doc/check-seclevel.py
author Gregory Szorc <gregory.szorc@gmail.com>
Mon, 13 Nov 2017 19:20:34 -0800
changeset 35132 e96613048bdd
parent 32577 e9f456183402
child 40292 9c6473d2038b
permissions -rwxr-xr-x
perf: add command to benchmark bundle reading Upcoming commits will be refactoring bundle2 I/O code. This commit establishes a `hg perfbundleread` command that measures how long it takes to read a bundle using various mechanisms. As a baseline, here's output from an uncompressed bundle1 bundle of my Firefox repo (7,098,622,890 bytes): ! read(8k) ! wall 0.763481 comb 0.760000 user 0.160000 sys 0.600000 (best of 6) ! read(16k) ! wall 0.644512 comb 0.640000 user 0.110000 sys 0.530000 (best of 16) ! read(32k) ! wall 0.581172 comb 0.590000 user 0.060000 sys 0.530000 (best of 18) ! read(128k) ! wall 0.535183 comb 0.530000 user 0.010000 sys 0.520000 (best of 19) ! cg1 deltaiter() ! wall 0.873500 comb 0.880000 user 0.840000 sys 0.040000 (best of 12) ! cg1 getchunks() ! wall 6.283797 comb 6.270000 user 5.570000 sys 0.700000 (best of 3) ! cg1 read(8k) ! wall 1.097173 comb 1.100000 user 0.400000 sys 0.700000 (best of 10) ! cg1 read(16k) ! wall 0.810750 comb 0.800000 user 0.200000 sys 0.600000 (best of 13) ! cg1 read(32k) ! wall 0.671215 comb 0.670000 user 0.110000 sys 0.560000 (best of 15) ! cg1 read(128k) ! wall 0.597857 comb 0.600000 user 0.020000 sys 0.580000 (best of 15) And from an uncompressed bundle2 bundle (6,070,036,163 bytes): ! read(8k) ! wall 0.676997 comb 0.680000 user 0.160000 sys 0.520000 (best of 15) ! read(16k) ! wall 0.592706 comb 0.590000 user 0.080000 sys 0.510000 (best of 17) ! read(32k) ! wall 0.529395 comb 0.530000 user 0.050000 sys 0.480000 (best of 16) ! read(128k) ! wall 0.491270 comb 0.490000 user 0.010000 sys 0.480000 (best of 19) ! bundle2 forwardchunks() ! wall 2.997131 comb 2.990000 user 2.270000 sys 0.720000 (best of 4) ! bundle2 iterparts() ! wall 12.247197 comb 10.670000 user 8.170000 sys 2.500000 (best of 3) ! bundle2 part seek() ! wall 11.761675 comb 10.500000 user 8.240000 sys 2.260000 (best of 3) ! bundle2 part read(8k) ! wall 9.116163 comb 9.110000 user 8.240000 sys 0.870000 (best of 3) ! bundle2 part read(16k) ! wall 8.984362 comb 8.970000 user 8.110000 sys 0.860000 (best of 3) ! bundle2 part read(32k) ! wall 8.758364 comb 8.740000 user 7.860000 sys 0.880000 (best of 3) ! bundle2 part read(128k) ! wall 8.749040 comb 8.730000 user 7.830000 sys 0.900000 (best of 3) We already see some interesting data. Notably that bundle2 has significant overhead compared to bundle1. This matters for e.g. stream clone bundles, which can be applied at >1Gbps. Differential Revision: https://phab.mercurial-scm.org/D1385

#!/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.note(('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.warn(('gap of section level at "%s" of %s\n') %
                    (title, name))
            showavailables(ui, initlevel)
            errorcnt += 1
            continue
        ui.note(('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.note(('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 names, sec, doc in helptable:
        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.note(('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.note(('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('ui', 'verbose', options.verbose, '--verbose')
    ui.setconfig('ui', 'debug', options.debug, '--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()