doc/docchecker

global: use raw strings for regular expressions with escapes

Escape sequences like \w, \s, and \d are technically invalid
in str/bytes. This became a deprecation warning in Python 3.6
(https://bugs.python.org/issue27364). Python 3.8 bumps it to
a SyntaxWarning (https://bugs.python.org/issue32912), which is
non-silent by default.

This commit changes a number of regular expressions to use
br'' so regular expression special sequences don't need \\
literals. This fixes roughly half of the SyntaxWarning we
see in the code base with Python 3.8.

Differential Revision: https://phab.mercurial-scm.org/D5815

#!/usr/bin/env python
#
# 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.

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()