view mercurial/py3kcompat.py @ 17658:a02c1ffddae9 stable

largefiles: handle commit -A properly, after a --large commit (issue3542)

Previous to this, 'commit -A' would add as normal files, files that were already
committed as largefiles, resulting in files being listed twice by 'status -A'.
It also missed when (only) a largefile was deleted, even though status reported
it as '!'.  This also has the side effect of properly reporting the state of the
affected largefiles in the post commit hook after a remove that also affected a
normal file (the largefiles used to be 'R', now are properly absent).

Since scmutil.addremove() is called both by the ui command (after some trivial
argument validation) and during the commit process when -A is specified, it
seems like a more appropriate method to wrap than the addremove command.

Currently, a repo is only enabled to use largefiles after an add that explicitly
identifies some file as large, and a subsequent commit.  Therefore, this patch
only changes behavior after such a largefile enabling commit.

Note that in the test, if the final commit had a '-v', 'removing large8' would
be printed twice.  Both of these originate in removelargefiles().  The first
print is in verbose mode after traversing remove + forget, the second is because
the '_isaddremove' attr is set and 'after' is not.

# py3kcompat.py - compatibility definitions for running hg in py3k
#
# Copyright 2010 Renato Cunha <[e-mail]>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

import os, builtins

from numbers import Number

def bytesformatter(format, args):
    '''Custom implementation of a formatter for bytestrings.

    This function currently relias on the string formatter to do the
    formatting and always returns bytes objects.

    >>> bytesformatter(20, 10)
    0
    >>> bytesformatter('unicode %s, %s!', ('string', 'foo'))
    b'unicode string, foo!'
    >>> bytesformatter(b'test %s', 'me')
    b'test me'
    >>> bytesformatter('test %s', 'me')
    b'test me'
    >>> bytesformatter(b'test %s', b'me')
    b'test me'
    >>> bytesformatter('test %s', b'me')
    b'test me'
    >>> bytesformatter('test %d: %s', (1, b'result'))
    b'test 1: result'
    '''
    # The current implementation just converts from bytes to unicode, do
    # what's needed and then convert the results back to bytes.
    # Another alternative is to use the Python C API implementation.
    if isinstance(format, Number):
        # If the fixer erroneously passes a number remainder operation to
        # bytesformatter, we just return the correct operation
        return format % args
    if isinstance(format, bytes):
        format = format.decode('utf-8', 'surrogateescape')
    if isinstance(args, bytes):
        args = args.decode('utf-8', 'surrogateescape')
    if isinstance(args, tuple):
        newargs = []
        for arg in args:
            if isinstance(arg, bytes):
                arg = arg.decode('utf-8', 'surrogateescape')
            newargs.append(arg)
        args = tuple(newargs)
    ret = format % args
    return ret.encode('utf-8', 'surrogateescape')
builtins.bytesformatter = bytesformatter

# Create bytes equivalents for os.environ values
for key in list(os.environ.keys()):
    # UTF-8 is fine for us
    bkey = key.encode('utf-8', 'surrogateescape')
    bvalue = os.environ[key].encode('utf-8', 'surrogateescape')
    os.environ[bkey] = bvalue

origord = builtins.ord
def fakeord(char):
    if isinstance(char, int):
        return char
    return origord(char)
builtins.ord = fakeord

if __name__ == '__main__':
    import doctest
    doctest.testmod()