view mercurial/minifileset.py @ 50338:81c7d04f4722 stable

match: match explicit file using a set The matcher as all the logic to do quick comparison against explicit patterns, however the pattern matcher was shadowing the code using that set and used the compiled regex pattern in all cases, which is quite slow. We restore the usage of the set based matching to boost performance. Building the regexp is still consuming a large amount of time (actually, the majority of the time), which is still silly. Maybe using re2 would help that, but this is a quest for another adventure. Another path to improve this is to have a pattern type dedicated to match the exact path to a file only (not a directory). This pattern could use the set matching only and be skipped in the regex all together. Benchmarks ========== In the following benchmark we are comparing the `hg cat` and `hg files` run time when matching against all files in the repository. They are run: - without the rust extensions - with the standard python engine (so without re2) Performance improvement in this series -------------------------------------- ###### hg files ############################################################### ### mercurial-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 0.230092 seconds prev-changeset: 0.230069 seconds this-changeset: 0.211425 seconds (-8.36%) ### mercurial-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 0.234235 seconds prev-changeset: 0.231165 seconds (-1.38%) this-changeset: 0.212300 seconds (-9.43%) ### pypy-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 0.613567 seconds prev-changeset: 0.616799 seconds this-changeset: 0.510852 seconds (-16.82%) ### pypy-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 0.801880 seconds prev-changeset: 0.616393 seconds (-23.22%) this-changeset: 0.511903 seconds (-36.23%) ### netbeans-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 21.541828 seconds prev-changeset: 21.586773 seconds this-changeset: 13.648347 seconds (-36.76%) ### netbeans-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 172.759857 seconds prev-changeset: 21.908197 seconds (-87.32%) this-changeset: 13.945110 seconds (-91.93%) ### mozilla-central-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 62.474221 seconds prev-changeset: 61.279490 seconds (-1.22%) this-changeset: 29.529469 seconds (-52.40%) ### mozilla-central-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 1364.180218 seconds prev-changeset: 62.473549 seconds (-95.40%) this-changeset: 30.625249 seconds (-97.75%) ###### hg cat ################################################################# ### mercurial-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 0.764407 seconds prev-changeset: 0.763883 seconds this-changeset: 0.737326 seconds (-3.68%) ### mercurial-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 0.768924 seconds prev-changeset: 0.765848 seconds this-changeset: 0.174d0b seconds (-4.44%) ### pypy-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 2.065220 seconds prev-changeset: 2.070498 seconds this-changeset: 1.939482 seconds (-6.08%) ### pypy-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 2.276388 seconds prev-changeset: 2.069197 seconds (-9.15%) this-changeset: 1.931746 seconds (-15.19%) ### netbeans-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 40.967983 seconds prev-changeset: 41.392423 seconds this-changeset: 32.181681 seconds (-22.20%) ### netbeans-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 216.388709 seconds prev-changeset: 41.648689 seconds (-80.88%) this-changeset: 32.580817 seconds (-85.04%) ### mozilla-central-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 105.228510 seconds prev-changeset: 103.315670 seconds (-1.23%) this-changeset: 69.416118 seconds (-33.64%) ### mozilla-central-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 1448.722784 seconds prev-changeset: 104.369358 seconds (-92.80%) this-changeset: 70.554789 seconds (-95.13%) Different way to list the same data with this revision ------------------------------------------------------ ###### hg files ############################################################### ### mercurial-2018-08-01-zstd-sparse-revlog root: 0.119182 seconds glob: 0.120697 seconds (+1.27%) sorted: 0.211425 seconds (+77.40%) shuffled: 0.212300 seconds (+78.13%) ### pypy-2018-08-01-zstd-sparse-revlog root: 0.121986 seconds glob: 0.124822 seconds (+2.32%) sorted: 0.510852 seconds (+318.78%) shuffled: 0.511903 seconds (+319.64%) ### netbeans-2018-08-01-zstd-sparse-revlog root: 0.173984 seconds glob: 0.227203 seconds (+30.59%) sorted: 13.648347 seconds (+7744.59%) shuffled: 13.945110 seconds (+7915.16%) ### mozilla-central-2018-08-01-zstd-sparse-revlog root: 0.366463 seconds glob: 0.491030 seconds (+33.99%) sorted: 29.529469 seconds (+7957.96%) shuffled: 30.625249 seconds (+8256.97%) ###### hg cat ################################################################# ### mercurial-2018-08-01-zstd-sparse-revlog glob: 0.647471 seconds root: 0.643120 seconds shuffled: 0.174d0b seconds (+13.92%) sorted: 0.737326 seconds (+13.88%) ### mozilla-central-2018-08-01-zstd-sparse-revlog glob: 40.596983 seconds root: 40.129136 seconds shuffled: 70.554789 seconds (+73.79%) sorted: 69.416118 seconds (+70.99%) ### netbeans-2018-08-01-zstd-sparse-revlog glob: 18.777924 seconds root: 18.613905 seconds shuffled: 32.580817 seconds (+73.51%) sorted: 32.181681 seconds (+71.38%) ### pypy-2018-08-01-zstd-sparse-revlog glob: 1.555319 seconds root: 1.536534 seconds shuffled: 1.931746 seconds (+24.20%) sorted: 1.939482 seconds (+24.70%)
author Pierre-Yves David <pierre-yves.david@octobus.net>
date Sat, 01 Apr 2023 05:58:59 +0200
parents 6000f5b25c9b
children f4733654f144
line wrap: on
line source

# minifileset.py - a simple language to select files
#
# Copyright 2017 Facebook, Inc.
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.


from .i18n import _
from . import (
    error,
    fileset,
    filesetlang,
    pycompat,
)


def _sizep(x):
    # i18n: "size" is a keyword
    expr = filesetlang.getstring(x, _(b"size requires an expression"))
    return fileset.sizematcher(expr)


def _compile(tree):
    if not tree:
        raise error.ParseError(_(b"missing argument"))
    op = tree[0]
    if op == b'withstatus':
        return _compile(tree[1])
    elif op in {b'symbol', b'string', b'kindpat'}:
        name = filesetlang.getpattern(
            tree, {b'path'}, _(b'invalid file pattern')
        )
        if name.startswith(b'**'):  # file extension test, ex. "**.tar.gz"
            ext = name[2:]
            for c in pycompat.bytestr(ext):
                if c in b'*{}[]?/\\':
                    raise error.ParseError(_(b'reserved character: %s') % c)
            return lambda n, s: n.endswith(ext)
        elif name.startswith(b'path:'):  # directory or full path test
            p = name[5:]  # prefix
            pl = len(p)
            f = lambda n, s: n.startswith(p) and (
                len(n) == pl or n[pl : pl + 1] == b'/'
            )
            return f
        raise error.ParseError(
            _(b"unsupported file pattern: %s") % name,
            hint=_(b'paths must be prefixed with "path:"'),
        )
    elif op in {b'or', b'patterns'}:
        funcs = [_compile(x) for x in tree[1:]]
        return lambda n, s: any(f(n, s) for f in funcs)
    elif op == b'and':
        func1 = _compile(tree[1])
        func2 = _compile(tree[2])
        return lambda n, s: func1(n, s) and func2(n, s)
    elif op == b'not':
        return lambda n, s: not _compile(tree[1])(n, s)
    elif op == b'func':
        symbols = {
            b'all': lambda n, s: True,
            b'none': lambda n, s: False,
            b'size': lambda n, s: _sizep(tree[2])(s),
        }

        name = filesetlang.getsymbol(tree[1])
        if name in symbols:
            return symbols[name]

        raise error.UnknownIdentifier(name, symbols.keys())
    elif op == b'minus':  # equivalent to 'x and not y'
        func1 = _compile(tree[1])
        func2 = _compile(tree[2])
        return lambda n, s: func1(n, s) and not func2(n, s)
    elif op == b'list':
        raise error.ParseError(
            _(b"can't use a list in this context"),
            hint=_(b'see \'hg help "filesets.x or y"\''),
        )
    raise error.ProgrammingError(b'illegal tree: %r' % (tree,))


def compile(text):
    """generate a function (path, size) -> bool from filter specification.

    "text" could contain the operators defined by the fileset language for
    common logic operations, and parenthesis for grouping.  The supported path
    tests are '**.extname' for file extension test, and '"path:dir/subdir"'
    for prefix test.  The ``size()`` predicate is borrowed from filesets to test
    file size.  The predicates ``all()`` and ``none()`` are also supported.

    '(**.php & size(">10MB")) | **.zip | (path:bin & !path:bin/README)' for
    example, will catch all php files whose size is greater than 10 MB, all
    files whose name ends with ".zip", and all files under "bin" in the repo
    root except for "bin/README".
    """
    tree = filesetlang.parse(text)
    tree = filesetlang.analyze(tree)
    tree = filesetlang.optimize(tree)
    return _compile(tree)