view tests/md5sum.py @ 20713:6a1a4c212d50

revset: improve head revset performance

Previously the head() revset would iterate over every item in the subset and
check if it was a head.  Since the subset is often the entire repo, this was
slow on large repos. Now we iterate over each item in the head list and check if
it's in the subset, which results in much less work.

hg log -r 'head()' on a large repo:
Before: 0.95s
After: 0.28s

#!/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)