view contrib/casesmash.py @ 21857:86c2d792a4b7

util: replace 'ellipsis' implementation by 'encoding.trim'

Before this patch, 'util.ellipsis' tried to avoid splitting at
intermediate multi-byte sequence, but its implementation was incorrect.

Internal function '_ellipsis' trims specified unicode sequence not at
most maxlength 'columns in display', but at most maxlength number of
'unicode characters'.

    def _ellipsis(text, maxlength):
        if len(text) <= maxlength:
            return text, False
        else:
            return "%s..." % (text[:maxlength - 3]), True

In many encodings, number of unicode characters can be different from
columns in display.

This patch replaces 'ellipsis' implementation by 'encoding.trim',
which can trim string at most maxlength columns in display correctly,
even though specified string contains multi-byte characters.

'_ellipsis' is removed in this patch, because it is referred only from
'ellipsis'.

import os, __builtin__
from mercurial import util

def lowerwrap(scope, funcname):
    f = getattr(scope, funcname)
    def wrap(fname, *args, **kwargs):
        d, base = os.path.split(fname)
        try:
            files = os.listdir(d or '.')
        except OSError:
            files = []
        if base in files:
            return f(fname, *args, **kwargs)
        for fn in files:
            if fn.lower() == base.lower():
                return f(os.path.join(d, fn), *args, **kwargs)
        return f(fname, *args, **kwargs)
    scope.__dict__[funcname] = wrap

def normcase(path):
    return path.lower()

os.path.normcase = normcase

for f in 'file open'.split():
    lowerwrap(__builtin__, f)

for f in "chmod chown open lstat stat remove unlink".split():
    lowerwrap(os, f)

for f in "exists lexists".split():
    lowerwrap(os.path, f)

lowerwrap(util, 'posixfile')