view doc/docchecker @ 51405:12881244e48a

phases: do filtering at read time

This remove the need for the `filterunknown` method at all.

#!/usr/bin/env python3
#
# docchecker - look for problematic markup
#
# Copyright 2016 timeless <[e-mail]> 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.


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()