doc/docchecker

match: remove obsolete catching of OverflowError

Since 0f6a1bdf89fb (match: handle large regexes, 2007-08-19), we catch
an OverflowError from the regex engine and split up the regex if that
happens. In 59a9dc9562e2 (ignore: split up huge patterns, 2008-02-11),
that was extended to raise an OverflowError in our code even if the
regex engine doesn't raise it. It's unclear if there was a range of
regex sizes where the OverflowError would be raised from the regex
engine but that were still below the limit we added in our
code. Either way, both limitations were probably removed in Python
2.7.4 when the regex code width was extended from 16bit to 32bit (or
Py_UCS4) integer (thanks to Yuya for finding that out).

If at least the first limitation was removed, we no longer should be
using OverflowError for flow control, so this patch changes that.

Differential Revision: https://phab.mercurial-scm.org/D5309

#!/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 re
import sys

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()