view mercurial/py3kcompat.py @ 20836:a8b4541bb961

grep: reuse the first "util.binary()" result for efficiency

Before this patch, to check whether the file in the specified revision
is binary or not, "util.binary()" is invoked via internal function
"binary()" of "hg grep" once per a line of "hg grep" output, even
though binary-ness is not changed in the same file.

This patch reuses the first "util.binary()" invocation result by
annotating internal function "binary()" with "@util.cachefunc".

Performance improvement measured by "hgperf grep -r 88d8e568add1 vfs
mercurial/scmutil.py":

  before this patch:
    ! wall 0.024000 comb 0.015600 user 0.015600 sys 0.000000 (best of 118)

  after this patch:
    ! wall 0.023000 comb 0.015600 user 0.015600 sys 0.000000 (best of 123)

Status of recent(88d8e568add1) "mercurial/scmutil.py":

  # of lines:     919 (may affect cost of search)
  # of bytes:   29633 (may affect cost of "util.binary()")
  # of matches:    22 (may affect frequency of "util.binary()")

# 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 relies 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()