contrib/dumprevlog

rust-parsers: switch to parse/pack_dirstate to mutate-on-loop

Both `parse_dirstate` and `pack_dirstate` can operate directly on the data
they're passed, which prevents the creation of intermediate data structures,
simplifies the function signatures and reduces boilerplate. They are exposed
directly to the Python for now, but a later patch will make use of them inside
`hg-core`.

Differential Revision: https://phab.mercurial-scm.org/D6628

#!/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))

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-")