view doc/docchecker @ 42618:c17e6a3e7356

phabricator: handle local:commits time being string or int

When setting local:commits arcanist has different behaviour depending on
whether the repo is git or hg. With hg it sets the time as a number, since it
calls PHP's strtotime on the value, but with git it sets it as a string.
Normally this wouldn't be an issue since phabread wouldn't be interacting with
Phabricator Revisions for git repos, but Mozilla has a secondary workflow for
git users that uses the git-cinnabar tool to interact with their hg repos. When
a git-cinnabar user uses the moz-phab tool to submit patches for mozilla-central
it makes use of Mozilla's fork of arcanist, which works with their local git
version of m-c, and thus sets the local:commit time as a string, and then
translates the commit hashes.

Currently when encountering such DREVS phabread dies with "TypeError: %d format:
a number is required, not str".

phabsend also used to set it as a string but wouldn't have encountered the
issue with its own DREVs since it would read hg:meta first.

Differential Revision: https://phab.mercurial-scm.org/D6650

#!/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()