view doc/check-seclevel.py @ 26909:e36118815a39

phase: improve retractboundary perf

The existing retractboundary implementation computed the new boundary by walking
all descendants of all existing roots and computing the new roots. This is
O(commits since first root), which on long repos can be hundreds of thousands of
commits.

The new algorithm only updates roots that are greater than the new root
locations. For common operations like commit on a repo with the earliest root
several hundred thousand commits ago, this makes retractboundary go from
1 second to 0.008 seconds.

I tested it by running the test suite with both implementations and checking
that the root results were always the identical.

There was some discussion on IRC about the safety of this (i.e. what if the new
nodes are already part of the phase, etc).  I've looked into it and believe this
patch is safe:

1) The old existing code already filters the input nodes to only contain nodes
   that require retracting (i.e. we only make node X a new root if the old phase
   is less than the target phase), so there's no chance of us adding a
   unnecessary root to the phase (unless the input root is made unnecessary by
   another root in the same input, but see point #3).

2) Another way of thinking about this is:  the only way the new algorithm would
   be different from the old algorithm is if it added a root that is a
   descendant of an old root (since the old algorithm would've caught this in
   the big "roots(%ln::)".  At the beginning of the function, when we filter out
   roots that already meet the phase criteria, the *definition* of meeting the
   phase criteria is "not being a descendant of an existing root".  Therefore,
   by definition none of the new roots we are processing are descendants of an
   existing root.

3) If two nodes are passed in as input, and one node is an ancestor of the other
   (and therefore the later node should not be a root), this is still caught by
   the 'roots(%ln::)' revset. So there's no chance of an extra root being
   introduced that way either.

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

import sys, os
import optparse

# import from the live mercurial repo
sys.path.insert(0, "..")
# fall back to pure modules if required C extensions are not available
sys.path.append(os.path.join('..', 'mercurial', 'pure'))
from mercurial import demandimport; demandimport.enable()
from mercurial.commands import table
from mercurial.help import helptable
from mercurial import extensions
from mercurial import minirst
from mercurial import ui as uimod

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

mark2level = {}
for m, l in zip(level2mark, xrange(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):
    ui.warn(('    available marks and order of them in this help: %s\n') %
            (', '.join(['%r' % (m * 4) for m in level2mark[initlevel + 1:]])))

def checkseclevel(ui, doc, name, initlevel):
    ui.note(('checking "%s"\n') % name)
    blocks, pruned = minirst.parse(doc, 0, ['verbose'])
    errorcnt = 0
    curlevel = initlevel
    for block in blocks:
        if block['type'] != 'section':
            continue
        mark = block['underline']
        title = block['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))
            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("|")[0].lstrip("^")
        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(extensions.enabled().keys() +
                       extensions.disabled().keys()):
        mod = extensions.load(None, 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 ' + name + ' extension',
                                      initlevel_ext_cmd)
    return errorcnt

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

    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("-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()
    ui.setconfig('ui', 'verbose', options.verbose, '--verbose')

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

if __name__ == "__main__":
    main()