view tests/md5sum.py @ 5451:0a43875677b1

revlog: break up compression of large deltas

Python's zlib apparently makes an internal copy of strings passed to
compress(). To avoid this, compress strings 1M at a time, then join
them at the end if the result would be smaller than the original.

For initial commits of large but compressible files, this cuts peak
memory usage nearly in half.

#!/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
import os
import md5

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.new()
    try:
        while 1:
            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)