view tests/md5sum.py @ 31397:8f5ed8fa39f8

perf: perform a garbage collection before each iteration

Currently, no explicit garbage collection is performed when running
the microbenchmarks in `hg perf`. I think this is wrong because
garbage collection can have a significant impact on execution times.
And, if gc is triggered via the default heuristics, it will
fire effectively randomly during subsequent benchmark iterations
due to variable amount of garbage left over from previous runs.

Running a gc before invoking the measured function will help ensure
state is more consistent across all iterations.

#!/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)