contrib/check-config.py
author Boris Feld <boris.feld@octobus.net>
Fri, 07 Sep 2018 11:17:29 -0400
changeset 39492 a33f394b2bfd
parent 35920 2912bed9b0c7
child 39708 fe28267d5223
permissions -rwxr-xr-x
snapshot: try intermediate snapshot against parents' base # Regarding The Series Started By This Changeset This is the first changesets of a group adjusting delta chain strategy to build a useful chain of intermediate snapshots. The series will introduce a full strategy to produce chains of multiple snapshots on top of which a "usual" delta chain will be built. That strategy will have multiple steps to maximize snapshot reuse, avoiding pathological cases and improving overall compression in very branchy repositories. An important property of sparse-revlog using such snapshot-chain is that they can use very short delta chain without problematic impact on the resulting compression. Shorter delta chains are important to achieve good performance. To make each step clear, we'll introduce them one by one. See the end of this series for full details. # Regarding This Changeset Before this change, if we cannot store the current revision as a delta against a "simple" candidate (p1, p2, prev), we created a new level-0 snapshot (also called full snapshot). As the first step, we introduce a simple strategy: try an intermediate level-1 snapshot against the chain base of the "current revision" parents. The "current revision" is the one we are currently trying to store in the revlog, triggering this search for a good delta base. The first item in the chain is always a level-0 snapshot. # Effect On The Test Repository We can already see the effect on the test-repository. Most of the snapshots have shifted from level 0 to level 1. The overall size has slightly decreased. (However, keep in mind that this repository only emulates real data) # Regarding Statistic The current series focuses on improving the chain built. Improving the performance of this logic will be done as a second step. Sparse-revlog is still experimental and disabled by default. We'll provide more statistic about resulting size and delta chain at the end of this series.

#!/usr/bin/env python
#
# check-config - a config flag documentation checker for Mercurial
#
# Copyright 2015 Matt Mackall <mpm@selenic.com>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

from __future__ import absolute_import, print_function
import re
import sys

foundopts = {}
documented = {}
allowinconsistent = set()

configre = re.compile(br'''
    # Function call
    ui\.config(?P<ctype>|int|bool|list)\(
        # First argument.
        ['"](?P<section>\S+)['"],\s*
        # Second argument
        ['"](?P<option>\S+)['"](,\s+
        (?:default=)?(?P<default>\S+?))?
    \)''', re.VERBOSE | re.MULTILINE)

configwithre = re.compile(b'''
    ui\.config(?P<ctype>with)\(
        # First argument is callback function. This doesn't parse robustly
        # if it is e.g. a function call.
        [^,]+,\s*
        ['"](?P<section>\S+)['"],\s*
        ['"](?P<option>\S+)['"](,\s+
        (?:default=)?(?P<default>\S+?))?
    \)''', re.VERBOSE | re.MULTILINE)

configpartialre = (br"""ui\.config""")

ignorere = re.compile(br'''
    \#\s(?P<reason>internal|experimental|deprecated|developer|inconsistent)\s
    config:\s(?P<config>\S+\.\S+)$
    ''', re.VERBOSE | re.MULTILINE)

def main(args):
    for f in args:
        sect = b''
        prevname = b''
        confsect = b''
        carryover = b''
        linenum = 0
        for l in open(f, 'rb'):
            linenum += 1

            # check topic-like bits
            m = re.match(b'\s*``(\S+)``', l)
            if m:
                prevname = m.group(1)
            if re.match(b'^\s*-+$', l):
                sect = prevname
                prevname = b''

            if sect and prevname:
                name = sect + b'.' + prevname
                documented[name] = 1

            # check docstring bits
            m = re.match(br'^\s+\[(\S+)\]', l)
            if m:
                confsect = m.group(1)
                continue
            m = re.match(br'^\s+(?:#\s*)?(\S+) = ', l)
            if m:
                name = confsect + b'.' + m.group(1)
                documented[name] = 1

            # like the bugzilla extension
            m = re.match(br'^\s*(\S+\.\S+)$', l)
            if m:
                documented[m.group(1)] = 1

            # like convert
            m = re.match(br'^\s*:(\S+\.\S+):\s+', l)
            if m:
                documented[m.group(1)] = 1

            # quoted in help or docstrings
            m = re.match(br'.*?``(\S+\.\S+)``', l)
            if m:
                documented[m.group(1)] = 1

            # look for ignore markers
            m = ignorere.search(l)
            if m:
                if m.group('reason') == 'inconsistent':
                    allowinconsistent.add(m.group('config'))
                else:
                    documented[m.group('config')] = 1

            # look for code-like bits
            line = carryover + l
            m = configre.search(line) or configwithre.search(line)
            if m:
                ctype = m.group('ctype')
                if not ctype:
                    ctype = 'str'
                name = m.group('section') + "." + m.group('option')
                default = m.group('default')
                if default in (None, 'False', 'None', '0', '[]', '""', "''"):
                    default = ''
                if re.match(b'[a-z.]+$', default):
                    default = '<variable>'
                if (name in foundopts and (ctype, default) != foundopts[name]
                    and name not in allowinconsistent):
                    print(l.rstrip())
                    print("conflict on %s: %r != %r" % (name, (ctype, default),
                                                        foundopts[name]))
                    print("at %s:%d:" % (f, linenum))
                foundopts[name] = (ctype, default)
                carryover = ''
            else:
                m = re.search(configpartialre, line)
                if m:
                    carryover = line
                else:
                    carryover = ''

    for name in sorted(foundopts):
        if name not in documented:
            if not (name.startswith("devel.") or
                    name.startswith("experimental.") or
                    name.startswith("debug.")):
                ctype, default = foundopts[name]
                if default:
                    default = ' [%s]' % default
                print("undocumented: %s (%s)%s" % (name, ctype, default))

if __name__ == "__main__":
    if len(sys.argv) > 1:
        sys.exit(main(sys.argv[1:]))
    else:
        sys.exit(main([l.rstrip() for l in sys.stdin]))