view mercurial/hgweb/hgwebdir_mod.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 dc9fe90bdbd5
children d4ba4d51f85f
line wrap: on
line source

# hgweb/hgwebdir_mod.py - Web interface for a directory of repositories.
#
# Copyright 21 May 2005 - (c) 2005 Jake Edge <jake@edge2.net>
# Copyright 2005, 2006 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 gc
import os
import time

from ..i18n import _

from .common import (
    ErrorResponse,
    HTTP_SERVER_ERROR,
    cspvalues,
    get_contact,
    get_mtime,
    ismember,
    paritygen,
    staticfile,
    statusmessage,
)

from .. import (
    configitems,
    encoding,
    error,
    extensions,
    hg,
    pathutil,
    profiling,
    pycompat,
    rcutil,
    registrar,
    scmutil,
    templater,
    templateutil,
    ui as uimod,
    util,
)

from . import (
    hgweb_mod,
    request as requestmod,
    webutil,
    wsgicgi,
)
from ..utils import dateutil


def cleannames(items):
    return [(util.pconvert(name).strip(b'/'), path) for name, path in items]


def findrepos(paths):
    repos = []
    for prefix, root in cleannames(paths):
        roothead, roottail = os.path.split(root)
        # "foo = /bar/*" or "foo = /bar/**" lets every repo /bar/N in or below
        # /bar/ be served as as foo/N .
        # '*' will not search inside dirs with .hg (except .hg/patches),
        # '**' will search inside dirs with .hg (and thus also find subrepos).
        try:
            recurse = {b'*': False, b'**': True}[roottail]
        except KeyError:
            repos.append((prefix, root))
            continue
        roothead = os.path.normpath(os.path.abspath(roothead))
        paths = scmutil.walkrepos(roothead, followsym=True, recurse=recurse)
        repos.extend(urlrepos(prefix, roothead, paths))
    return repos


def urlrepos(prefix, roothead, paths):
    """yield url paths and filesystem paths from a list of repo paths

    >>> conv = lambda seq: [(v, util.pconvert(p)) for v,p in seq]
    >>> conv(urlrepos(b'hg', b'/opt', [b'/opt/r', b'/opt/r/r', b'/opt']))
    [('hg/r', '/opt/r'), ('hg/r/r', '/opt/r/r'), ('hg', '/opt')]
    >>> conv(urlrepos(b'', b'/opt', [b'/opt/r', b'/opt/r/r', b'/opt']))
    [('r', '/opt/r'), ('r/r', '/opt/r/r'), ('', '/opt')]
    """
    for path in paths:
        path = os.path.normpath(path)
        yield (
            prefix + b'/' + util.pconvert(path[len(roothead) :]).lstrip(b'/')
        ).strip(b'/'), path


def readallowed(ui, req):
    """Check allow_read and deny_read config options of a repo's ui object
    to determine user permissions.  By default, with neither option set (or
    both empty), allow all users to read the repo.  There are two ways a
    user can be denied read access:  (1) deny_read is not empty, and the
    user is unauthenticated or deny_read contains user (or *), and (2)
    allow_read is not empty and the user is not in allow_read.  Return True
    if user is allowed to read the repo, else return False."""

    user = req.remoteuser

    deny_read = ui.configlist(b'web', b'deny_read', untrusted=True)
    if deny_read and (not user or ismember(ui, user, deny_read)):
        return False

    allow_read = ui.configlist(b'web', b'allow_read', untrusted=True)
    # by default, allow reading if no allow_read option has been set
    if not allow_read or ismember(ui, user, allow_read):
        return True

    return False


def rawindexentries(ui, repos, req, subdir=b''):
    descend = ui.configbool(b'web', b'descend')
    collapse = ui.configbool(b'web', b'collapse')
    seenrepos = set()
    seendirs = set()
    for name, path in repos:

        if not name.startswith(subdir):
            continue
        name = name[len(subdir) :]
        directory = False

        if b'/' in name:
            if not descend:
                continue

            nameparts = name.split(b'/')
            rootname = nameparts[0]

            if not collapse:
                pass
            elif rootname in seendirs:
                continue
            elif rootname in seenrepos:
                pass
            else:
                directory = True
                name = rootname

                # redefine the path to refer to the directory
                discarded = b'/'.join(nameparts[1:])

                # remove name parts plus accompanying slash
                path = path[: -len(discarded) - 1]

                try:
                    hg.repository(ui, path)
                    directory = False
                except (IOError, error.RepoError):
                    pass

        parts = [
            req.apppath.strip(b'/'),
            subdir.strip(b'/'),
            name.strip(b'/'),
        ]
        url = b'/' + b'/'.join(p for p in parts if p) + b'/'

        # show either a directory entry or a repository
        if directory:
            # get the directory's time information
            try:
                d = (get_mtime(path), dateutil.makedate()[1])
            except OSError:
                continue

            # add '/' to the name to make it obvious that
            # the entry is a directory, not a regular repository
            row = {
                b'contact': b"",
                b'contact_sort': b"",
                b'name': name + b'/',
                b'name_sort': name,
                b'url': url,
                b'description': b"",
                b'description_sort': b"",
                b'lastchange': d,
                b'lastchange_sort': d[1] - d[0],
                b'archives': templateutil.mappinglist([]),
                b'isdirectory': True,
                b'labels': templateutil.hybridlist([], name=b'label'),
            }

            seendirs.add(name)
            yield row
            continue

        u = ui.copy()
        if rcutil.use_repo_hgrc():
            try:
                u.readconfig(os.path.join(path, b'.hg', b'hgrc'))
            except Exception as e:
                u.warn(_(b'error reading %s/.hg/hgrc: %s\n') % (path, e))
                continue

        def get(section, name, default=uimod._unset):
            return u.config(section, name, default, untrusted=True)

        if u.configbool(b"web", b"hidden", untrusted=True):
            continue

        if not readallowed(u, req):
            continue

        # update time with local timezone
        try:
            r = hg.repository(ui, path)
        except IOError:
            u.warn(_(b'error accessing repository at %s\n') % path)
            continue
        except error.RepoError:
            u.warn(_(b'error accessing repository at %s\n') % path)
            continue
        try:
            d = (get_mtime(r.spath), dateutil.makedate()[1])
        except OSError:
            continue

        contact = get_contact(get)
        description = get(b"web", b"description")
        seenrepos.add(name)
        name = get(b"web", b"name", name)
        labels = u.configlist(b'web', b'labels', untrusted=True)
        row = {
            b'contact': contact or b"unknown",
            b'contact_sort': contact.upper() or b"unknown",
            b'name': name,
            b'name_sort': name,
            b'url': url,
            b'description': description or b"unknown",
            b'description_sort': description.upper() or b"unknown",
            b'lastchange': d,
            b'lastchange_sort': d[1] - d[0],
            b'archives': webutil.archivelist(u, b"tip", url),
            b'isdirectory': None,
            b'labels': templateutil.hybridlist(labels, name=b'label'),
        }

        yield row


def _indexentriesgen(
    context, ui, repos, req, stripecount, sortcolumn, descending, subdir
):
    rows = rawindexentries(ui, repos, req, subdir=subdir)

    sortdefault = None, False

    if sortcolumn and sortdefault != (sortcolumn, descending):
        sortkey = b'%s_sort' % sortcolumn
        rows = sorted(rows, key=lambda x: x[sortkey], reverse=descending)

    for row, parity in zip(rows, paritygen(stripecount)):
        row[b'parity'] = parity
        yield row


def indexentries(
    ui, repos, req, stripecount, sortcolumn=b'', descending=False, subdir=b''
):
    args = (ui, repos, req, stripecount, sortcolumn, descending, subdir)
    return templateutil.mappinggenerator(_indexentriesgen, args=args)


class hgwebdir(object):
    """HTTP server for multiple repositories.

    Given a configuration, different repositories will be served depending
    on the request path.

    Instances are typically used as WSGI applications.
    """

    def __init__(self, conf, baseui=None):
        self.conf = conf
        self.baseui = baseui
        self.ui = None
        self.lastrefresh = 0
        self.motd = None
        self.refresh()
        if not baseui:
            # set up environment for new ui
            extensions.loadall(self.ui)
            extensions.populateui(self.ui)

    def refresh(self):
        if self.ui:
            refreshinterval = self.ui.configint(b'web', b'refreshinterval')
        else:
            item = configitems.coreitems[b'web'][b'refreshinterval']
            refreshinterval = item.default

        # refreshinterval <= 0 means to always refresh.
        if (
            refreshinterval > 0
            and self.lastrefresh + refreshinterval > time.time()
        ):
            return

        if self.baseui:
            u = self.baseui.copy()
        else:
            u = uimod.ui.load()
            u.setconfig(b'ui', b'report_untrusted', b'off', b'hgwebdir')
            u.setconfig(b'ui', b'nontty', b'true', b'hgwebdir')
            # displaying bundling progress bar while serving feels wrong and may
            # break some wsgi implementations.
            u.setconfig(b'progress', b'disable', b'true', b'hgweb')

        if not isinstance(self.conf, (dict, list, tuple)):
            map = {b'paths': b'hgweb-paths'}
            if not os.path.exists(self.conf):
                raise error.Abort(_(b'config file %s not found!') % self.conf)
            u.readconfig(self.conf, remap=map, trust=True)
            paths = []
            for name, ignored in u.configitems(b'hgweb-paths'):
                for path in u.configlist(b'hgweb-paths', name):
                    paths.append((name, path))
        elif isinstance(self.conf, (list, tuple)):
            paths = self.conf
        elif isinstance(self.conf, dict):
            paths = self.conf.items()
        extensions.populateui(u)

        repos = findrepos(paths)
        for prefix, root in u.configitems(b'collections'):
            prefix = util.pconvert(prefix)
            for path in scmutil.walkrepos(root, followsym=True):
                repo = os.path.normpath(path)
                name = util.pconvert(repo)
                if name.startswith(prefix):
                    name = name[len(prefix) :]
                repos.append((name.lstrip(b'/'), repo))

        self.repos = repos
        self.ui = u
        encoding.encoding = self.ui.config(b'web', b'encoding')
        self.style = self.ui.config(b'web', b'style')
        self.templatepath = self.ui.config(
            b'web', b'templates', untrusted=False
        )
        self.stripecount = self.ui.config(b'web', b'stripes')
        if self.stripecount:
            self.stripecount = int(self.stripecount)
        prefix = self.ui.config(b'web', b'prefix')
        if prefix.startswith(b'/'):
            prefix = prefix[1:]
        if prefix.endswith(b'/'):
            prefix = prefix[:-1]
        self.prefix = prefix
        self.lastrefresh = time.time()

    def run(self):
        if not encoding.environ.get(b'GATEWAY_INTERFACE', b'').startswith(
            b"CGI/1."
        ):
            raise RuntimeError(
                b"This function is only intended to be "
                b"called while running as a CGI script."
            )
        wsgicgi.launch(self)

    def __call__(self, env, respond):
        baseurl = self.ui.config(b'web', b'baseurl')
        req = requestmod.parserequestfromenv(env, altbaseurl=baseurl)
        res = requestmod.wsgiresponse(req, respond)

        return self.run_wsgi(req, res)

    def run_wsgi(self, req, res):
        profile = self.ui.configbool(b'profiling', b'enabled')
        with profiling.profile(self.ui, enabled=profile):
            try:
                for r in self._runwsgi(req, res):
                    yield r
            finally:
                # There are known cycles in localrepository that prevent
                # those objects (and tons of held references) from being
                # collected through normal refcounting. We mitigate those
                # leaks by performing an explicit GC on every request.
                # TODO remove this once leaks are fixed.
                # TODO only run this on requests that create localrepository
                # instances instead of every request.
                gc.collect()

    def _runwsgi(self, req, res):
        try:
            self.refresh()

            csp, nonce = cspvalues(self.ui)
            if csp:
                res.headers[b'Content-Security-Policy'] = csp

            virtual = req.dispatchpath.strip(b'/')
            tmpl = self.templater(req, nonce)
            ctype = tmpl.render(b'mimetype', {b'encoding': encoding.encoding})

            # Global defaults. These can be overridden by any handler.
            res.status = b'200 Script output follows'
            res.headers[b'Content-Type'] = ctype

            # a static file
            if virtual.startswith(b'static/') or b'static' in req.qsparams:
                if virtual.startswith(b'static/'):
                    fname = virtual[7:]
                else:
                    fname = req.qsparams[b'static']
                static = self.ui.config(b"web", b"static", untrusted=False)
                staticfile(self.templatepath, static, fname, res)
                return res.sendresponse()

            # top-level index

            repos = dict(self.repos)

            if (not virtual or virtual == b'index') and virtual not in repos:
                return self.makeindex(req, res, tmpl)

            # nested indexes and hgwebs

            if virtual.endswith(b'/index') and virtual not in repos:
                subdir = virtual[: -len(b'index')]
                if any(r.startswith(subdir) for r in repos):
                    return self.makeindex(req, res, tmpl, subdir)

            def _virtualdirs():
                # Check the full virtual path, and each parent
                yield virtual
                for p in pathutil.finddirs(virtual):
                    yield p

            for virtualrepo in _virtualdirs():
                real = repos.get(virtualrepo)
                if real:
                    # Re-parse the WSGI environment to take into account our
                    # repository path component.
                    uenv = req.rawenv
                    if pycompat.ispy3:
                        uenv = {
                            k.decode('latin1'): v
                            for k, v in pycompat.iteritems(uenv)
                        }
                    req = requestmod.parserequestfromenv(
                        uenv,
                        reponame=virtualrepo,
                        altbaseurl=self.ui.config(b'web', b'baseurl'),
                        # Reuse wrapped body file object otherwise state
                        # tracking can get confused.
                        bodyfh=req.bodyfh,
                    )
                    try:
                        # ensure caller gets private copy of ui
                        repo = hg.repository(self.ui.copy(), real)
                        return hgweb_mod.hgweb(repo).run_wsgi(req, res)
                    except IOError as inst:
                        msg = encoding.strtolocal(inst.strerror)
                        raise ErrorResponse(HTTP_SERVER_ERROR, msg)
                    except error.RepoError as inst:
                        raise ErrorResponse(HTTP_SERVER_ERROR, bytes(inst))

            # browse subdirectories
            subdir = virtual + b'/'
            if [r for r in repos if r.startswith(subdir)]:
                return self.makeindex(req, res, tmpl, subdir)

            # prefixes not found
            res.status = b'404 Not Found'
            res.setbodygen(tmpl.generate(b'notfound', {b'repo': virtual}))
            return res.sendresponse()

        except ErrorResponse as e:
            res.status = statusmessage(e.code, pycompat.bytestr(e))
            res.setbodygen(
                tmpl.generate(b'error', {b'error': e.message or b''})
            )
            return res.sendresponse()
        finally:
            del tmpl

    def makeindex(self, req, res, tmpl, subdir=b""):
        self.refresh()
        sortable = [b"name", b"description", b"contact", b"lastchange"]
        sortcolumn, descending = None, False
        if b'sort' in req.qsparams:
            sortcolumn = req.qsparams[b'sort']
            descending = sortcolumn.startswith(b'-')
            if descending:
                sortcolumn = sortcolumn[1:]
            if sortcolumn not in sortable:
                sortcolumn = b""

        sort = [
            (
                b"sort_%s" % column,
                b"%s%s"
                % (
                    (not descending and column == sortcolumn) and b"-" or b"",
                    column,
                ),
            )
            for column in sortable
        ]

        self.refresh()

        entries = indexentries(
            self.ui,
            self.repos,
            req,
            self.stripecount,
            sortcolumn=sortcolumn,
            descending=descending,
            subdir=subdir,
        )

        mapping = {
            b'entries': entries,
            b'subdir': subdir,
            b'pathdef': hgweb_mod.makebreadcrumb(b'/' + subdir, self.prefix),
            b'sortcolumn': sortcolumn,
            b'descending': descending,
        }
        mapping.update(sort)
        res.setbodygen(tmpl.generate(b'index', mapping))
        return res.sendresponse()

    def templater(self, req, nonce):
        def config(*args, **kwargs):
            kwargs.setdefault('untrusted', True)
            return self.ui.config(*args, **kwargs)

        vars = {}
        styles, (style, mapfile, fp) = hgweb_mod.getstyle(
            req, config, self.templatepath
        )
        if style == styles[0]:
            vars[b'style'] = style

        sessionvars = webutil.sessionvars(vars, b'?')
        logourl = config(b'web', b'logourl')
        logoimg = config(b'web', b'logoimg')
        staticurl = (
            config(b'web', b'staticurl')
            or req.apppath.rstrip(b'/') + b'/static/'
        )
        if not staticurl.endswith(b'/'):
            staticurl += b'/'

        defaults = {
            b"encoding": encoding.encoding,
            b"url": req.apppath + b'/',
            b"logourl": logourl,
            b"logoimg": logoimg,
            b"staticurl": staticurl,
            b"sessionvars": sessionvars,
            b"style": style,
            b"nonce": nonce,
        }
        templatekeyword = registrar.templatekeyword(defaults)

        @templatekeyword(b'motd', requires=())
        def motd(context, mapping):
            if self.motd is not None:
                yield self.motd
            else:
                yield config(b'web', b'motd')

        return templater.templater.frommapfile(
            mapfile, fp=fp, defaults=defaults
        )