view doc/docchecker @ 42373:f3d06d37e194

copies: split up _chain() in naive chaining and filtering steps

The function now has two clearly defined steps. The first step is the
actual chaining. This step is very cheap. The second step is filtering
out invalid copies. This step is expensive. For changeset-centric copy
tracing, I want to do the filtering step only at the end. This patch
prepares for that.

Differential Revision: https://phab.mercurial-scm.org/D6418

#!/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()