view doc/docchecker @ 44651:00e0c5c06ed5

pycompat: change argv conversion semantics

Use of os.fsencode() to convert Python's sys.argv back to bytes
was not correct because it isn't the logically inverse operation
from what CPython was doing under the hood.

This commit changes the logic for doing the str -> bytes
conversion. This required a separate implementation for
POSIX and Windows.

The Windows behavior is arguably not ideal. The previous
behavior on Windows was leading to failing tests, such as
test-http-branchmap.t, which defines a utf-8 branch name
via a command argument. Previously, Mercurial's argument
parser looked to be receiving wchar_t bytes in some cases.
After this commit, behavior on Windows is compatible with
Python 2, where CPython did not implement `int wmain()` and
Windows was performing a Unicode to ANSI conversion on the
wchar_t native command line.

Arguably better behavior on Windows would be for Mercurial to
preserve the original Unicode sequence coming from Python and
to wrap this in a bytes-like type so we can round trip safely.
But, this would be new, backwards incompatible behavior. My
goal for this commit was to converge Mercurial behavior on
Python 3 on Windows to fix busted tests. And I believe I was
successful, as this commit fixes 9 tests on my Windows
machine and 14 tests in the AWS CI environment!

Differential Revision: https://phab.mercurial-scm.org/D8337

#!/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()