view mercurial/fileset.py @ 46582:b0a3ca02d17a

copies-rust: implement PartialEqual manually Now that we know that each (dest, rev) pair has at most a unique CopySource, we can simplify comparison a lot. This "simple" step buy a good share of the previous slowdown back in some case: Repo Case Source-Rev Dest-Rev # of revisions old time new time Difference Factor time per rev --------------------------------------------------------------------------------------------------------------------------------------------------------------- mozilla-try x00000_revs_x00000_added_x000_copies 9b2a99adc05e 8e29777b48e6 : 382065 revs, 43.304637 s, 34.443661 s, -8.860976 s, × 0.7954, 90 µs/rev Full benchmark: Repo Case Source-Rev Dest-Rev # of revisions old time new time Difference Factor time per rev --------------------------------------------------------------------------------------------------------------------------------------------------------------- mercurial x_revs_x_added_0_copies ad6b123de1c7 39cfcef4f463 : 1 revs, 0.000043 s, 0.000043 s, +0.000000 s, × 1.0000, 43 µs/rev mercurial x_revs_x_added_x_copies 2b1c78674230 0c1d10351869 : 6 revs, 0.000114 s, 0.000117 s, +0.000003 s, × 1.0263, 19 µs/rev mercurial x000_revs_x000_added_x_copies 81f8ff2a9bf2 dd3267698d84 : 1032 revs, 0.004937 s, 0.004892 s, -0.000045 s, × 0.9909, 4 µs/rev pypy x_revs_x_added_0_copies aed021ee8ae8 099ed31b181b : 9 revs, 0.000339 s, 0.000196 s, -0.000143 s, × 0.5782, 21 µs/rev pypy x_revs_x000_added_0_copies 4aa4e1f8e19a 359343b9ac0e : 1 revs, 0.000049 s, 0.000050 s, +0.000001 s, × 1.0204, 50 µs/rev pypy x_revs_x_added_x_copies ac52eb7bbbb0 72e022663155 : 7 revs, 0.000202 s, 0.000117 s, -0.000085 s, × 0.5792, 16 µs/rev pypy x_revs_x00_added_x_copies c3b14617fbd7 ace7255d9a26 : 1 revs, 0.000409 s, 0.6f1f4a s, -0.000087 s, × 0.7873, 322 µs/rev pypy x_revs_x000_added_x000_copies df6f7a526b60 a83dc6a2d56f : 6 revs, 0.011984 s, 0.011949 s, -0.000035 s, × 0.9971, 1991 µs/rev pypy x000_revs_xx00_added_0_copies 89a76aede314 2f22446ff07e : 4785 revs, 0.050820 s, 0.050802 s, -0.000018 s, × 0.9996, 10 µs/rev pypy x000_revs_x000_added_x_copies 8a3b5bfd266e 2c68e87c3efe : 6780 revs, 0.087953 s, 0.088090 s, +0.000137 s, × 1.0016, 12 µs/rev pypy x000_revs_x000_added_x000_copies 89a76aede314 7b3dda341c84 : 5441 revs, 0.062902 s, 0.062079 s, -0.000823 s, × 0.9869, 11 µs/rev pypy x0000_revs_x_added_0_copies d1defd0dc478 c9cb1334cc78 : 43645 revs, 0.679234 s, 0.635337 s, -0.043897 s, × 0.9354, 14 µs/rev pypy x0000_revs_xx000_added_0_copies bf2c629d0071 4ffed77c095c : 2 revs, 0.013095 s, 0.013262 s, +0.000167 s, × 1.0128, 6631 µs/rev pypy x0000_revs_xx000_added_x000_copies 08ea3258278e d9fa043f30c0 : 11316 revs, 0.120910 s, 0.120085 s, -0.000825 s, × 0.9932, 10 µs/rev netbeans x_revs_x_added_0_copies fb0955ffcbcd a01e9239f9e7 : 2 revs, 0.000087 s, 0.000085 s, -0.000002 s, × 0.9770, 42 µs/rev netbeans x_revs_x000_added_0_copies 6f360122949f 20eb231cc7d0 : 2 revs, 0.000107 s, 0.000110 s, +0.000003 s, × 1.0280, 55 µs/rev netbeans x_revs_x_added_x_copies 1ada3faf6fb6 5a39d12eecf4 : 3 revs, 0.000186 s, 0.000177 s, -0.000009 s, × 0.9516, 59 µs/rev netbeans x_revs_x00_added_x_copies 35be93ba1e2c 9eec5e90c05f : 9 revs, 0.000754 s, 0.000743 s, -0.000011 s, × 0.9854, 82 µs/rev netbeans x000_revs_xx00_added_0_copies eac3045b4fdd 51d4ae7f1290 : 1421 revs, 0.010443 s, 0.010168 s, -0.000275 s, × 0.9737, 7 µs/rev netbeans x000_revs_x000_added_x_copies e2063d266acd 6081d72689dc : 1533 revs, 0.015697 s, 0.015946 s, +0.000249 s, × 1.0159, 10 µs/rev netbeans x000_revs_x000_added_x000_copies ff453e9fee32 411350406ec2 : 5750 revs, 0.063528 s, 0.062712 s, -0.000816 s, × 0.9872, 10 µs/rev netbeans x0000_revs_xx000_added_x000_copies 588c2d1ced70 1aad62e59ddd : 66949 revs, 0.545515 s, 0.523832 s, -0.021683 s, × 0.9603, 7 µs/rev mozilla-central x_revs_x_added_0_copies 3697f962bb7b 7015fcdd43a2 : 2 revs, 0.000089 s, 0.000090 s, +0.000001 s, × 1.0112, 45 µs/rev mozilla-central x_revs_x000_added_0_copies dd390860c6c9 40d0c5bed75d : 8 revs, 0.000265 s, 0.000264 s, -0.000001 s, × 0.9962, 33 µs/rev mozilla-central x_revs_x_added_x_copies 8d198483ae3b 14207ffc2b2f : 9 revs, 0.000381 s, 0.000187 s, -0.000194 s, × 0.4908, 20 µs/rev mozilla-central x_revs_x00_added_x_copies 98cbc58cc6bc 446a150332c3 : 7 revs, 0.000672 s, 0.000665 s, -0.000007 s, × 0.9896, 95 µs/rev mozilla-central x_revs_x000_added_x000_copies 3c684b4b8f68 0a5e72d1b479 : 3 revs, 0.003497 s, 0.003556 s, +0.000059 s, × 1.0169, 1185 µs/rev mozilla-central x_revs_x0000_added_x0000_copies effb563bb7e5 c07a39dc4e80 : 6 revs, 0.073204 s, 0.071345 s, -0.001859 s, × 0.9746, 11890 µs/rev mozilla-central x000_revs_xx00_added_0_copies 6100d773079a 04a55431795e : 1593 revs, 0.006482 s, 0.006551 s, +0.000069 s, × 1.0106, 4 µs/rev mozilla-central x000_revs_x000_added_x_copies 9f17a6fc04f9 2d37b966abed : 41 revs, 0.005066 s, 0.005078 s, +0.000012 s, × 1.0024, 123 µs/rev mozilla-central x000_revs_x000_added_x000_copies 7c97034feb78 4407bd0c6330 : 7839 revs, 0.065707 s, 0.065823 s, +0.000116 s, × 1.0018, 8 µs/rev mozilla-central x0000_revs_xx000_added_0_copies 9eec5917337d 67118cc6dcad : 615 revs, 0.026800 s, 0.027050 s, +0.000250 s, × 1.0093, 43 µs/rev mozilla-central x0000_revs_xx000_added_x000_copies f78c615a656c 96a38b690156 : 30263 revs, 0.203856 s, 0.202443 s, -0.001413 s, × 0.9931, 6 µs/rev mozilla-central x00000_revs_x0000_added_x0000_copies 6832ae71433c 4c222a1d9a00 : 153721 revs, 1.293394 s, 1.261583 s, -0.031811 s, × 0.9754, 8 µs/rev mozilla-central x00000_revs_x00000_added_x000_copies 76caed42cf7c 1daa622bbe42 : 204976 revs, 1.698239 s, 1.643869 s, -0.054370 s, × 0.9680, 8 µs/rev mozilla-try x_revs_x_added_0_copies aaf6dde0deb8 9790f499805a : 2 revs, 0.000875 s, 0.000868 s, -0.000007 s, × 0.9920, 434 µs/rev mozilla-try x_revs_x000_added_0_copies d8d0222927b4 5bb8ce8c7450 : 2 revs, 0.000891 s, 0.000887 s, -0.000004 s, × 0.9955, 443 µs/rev mozilla-try x_revs_x_added_x_copies 092fcca11bdb 936255a0384a : 4 revs, 0.000292 s, 0.000168 s, -0.000124 s, × 0.5753, 42 µs/rev mozilla-try x_revs_x00_added_x_copies b53d2fadbdb5 017afae788ec : 2 revs, 0.003939 s, 0.001160 s, -0.002779 s, × 0.2945, 580 µs/rev mozilla-try x_revs_x000_added_x000_copies 20408ad61ce5 6f0ee96e21ad : 1 revs, 0.033027 s, 0.033016 s, -0.000011 s, × 0.9997, 33016 µs/rev mozilla-try x_revs_x0000_added_x0000_copies effb563bb7e5 c07a39dc4e80 : 6 revs, 0.073703 s, 0.073312 s, -0.39ae31 s, × 0.9947, 12218 µs/rev mozilla-try x000_revs_xx00_added_0_copies 6100d773079a 04a55431795e : 1593 revs, 0.006469 s, 0.006485 s, +0.000016 s, × 1.0025, 4 µs/rev mozilla-try x000_revs_x000_added_x_copies 9f17a6fc04f9 2d37b966abed : 41 revs, 0.005278 s, 0.005494 s, +0.000216 s, × 1.0409, 134 µs/rev mozilla-try x000_revs_x000_added_x000_copies 1346fd0130e4 4c65cbdabc1f : 6657 revs, 0.064995 s, 0.064879 s, -0.000116 s, × 0.9982, 9 µs/rev mozilla-try x0000_revs_x_added_0_copies 63519bfd42ee a36a2a865d92 : 40314 revs, 0.301041 s, 0.301469 s, +0.000428 s, × 1.0014, 7 µs/rev mozilla-try x0000_revs_x_added_x_copies 9fe69ff0762d bcabf2a78927 : 38690 revs, 0.285575 s, 0.297113 s, +0.011538 s, × 1.0404, 7 µs/rev mozilla-try x0000_revs_xx000_added_x_copies 156f6e2674f2 4d0f2c178e66 : 8598 revs, 0.085597 s, 0.085890 s, +0.000293 s, × 1.0034, 9 µs/rev mozilla-try x0000_revs_xx000_added_0_copies 9eec5917337d 67118cc6dcad : 615 revs, 0.027118 s, 0.027718 s, +0.000600 s, × 1.0221, 45 µs/rev mozilla-try x0000_revs_xx000_added_x000_copies 89294cd501d9 7ccb2fc7ccb5 : 97052 revs, 2.119204 s, 2.048949 s, -0.070255 s, × 0.9668, 21 µs/rev mozilla-try x0000_revs_x0000_added_x0000_copies e928c65095ed e951f4ad123a : 52031 revs, 0.701479 s, 0.685924 s, -0.015555 s, × 0.9778, 13 µs/rev mozilla-try x00000_revs_x_added_0_copies 6a320851d377 1ebb79acd503 : 363753 revs, 4.482399 s, 4.482891 s, +0.000492 s, × 1.0001, 12 µs/rev mozilla-try x00000_revs_x00000_added_0_copies dc8a3ca7010e d16fde900c9c : 34414 revs, 0.574082 s, 0.577633 s, +0.003551 s, × 1.0062, 16 µs/rev mozilla-try x00000_revs_x_added_x_copies 5173c4b6f97c 95d83ee7242d : 362229 revs, 4.480366 s, 4.397816 s, -0.082550 s, × 0.9816, 12 µs/rev mozilla-try x00000_revs_x000_added_x_copies 9126823d0e9c ca82787bb23c : 359344 revs, 4.369070 s, 4.370538 s, +0.001468 s, × 1.0003, 12 µs/rev mozilla-try x00000_revs_x0000_added_x0000_copies 8d3fafa80d4b eb884023b810 : 192665 revs, 1.592506 s, 1.570439 s, -0.022067 s, × 0.9861, 8 µs/rev mozilla-try x00000_revs_x00000_added_x0000_copies 1b661134e2ca 1ae03d022d6d : 228985 revs, 87.824489 s, 88.388512 s, +0.564023 s, × 1.0064, 386 µs/rev mozilla-try x00000_revs_x00000_added_x000_copies 9b2a99adc05e 8e29777b48e6 : 382065 revs, 43.304637 s, 34.443661 s, -8.860976 s, × 0.7954, 90 µs/rev private : 459513 revs, 33.853687 s, 27.370148 s, -6.483539 s, × 0.8085, 59 µs/rev Differential Revision: https://phab.mercurial-scm.org/D9653
author Pierre-Yves David <pierre-yves.david@octobus.net>
date Wed, 16 Dec 2020 11:11:05 +0100
parents 89a2afe31e82
children d4ba4d51f85f
line wrap: on
line source

# fileset.py - file set queries for mercurial
#
# Copyright 2010 Matt Mackall <mpm@selenic.com>
#
# 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

import errno
import re

from .i18n import _
from .pycompat import getattr
from . import (
    error,
    filesetlang,
    match as matchmod,
    mergestate as mergestatemod,
    pycompat,
    registrar,
    scmutil,
    util,
)
from .utils import stringutil

# common weight constants
_WEIGHT_CHECK_FILENAME = filesetlang.WEIGHT_CHECK_FILENAME
_WEIGHT_READ_CONTENTS = filesetlang.WEIGHT_READ_CONTENTS
_WEIGHT_STATUS = filesetlang.WEIGHT_STATUS
_WEIGHT_STATUS_THOROUGH = filesetlang.WEIGHT_STATUS_THOROUGH

# helpers for processing parsed tree
getsymbol = filesetlang.getsymbol
getstring = filesetlang.getstring
_getkindpat = filesetlang.getkindpat
getpattern = filesetlang.getpattern
getargs = filesetlang.getargs


def getmatch(mctx, x):
    if not x:
        raise error.ParseError(_(b"missing argument"))
    return methods[x[0]](mctx, *x[1:])


def getmatchwithstatus(mctx, x, hint):
    keys = set(getstring(hint, b'status hint must be a string').split())
    return getmatch(mctx.withstatus(keys), x)


def stringmatch(mctx, x):
    return mctx.matcher([x])


def kindpatmatch(mctx, x, y):
    return stringmatch(
        mctx,
        _getkindpat(
            x, y, matchmod.allpatternkinds, _(b"pattern must be a string")
        ),
    )


def patternsmatch(mctx, *xs):
    allkinds = matchmod.allpatternkinds
    patterns = [
        getpattern(x, allkinds, _(b"pattern must be a string")) for x in xs
    ]
    return mctx.matcher(patterns)


def andmatch(mctx, x, y):
    xm = getmatch(mctx, x)
    ym = getmatch(mctx.narrowed(xm), y)
    return matchmod.intersectmatchers(xm, ym)


def ormatch(mctx, *xs):
    ms = [getmatch(mctx, x) for x in xs]
    return matchmod.unionmatcher(ms)


def notmatch(mctx, x):
    m = getmatch(mctx, x)
    return mctx.predicate(lambda f: not m(f), predrepr=(b'<not %r>', m))


def minusmatch(mctx, x, y):
    xm = getmatch(mctx, x)
    ym = getmatch(mctx.narrowed(xm), y)
    return matchmod.differencematcher(xm, ym)


def listmatch(mctx, *xs):
    raise error.ParseError(
        _(b"can't use a list in this context"),
        hint=_(b'see \'hg help "filesets.x or y"\''),
    )


def func(mctx, a, b):
    funcname = getsymbol(a)
    if funcname in symbols:
        return symbols[funcname](mctx, b)

    keep = lambda fn: getattr(fn, '__doc__', None) is not None

    syms = [s for (s, fn) in symbols.items() if keep(fn)]
    raise error.UnknownIdentifier(funcname, syms)


# symbols are callable like:
#  fun(mctx, x)
# with:
#  mctx - current matchctx instance
#  x - argument in tree form
symbols = filesetlang.symbols

predicate = registrar.filesetpredicate(symbols)


@predicate(b'modified()', callstatus=True, weight=_WEIGHT_STATUS)
def modified(mctx, x):
    """File that is modified according to :hg:`status`."""
    # i18n: "modified" is a keyword
    getargs(x, 0, 0, _(b"modified takes no arguments"))
    s = set(mctx.status().modified)
    return mctx.predicate(s.__contains__, predrepr=b'modified')


@predicate(b'added()', callstatus=True, weight=_WEIGHT_STATUS)
def added(mctx, x):
    """File that is added according to :hg:`status`."""
    # i18n: "added" is a keyword
    getargs(x, 0, 0, _(b"added takes no arguments"))
    s = set(mctx.status().added)
    return mctx.predicate(s.__contains__, predrepr=b'added')


@predicate(b'removed()', callstatus=True, weight=_WEIGHT_STATUS)
def removed(mctx, x):
    """File that is removed according to :hg:`status`."""
    # i18n: "removed" is a keyword
    getargs(x, 0, 0, _(b"removed takes no arguments"))
    s = set(mctx.status().removed)
    return mctx.predicate(s.__contains__, predrepr=b'removed')


@predicate(b'deleted()', callstatus=True, weight=_WEIGHT_STATUS)
def deleted(mctx, x):
    """Alias for ``missing()``."""
    # i18n: "deleted" is a keyword
    getargs(x, 0, 0, _(b"deleted takes no arguments"))
    s = set(mctx.status().deleted)
    return mctx.predicate(s.__contains__, predrepr=b'deleted')


@predicate(b'missing()', callstatus=True, weight=_WEIGHT_STATUS)
def missing(mctx, x):
    """File that is missing according to :hg:`status`."""
    # i18n: "missing" is a keyword
    getargs(x, 0, 0, _(b"missing takes no arguments"))
    s = set(mctx.status().deleted)
    return mctx.predicate(s.__contains__, predrepr=b'deleted')


@predicate(b'unknown()', callstatus=True, weight=_WEIGHT_STATUS_THOROUGH)
def unknown(mctx, x):
    """File that is unknown according to :hg:`status`."""
    # i18n: "unknown" is a keyword
    getargs(x, 0, 0, _(b"unknown takes no arguments"))
    s = set(mctx.status().unknown)
    return mctx.predicate(s.__contains__, predrepr=b'unknown')


@predicate(b'ignored()', callstatus=True, weight=_WEIGHT_STATUS_THOROUGH)
def ignored(mctx, x):
    """File that is ignored according to :hg:`status`."""
    # i18n: "ignored" is a keyword
    getargs(x, 0, 0, _(b"ignored takes no arguments"))
    s = set(mctx.status().ignored)
    return mctx.predicate(s.__contains__, predrepr=b'ignored')


@predicate(b'clean()', callstatus=True, weight=_WEIGHT_STATUS)
def clean(mctx, x):
    """File that is clean according to :hg:`status`."""
    # i18n: "clean" is a keyword
    getargs(x, 0, 0, _(b"clean takes no arguments"))
    s = set(mctx.status().clean)
    return mctx.predicate(s.__contains__, predrepr=b'clean')


@predicate(b'tracked()')
def tracked(mctx, x):
    """File that is under Mercurial control."""
    # i18n: "tracked" is a keyword
    getargs(x, 0, 0, _(b"tracked takes no arguments"))
    return mctx.predicate(mctx.ctx.__contains__, predrepr=b'tracked')


@predicate(b'binary()', weight=_WEIGHT_READ_CONTENTS)
def binary(mctx, x):
    """File that appears to be binary (contains NUL bytes)."""
    # i18n: "binary" is a keyword
    getargs(x, 0, 0, _(b"binary takes no arguments"))
    return mctx.fpredicate(
        lambda fctx: fctx.isbinary(), predrepr=b'binary', cache=True
    )


@predicate(b'exec()')
def exec_(mctx, x):
    """File that is marked as executable."""
    # i18n: "exec" is a keyword
    getargs(x, 0, 0, _(b"exec takes no arguments"))
    ctx = mctx.ctx
    return mctx.predicate(lambda f: ctx.flags(f) == b'x', predrepr=b'exec')


@predicate(b'symlink()')
def symlink(mctx, x):
    """File that is marked as a symlink."""
    # i18n: "symlink" is a keyword
    getargs(x, 0, 0, _(b"symlink takes no arguments"))
    ctx = mctx.ctx
    return mctx.predicate(lambda f: ctx.flags(f) == b'l', predrepr=b'symlink')


@predicate(b'resolved()', weight=_WEIGHT_STATUS)
def resolved(mctx, x):
    """File that is marked resolved according to :hg:`resolve -l`."""
    # i18n: "resolved" is a keyword
    getargs(x, 0, 0, _(b"resolved takes no arguments"))
    if mctx.ctx.rev() is not None:
        return mctx.never()
    ms = mergestatemod.mergestate.read(mctx.ctx.repo())
    return mctx.predicate(
        lambda f: f in ms and ms[f] == b'r', predrepr=b'resolved'
    )


@predicate(b'unresolved()', weight=_WEIGHT_STATUS)
def unresolved(mctx, x):
    """File that is marked unresolved according to :hg:`resolve -l`."""
    # i18n: "unresolved" is a keyword
    getargs(x, 0, 0, _(b"unresolved takes no arguments"))
    if mctx.ctx.rev() is not None:
        return mctx.never()
    ms = mergestatemod.mergestate.read(mctx.ctx.repo())
    return mctx.predicate(
        lambda f: f in ms and ms[f] == b'u', predrepr=b'unresolved'
    )


@predicate(b'hgignore()', weight=_WEIGHT_STATUS)
def hgignore(mctx, x):
    """File that matches the active .hgignore pattern."""
    # i18n: "hgignore" is a keyword
    getargs(x, 0, 0, _(b"hgignore takes no arguments"))
    return mctx.ctx.repo().dirstate._ignore


@predicate(b'portable()', weight=_WEIGHT_CHECK_FILENAME)
def portable(mctx, x):
    """File that has a portable name. (This doesn't include filenames with case
    collisions.)
    """
    # i18n: "portable" is a keyword
    getargs(x, 0, 0, _(b"portable takes no arguments"))
    return mctx.predicate(
        lambda f: util.checkwinfilename(f) is None, predrepr=b'portable'
    )


@predicate(b'grep(regex)', weight=_WEIGHT_READ_CONTENTS)
def grep(mctx, x):
    """File contains the given regular expression."""
    try:
        # i18n: "grep" is a keyword
        r = re.compile(getstring(x, _(b"grep requires a pattern")))
    except re.error as e:
        raise error.ParseError(
            _(b'invalid match pattern: %s') % stringutil.forcebytestr(e)
        )
    return mctx.fpredicate(
        lambda fctx: r.search(fctx.data()),
        predrepr=(b'grep(%r)', r.pattern),
        cache=True,
    )


def _sizetomax(s):
    try:
        s = s.strip().lower()
        for k, v in util._sizeunits:
            if s.endswith(k):
                # max(4k) = 5k - 1, max(4.5k) = 4.6k - 1
                n = s[: -len(k)]
                inc = 1.0
                if b"." in n:
                    inc /= 10 ** len(n.split(b".")[1])
                return int((float(n) + inc) * v) - 1
        # no extension, this is a precise value
        return int(s)
    except ValueError:
        raise error.ParseError(_(b"couldn't parse size: %s") % s)


def sizematcher(expr):
    """Return a function(size) -> bool from the ``size()`` expression"""
    expr = expr.strip()
    if b'-' in expr:  # do we have a range?
        a, b = expr.split(b'-', 1)
        a = util.sizetoint(a)
        b = util.sizetoint(b)
        return lambda x: x >= a and x <= b
    elif expr.startswith(b"<="):
        a = util.sizetoint(expr[2:])
        return lambda x: x <= a
    elif expr.startswith(b"<"):
        a = util.sizetoint(expr[1:])
        return lambda x: x < a
    elif expr.startswith(b">="):
        a = util.sizetoint(expr[2:])
        return lambda x: x >= a
    elif expr.startswith(b">"):
        a = util.sizetoint(expr[1:])
        return lambda x: x > a
    else:
        a = util.sizetoint(expr)
        b = _sizetomax(expr)
        return lambda x: x >= a and x <= b


@predicate(b'size(expression)', weight=_WEIGHT_STATUS)
def size(mctx, x):
    """File size matches the given expression. Examples:

    - size('1k') - files from 1024 to 2047 bytes
    - size('< 20k') - files less than 20480 bytes
    - size('>= .5MB') - files at least 524288 bytes
    - size('4k - 1MB') - files from 4096 bytes to 1048576 bytes
    """
    # i18n: "size" is a keyword
    expr = getstring(x, _(b"size requires an expression"))
    m = sizematcher(expr)
    return mctx.fpredicate(
        lambda fctx: m(fctx.size()), predrepr=(b'size(%r)', expr), cache=True
    )


@predicate(b'encoding(name)', weight=_WEIGHT_READ_CONTENTS)
def encoding(mctx, x):
    """File can be successfully decoded with the given character
    encoding. May not be useful for encodings other than ASCII and
    UTF-8.
    """

    # i18n: "encoding" is a keyword
    enc = getstring(x, _(b"encoding requires an encoding name"))

    def encp(fctx):
        d = fctx.data()
        try:
            d.decode(pycompat.sysstr(enc))
            return True
        except LookupError:
            raise error.Abort(_(b"unknown encoding '%s'") % enc)
        except UnicodeDecodeError:
            return False

    return mctx.fpredicate(encp, predrepr=(b'encoding(%r)', enc), cache=True)


@predicate(b'eol(style)', weight=_WEIGHT_READ_CONTENTS)
def eol(mctx, x):
    """File contains newlines of the given style (dos, unix, mac). Binary
    files are excluded, files with mixed line endings match multiple
    styles.
    """

    # i18n: "eol" is a keyword
    enc = getstring(x, _(b"eol requires a style name"))

    def eolp(fctx):
        if fctx.isbinary():
            return False
        d = fctx.data()
        if (enc == b'dos' or enc == b'win') and b'\r\n' in d:
            return True
        elif enc == b'unix' and re.search(b'(?<!\r)\n', d):
            return True
        elif enc == b'mac' and re.search(b'\r(?!\n)', d):
            return True
        return False

    return mctx.fpredicate(eolp, predrepr=(b'eol(%r)', enc), cache=True)


@predicate(b'copied()')
def copied(mctx, x):
    """File that is recorded as being copied."""
    # i18n: "copied" is a keyword
    getargs(x, 0, 0, _(b"copied takes no arguments"))

    def copiedp(fctx):
        p = fctx.parents()
        return p and p[0].path() != fctx.path()

    return mctx.fpredicate(copiedp, predrepr=b'copied', cache=True)


@predicate(b'revs(revs, pattern)', weight=_WEIGHT_STATUS)
def revs(mctx, x):
    """Evaluate set in the specified revisions. If the revset match multiple
    revs, this will return file matching pattern in any of the revision.
    """
    # i18n: "revs" is a keyword
    r, x = getargs(x, 2, 2, _(b"revs takes two arguments"))
    # i18n: "revs" is a keyword
    revspec = getstring(r, _(b"first argument to revs must be a revision"))
    repo = mctx.ctx.repo()
    revs = scmutil.revrange(repo, [revspec])

    matchers = []
    for r in revs:
        ctx = repo[r]
        mc = mctx.switch(ctx.p1(), ctx)
        matchers.append(getmatch(mc, x))
    if not matchers:
        return mctx.never()
    if len(matchers) == 1:
        return matchers[0]
    return matchmod.unionmatcher(matchers)


@predicate(b'status(base, rev, pattern)', weight=_WEIGHT_STATUS)
def status(mctx, x):
    """Evaluate predicate using status change between ``base`` and
    ``rev``. Examples:

    - ``status(3, 7, added())`` - matches files added from "3" to "7"
    """
    repo = mctx.ctx.repo()
    # i18n: "status" is a keyword
    b, r, x = getargs(x, 3, 3, _(b"status takes three arguments"))
    # i18n: "status" is a keyword
    baseerr = _(b"first argument to status must be a revision")
    baserevspec = getstring(b, baseerr)
    if not baserevspec:
        raise error.ParseError(baseerr)
    reverr = _(b"second argument to status must be a revision")
    revspec = getstring(r, reverr)
    if not revspec:
        raise error.ParseError(reverr)
    basectx, ctx = scmutil.revpair(repo, [baserevspec, revspec])
    mc = mctx.switch(basectx, ctx)
    return getmatch(mc, x)


@predicate(b'subrepo([pattern])')
def subrepo(mctx, x):
    """Subrepositories whose paths match the given pattern."""
    # i18n: "subrepo" is a keyword
    getargs(x, 0, 1, _(b"subrepo takes at most one argument"))
    ctx = mctx.ctx
    sstate = ctx.substate
    if x:
        pat = getpattern(
            x,
            matchmod.allpatternkinds,
            # i18n: "subrepo" is a keyword
            _(b"subrepo requires a pattern or no arguments"),
        )
        fast = not matchmod.patkind(pat)
        if fast:

            def m(s):
                return s == pat

        else:
            m = matchmod.match(ctx.repo().root, b'', [pat], ctx=ctx)
        return mctx.predicate(
            lambda f: f in sstate and m(f), predrepr=(b'subrepo(%r)', pat)
        )
    else:
        return mctx.predicate(sstate.__contains__, predrepr=b'subrepo')


methods = {
    b'withstatus': getmatchwithstatus,
    b'string': stringmatch,
    b'symbol': stringmatch,
    b'kindpat': kindpatmatch,
    b'patterns': patternsmatch,
    b'and': andmatch,
    b'or': ormatch,
    b'minus': minusmatch,
    b'list': listmatch,
    b'not': notmatch,
    b'func': func,
}


class matchctx(object):
    def __init__(self, basectx, ctx, cwd, badfn=None):
        self._basectx = basectx
        self.ctx = ctx
        self._badfn = badfn
        self._match = None
        self._status = None
        self.cwd = cwd

    def narrowed(self, match):
        """Create matchctx for a sub-tree narrowed by the given matcher"""
        mctx = matchctx(self._basectx, self.ctx, self.cwd, self._badfn)
        mctx._match = match
        # leave wider status which we don't have to care
        mctx._status = self._status
        return mctx

    def switch(self, basectx, ctx):
        mctx = matchctx(basectx, ctx, self.cwd, self._badfn)
        mctx._match = self._match
        return mctx

    def withstatus(self, keys):
        """Create matchctx which has precomputed status specified by the keys"""
        mctx = matchctx(self._basectx, self.ctx, self.cwd, self._badfn)
        mctx._match = self._match
        mctx._buildstatus(keys)
        return mctx

    def _buildstatus(self, keys):
        self._status = self._basectx.status(
            self.ctx,
            self._match,
            listignored=b'ignored' in keys,
            listclean=b'clean' in keys,
            listunknown=b'unknown' in keys,
        )

    def status(self):
        return self._status

    def matcher(self, patterns):
        return self.ctx.match(patterns, badfn=self._badfn, cwd=self.cwd)

    def predicate(self, predfn, predrepr=None, cache=False):
        """Create a matcher to select files by predfn(filename)"""
        if cache:
            predfn = util.cachefunc(predfn)
        return matchmod.predicatematcher(
            predfn, predrepr=predrepr, badfn=self._badfn
        )

    def fpredicate(self, predfn, predrepr=None, cache=False):
        """Create a matcher to select files by predfn(fctx) at the current
        revision

        Missing files are ignored.
        """
        ctx = self.ctx
        if ctx.rev() is None:

            def fctxpredfn(f):
                try:
                    fctx = ctx[f]
                except error.LookupError:
                    return False
                try:
                    fctx.audit()
                except error.Abort:
                    return False
                try:
                    return predfn(fctx)
                except (IOError, OSError) as e:
                    # open()-ing a directory fails with EACCES on Windows
                    if e.errno in (
                        errno.ENOENT,
                        errno.EACCES,
                        errno.ENOTDIR,
                        errno.EISDIR,
                    ):
                        return False
                    raise

        else:

            def fctxpredfn(f):
                try:
                    fctx = ctx[f]
                except error.LookupError:
                    return False
                return predfn(fctx)

        return self.predicate(fctxpredfn, predrepr=predrepr, cache=cache)

    def never(self):
        """Create a matcher to select nothing"""
        return matchmod.never(badfn=self._badfn)


def match(ctx, cwd, expr, badfn=None):
    """Create a matcher for a single fileset expression"""
    tree = filesetlang.parse(expr)
    tree = filesetlang.analyze(tree)
    tree = filesetlang.optimize(tree)
    mctx = matchctx(ctx.p1(), ctx, cwd, badfn=badfn)
    return getmatch(mctx, tree)


def loadpredicate(ui, extname, registrarobj):
    """Load fileset predicates from specified registrarobj"""
    for name, func in pycompat.iteritems(registrarobj._table):
        symbols[name] = func


# tell hggettext to extract docstrings from these functions:
i18nfunctions = symbols.values()