tests/md5sum.py

revset: fix order of nested 'or' expression (BC)

This fixes the order of 'x & (y + z)' where 'y' and 'z' are not trivial.

The follow-order 'or' operation is slower than the ordered operation if
an input set is large:

       #0           #1           #2           #3
    0) 0.002968     0.002980     0.002982     0.073042
    1) 0.004513     0.004485     0.012029     0.075261

    #0: 0:4000 & (0:1099 + 1000:2099 + 2000:3099)
    #1: 4000:0 & (0:1099 + 1000:2099 + 2000:3099)
    #2: 10000:0 & (0:1099 + 1000:2099 + 2000:3099)
    #3: file("path:hg") & (0:1099 + 1000:2099 + 2000:3099)

I've tried another implementation, but which appeared to be slower than
this version.

    ss = [getset(repo, fullreposet(repo), x) for x in xs]
    return subset.filter(lambda r: any(r in s for s in ss), cache=False)

#!/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.

from __future__ import absolute_import

import os
import sys

try:
    import hashlib
    md5 = hashlib.md5
except ImportError:
    import md5
    md5 = md5.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 as msg:
        sys.stderr.write('%s: Can\'t open: %s\n' % (filename, msg))
        sys.exit(1)

    m = md5()
    try:
        for data in iter(lambda: fp.read(8192), ''):
            m.update(data)
    except IOError as 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)