mercurial/minifileset.py
author Georges Racinet <georges.racinet@octobus.net>
Tue, 18 Feb 2020 19:11:15 +0100
changeset 44386 8f7c6656ac79
parent 43077 687b865b95ad
child 48875 6000f5b25c9b
permissions -rw-r--r--
rust-nodemap: pure Rust example To run, use `cargo run --release --example nodemap` This demonstrates that simple scenarios entirely written in Rust can content themselves with `NodeTree<T>`. The example mmaps both the nodemap file and the changelog index. We had of course to include an implementation of `RevlogIndex` directly, which isn't much at this stage. It felt a bit prematurate to include it in the lib. Here are some first performance measurements, obtained with this example, on a clone of mozilla-central with 440000 changesets: (create) Nodemap constructed in RAM in 153.638305ms (query CAE63161B68962) found in 22.362us: Ok(Some(269489)) (bench) Did 3 queries in 36.418µs (mean 12.139µs) (bench) Did 50 queries in 184.318µs (mean 3.686µs) (bench) Did 100000 queries in 31.053461ms (mean 310ns) To be fair, even between bench runs, results tend to depend whether the file is still in kernel caches, and it's not so easy to get back to a real cold start. The worst we've seen was in the 50us ballpark. In any busy server setting, the pages would always be in RAM. We hope it's good enough not to be significantly slower on any concrete Mercurial operation than the C nodetree when fully in RAM, and of course this implementation has the serious headstart advantage of persistence. Differential Revision: https://phab.mercurial-scm.org/D7797

# 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 __future__ import absolute_import

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)