view doc/check-seclevel.py @ 42377:0546ead39a7e stable

manifest: avoid corruption by dropping removed files with pure (issue5801)

Previously, removed files would simply be marked by overwriting the first byte
with NUL and dropping their entry in `self.position`.  But no effort was made to
ignore them when compacting the dictionary into text form.  This allowed them to
slip into the manifest revision, since the code seems to be trying to minimize
the string operations by copying as large a chunk as possible.  As part of this,
compact() walks the existing text based on entries in the `positions` list, and
consumed everything up to the next position entry.   This typically resulted in
a ValueError complaining about unsorted manifest entries.

Sometimes it seems that files do get dropped in large repos- it seems to
correspond to there being a new entry that would take the same slot.  A much
more trivial problem is that if the only changes were removals, `_compact()`
didn't even run because `__delitem__` doesn't add anything to `self.extradata`.
Now there's an explicit variable to flag this, both to allow `_compact()` to
run, and to avoid searching the manifest in cases where there are no removals.

In practice, this behavior was mostly obscured by the check in fastdelta() which
takes a different path that explicitly drops removed files if there are fewer
than 1000 changes.  However, timeless has a repo where after rebasing tens of
commits, a totally different path[1] is taken that bypasses the change count
check and hits this problem.

[1] https://www.mercurial-scm.org/repo/hg/file/2338bdea4474/mercurial/manifest.py#l1511

#!/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 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.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(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()