view tests/md5sum.py @ 21564:2e91d4964ecd stable

subrepo: make "_sanitize()" work

"_sanitize()" was introduced by 224e96078708 on "stable" branch, but
it has done nothing for sanitizing since 224e96078708.

"_sanitize()" assumes "Visitor" design pattern:

    "os.walk()" should invoke specified function ("v" in this case)
    for each directory elements under specified path

but "os.walk()" assumes "Iterator" design pattern:

    callers of it should drive loop to scan each directory elements
    under specified path by themselves with the returned generator
    object

Because of this mismatching, "_sanitize()" just discards the generator
object returned by "os.walk()" and does nothing for sanitizing.

This patch makes "_sanitize()" work.

This patch also changes the format of warning message to show each
unlinked files, for multiple appearances of "potentially hostile
.hg/hgrc".

#!/usr/bin/env python
#
# Based on python's Tools/scripts/md5sum.py
#
# This software may be used and distributed according to the terms
# of the PYTHON SOFTWARE FOUNDATION LICENSE VERSION 2, which is
# GPL-compatible.

import sys, os

try:
    from hashlib import md5
except ImportError:
    from md5 import md5

try:
    import msvcrt
    msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
    msvcrt.setmode(sys.stderr.fileno(), os.O_BINARY)
except ImportError:
    pass

for filename in sys.argv[1:]:
    try:
        fp = open(filename, 'rb')
    except IOError, msg:
        sys.stderr.write('%s: Can\'t open: %s\n' % (filename, msg))
        sys.exit(1)

    m = md5()
    try:
        while True:
            data = fp.read(8192)
            if not data:
                break
            m.update(data)
    except IOError, msg:
        sys.stderr.write('%s: I/O error: %s\n' % (filename, msg))
        sys.exit(1)
    sys.stdout.write('%s  %s\n' % (m.hexdigest(), filename))

sys.exit(0)