view doc/check-seclevel.py @ 44363:f7459da77f23

nodemap: introduce an option to use mmap to read the nodemap mapping The performance and memory benefit is much greater if we don't have to copy all the data in memory for each information. So we introduce an option (on by default) to read the data using mmap. This changeset is the last one definition the API for index support nodemap data. (they have to be able to use the mmaping). Below are some benchmark comparing the best we currently have in 5.3 with the final step of this series (using the persistent nodemap implementation in Rust). The benchmark run `hg perfindex` with various revset and the following variants: Before: * do not use the persistent nodemap * use the CPython implementation of the index for nodemap * use mmapping of the changelog index After: * use the MixedIndex Rust code, with the NodeTree object for nodemap access (still in review) * use the persistent nodemap data from disk * access the persistent nodemap data through mmap * use mmapping of the changelog index The persistent nodemap greatly speed up most operation on very large repositories. Some of the previously very fast lookup end up a bit slower because the persistent nodemap has to be setup. However the absolute slowdown is very small and won't matters in the big picture. Here are some numbers (in seconds) for the reference copy of mozilla-try: Revset Before After abs-change speedup -10000: 0.004622 0.005532 0.000910 × 0.83 -10: 0.000050 0.000132 0.000082 × 0.37 tip 0.000052 0.000085 0.000033 × 0.61 0 + (-10000:) 0.028222 0.005337 -0.022885 × 5.29 0 0.023521 0.000084 -0.023437 × 280.01 (-10000:) + 0 0.235539 0.005308 -0.230231 × 44.37 (-10:) + :9 0.232883 0.000180 -0.232703 ×1293.79 (-10000:) + (:99) 0.238735 0.005358 -0.233377 × 44.55 :99 + (-10000:) 0.317942 0.005593 -0.312349 × 56.84 :9 + (-10:) 0.313372 0.000179 -0.313193 ×1750.68 :9 0.316450 0.000143 -0.316307 ×2212.93 On smaller repositories, the cost of nodemap related operation is not as big, so the win is much more modest. Yet it helps shaving a handful of millisecond here and there. Here are some numbers (in seconds) for the reference copy of mercurial: Revset Before After abs-change speedup -10: 0.000065 0.000097 0.000032 × 0.67 tip 0.000063 0.000078 0.000015 × 0.80 0 0.000561 0.000079 -0.000482 × 7.10 -10000: 0.004609 0.003648 -0.000961 × 1.26 0 + (-10000:) 0.005023 0.003715 -0.001307 × 1.35 (-10:) + :9 0.002187 0.000108 -0.002079 ×20.25 (-10000:) + 0 0.006252 0.003716 -0.002536 × 1.68 (-10000:) + (:99) 0.006367 0.003707 -0.002660 × 1.71 :9 + (-10:) 0.003846 0.000110 -0.003736 ×34.96 :9 0.003854 0.000099 -0.003755 ×38.92 :99 + (-10000:) 0.007644 0.003778 -0.003866 × 2.02 Differential Revision: https://phab.mercurial-scm.org/D7894
author Pierre-Yves David <pierre-yves.david@octobus.net>
date Tue, 11 Feb 2020 11:18:52 +0100
parents e8cf9ad52a78
children c102b704edb5
line wrap: on
line source

#!/usr/bin/env python
#
# checkseclevel - checking section title levels in each online help document

from __future__ import absolute_import

import optparse
import os
import sys

# import from the live mercurial repo
os.environ['HGMODULEPOLICY'] = 'py'
sys.path.insert(0, "..")
from mercurial import demandimport

demandimport.enable()
from mercurial import (
    commands,
    extensions,
    help,
    minirst,
    ui as uimod,
)

table = commands.table
helptable = help.helptable

level2mark = [b'"', b'=', b'-', b'.', b'#']
reservedmarks = [b'"']

mark2level = {}
for m, l in zip(level2mark, range(len(level2mark))):
    if m not in reservedmarks:
        mark2level[m] = l

initlevel_topic = 0
initlevel_cmd = 1
initlevel_ext = 1
initlevel_ext_cmd = 3


def showavailables(ui, initlevel):
    avail = '    available marks and order of them in this help: %s\n' % (
        ', '.join(['%r' % (m * 4) for m in level2mark[initlevel + 1 :]])
    )
    ui.warn(avail.encode('utf-8'))


def checkseclevel(ui, doc, name, initlevel):
    ui.notenoi18n('checking "%s"\n' % name)
    if not isinstance(doc, bytes):
        doc = doc.encode('utf-8')
    blocks, pruned = minirst.parse(doc, 0, ['verbose'])
    errorcnt = 0
    curlevel = initlevel
    for block in blocks:
        if block[b'type'] != b'section':
            continue
        mark = block[b'underline']
        title = block[b'lines'][0]
        if (mark not in mark2level) or (mark2level[mark] <= initlevel):
            ui.warn(
                (
                    'invalid section mark %r for "%s" of %s\n'
                    % (mark * 4, title, name)
                ).encode('utf-8')
            )
            showavailables(ui, initlevel)
            errorcnt += 1
            continue
        nextlevel = mark2level[mark]
        if curlevel < nextlevel and curlevel + 1 != nextlevel:
            ui.warnnoi18n(
                'gap of section level at "%s" of %s\n' % (title, name)
            )
            showavailables(ui, initlevel)
            errorcnt += 1
            continue
        ui.notenoi18n(
            'appropriate section level for "%s %s"\n'
            % (mark * (nextlevel * 2), title)
        )
        curlevel = nextlevel

    return errorcnt


def checkcmdtable(ui, cmdtable, namefmt, initlevel):
    errorcnt = 0
    for k, entry in cmdtable.items():
        name = k.split(b"|")[0].lstrip(b"^")
        if not entry[0].__doc__:
            ui.notenoi18n(
                'skip checking %s: no help document\n' % (namefmt % name)
            )
            continue
        errorcnt += checkseclevel(
            ui, entry[0].__doc__, namefmt % name, initlevel
        )
    return errorcnt


def checkhghelps(ui):
    errorcnt = 0
    for h in helptable:
        names, sec, doc = h[0:3]
        if callable(doc):
            doc = doc(ui)
        errorcnt += checkseclevel(
            ui, doc, '%s help topic' % names[0], initlevel_topic
        )

    errorcnt += checkcmdtable(ui, table, '%s command', initlevel_cmd)

    for name in sorted(
        list(extensions.enabled()) + list(extensions.disabled())
    ):
        mod = extensions.load(ui, name, None)
        if not mod.__doc__:
            ui.notenoi18n(
                'skip checking %s extension: no help document\n' % name
            )
            continue
        errorcnt += checkseclevel(
            ui, mod.__doc__, '%s extension' % name, initlevel_ext
        )

        cmdtable = getattr(mod, 'cmdtable', None)
        if cmdtable:
            errorcnt += checkcmdtable(
                ui,
                cmdtable,
                '%%s command of %s extension' % name,
                initlevel_ext_cmd,
            )
    return errorcnt


def checkfile(ui, filename, initlevel):
    if filename == '-':
        filename = 'stdin'
        doc = sys.stdin.read()
    else:
        with open(filename) as fp:
            doc = fp.read()

    ui.notenoi18n(
        'checking input from %s with initlevel %d\n' % (filename, initlevel)
    )
    return checkseclevel(ui, doc, 'input from %s' % filename, initlevel)


def main():
    optparser = optparse.OptionParser(
        """%prog [options]

This checks all help documents of Mercurial (topics, commands,
extensions and commands of them), if no file is specified by --file
option.
"""
    )
    optparser.add_option(
        "-v", "--verbose", help="enable additional output", action="store_true"
    )
    optparser.add_option(
        "-d", "--debug", help="debug mode", action="store_true"
    )
    optparser.add_option(
        "-f",
        "--file",
        help="filename to read in (or '-' for stdin)",
        action="store",
        default="",
    )

    optparser.add_option(
        "-t",
        "--topic",
        help="parse file as help topic",
        action="store_const",
        dest="initlevel",
        const=0,
    )
    optparser.add_option(
        "-c",
        "--command",
        help="parse file as help of core command",
        action="store_const",
        dest="initlevel",
        const=1,
    )
    optparser.add_option(
        "-e",
        "--extension",
        help="parse file as help of extension",
        action="store_const",
        dest="initlevel",
        const=1,
    )
    optparser.add_option(
        "-C",
        "--extension-command",
        help="parse file as help of extension command",
        action="store_const",
        dest="initlevel",
        const=3,
    )

    optparser.add_option(
        "-l",
        "--initlevel",
        help="set initial section level manually",
        action="store",
        type="int",
        default=0,
    )

    (options, args) = optparser.parse_args()

    ui = uimod.ui.load()
    ui.setconfig(b'ui', b'verbose', options.verbose, b'--verbose')
    ui.setconfig(b'ui', b'debug', options.debug, b'--debug')

    if options.file:
        if checkfile(ui, options.file, options.initlevel):
            sys.exit(1)
    else:
        if checkhghelps(ui):
            sys.exit(1)


if __name__ == "__main__":
    main()