doc/docchecker

pure: write a really lazy version of pure indexObject

On PyPy this version performs reasonably well compared to C version.
Example command is "hg id" which gets faster, depending on details
of your operating system and hard drive (it's bottlenecked on stat mostly)
There is potential for improvements by storing extra as a condensed struct too.

#!/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.
import sys
import re

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

checks = [
  (r""":hg:`[^`]*'[^`]*`""",
    """warning: please avoid nesting ' in :hg:`...`"""),
  (r'\w:hg:`',
    'warning: please have a space before :hg:'),
  (r"""(?:[^a-z][^'.])hg ([^,;"`]*'(?!hg)){2}""",
    '''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:
        print(line)
        for msg in messages:
            print(msg)

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

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

        lead, line = match.group(1), match.group(2)
        if (lead == llead):
            if (lline != ''):
                lline += ' ' + 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) as file:
                work(file)
        except BaseException as e:
            print("failed to process %s: %s" % (f, e))

main()