view contrib/dumprevlog @ 44832:ad1ec40975aa

rust-regex: fix issues with regex anchoring and performance

It turns out that the way I tried to work around `regex`'s behavior difference
with `re2` and Python's `re` was 1) buggy and 2) much more complicated than
needed.

In a few words:
`regex` adds `.*` on either side of patterns when no start or end anchor is
present. My previous workaround put `^` or `$` for every pattern, which is
wrong even without the other 2 bugs on top of it.
Using `^(?:<patterns>)` right at the end of the `regex` path fixes the issue.
I've opened an issue to get a build option instead:
https://github.com/rust-lang/regex/issues/675

Differential Revision: https://phab.mercurial-scm.org/D8506

#!/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-")