This is an archive of the discontinued Mercurial Phabricator instance.

Differential D10305

revlog: move the details of revlog "v2" index inside revlog.utils.constants
ClosedPublic

Authored by marmoute on Apr 5 2021, 11:49 AM.

Details

Reviewers
indygreg
Alphare
pulkit
Group Reviewers
hg-reviewers
Commits
rHG85e3a630cad9: revlog: move the details of revlog "v2" index inside revlog.utils.constants
Summary

the revlog module is quite large and this kind of format information would handy
for other module. So let us start to gather this information about the format in
a more appropriate place.

We update various reference to this information to use the new "source of truth"
in the process.

Diff Detail

Repository
rHG Mercurial
Lint
Automatic diff as part of commit; lint not applicable.
Unit
Automatic diff as part of commit; unit tests not applicable.

Revision Contents
Changeset List

Diff 26695

mercurial/pure/parsers.py

if not inline: if not inline:
cls = IndexObject2 if revlogv2 else IndexObject cls = IndexObject2 if revlogv2 else IndexObject
return cls(data), None return cls(data), None
cls = InlinedIndexObject2 if revlogv2 else InlinedIndexObject cls = InlinedIndexObject2 if revlogv2 else InlinedIndexObject
return cls(data, inline), (0, data) return cls(data, inline), (0, data)
class Index2Mixin(object): class Index2Mixin(object):
# 6 bytes: offset index_format = revlog_constants.INDEX_ENTRY_V2.format
# 2 bytes: flags index_size = revlog_constants.INDEX_ENTRY_V2.size
# 4 bytes: compressed length
# 4 bytes: uncompressed length
# 4 bytes: base rev
# 4 bytes: link rev
# 4 bytes: parent 1 rev
# 4 bytes: parent 2 rev
# 32 bytes: nodeid
# 8 bytes: sidedata offset
# 4 bytes: sidedata compressed length
# 20 bytes: Padding to align to 96 bytes (see RevlogV2Plan wiki page)
index_format = b">Qiiiiii20s12xQi20x"
index_size = struct.calcsize(index_format)
assert index_size == 96, index_size
null_item = (0, 0, 0, -1, -1, -1, -1, nullid, 0, 0) null_item = (0, 0, 0, -1, -1, -1, -1, nullid, 0, 0)
def replace_sidedata_info(self, i, sidedata_offset, sidedata_length): def replace_sidedata_info(self, i, sidedata_offset, sidedata_length):
""" """
Replace an existing index entry's sidedata offset and length with new Replace an existing index entry's sidedata offset and length with new
ones. ones.
This cannot be used outside of the context of sidedata rewriting, This cannot be used outside of the context of sidedata rewriting,
inside the transaction that creates the revision `i`. inside the transaction that creates the revision `i`.

mercurial/revlog.py

) )
from .i18n import _ from .i18n import _
from .pycompat import getattr from .pycompat import getattr
from .revlogutils.constants import ( from .revlogutils.constants import (
FLAG_GENERALDELTA, FLAG_GENERALDELTA,
FLAG_INLINE_DATA, FLAG_INLINE_DATA,
INDEX_ENTRY_V0, INDEX_ENTRY_V0,
INDEX_ENTRY_V1, INDEX_ENTRY_V1,
INDEX_ENTRY_V2,
REVLOGV0, REVLOGV0,
REVLOGV1, REVLOGV1,
REVLOGV1_FLAGS, REVLOGV1_FLAGS,
REVLOGV2, REVLOGV2,
REVLOGV2_FLAGS, REVLOGV2_FLAGS,
REVLOG_DEFAULT_FLAGS, REVLOG_DEFAULT_FLAGS,
REVLOG_DEFAULT_FORMAT, REVLOG_DEFAULT_FORMAT,
REVLOG_DEFAULT_VERSION, REVLOG_DEFAULT_VERSION,
flagutil, flagutil,
nodemap as nodemaputil, nodemap as nodemaputil,
sidedata as sidedatautil, sidedata as sidedatautil,
) )
from .utils import ( from .utils import (
storageutil, storageutil,
stringutil, stringutil,
) )
from .pure import parsers as pureparsers
# blanked usage of all the name to prevent pyflakes constraints # blanked usage of all the name to prevent pyflakes constraints
# We need these name available in the module for extensions. # We need these name available in the module for extensions.
REVLOGV0 REVLOGV0
REVLOGV1 REVLOGV1
REVLOGV2 REVLOGV2
FLAG_INLINE_DATA FLAG_INLINE_DATA
FLAG_GENERALDELTA FLAG_GENERALDELTA
def packentry(self, entry, node, version, rev): def packentry(self, entry, node, version, rev):
p = INDEX_ENTRY_V1.pack(*entry) p = INDEX_ENTRY_V1.pack(*entry)
if rev == 0: if rev == 0:
p = versionformat_pack(version) + p[4:] p = versionformat_pack(version) + p[4:]
return p return p
indexformatv2 = struct.Struct(pureparsers.Index2Mixin.index_format)
indexformatv2_pack = indexformatv2.pack
class revlogv2io(object): class revlogv2io(object):
def __init__(self): def __init__(self):
self.size = indexformatv2.size self.size = INDEX_ENTRY_V2.size
def parseindex(self, data, inline): def parseindex(self, data, inline):
index, cache = parsers.parse_index2(data, inline, revlogv2=True) index, cache = parsers.parse_index2(data, inline, revlogv2=True)
return index, cache return index, cache
def packentry(self, entry, node, version, rev): def packentry(self, entry, node, version, rev):
p = indexformatv2_pack(*entry) p = INDEX_ENTRY_V2.pack(*entry)
if rev == 0: if rev == 0:
p = versionformat_pack(version) + p[4:] p = versionformat_pack(version) + p[4:]
return p return p
NodemapRevlogIO = None NodemapRevlogIO = None
if util.safehasattr(parsers, 'parse_index_devel_nodemap'): if util.safehasattr(parsers, 'parse_index_devel_nodemap'):

mercurial/revlogutils/constants.py

# 4 bytes: base rev # 4 bytes: base rev
# 4 bytes: link rev # 4 bytes: link rev
# 4 bytes: parent 1 rev # 4 bytes: parent 1 rev
# 4 bytes: parent 2 rev # 4 bytes: parent 2 rev
# 32 bytes: nodeid # 32 bytes: nodeid
INDEX_ENTRY_V1 = struct.Struct(b">Qiiiiii20s12x") INDEX_ENTRY_V1 = struct.Struct(b">Qiiiiii20s12x")
assert INDEX_ENTRY_V1.size == 32 * 2 assert INDEX_ENTRY_V1.size == 32 * 2
# 6 bytes: offset
# 2 bytes: flags
# 4 bytes: compressed length
# 4 bytes: uncompressed length
# 4 bytes: base rev
# 4 bytes: link rev
# 4 bytes: parent 1 rev
# 4 bytes: parent 2 rev
# 32 bytes: nodeid
# 8 bytes: sidedata offset
# 4 bytes: sidedata compressed length
# 20 bytes: Padding to align to 96 bytes (see RevlogV2Plan wiki page)
INDEX_ENTRY_V2 = struct.Struct(b">Qiiiiii20s12xQi20x")
assert INDEX_ENTRY_V2.size == 32 * 3
# revlog index flags # revlog index flags
# For historical reasons, revlog's internal flags were exposed via the # For historical reasons, revlog's internal flags were exposed via the
# wire protocol and are even exposed in parts of the storage APIs. # wire protocol and are even exposed in parts of the storage APIs.
# revision has censor metadata, must be verified # revision has censor metadata, must be verified
REVIDX_ISCENSORED = repository.REVISION_FLAG_CENSORED REVIDX_ISCENSORED = repository.REVISION_FLAG_CENSORED
# revision hash does not match data (narrowhg) # revision hash does not match data (narrowhg)