doc/docchecker
author Pierre-Yves David <pierre-yves.david@octobus.net>
Tue, 09 Apr 2024 02:54:12 +0200
changeset 51577 b5d494f7d28a
parent 48875 6000f5b25c9b
permissions -rwxr-xr-x
push: rework the computation of fallbackheads to be correct The previous computation tried to be smart but ended up being wrong. This was caught by phase movement test while reworking the phase discovery logic to be faster. The previous logic was failing to catch case where the pushed set was not based on a common heads (i.e. when the discovery seemed to have "over discovered" content, outside the pushed set) In the following graph, `e` is a common head and we `hg push -r f`. We need to detect `c` as a fallback heads and we previous failed to do so:: e | d f |/ c | b | a The performance impact of the change seems minimal. On the most impacted repository at hand (mozilla-try), the slowdown seems mostly mixed in the overall noise `hg push` but seems to be in the hundred of milliseconds order of magnitude. When using rust, we seems to be a bit faster, probably because we leverage more accelaratd internals. I added a couple of performance related common for further investigation later on.

#!/usr/bin/env python3
#
# docchecker - look for problematic markup
#
# Copyright 2016 timeless <timeless@mozdev.org> 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 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()