view contrib/dumprevlog @ 43325:7d4f2e4899c5 stable

py3: fix headencode() with display=False

We previously called str() on a email.header.Header object. On Python 2,
this returns a bytestring and the __str__ method is actually an alias to
.encode() method. On Python 3, __str__ does not perform encoding (and
returns a unicode string). To keep a consistent behavior across Python
versions, we explicitly use .encode() and we wrap the result with
encoding.strtolocal() to get a bytestring in all cases. As a side effect
of forcing bytes conversion, we need to decode back in _addressencode().

This is to make test-notify.t pass on Python 3.

Also note that headers are now encoded in some patchbomb tests; this is
because the charset is not always "us-ascii" ("iso-8859-1" otherwise) on
Python 3.

#!/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-")