contrib/check-config.py

fncache: avoid loading the filename cache when not actually modifying it

With time, fncache can become very large. The mozilla-central repo for example,
has a 31M and growing fncache file. Loading this file takes time (280ms for the
mozilla-central repository).

In many scenarios, we don't need to load fncache at all. For example, when
committing changes to existing files, or pushing such commits to another clone.
This patch detects when a name is added via store.vfs(), and only loads the
cache if a) the data metadata file doesn't already exist, or b) when opening
for appending, the data or metadata file exists but has size  (a transaction
rollback leaves behind such files).

Benchmarks (run on Macos 10.13 on a 2017-model Macbook Pro with Core i7 2.9GHz
and flash drive), each test without and with patch run 5 times:

* committing to an existing file, against the mozilla-central repository.
  Baseline real time average 2.3736, with patch 1.9884.

* unbundling a large changeset consisting *only* of existing-file modifications
  (159 revisions, 1050 modifications, mozilla-central
  4a250a0e4f29:beea9ac7d823), into a clone limited to the ancestor revision of
  that revset). Baseline real time average 1.5048, with patch 1.3108.

#!/usr/bin/env python
#
# check-config - a config flag documentation checker for Mercurial
#
# Copyright 2015 Matt Mackall <[e-mail]>
#
# 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]))