comparison mercurial/util.py @ 15065:24a6c3f903bb stable

util: wrap lines with multi-byte characters correctly (issue2943)

This re-introduces the unicode conversion what was lost in d320e70442a5 5 years
ago and had the comment:
  To avoid corrupting multi-byte characters in line, we must wrap
  a Unicode string instead of a bytestring.

15064:1f581a8b1948

        representation, or encoding of the underlying string)
        """
        def __init__(self, **kwargs):
            textwrap.TextWrapper.__init__(self, **kwargs)

        def _cutdown(self, str, space_left):
            l = 0
            ucstr = unicode(str, encoding.encoding)
            colwidth = unicodedata.east_asian_width
            for i in xrange(len(ucstr)):
                l += colwidth(ucstr[i]) in 'WFA' and 2 or 1
                if space_left < l:
                    return (ucstr[:i].encode(encoding.encoding),
                            ucstr[i:].encode(encoding.encoding))
            return str, ''

        # overriding of base class
        def _handle_long_word(self, reversed_chunks, cur_line, cur_len, width):
            space_left = max(width - cur_len, 1)

def wrap(line, width, initindent='', hangindent=''):
    maxindent = max(len(hangindent), len(initindent))
    if width <= maxindent:
        # adjust for weird terminal size
        width = max(78, maxindent + 1)
    wrapper = MBTextWrapper(width=width,
                            initial_indent=initindent,
                            subsequent_indent=hangindent)
    return wrapper.fill(line)

def iterlines(iterator):
    for chunk in iterator:
        for line in chunk.splitlines():
            yield line

15065:24a6c3f903bb

        representation, or encoding of the underlying string)
        """
        def __init__(self, **kwargs):
            textwrap.TextWrapper.__init__(self, **kwargs)

        def _cutdown(self, ucstr, space_left):
            l = 0
            colwidth = unicodedata.east_asian_width
            for i in xrange(len(ucstr)):
                l += colwidth(ucstr[i]) in 'WFA' and 2 or 1
                if space_left < l:
                    return (ucstr[:i], ucstr[i:])
            return ucstr, ''

        # overriding of base class
        def _handle_long_word(self, reversed_chunks, cur_line, cur_len, width):
            space_left = max(width - cur_len, 1)

def wrap(line, width, initindent='', hangindent=''):
    maxindent = max(len(hangindent), len(initindent))
    if width <= maxindent:
        # adjust for weird terminal size
        width = max(78, maxindent + 1)
    line = line.decode(encoding.encoding, encoding.encodingmode)
    initindent = initindent.decode(encoding.encoding, encoding.encodingmode)
    hangindent = hangindent.decode(encoding.encoding, encoding.encodingmode)
    wrapper = MBTextWrapper(width=width,
                            initial_indent=initindent,
                            subsequent_indent=hangindent)
    return wrapper.fill(line).encode(encoding.encoding)

def iterlines(iterator):
    for chunk in iterator:
        for line in chunk.splitlines():
            yield line