view tests/md5sum.py @ 30190:56b930238036 stable

largefiles: more safe handling of interruptions while updating modifications

Largefiles are fragile with the design where dirstate and lfdirstate must be
kept in sync.

To be less fragile, mark all clean largefiles as unsure ("normallookup") before
updating standins. After standins have been updated and we know exactly which
largefile standins actually was changed, mark the unchanged largefiles back to
clean ("normal").

This will make the failure mode more safe. If interrupted, the next command
will continue to perform extra hashing of all largefiles. That will do that all
largefiles that are out of sync with their standin will be marked dirty and
they will show up in status and can be cleaned with update --clean.

#!/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:
        while True:
            data = fp.read(8192)
            if not data:
                break
            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)