view doc/docchecker @ 45022:e3b19004087a stable

convert: correctly convert paths to UTF-8 for Subversion The previous code using encoding.tolocal() only worked by chance in these situations: * The string is ASCII: The fast path was triggered and the string was returned unmodified. * The local encoding is UTF-8: The source and target encoding is the same. * The string is not valid UTF-8 and the native encoding is ISO-8859-1: If the string doesn’t decode using UTF-8, ISO-8859-1 is tried as a fallback. During `hg convert`, the local encoding is always UTF-8. The irony is that in this case, encoding.tolocal() behaves like what someone would expect the reverse function, encoding.fromlocal(), to do. When the locale encoding is ISO-8859-15, trying to convert a SVN repo `/tmp/a€` failed before like this: file:///tmp/a%C2%A4 does not look like a Subversion repository to libsvn version 1.14.0 The correct URL is `file:///tmp/a%E2%82%AC`. Unlike previously (with the ISO-8859-1 fallback), decoding the path using the locale encoding can fail. In this case, we have to bail out, as Subversion won’t be able to do anything useful with the path.
author Manuel Jacob <me@manueljacob.de>
date Mon, 29 Jun 2020 15:03:36 +0200
parents 47ef023d0165
children c102b704edb5
line wrap: on
line source

#!/usr/bin/env python
#
# docchecker - look for problematic markup
#
# Copyright 2016 timeless <timeless@mozdev.org> and others
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

from __future__ import absolute_import, print_function

import os
import re
import sys

try:
    import msvcrt

    msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
    msvcrt.setmode(sys.stderr.fileno(), os.O_BINARY)
except ImportError:
    pass

stdout = getattr(sys.stdout, 'buffer', sys.stdout)

leadingline = re.compile(br'(^\s*)(\S.*)$')

checks = [
    (
        br""":hg:`[^`]*'[^`]*`""",
        b"""warning: please avoid nesting ' in :hg:`...`""",
    ),
    (br'\w:hg:`', b'warning: please have a space before :hg:'),
    (
        br"""(?:[^a-z][^'.])hg ([^,;"`]*'(?!hg)){2}""",
        b'''warning: please use " instead of ' for hg ... "..."''',
    ),
]


def check(line):
    messages = []
    for match, msg in checks:
        if re.search(match, line):
            messages.append(msg)
    if messages:
        stdout.write(b'%s\n' % line)
        for msg in messages:
            stdout.write(b'%s\n' % msg)


def work(file):
    (llead, lline) = (b'', b'')

    for line in file:
        # this section unwraps lines
        match = leadingline.match(line)
        if not match:
            check(lline)
            (llead, lline) = (b'', b'')
            continue

        lead, line = match.group(1), match.group(2)
        if lead == llead:
            if lline != b'':
                lline += b' ' + line
            else:
                lline = line
        else:
            check(lline)
            (llead, lline) = (lead, line)
    check(lline)


def main():
    for f in sys.argv[1:]:
        try:
            with open(f, 'rb') as file:
                work(file)
        except BaseException as e:
            sys.stdout.write(r"failed to process %s: %s\n" % (f, e))


main()