view contrib/dumprevlog @ 39857:8dab7c8a93eb

upgrade: report size of backing files, not internal storage size upgrade.py is the only consumer of filelog.index, which I'd like to eliminate from the file storage interface. This commit changes the upgrade code to report the storage size of files by looking at the size of the files backing its storage instead of looking at the index. I'm not convinced the approach in this patch will live very long because it is relying on low-level attributes like "opener" and "files," which may behave very differently on non-revlog storage. But the data is only used for reporting purposes and it does get us one step closer to eliminating "index." A side-effect of this change is we now report the size of the revlog index data - not just the revision data. I think this is more accurate. Differential Revision: https://phab.mercurial-scm.org/D4717
author Gregory Szorc <gregory.szorc@gmail.com>
date Mon, 24 Sep 2018 09:37:19 -0700
parents a8a902d7176e
children a063b84ce064
line wrap: on
line source

#!/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 (
    node,
    revlog,
)
from mercurial.utils import (
    procutil,
)

for fp in (sys.stdin, sys.stdout, sys.stderr):
    procutil.setbinary(fp)

def binopen(path, mode='rb'):
    if 'b' not in mode:
        mode = mode + 'b'
    return open(path, mode)

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