mercurial/minifileset.py

copies: avoid instancing more changectx to access parent revisions

We just need to know the revision numbers of the parents, creating full context
is needlessly expensive.

This provide a small, but noticeable performance boost.

revision: large amount; added files: large amount; rename small amount; c3b14617fbd7 9ba6ab77fd29
before: ! wall 2.885636 comb 2.900000 user 2.870000 sys 0.030000 (median of 10)
after:  ! wall 2.702270 comb 2.710000 user 2.690000 sys 0.020000 (median of 10)
revision: large amount; added files: small amount; rename small amount; c3b14617fbd7 f650a9b140d2
before: ! wall 4.298271 comb 4.290000 user 4.240000 sys 0.050000 (median of 10)
after:  ! wall 3.976610 comb 3.970000 user 3.920000 sys 0.050000 (median of 10)
revision: large amount; added files: large amount; rename large amount; 08ea3258278e d9fa043f30c0
before: ! wall 0.773397 comb 0.770000 user 0.770000 sys 0.000000 (median of 11)
after:  ! wall 0.701634 comb 0.700000 user 0.700000 sys 0.000000 (median of 13)
revision: small amount; added files: large amount; rename large amount; df6f7a526b60 a83dc6a2d56f
before: ! wall 0.013585 comb 0.010000 user 0.010000 sys 0.000000 (median of 217)
after:  ! wall 0.013550 comb 0.010000 user 0.010000 sys 0.000000 (median of 218)
revision: small amount; added files: large amount; rename small amount; 4aa4e1f8e19a 169138063d63
before: ! wall 0.003202 comb 0.000000 user 0.000000 sys 0.000000 (median of 929)
after:  ! wall 0.002993 comb 0.010000 user 0.010000 sys 0.000000 (median of 992)
revision: small amount; added files: small amount; rename small amount; 4bc173b045a6 964879152e2e
before: ! wall 0.000077 comb 0.000000 user 0.000000 sys 0.000000 (median of 12060)
after:  ! wall 0.000072 comb 0.000000 user 0.000000 sys 0.000000 (median of 12804)
revision: medium amount; added files: large amount; rename medium amount; c95f1ced15f2 2c68e87c3efe
before: ! wall 0.510614 comb 0.500000 user 0.500000 sys 0.000000 (median of 18)
after:  ! wall 0.473681 comb 0.470000 user 0.470000 sys 0.000000 (median of 20)
revision: medium amount; added files: medium amount; rename small amount; d343da0c55a8 d7746d32bf9d
before: ! wall 0.126552 comb 0.130000 user 0.130000 sys 0.000000 (median of 77)
after:  ! wall 0.115240 comb 0.110000 user 0.110000 sys 0.000000 (median of 85)

Differential Revision: https://phab.mercurial-scm.org/D7122

# 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)