Mercurial > hg
view contrib/simplemerge @ 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 <daydream.trippers@gmail.com>.
author | FUJIWARA Katsunori <foozy@lares.dti.ne.jp> |
---|---|
date | Sun, 06 Jun 2010 17:20:10 +0900 |
parents | bb9f13974d8e |
children | 659f34b833b9 |
line wrap: on
line source
#!/usr/bin/env python from mercurial import demandimport demandimport.enable() import os, sys from mercurial.i18n import _ from mercurial import simplemerge, fancyopts, util, ui options = [('L', 'label', [], _('labels to use on conflict markers')), ('a', 'text', None, _('treat all files as text')), ('p', 'print', None, _('print results instead of overwriting LOCAL')), ('', 'no-minimal', None, _('do not try to minimize conflict regions')), ('h', 'help', None, _('display help and exit')), ('q', 'quiet', None, _('suppress output'))] usage = _('''simplemerge [OPTS] LOCAL BASE OTHER Simple three-way file merge utility with a minimal feature set. Apply to LOCAL the changes necessary to go from BASE to OTHER. By default, LOCAL is overwritten with the results of this operation. ''') class ParseError(Exception): """Exception raised on errors in parsing the command line.""" def showhelp(): sys.stdout.write(usage) sys.stdout.write('\noptions:\n') out_opts = [] for shortopt, longopt, default, desc in options: out_opts.append(('%2s%s' % (shortopt and '-%s' % shortopt, longopt and ' --%s' % longopt), '%s' % desc)) opts_len = max([len(opt[0]) for opt in out_opts]) for first, second in out_opts: sys.stdout.write(' %-*s %s\n' % (opts_len, first, second)) try: for fp in (sys.stdin, sys.stdout, sys.stderr): util.set_binary(fp) opts = {} try: args = fancyopts.fancyopts(sys.argv[1:], options, opts) except fancyopts.getopt.GetoptError, e: raise ParseError(e) if opts['help']: showhelp() sys.exit(0) if len(args) != 3: raise ParseError(_('wrong number of arguments')) sys.exit(simplemerge.simplemerge(ui.ui(), *args, **opts)) except ParseError, e: sys.stdout.write("%s: %s\n" % (sys.argv[0], e)) showhelp() sys.exit(1) except util.Abort, e: sys.stderr.write("abort: %s\n" % e) sys.exit(255) except KeyboardInterrupt: sys.exit(255)