doc/docchecker

doc: translate from :hg:`help config.SECTION` to a valid link to hgrc.5.html

Before this patch, ":hg:`help config.SECTION`" in online help text is
translated to a link to "hg.1.html#config.SECTION" in HTML
unintentionally.

This patch translates from :hg:`help config.SECTION` in online help
text to a valid link to "hgrc.5.html#SECTION" in HTML.

This patch ignores element(s) under "SECTION" (e.g. "ITEM" of
":hg:`help config.SECTION.ITEM`"), because there is no way to refer
directly to it in HTML, yet.

#!/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:`[^`]*'[^`]*`""")
hg_cramped = re.compile(r'\w:hg:`')

def check(line):
    if hg_backtick.search(line):
        print(line)
        print("""warning: please avoid nesting ' in :hg:`...`""")
    if hg_cramped.search(line):
        print(line)
        print('warning: please have a space before :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 BaseException as e:
            print("failed to process %s: %s" % (f, e))

main()