#
# $ HGREPOFEATURES="simplestore" ./run-tests.py \
# --extra-config-opt extensions.simplestore=`pwd`/simplestorerepo.py
from __future__ import absolute_import
import stat
from mercurial.i18n import _
from mercurial.node import (
bin,
hex,
nullid,
nullrev,
)
from mercurial.thirdparty import attr
from mercurial import (
ancestor,
bundlerepo,
error,
extensions,
localrepo,
mdiff,
pycompat,
revlog,
store,
verify,
)
from mercurial.interfaces import (
repository,
util as interfaceutil,
)
from mercurial.utils import (
cborutil,
storageutil,
)
from mercurial.revlogutils import flagutil
# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
# extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
# be specifying the version(s) of Mercurial they are tested with, or
# leave the attribute unspecified.
testedwith = b'ships-with-hg-core'
REQUIREMENT = b'testonly-simplestore'
def validatenode(node):
if isinstance(node, int):
raise ValueError('expected node; got int')
if len(node) != 20:
raise ValueError('expected 20 byte node')
def validaterev(rev):
if not isinstance(rev, int):
raise ValueError('expected int')
class simplestoreerror(error.StorageError):
pass
@interfaceutil.implementer(repository.irevisiondelta)
@attr.s(slots=True)
class simplestorerevisiondelta(object):
node = attr.ib()
p1node = attr.ib()
p2node = attr.ib()
basenode = attr.ib()
flags = attr.ib()
baserevisionsize = attr.ib()
revision = attr.ib()
delta = attr.ib()
linknode = attr.ib(default=None)
@interfaceutil.implementer(repository.iverifyproblem)
@attr.s(frozen=True)
class simplefilestoreproblem(object):
warning = attr.ib(default=None)
error = attr.ib(default=None)
node = attr.ib(default=None)
@interfaceutil.implementer(repository.ifilestorage)
class filestorage(object):
"""Implements storage for a tracked path.
Data is stored in the VFS in a directory corresponding to the tracked
path.
Index data is stored in an ``index`` file using CBOR.
Fulltext data is stored in files having names of the node.
"""
_flagserrorclass = simplestoreerror
def __init__(self, svfs, path):
self._svfs = svfs
self._path = path
self._storepath = b'/'.join([b'data', path])
self._indexpath = b'/'.join([self._storepath, b'index'])
indexdata = self._svfs.tryread(self._indexpath)
if indexdata:
indexdata = cborutil.decodeall(indexdata)
self._indexdata = indexdata or []
self._indexbynode = {}
self._indexbyrev = {}
self._index = []
self._refreshindex()
self._flagprocessors = dict(flagutil.flagprocessors)
def _refreshindex(self):
self._indexbynode.clear()
self._indexbyrev.clear()
self._index = []
for i, entry in enumerate(self._indexdata):
self._indexbynode[entry[b'node']] = entry
self._indexbyrev[i] = entry
self._indexbynode[nullid] = {
b'node': nullid,
b'p1': nullid,
b'p2': nullid,
b'linkrev': nullrev,
b'flags': 0,
}
self._indexbyrev[nullrev] = {
b'node': nullid,
b'p1': nullid,
b'p2': nullid,
b'linkrev': nullrev,
b'flags': 0,
}
for i, entry in enumerate(self._indexdata):
p1rev, p2rev = self.parentrevs(self.rev(entry[b'node']))
# start, length, rawsize, chainbase, linkrev, p1, p2, node
self._index.append(
(0, 0, 0, -1, entry[b'linkrev'], p1rev, p2rev, entry[b'node'])
)
self._index.append((0, 0, 0, -1, -1, -1, -1, nullid))
def __len__(self):
return len(self._indexdata)
def __iter__(self):
return iter(range(len(self)))
def revs(self, start=0, stop=None):
step = 1
if stop is not None:
if start > stop:
step = -1
stop += step
else:
stop = len(self)
return range(start, stop, step)
def parents(self, node):
validatenode(node)
if node not in self._indexbynode:
raise KeyError('unknown node')
entry = self._indexbynode[node]
return entry[b'p1'], entry[b'p2']
def parentrevs(self, rev):
p1, p2 = self.parents(self._indexbyrev[rev][b'node'])
return self.rev(p1), self.rev(p2)
def rev(self, node):
validatenode(node)
try:
self._indexbynode[node]
except KeyError:
raise error.LookupError(node, self._indexpath, _('no node'))
for rev, entry in self._indexbyrev.items():
if entry[b'node'] == node:
return rev
raise error.ProgrammingError(b'this should not occur')
def node(self, rev):
validaterev(rev)
return self._indexbyrev[rev][b'node']
def hasnode(self, node):
validatenode(node)
return node in self._indexbynode
def censorrevision(self, tr, censornode, tombstone=b''):
raise NotImplementedError('TODO')
def lookup(self, node):
if isinstance(node, int):
return self.node(node)
if len(node) == 20:
self.rev(node)
return node
try:
rev = int(node)
if '%d' % rev != node:
raise ValueError
if rev < 0:
rev = len(self) + rev
if rev < 0 or rev >= len(self):
raise ValueError
return self.node(rev)
except (ValueError, OverflowError):
pass
if len(node) == 40:
try:
rawnode = bin(node)
self.rev(rawnode)
return rawnode
except TypeError:
pass
raise error.LookupError(node, self._path, _('invalid lookup input'))
def linkrev(self, rev):
validaterev(rev)
return self._indexbyrev[rev][b'linkrev']
def _flags(self, rev):
validaterev(rev)
return self._indexbyrev[rev][b'flags']
def _candelta(self, baserev, rev):
validaterev(baserev)
validaterev(rev)
if (self._flags(baserev) & revlog.REVIDX_RAWTEXT_CHANGING_FLAGS) or (
self._flags(rev) & revlog.REVIDX_RAWTEXT_CHANGING_FLAGS
):
return False
return True
def checkhash(self, text, node, p1=None, p2=None, rev=None):
if p1 is None and p2 is None:
p1, p2 = self.parents(node)
if node != storageutil.hashrevisionsha1(text, p1, p2):
raise simplestoreerror(
_("integrity check failed on %s") % self._path
)
def revision(self, nodeorrev, raw=False):
if isinstance(nodeorrev, int):
node = self.node(nodeorrev)
else:
node = nodeorrev
validatenode(node)
if node == nullid:
return b''
rev = self.rev(node)
flags = self._flags(rev)
path = b'/'.join([self._storepath, hex(node)])
rawtext = self._svfs.read(path)
if raw:
validatehash = flagutil.processflagsraw(self, rawtext, flags)
text = rawtext
else:
r = flagutil.processflagsread(self, rawtext, flags)
text, validatehash, sidedata = r
if validatehash:
self.checkhash(text, node, rev=rev)
return text
def rawdata(self, nodeorrev):
return self.revision(raw=True)
def read(self, node):
validatenode(node)
revision = self.revision(node)
if not revision.startswith(b'\1\n'):
return revision
start = revision.index(b'\1\n', 2)
return revision[start + 2 :]
def renamed(self, node):
validatenode(node)
if self.parents(node)[0] != nullid:
return False
fulltext = self.revision(node)
m = storageutil.parsemeta(fulltext)[0]
if m and 'copy' in m:
return m['copy'], bin(m['copyrev'])
return False
def cmp(self, node, text):
validatenode(node)
t = text
if text.startswith(b'\1\n'):
t = b'\1\n\1\n' + text
p1, p2 = self.parents(node)
if storageutil.hashrevisionsha1(t, p1, p2) == node:
return False
if self.iscensored(self.rev(node)):
return text != b''
if self.renamed(node):
t2 = self.read(node)
return t2 != text
return True
def size(self, rev):
validaterev(rev)
node = self._indexbyrev[rev][b'node']
if self.renamed(node):
return len(self.read(node))
if self.iscensored(rev):
return 0
return len(self.revision(node))
def iscensored(self, rev):
validaterev(rev)
return self._flags(rev) & repository.REVISION_FLAG_CENSORED
def commonancestorsheads(self, a, b):
validatenode(a)
validatenode(b)
a = self.rev(a)
b = self.rev(b)
ancestors = ancestor.commonancestorsheads(self.parentrevs, a, b)
return pycompat.maplist(self.node, ancestors)
def descendants(self, revs):
# This is a copy of revlog.descendants()
first = min(revs)
if first == nullrev:
for i in self:
yield i
return
seen = set(revs)
for i in self.revs(start=first + 1):
for x in self.parentrevs(i):
if x != nullrev and x in seen:
seen.add(i)
yield i
break
# Required by verify.
def files(self):
entries = self._svfs.listdir(self._storepath)
# Strip out undo.backup.* files created as part of transaction
# recording.
entries = [f for f in entries if not f.startswith('undo.backup.')]
return [b'/'.join((self._storepath, f)) for f in entries]
def storageinfo(
self,
exclusivefiles=False,
sharedfiles=False,
revisionscount=False,
trackedsize=False,
storedsize=False,
):
# TODO do a real implementation of this
return {
'exclusivefiles': [],
'sharedfiles': [],
'revisionscount': len(self),
'trackedsize': 0,
'storedsize': None,
}
def verifyintegrity(self, state):
state['skipread'] = set()
for rev in self:
node = self.node(rev)
try:
self.revision(node)
except Exception as e:
yield simplefilestoreproblem(
error='unpacking %s: %s' % (node, e), node=node
)
state['skipread'].add(node)
def emitrevisions(
self,
nodes,
nodesorder=None,
revisiondata=False,
assumehaveparentrevisions=False,
deltamode=repository.CG_DELTAMODE_STD,
):
# TODO this will probably break on some ordering options.
nodes = [n for n in nodes if n != nullid]
if not nodes:
return
for delta in storageutil.emitrevisions(
self,
nodes,
nodesorder,
simplestorerevisiondelta,
revisiondata=revisiondata,
assumehaveparentrevisions=assumehaveparentrevisions,
deltamode=deltamode,
):
yield delta
def add(self, text, meta, transaction, linkrev, p1, p2):
if meta or text.startswith(b'\1\n'):
text = storageutil.packmeta(meta, text)
return self.addrevision(text, transaction, linkrev, p1, p2)
def addrevision(
self,
text,
transaction,
linkrev,
p1,
p2,
node=None,
flags=revlog.REVIDX_DEFAULT_FLAGS,
cachedelta=None,
):
validatenode(p1)
validatenode(p2)
if flags:
node = node or storageutil.hashrevisionsha1(text, p1, p2)
rawtext, validatehash = flagutil.processflagswrite(self, text, flags)
node = node or storageutil.hashrevisionsha1(text, p1, p2)
if node in self._indexbynode:
return node
if validatehash:
self.checkhash(rawtext, node, p1=p1, p2=p2)
return self._addrawrevision(
node, rawtext, transaction, linkrev, p1, p2, flags
)
def _addrawrevision(self, node, rawtext, transaction, link, p1, p2, flags):
transaction.addbackup(self._indexpath)
path = b'/'.join([self._storepath, hex(node)])
self._svfs.write(path, rawtext)
self._indexdata.append(
{
b'node': node,
b'p1': p1,
b'p2': p2,
b'linkrev': link,
b'flags': flags,
}
)
self._reflectindexupdate()
return node
def _reflectindexupdate(self):
self._refreshindex()
self._svfs.write(
self._indexpath, ''.join(cborutil.streamencode(self._indexdata))
)
def addgroup(
self,
deltas,
linkmapper,
transaction,
addrevisioncb=None,
duplicaterevisioncb=None,
maybemissingparents=False,
):
if maybemissingparents:
raise error.Abort(
_('simple store does not support missing parents ' 'write mode')
)
empty = True
transaction.addbackup(self._indexpath)
for node, p1, p2, linknode, deltabase, delta, flags in deltas:
linkrev = linkmapper(linknode)
flags = flags or revlog.REVIDX_DEFAULT_FLAGS
if node in self._indexbynode:
if duplicaterevisioncb:
duplicaterevisioncb(self, node)
empty = False
continue
# Need to resolve the fulltext from the delta base.
if deltabase == nullid:
text = mdiff.patch(b'', delta)
else:
text = mdiff.patch(self.revision(deltabase), delta)
self._addrawrevision(
node, text, transaction, linkrev, p1, p2, flags
)
if addrevisioncb:
addrevisioncb(self, node)
empty = False
return not empty
def _headrevs(self):
# Assume all revisions are heads by default.
revishead = {rev: True for rev in self._indexbyrev}
for rev, entry in self._indexbyrev.items():
# Unset head flag for all seen parents.
revishead[self.rev(entry[b'p1'])] = False
revishead[self.rev(entry[b'p2'])] = False
return [rev for rev, ishead in sorted(revishead.items()) if ishead]
def heads(self, start=None, stop=None):
# This is copied from revlog.py.
if start is None and stop is None:
if not len(self):
return [nullid]
return [self.node(r) for r in self._headrevs()]
if start is None:
start = nullid
if stop is None:
stop = []
stoprevs = {self.rev(n) for n in stop}
startrev = self.rev(start)
reachable = {startrev}
heads = {startrev}
parentrevs = self.parentrevs
for r in self.revs(start=startrev + 1):
for p in parentrevs(r):
if p in reachable:
if r not in stoprevs:
reachable.add(r)
heads.add(r)
if p in heads and p not in stoprevs:
heads.remove(p)
return [self.node(r) for r in heads]
def children(self, node):
validatenode(node)
# This is a copy of revlog.children().
c = []
p = self.rev(node)
for r in self.revs(start=p + 1):
prevs = [pr for pr in self.parentrevs(r) if pr != nullrev]
if prevs:
for pr in prevs:
if pr == p:
c.append(self.node(r))
elif p == nullrev:
c.append(self.node(r))
return c
def getstrippoint(self, minlink):
return storageutil.resolvestripinfo(
minlink,
len(self) - 1,
self._headrevs(),
self.linkrev,
self.parentrevs,
)
def strip(self, minlink, transaction):
if not len(self):
return
rev, _ignored = self.getstrippoint(minlink)
if rev == len(self):
return
# Purge index data starting at the requested revision.
self._indexdata[rev:] = []
self._reflectindexupdate()
def issimplestorefile(f, kind, st):
if kind != stat.S_IFREG:
return False
if store.isrevlog(f, kind, st):
return False
# Ignore transaction undo files.
if f.startswith('undo.'):
return False
# Otherwise assume it belongs to the simple store.
return True
class simplestore(store.encodedstore):
def datafiles(self):
for x in super(simplestore, self).datafiles():
yield x
# Supplement with non-revlog files.
extrafiles = self._walk('data', True, filefilter=issimplestorefile)
for unencoded, encoded, size in extrafiles:
try:
unencoded = store.decodefilename(unencoded)
except KeyError:
unencoded = None
yield unencoded, encoded, size
def reposetup(ui, repo):
if not repo.local():
return
if isinstance(repo, bundlerepo.bundlerepository):
raise error.Abort(_('cannot use simple store with bundlerepo'))
class simplestorerepo(repo.__class__):
def file(self, f):
return filestorage(self.svfs, f)
repo.__class__ = simplestorerepo
def featuresetup(ui, supported):
supported.add(REQUIREMENT)
def newreporequirements(orig, ui, createopts):
"""Modifies default requirements for new repos to use the simple store."""
requirements = orig(ui, createopts)
# These requirements are only used to affect creation of the store
# object. We have our own store. So we can remove them.
# TODO do this once we feel like taking the test hit.
# if 'fncache' in requirements:
# requirements.remove('fncache')
# if 'dotencode' in requirements:
# requirements.remove('dotencode')
requirements.add(REQUIREMENT)
return requirements
def makestore(orig, requirements, path, vfstype):
if REQUIREMENT not in requirements:
return orig(requirements, path, vfstype)
return simplestore(path, vfstype)
def verifierinit(orig, self, *args, **kwargs):
orig(self, *args, **kwargs)
# We don't care that files in the store don't align with what is
# advertised. So suppress these warnings.
self.warnorphanstorefiles = False
def extsetup(ui):
localrepo.featuresetupfuncs.add(featuresetup)
extensions.wrapfunction(
localrepo, 'newreporequirements', newreporequirements
)
extensions.wrapfunction(localrepo, 'makestore', makestore)
extensions.wrapfunction(verify.verifier, '__init__', verifierinit)