branchcache: skip entries that are topological heads in the on disk file
In the majority of cases, topological heads are also branch heads. We have
efficient way to get the topological heads and efficient way to retrieve
their branch information. So there is little value in putting them in the branch
cache file explicitly. On the contrary, writing them explicitly tend to create
very large cache file that are inefficient to read and update.
So the branch cache v3 format is no longer including them. This changeset focus
on the format aspect and have no focus on the performance aspect. We will cover
that later.
#!/usr/bin/env python3
# Dump revlogs as raw data stream
# $ find .hg/store/ -name "*.i" | xargs dumprevlog > repo.dump
import sys
from mercurial.node import hex
from mercurial import (
encoding,
pycompat,
revlog,
)
from mercurial.utils import procutil
from mercurial.revlogutils import (
constants as revlog_constants,
)
for fp in (sys.stdin, sys.stdout, sys.stderr):
procutil.setbinary(fp)
def binopen(path, mode=b'rb'):
if b'b' not in mode:
mode = mode + b'b'
return open(path, pycompat.sysstr(mode))
binopen.options = {}
def printb(data, end=b'\n'):
sys.stdout.flush()
procutil.stdout.write(data + end)
for f in sys.argv[1:]:
localf = encoding.strtolocal(f)
if not localf.endswith(b'.i'):
print("file:", f, file=sys.stderr)
print(" invalid filename", file=sys.stderr)
r = revlog.revlog(
binopen,
target=(revlog_constants.KIND_OTHER, b'dump-revlog'),
radix=localf[:-2],
)
print("file:", f)
for i in r:
n = r.node(i)
p = r.parents(n)
d = r.revision(n)
printb(b"node: %s" % hex(n))
printb(b"linkrev: %d" % r.linkrev(i))
printb(b"parents: %s %s" % (hex(p[0]), hex(p[1])))
printb(b"length: %d" % len(d))
printb(b"-start-")
printb(d)
printb(b"-end-")