doc/check-seclevel.py
author Pierre-Yves David <pierre-yves.david@octobus.net>
Tue, 09 Apr 2024 02:54:19 +0200
changeset 51586 1cef1412af3e
parent 49796 98e7be1ed6c5
permissions -rwxr-xr-x
phases: rework the logic of _pushdiscoveryphase to bound complexity This rework the various graph traversal in _pushdiscoveryphase to keep the complexity in check. This is done though a couple of things: - first, limiting the space we have to explore, for example, if we are not in publishing push, we don't need to consider remote draft roots that are also draft locally, as there is nothing to be moved there. - avoid unbounded descendant computation, and use the faster "rev between" computation. This provide a massive boost to performance when exchanging with repository with a massive amount of draft, like mozilla-try: ### data-env-vars.name = mozilla-try-2023-03-22-zstd-sparse-revlog # benchmark.name = hg.command.push # bin-env-vars.hg.flavor = default # bin-env-vars.hg.py-re2-module = default # benchmark.variants.explicit-rev = all-out-heads # benchmark.variants.issue6528 = disabled # benchmark.variants.protocol = ssh # benchmark.variants.reuse-external-delta-parent = default ## benchmark.variants.revs = any-1-extra-rev before: 20.346590 seconds after: 11.232059 seconds (-38.15%, -7.48 seconds) ## benchmark.variants.revs = any-100-extra-rev before: 24.752051 seconds after: 15.367412 seconds (-37.91%, -9.38 seconds) After this changes, the push operation is still quite too slow. Some of this can be attributed to general phases slowness (reading all the roots from disk for example) and other know slowness (not using persistent-nodemap, branchmap, tags, etc. We are also working on them, but with this series, phase discovery during push no longer showing up in profile and this is a pretty nice and bit low-hanging fruit out of the way. ### (same case as the above) # benchmark.variants.revs = any-1-extra-rev pre-%ln-change: 44.235070 this-changeset: 11.232059 seconds (-74.61%, -33.00 seconds) # benchmark.variants.revs = any-100-extra-rev pre-%ln-change: 49.234697 this-changeset: 15.367412 seconds (-68.79%, -33.87 seconds) Note that with this change, the `hg push` performance is now much closer to the `hg pull` performance, even it still lagging behind a bit. (and the overall performance are still too slow). ### data-env-vars.name = mozilla-try-2023-03-22-ds2-pnm # benchmark.variants.explicit-rev = all-out-heads # benchmark.variants.issue6528 = disabled # benchmark.variants.protocol = ssh # benchmark.variants.pulled-delta-reuse-policy = default # bin-env-vars.hg.flavor = rust ## benchmark.variants.revs = any-1-extra-rev hg.command.pull: 6.517450 hg.command.push: 11.219888 ## benchmark.variants.revs = any-100-extra-rev hg.command.pull: 10.160991 hg.command.push: 14.251107 ### data-env-vars.name = mozilla-try-2023-03-22-zstd-sparse-revlog # bin-env-vars.hg.py-re2-module = default # benchmark.variants.explicit-rev = all-out-heads # benchmark.variants.issue6528 = disabled # benchmark.variants.protocol = ssh # benchmark.variants.pulled-delta-reuse-policy = default ## bin-env-vars.hg.flavor = default ## benchmark.variants.revs = any-1-extra-rev hg.command.pull: 8.577772 hg.command.push: 11.232059 ## bin-env-vars.hg.flavor = default ## benchmark.variants.revs = any-100-extra-rev hg.command.pull: 13.152976 hg.command.push: 15.367412 ## bin-env-vars.hg.flavor = rust ## benchmark.variants.revs = any-1-extra-rev hg.command.pull: 8.731982 hg.command.push: 11.178751 ## bin-env-vars.hg.flavor = rust ## benchmark.variants.revs = any-100-extra-rev hg.command.pull: 13.184236 hg.command.push: 15.620843

#!/usr/bin/env python3
#
# checkseclevel - checking section title levels in each online help document


import optparse
import os
import sys

# import from the live mercurial repo
os.environ['HGMODULEPOLICY'] = 'py'
sys.path.insert(0, os.path.abspath(".."))
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).encode('utf-8'))
    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)).encode(
                    'utf-8'
                )
            )
            showavailables(ui, initlevel)
            errorcnt += 1
            continue
        ui.notenoi18n(
            (
                'appropriate section level for "%s %s"\n'
                % (mark * (nextlevel * 2), title)
            ).encode('utf-8')
        )
        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)
                ).encode('utf-8')
            )
            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
                ).encode('utf-8')
            )
            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)
        ).encode('utf-8')
    )
    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()