doc/docchecker

docchecker: introduce a way to check for poor markup

Specifically, :hg:`foo 'bar baz'` when rendered by `hg help`
results in:

  'hg foo 'bar baz''

... which is hard to read.

We encourage :hg:`foo "bar baz"` instead.

#!/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.*)$')
hg_backtick = re.compile(r""":hg:`[^`]*'[^`]*`""")

def check(line):
  if hg_backtick.search(line):
    print(line)
    print("""warning: please avoid nesting ' in :hg:`...`""")

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:
      print("failed to process %s" % f)

main()