Mercurial > hg
view doc/gendoc.py @ 9424:799373ff2554
highlight: fixes garbled text in non-UTF-8 environment
This patch treats all files inside repository as encoded by
locale's encoding when pygmentize.
We can assume that most files are written in locale's encoding,
but current implementation treats them as UTF-8.
So there's no way to specify the encoding of files.
Current implementation, db7557359636 (issue1341):
1. Convert original `text`, which is treated as UTF-8, to locale's encoding.
`encoding.tolocal()` is the method to convert from internal UTF-8 to local.
If original `text` is not UTF-8, e.g. Japanese EUC-JP, some characters
become garbled here.
2. pygmentize, with no UnicodeDecodeError.
This patch:
1. Convert original `text`, which is treated as locale's encoding, to unicode.
Pygments prefers unicode object than raw str. [1]_
If original `text` is not encoded by locale's encoding, some characters
become garbled here.
2. pygmentize, also with no UnicodeDecodeError :)
3. Convert unicode back to raw str, which is encoded by locale's.
.. [1] http://pygments.org/docs/unicode/
author | Yuya Nishihara <yuya@tcha.org> |
---|---|
date | Sat, 29 Aug 2009 15:24:15 +0900 |
parents | b6cb3af61582 |
children | d98cef25b5af |
line wrap: on
line source
import os, sys, textwrap # import from the live mercurial repo sys.path.insert(0, "..") # fall back to pure modules if required C extensions are not available sys.path.append(os.path.join('..', 'mercurial', 'pure')) from mercurial import demandimport; demandimport.enable() from mercurial.commands import table, globalopts from mercurial.i18n import _ from mercurial.help import helptable def get_desc(docstr): if not docstr: return "", "" # sanitize docstr = docstr.strip("\n") docstr = docstr.rstrip() shortdesc = docstr.splitlines()[0].strip() i = docstr.find("\n") if i != -1: desc = docstr[i+2:] else: desc = " %s" % shortdesc return (shortdesc, desc) def get_opts(opts): for shortopt, longopt, default, desc in opts: allopts = [] if shortopt: allopts.append("-%s" % shortopt) if longopt: allopts.append("--%s" % longopt) desc += default and _(" (default: %s)") % default or "" yield(", ".join(allopts), desc) def get_cmd(cmd): d = {} attr = table[cmd] cmds = cmd.lstrip("^").split("|") d['cmd'] = cmds[0] d['aliases'] = cmd.split("|")[1:] d['desc'] = get_desc(attr[0].__doc__) d['opts'] = list(get_opts(attr[1])) s = 'hg ' + cmds[0] if len(attr) > 2: if not attr[2].startswith('hg'): s += ' ' + attr[2] else: s = attr[2] d['synopsis'] = s return d def show_doc(ui): def bold(s, text=""): ui.write("%s\n%s\n%s\n" % (s, "="*len(s), text)) def underlined(s, text=""): ui.write("%s\n%s\n%s\n" % (s, "-"*len(s), text)) # print options underlined(_("OPTIONS")) for optstr, desc in get_opts(globalopts): ui.write("%s::\n %s\n\n" % (optstr, desc)) # print cmds underlined(_("COMMANDS")) h = {} for c, attr in table.items(): f = c.split("|")[0] f = f.lstrip("^") h[f] = c cmds = h.keys() cmds.sort() for f in cmds: if f.startswith("debug"): continue d = get_cmd(h[f]) # synopsis ui.write("[[%s]]\n" % d['cmd']) ui.write("%s::\n" % d['synopsis'].replace("hg ","", 1)) # description ui.write("%s\n\n" % d['desc'][1]) # options opt_output = list(d['opts']) if opt_output: opts_len = max([len(line[0]) for line in opt_output]) ui.write(_(" options:\n")) for optstr, desc in opt_output: if desc: s = "%-*s %s" % (opts_len, optstr, desc) else: s = optstr s = textwrap.fill(s, initial_indent=4 * " ", subsequent_indent=(6 + opts_len) * " ") ui.write("%s\n" % s) ui.write("\n") # aliases if d['aliases']: ui.write(_(" aliases: %s\n\n") % " ".join(d['aliases'])) # print topics for names, section, doc in helptable: underlined(section.upper()) if callable(doc): doc = doc() ui.write(doc) ui.write("\n") if __name__ == "__main__": show_doc(sys.stdout)