contrib/dumprevlog

rhg: in path_encode, split Dest into VecDest and MeasureDest

Two separate types make the write semantics easier to understand
because we can consider the two sinks separately.

Having two independent compiled functions for size measurement
and for actual encoding seems likely to improve performance, too.
(and maybe we should get rid of measurement altogether)

Getting rid of [Dest] also removes the ugly option rewrapping
code, which is good.

#!/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-")