contrib/dumprevlog

tests: alter email `From` line to a value that's consistently parsed

Python2:
>>> email.header.decode_header('=?UTF-8?q?Rapha=C3=ABl=20Hertzog?= <[e-mail]>')
[('Rapha\xc3\xabl Hertzog', 'utf-8'), ('<[e-mail]>', None)]

Python3:
>>> email.header.decode_header('=?UTF-8?q?Rapha=C3=ABl=20Hertzog?= <[e-mail]>')
[(b'Rapha\xc3\xabl Hertzog', 'utf-8'), (b' <[e-mail]>', None)]

So alter the input to an input that parses to the same result
consistently. After skimming the relevant RFC (1342), I'm not sure if
what we had was valid, or how I could modify it to be more consistent.

Differential Revision: https://phab.mercurial-scm.org/D5769

#!/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-")