view contrib/check-config.py @ 32151:4d504e541d3d

rebase: use matcher to optimize manifestmerge

The old merge code would call manifestmerge and calculate the complete diff
between the source to the destination. In many cases, like rebase, the vast
majority of differences between the source and destination are irrelevant
because they are differences between the destination and the common ancestor
only, and therefore don't affect the merge. Since most actions are 'keep', all
the effort to compute them is wasted.

Instead, let's compute the difference between the source and the common ancestor
and only perform the diff of those files against the merge destination. When
using treemanifest, this lets us avoid loading almost the entire tree when
rebasing from a very old ancestor. This speeds up rebase of an old stack of 27
commits by 20x.

In mozilla-central, without treemanifest, when rebasing a commit from
default~100000 to default, this speeds up the manifestmerge step from 2.6s to
1.2s.  However, the additional diff adds an overhead to all manifestmerge calls,
especially for flat manifests. When rebasing a commit from default~1 to default
it appears to add 100ms in mozilla-central. While we could put this optimization
behind a flag, I think the fact that it makes merge O(number of changes being
applied) instead of O(number of changes between X and Y) justifies it.

#!/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 = {}

configre = (r"""ui\.config(|int|bool|list)\(['"](\S+)['"],\s*"""
            r"""['"](\S+)['"](,\s+(?:default=)?(\S+?))?\)""")
configpartialre = (r"""ui\.config""")

def main(args):
    for f in args:
        sect = ''
        prevname = ''
        confsect = ''
        carryover = ''
        for l in open(f):

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

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

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

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

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

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

            # look for ignore markers
            m = re.search(r'# (?:internal|experimental|deprecated|developer)'
                          ' config: (\S+\.\S+)$', l)
            if m:
                documented[m.group(1)] = 1

            # look for code-like bits
            line = carryover + l
            m = re.search(configre, line, re.MULTILINE)
            if m:
                ctype = m.group(1)
                if not ctype:
                    ctype = 'str'
                name = m.group(2) + "." + m.group(3)
                default = m.group(5)
                if default in (None, 'False', 'None', '0', '[]', '""', "''"):
                    default = ''
                if re.match('[a-z.]+$', default):
                    default = '<variable>'
                if name in foundopts and (ctype, default) != foundopts[name]:
                    print(l)
                    print("conflict on %s: %r != %r" % (name, (ctype, default),
                                                        foundopts[name]))
                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]))