view contrib/dumprevlog @ 43231:30570a056fa8

sidedatacopies: only store an entry if it has values

This will make for a shorter storage and help use to write faster code in simple
case. This change already provided a speed boost for copy tracing.

For example here is combined time of running copies tracing on a 6989 pairs of
revision on the pypy repos:

before: 771s
after:  631s - 18%

This also has a very positive impact on changelog size. For example here are the
number for the `00changelog.d` file of pypy.

before: 30449712 Bytes
after:  24973718 Bytes - 18%

This give an overall quite acceptable overhead for storing copies into the
changelog:

filelog-only: 23370586
sidedata:     24973718 Bytes + 7%

Differential Revision: https://phab.mercurial-scm.org/D7068

#!/usr/bin/env python
# Dump revlogs as raw data stream
# $ find .hg/store/ -name "*.i" | xargs dumprevlog > repo.dump

from __future__ import absolute_import, print_function

import sys
from mercurial import (
    encoding,
    node,
    pycompat,
    revlog,
)
from mercurial.utils import (
    procutil,
)

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()
    pycompat.stdout.write(data + end)

for f in sys.argv[1:]:
    r = revlog.revlog(binopen, encoding.strtolocal(f))
    print("file:", f)
    for i in r:
        n = r.node(i)
        p = r.parents(n)
        d = r.revision(n)
        printb(b"node: %s" % node.hex(n))
        printb(b"linkrev: %d" % r.linkrev(i))
        printb(b"parents: %s %s" % (node.hex(p[0]), node.hex(p[1])))
        printb(b"length: %d" % len(d))
        printb(b"-start-")
        printb(d)
        printb(b"-end-")