comparison mercurial/util.py @ 11297:d320e70442a5

replace Python standard textwrap by MBCS sensitive one for i18n text

Mercurial has problem around text wrapping/filling in MBCS encoding
environment, because standard 'textwrap' module of Python can not
treat it correctly. It splits byte sequence for one character into two
lines.

According to unicode specification, "east asian width" classifies
characters into:

   W(ide), N(arrow), F(ull-width), H(alf-width), A(mbiguous)


W/N/F/H can be always recognized as 2/1/2/1 bytes in byte sequence,
but 'A' can not. Size of 'A' depends on language in which it is used.

Unicode specification says:

   If the context(= language) cannot be established reliably they
   should be treated as narrow characters by default

but many of class 'A' characters are full-width, at least, in Japanese
environment.

So, this patch treats class 'A' characters as full-width always for
safety wrapping.

This patch focuses only on MBCS safe-ness, not on writing/printing
rule strict wrapping for each languages

MBCS sensitive textwrap class is originally implemented
by ITO Nobuaki <[e-mail]>.

11296:0054a328b98f

"""

from i18n import _
import error, osutil, encoding
import cStringIO, errno, re, shutil, sys, tempfile, traceback
import os, stat, time, calendar, textwrap, signal
import imp

# Python compatibility

def sha1(s):

def uirepr(s):
    # Avoid double backslash in Windows path repr()
    return repr(s).replace('\\\\', '\\')

def wrap(line, hangindent, width=None):
    if width is None:
        width = termwidth() - 2
    if width <= hangindent:
        # adjust for weird terminal size
        width = max(78, hangindent + 1)
    padding = '\n' + ' ' * hangindent
    # To avoid corrupting multi-byte characters in line, we must wrap
    # a Unicode string instead of a bytestring.
    try:
        u = line.decode(encoding.encoding)
        w = padding.join(textwrap.wrap(u, width=width - hangindent))
        return w.encode(encoding.encoding)
    except UnicodeDecodeError:
        return padding.join(textwrap.wrap(line, width=width - hangindent))

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

11297:d320e70442a5

"""

from i18n import _
import error, osutil, encoding
import cStringIO, errno, re, shutil, sys, tempfile, traceback
import os, stat, time, calendar, textwrap, unicodedata, signal
import imp

# Python compatibility

def sha1(s):

def uirepr(s):
    # Avoid double backslash in Windows path repr()
    return repr(s).replace('\\\\', '\\')

#### naming convention of below implementation follows 'textwrap' module

class MBTextWrapper(textwrap.TextWrapper):
    def __init__(self, **kwargs):
        textwrap.TextWrapper.__init__(self, **kwargs)

    def _cutdown(self, str, space_left):
        l = 0
        ucstr = unicode(str, encoding.encoding)
        w = unicodedata.east_asian_width
        for i in xrange(len(ucstr)):
            l += w(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)

        if self.break_long_words:
            cut, res = self._cutdown(reversed_chunks[-1], space_left)
            cur_line.append(cut)
            reversed_chunks[-1] = res
        elif not cur_line:
            cur_line.append(reversed_chunks.pop())

#### naming convention of above implementation follows 'textwrap' module

def wrap(line, width=None, initindent='', hangindent=''):
    if width is None:
        width = termwidth() - 2
    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