doc/docchecker
author Simon Sapin <simon.sapin@octobus.net>
Fri, 21 Jan 2022 17:54:03 +0100
changeset 48745 94e36b230990
parent 45830 c102b704edb5
child 48875 6000f5b25c9b
permissions -rwxr-xr-x
status: prefer relative paths in Rust code … when the repository root is under the current directory, so the kernel needs to traverse fewer directory in every call to `read_dir` or `symlink_metadata`. Better yet would be to use libc functions like `openat` and `fstatat` to remove such repeated traversals entirely, but the standard library does not provide APIs based on those. Maybe with a crate like https://crates.io/crates/openat instead? Benchmarks of `rhg status` show that this patch is neutral in some configurations, and makes the command up to ~20% faster in others. Below is semi-arbitrary subset of results. The four numeric columns are: time (in seconds) with this changeset’s parent, time with this changeset, time difference (negative is better), time ratio (less than 1 is better). ``` mercurial-dirstate-v1 | default-plain-clean.no-iu.pbr | 0.0061 -> 0.0059: -0.0002 (0.97) mercurial-dirstate-v2 | default-plain-clean.no-iu.pbr | 0.0029 -> 0.0028: -0.0001 (0.97) mozilla-dirstate-v1 | default-plain-clean.no-iu.pbr | 0.2110 -> 0.2102: -0.0007 (1.00) mozilla-dirstate-v2 | default-copies-clean.ignored.pbr | 0.0489 -> 0.0401: -0.0088 (0.82) mozilla-dirstate-v2 | default-copies-clean.no-iu.pbr | 0.0479 -> 0.0393: -0.0085 (0.82) mozilla-dirstate-v2 | default-copies-large.all.pbr | 0.1262 -> 0.1210: -0.0051 (0.96) mozilla-dirstate-v2 | default-copies-small.ignored-unknown.pbr | 0.1262 -> 0.1200: -0.0062 (0.95) mozilla-dirstate-v2 | default-copies-small.ignored.pbr | 0.0536 -> 0.0417: -0.0119 (0.78) mozilla-dirstate-v2 | default-copies-small.no-iu.pbr | 0.0482 -> 0.0393: -0.0089 (0.81) mozilla-dirstate-v2 | default-plain-clean.ignored.pbr | 0.0518 -> 0.0402: -0.0116 (0.78) mozilla-dirstate-v2 | default-plain-clean.no-iu.pbr | 0.0481 -> 0.0392: -0.0088 (0.82) mozilla-dirstate-v2 | default-plain-large.all.pbr | 0.1271 -> 0.1218: -0.0052 (0.96) mozilla-dirstate-v2 | default-plain-small.ignored-unknown.pbr | 0.1225 -> 0.1202: -0.0022 (0.98) mozilla-dirstate-v2 | default-plain-small.ignored.pbr | 0.0510 -> 0.0418: -0.0092 (0.82) mozilla-dirstate-v2 | default-plain-small.no-iu.pbr | 0.0480 -> 0.0394: -0.0086 (0.82) netbeans-dirstate-v1 | default-plain-clean.no-iu.pbr | 0.1442 -> 0.1422: -0.0020 (0.99) netbeans-dirstate-v2 | default-plain-clean.no-iu.pbr | 0.0325 -> 0.0282: -0.0043 (0.87) ``` Differential Revision: https://phab.mercurial-scm.org/D12175

#!/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.

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()