view mercurial/fileset.py @ 45892:06b64fabf91c

copies: cache the ancestor checking call when tracing copy A good share of the time spent in this function is spent doing ancestors checking. To avoid spending time in duplicated call, we cache the result of calls. In the slower case, this provide a quite significant performance boost. Below are the result for a set of selected pairs (many of them pathological): (And further down is another table that summarize the current state of filelog based vs changeset base copy tracing) The benchmark have been configured to be killed after 6 minutes of runtime, which mean that any detect slower than 2 minutes will be marked as "killed". This drop some useful information about how much slower these case are? but also prevent 99% of the benchmark time to be spent on case that can be labelled "very slow" anyway. Repo Case Source-Rev Dest-Rev Old-Time New-Time Difference Factor ------------------------------------------------------------------------------------------------------------------------------------ mercurial x_revs_x_added_0_copies ad6b123de1c7 39cfcef4f463 : 0.000044 s, 0.000044 s, +0.000000 s, ? 1.0000 mercurial x_revs_x_added_x_copies 2b1c78674230 0c1d10351869 : 0.000138 s, 0.000138 s, +0.000000 s, ? 1.0000 mercurial x000_revs_x000_added_x_copies 81f8ff2a9bf2 dd3267698d84 : 0.005067 s, 0.005052 s, -0.000015 s, ? 0.9970 pypy x_revs_x_added_0_copies aed021ee8ae8 099ed31b181b : 0.000218 s, 0.000219 s, +0.000001 s, ? 1.0046 pypy x_revs_x000_added_0_copies 4aa4e1f8e19a 359343b9ac0e : 0.000053 s, 0.000055 s, +0.000002 s, ? 1.0377 pypy x_revs_x_added_x_copies ac52eb7bbbb0 72e022663155 : 0.000125 s, 0.000128 s, +0.000003 s, ? 1.0240 pypy x_revs_x00_added_x_copies c3b14617fbd7 ace7255d9a26 : 0.001098 s, 0.001089 s, -0.000009 s, ? 0.9918 pypy x_revs_x000_added_x000_copies df6f7a526b60 a83dc6a2d56f : 0.017546 s, 0.017407 s, -0.000139 s, ? 0.9921 pypy x000_revs_xx00_added_0_copies 89a76aede314 2f22446ff07e : 0.096723 s, 0.094175 s, -0.002548 s, ? 0.9737 pypy x000_revs_x000_added_x_copies 8a3b5bfd266e 2c68e87c3efe : 0.271796 s, 0.238009 s, -0.033787 s, ? 0.8757 pypy x000_revs_x000_added_x000_copies 89a76aede314 7b3dda341c84 : 0.128602 s, 0.125876 s, -0.002726 s, ? 0.9788 pypy x0000_revs_x_added_0_copies d1defd0dc478 c9cb1334cc78 : 7.086742 s, 3.581556 s, -3.505186 s, ? 0.5054 pypy x0000_revs_xx000_added_0_copies bf2c629d0071 4ffed77c095c : 0.016634 s, 0.016721 s, +0.000087 s, ? 1.0052 pypy x0000_revs_xx000_added_x000_copies 08ea3258278e d9fa043f30c0 : 0.254225 s, 0.242367 s, -0.011858 s, ? 0.9534 netbeans x_revs_x_added_0_copies fb0955ffcbcd a01e9239f9e7 : 0.000166 s, 0.000165 s, -0.000001 s, ? 0.9940 netbeans x_revs_x000_added_0_copies 6f360122949f 20eb231cc7d0 : 0.000118 s, 0.000114 s, -0.000004 s, ? 0.9661 netbeans x_revs_x_added_x_copies 1ada3faf6fb6 5a39d12eecf4 : 0.000296 s, 0.000296 s, +0.000000 s, ? 1.0000 netbeans x_revs_x00_added_x_copies 35be93ba1e2c 9eec5e90c05f : 0.001137 s, 0.001124 s, -0.000013 s, ? 0.9886 netbeans x000_revs_xx00_added_0_copies eac3045b4fdd 51d4ae7f1290 : 0.014133 s, 0.013060 s, -0.001073 s, ? 0.9241 netbeans x000_revs_x000_added_x_copies e2063d266acd 6081d72689dc : 0.016988 s, 0.017112 s, +0.000124 s, ? 1.0073 netbeans x000_revs_x000_added_x000_copies ff453e9fee32 411350406ec2 : 0.676361 s, 0.660350 s, -0.016011 s, ? 0.9763 netbeans x0000_revs_xx000_added_x000_copies 588c2d1ced70 1aad62e59ddd : 12.515149 s, 10.032499 s, -2.482650 s, ? 0.8016 mozilla-central x_revs_x_added_0_copies 3697f962bb7b 7015fcdd43a2 : 0.000186 s, 0.000189 s, +0.000003 s, ? 1.0161 mozilla-central x_revs_x000_added_0_copies dd390860c6c9 40d0c5bed75d : 0.000459 s, 0.000462 s, +0.000003 s, ? 1.0065 mozilla-central x_revs_x_added_x_copies 8d198483ae3b 14207ffc2b2f : 0.000273 s, 0.000270 s, -0.000003 s, ? 0.9890 mozilla-central x_revs_x00_added_x_copies 98cbc58cc6bc 446a150332c3 : 0.001503 s, 0.001474 s, -0.000029 s, ? 0.9807 mozilla-central x_revs_x000_added_x000_copies 3c684b4b8f68 0a5e72d1b479 : 0.004862 s, 0.004806 s, -0.000056 s, ? 0.9885 mozilla-central x_revs_x0000_added_x0000_copies effb563bb7e5 c07a39dc4e80 : 0.088291 s, 0.085150 s, -0.003141 s, ? 0.9644 mozilla-central x000_revs_xx00_added_0_copies 6100d773079a 04a55431795e : 0.007113 s, 0.007064 s, -0.000049 s, ? 0.9931 mozilla-central x000_revs_x000_added_x_copies 9f17a6fc04f9 2d37b966abed : 0.004687 s, 0.004741 s, +0.000054 s, ? 1.0115 mozilla-central x000_revs_x000_added_x000_copies 7c97034feb78 4407bd0c6330 : 0.198710 s, 0.190133 s, -0.008577 s, ? 0.9568 mozilla-central x0000_revs_xx000_added_0_copies 9eec5917337d 67118cc6dcad : 0.036068 s, 0.035651 s, -0.000417 s, ? 0.9884 mozilla-central x0000_revs_xx000_added_x000_copies f78c615a656c 96a38b690156 : 0.465362 s, 0.440694 s, -0.024668 s, ? 0.9470 mozilla-central x00000_revs_x0000_added_x0000_copies 6832ae71433c 4c222a1d9a00 : 24.519684 s, 18.454163 s, -6.065521 s, ? 0.7526 mozilla-central x00000_revs_x00000_added_x000_copies 76caed42cf7c 1daa622bbe42 : 42.711897 s, 31.562719 s, -11.149178 s, ? 0.7390 mozilla-try x_revs_x_added_0_copies aaf6dde0deb8 9790f499805a : 0.001201 s, 0.001189 s, -0.000012 s, ? 0.9900 mozilla-try x_revs_x000_added_0_copies d8d0222927b4 5bb8ce8c7450 : 0.001216 s, 0.001204 s, -0.000012 s, ? 0.9901 mozilla-try x_revs_x_added_x_copies 092fcca11bdb 936255a0384a : 0.000595 s, 0.000586 s, -0.000009 s, ? 0.9849 mozilla-try x_revs_x00_added_x_copies b53d2fadbdb5 017afae788ec : 0.001856 s, 0.001845 s, -0.000011 s, ? 0.9941 mozilla-try x_revs_x000_added_x000_copies 20408ad61ce5 6f0ee96e21ad : 0.064936 s, 0.063822 s, -0.001114 s, ? 0.9828 mozilla-try x_revs_x0000_added_x0000_copies effb563bb7e5 c07a39dc4e80 : 0.090601 s, 0.088038 s, -0.002563 s, ? 0.9717 mozilla-try x000_revs_xx00_added_0_copies 6100d773079a 04a55431795e : 0.007510 s, 0.007389 s, -0.000121 s, ? 0.9839 mozilla-try x000_revs_x000_added_x_copies 9f17a6fc04f9 2d37b966abed : 0.004911 s, 0.004868 s, -0.000043 s, ? 0.9912 mozilla-try x000_revs_x000_added_x000_copies 1346fd0130e4 4c65cbdabc1f : 0.233231 s, 0.222450 s, -0.010781 s, ? 0.9538 mozilla-try x0000_revs_x_added_0_copies 63519bfd42ee a36a2a865d92 : 0.419989 s, 0.370675 s, -0.049314 s, ? 0.8826 mozilla-try x0000_revs_x_added_x_copies 9fe69ff0762d bcabf2a78927 : 0.401521 s, 0.358020 s, -0.043501 s, ? 0.8917 mozilla-try x0000_revs_xx000_added_x_copies 156f6e2674f2 4d0f2c178e66 : 0.179555 s, 0.145235 s, -0.034320 s, ? 0.8089 mozilla-try x0000_revs_xx000_added_0_copies 9eec5917337d 67118cc6dcad : 0.038004 s, 0.037606 s, -0.000398 s, ? 0.9895 mozilla-try x0000_revs_xx000_added_x000_copies 89294cd501d9 7ccb2fc7ccb5 : 52.838482 s, 7.382439 s, -45.456043 s, ? 0.1397 mozilla-try x0000_revs_x0000_added_x0000_copies e928c65095ed e951f4ad123a : 8.705874 s, 7.273506 s, -1.432368 s, ? 0.8355 mozilla-try x00000_revs_x00000_added_0_copies dc8a3ca7010e d16fde900c9c : 1.126708 s, 1.074593 s, -0.052115 s, ? 0.9537 mozilla-try x00000_revs_x0000_added_x0000_copies 8d3fafa80d4b eb884023b810 : 83.854020 s, 27.746195 s, -56.107825 s, ? 0.3309 Below is a table comparing the runtime of the current "filelog centric" algorithm, with the "changeset centric" one, we just modified. The changeset centric algorithm is a significant win in many scenario, but they are still various cases where it is quite slower. When many revision has to be considered the cost of retrieving the copy information, creating new dictionaries, merging dictionaries and checking if revision are ancestors of each other can slow things down. The rest of this series, will introduce a rust version of the copy tracing code to deal with most of theses issues. Repo Case Source-Rev Dest-Rev filelog sidedata Difference Factor --------------------------------------------------------------------------------------------------------------------------------------- mercurial x_revs_x_added_0_copies ad6b123de1c7 39cfcef4f463 : 0.000914 s, 0.000044 s, - 0.000870 s, ? 0.048140 mercurial x_revs_x_added_x_copies 2b1c78674230 0c1d10351869 : 0.001812 s, 0.000138 s, - 0.001674 s, ? 0.076159 mercurial x000_revs_x000_added_x_copies 81f8ff2a9bf2 dd3267698d84 : 0.017954 s, 0.005052 s, - 0.012902 s, ? 0.281386 pypy x_revs_x_added_0_copies aed021ee8ae8 099ed31b181b : 0.001509 s, 0.000219 s, - 0.001290 s, ? 0.145129 pypy x_revs_x000_added_0_copies 4aa4e1f8e19a 359343b9ac0e : 0.206881 s, 0.000055 s, - 0.206826 s, ? 0.000266 pypy x_revs_x_added_x_copies ac52eb7bbbb0 72e022663155 : 0.016951 s, 0.000128 s, - 0.016823 s, ? 0.007551 pypy x_revs_x00_added_x_copies c3b14617fbd7 ace7255d9a26 : 0.019096 s, 0.001089 s, - 0.018007 s, ? 0.057028 pypy x_revs_x000_added_x000_copies df6f7a526b60 a83dc6a2d56f : 0.762506 s, 0.017407 s, - 0.745099 s, ? 0.022829 pypy x000_revs_xx00_added_0_copies 89a76aede314 2f22446ff07e : 1.179211 s, 0.094175 s, - 1.085036 s, ? 0.079863 pypy x000_revs_x000_added_x_copies 8a3b5bfd266e 2c68e87c3efe : 1.249058 s, 0.238009 s, - 1.011049 s, ? 0.190551 pypy x000_revs_x000_added_x000_copies 89a76aede314 7b3dda341c84 : 1.614107 s, 0.125876 s, - 1.488231 s, ? 0.077985 pypy x0000_revs_x_added_0_copies d1defd0dc478 c9cb1334cc78 : 0.001064 s, 3.581556 s, + 3.580492 s, ? 3366.124060 pypy x0000_revs_xx000_added_0_copies bf2c629d0071 4ffed77c095c : 1.061275 s, 0.016721 s, - 1.044554 s, ? 0.015756 pypy x0000_revs_xx000_added_x000_copies 08ea3258278e d9fa043f30c0 : 1.341119 s, 0.242367 s, - 1.098752 s, ? 0.180720 netbeans x_revs_x_added_0_copies fb0955ffcbcd a01e9239f9e7 : 0.027803 s, 0.000165 s, - 0.027638 s, ? 0.005935 netbeans x_revs_x000_added_0_copies 6f360122949f 20eb231cc7d0 : 0.130014 s, 0.000114 s, - 0.129900 s, ? 0.000877 netbeans x_revs_x_added_x_copies 1ada3faf6fb6 5a39d12eecf4 : 0.024990 s, 0.000296 s, - 0.024694 s, ? 0.011845 netbeans x_revs_x00_added_x_copies 35be93ba1e2c 9eec5e90c05f : 0.052201 s, 0.001124 s, - 0.051077 s, ? 0.021532 netbeans x000_revs_xx00_added_0_copies eac3045b4fdd 51d4ae7f1290 : 0.037642 s, 0.013060 s, - 0.024582 s, ? 0.346953 netbeans x000_revs_x000_added_x_copies e2063d266acd 6081d72689dc : 0.197086 s, 0.017112 s, - 0.179974 s, ? 0.086825 netbeans x000_revs_x000_added_x000_copies ff453e9fee32 411350406ec2 : 0.935148 s, 0.660350 s, - 0.274798 s, ? 0.706145 netbeans x0000_revs_xx000_added_x000_copies 588c2d1ced70 1aad62e59ddd : 3.920674 s, 10.032499 s, + 6.111825 s, ? 2.558871 mozilla-central x_revs_x_added_0_copies 3697f962bb7b 7015fcdd43a2 : 0.024232 s, 0.000189 s, - 0.024043 s, ? 0.007800 mozilla-central x_revs_x000_added_0_copies dd390860c6c9 40d0c5bed75d : 0.141483 s, 0.000462 s, - 0.141021 s, ? 0.003265 mozilla-central x_revs_x_added_x_copies 8d198483ae3b 14207ffc2b2f : 0.025775 s, 0.000270 s, - 0.025505 s, ? 0.010475 mozilla-central x_revs_x00_added_x_copies 98cbc58cc6bc 446a150332c3 : 0.084922 s, 0.001474 s, - 0.083448 s, ? 0.017357 mozilla-central x_revs_x000_added_x000_copies 3c684b4b8f68 0a5e72d1b479 : 0.194784 s, 0.004806 s, - 0.189978 s, ? 0.024673 mozilla-central x_revs_x0000_added_x0000_copies effb563bb7e5 c07a39dc4e80 : 2.161103 s, 0.085150 s, - 2.075953 s, ? 0.039401 mozilla-central x000_revs_xx00_added_0_copies 6100d773079a 04a55431795e : 0.089347 s, 0.007064 s, - 0.082283 s, ? 0.079063 mozilla-central x000_revs_x000_added_x_copies 9f17a6fc04f9 2d37b966abed : 0.732171 s, 0.004741 s, - 0.727430 s, ? 0.006475 mozilla-central x000_revs_x000_added_x000_copies 7c97034feb78 4407bd0c6330 : 1.157287 s, 0.190133 s, - 0.967154 s, ? 0.164292 mozilla-central x0000_revs_xx000_added_0_copies 9eec5917337d 67118cc6dcad : 6.726568 s, 0.035651 s, - 6.690917 s, ? 0.005300 mozilla-central x0000_revs_xx000_added_x000_copies f78c615a656c 96a38b690156 : 3.266229 s, 0.440694 s, - 2.825535 s, ? 0.134924 mozilla-central x00000_revs_x0000_added_x0000_copies 6832ae71433c 4c222a1d9a00 : 15.860534 s, 18.454163 s, + 2.593629 s, ? 1.163527 mozilla-central x00000_revs_x00000_added_x000_copies 76caed42cf7c 1daa622bbe42 : 20.450475 s, 31.562719 s, +11.112244 s, ? 1.543373 mozilla-try x_revs_x_added_0_copies aaf6dde0deb8 9790f499805a : 0.080442 s, 0.001189 s, - 0.079253 s, ? 0.014781 mozilla-try x_revs_x000_added_0_copies d8d0222927b4 5bb8ce8c7450 : 0.497672 s, 0.001204 s, - 0.496468 s, ? 0.002419 mozilla-try x_revs_x_added_x_copies 092fcca11bdb 936255a0384a : 0.021183 s, 0.000586 s, - 0.020597 s, ? 0.027664 mozilla-try x_revs_x00_added_x_copies b53d2fadbdb5 017afae788ec : 0.230991 s, 0.001845 s, - 0.229146 s, ? 0.007987 mozilla-try x_revs_x000_added_x000_copies 20408ad61ce5 6f0ee96e21ad : 1.118461 s, 0.063822 s, - 1.054639 s, ? 0.057062 mozilla-try x_revs_x0000_added_x0000_copies effb563bb7e5 c07a39dc4e80 : 2.206083 s, 0.088038 s, - 2.118045 s, ? 0.039907 mozilla-try x000_revs_xx00_added_0_copies 6100d773079a 04a55431795e : 0.089404 s, 0.007389 s, - 0.082015 s, ? 0.082647 mozilla-try x000_revs_x000_added_x_copies 9f17a6fc04f9 2d37b966abed : 0.733043 s, 0.004868 s, - 0.728175 s, ? 0.006641 mozilla-try x000_revs_x000_added_x000_copies 1346fd0130e4 4c65cbdabc1f : 1.163367 s, 0.222450 s, - 0.940917 s, ? 0.191212 mozilla-try x0000_revs_x_added_0_copies 63519bfd42ee a36a2a865d92 : 0.085456 s, 0.370675 s, + 0.285219 s, ? 4.337612 mozilla-try x0000_revs_x_added_x_copies 9fe69ff0762d bcabf2a78927 : 0.083601 s, 0.358020 s, + 0.274419 s, ? 4.282485 mozilla-try x0000_revs_xx000_added_x_copies 156f6e2674f2 4d0f2c178e66 : 7.366614 s, 0.145235 s, - 7.221379 s, ? 0.019715 mozilla-try x0000_revs_xx000_added_0_copies 9eec5917337d 67118cc6dcad : 6.664464 s, 0.037606 s, - 6.626858 s, ? 0.005643 mozilla-try x0000_revs_xx000_added_x000_copies 89294cd501d9 7ccb2fc7ccb5 : 7.467836 s, 7.382439 s, - 0.085397 s, ? 0.988565 mozilla-try x0000_revs_x0000_added_x0000_copies e928c65095ed e951f4ad123a : 9.801294 s, 7.273506 s, - 2.527788 s, ? 0.742097 mozilla-try x00000_revs_x_added_0_copies 6a320851d377 1ebb79acd503 : 0.091886 s, killed mozilla-try x00000_revs_x00000_added_0_copies dc8a3ca7010e d16fde900c9c : 26.491140 s, 1.074593 s, -25.416547 s, ? 0.040564 mozilla-try x00000_revs_x_added_x_copies 5173c4b6f97c 95d83ee7242d : 0.092863 s, killed mozilla-try x00000_revs_x000_added_x_copies 9126823d0e9c ca82787bb23c : 0.226823 s, killed mozilla-try x00000_revs_x0000_added_x0000_copies 8d3fafa80d4b eb884023b810 : 18.914630 s, 27.746195 s, + 8.831565 s, ? 1.466917 mozilla-try x00000_revs_x00000_added_x0000_copies 1b661134e2ca 1ae03d022d6d : 21.198903 s, killed mozilla-try x00000_revs_x00000_added_x000_copies 9b2a99adc05e 8e29777b48e6 : 24.952268 s, killed Differential Revision: https://phab.mercurial-scm.org/D9296
author Pierre-Yves David <pierre-yves.david@octobus.net>
date Mon, 02 Nov 2020 11:03:56 +0100
parents b7808443ed6a
children 89a2afe31e82
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()