view mercurial/wireprotoserver.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 b7b8a1538161
children 71443f742886
line wrap: on
line source

# Copyright 21 May 2005 - (c) 2005 Jake Edge <jake@edge2.net>
# Copyright 2005-2007 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 contextlib
import struct
import threading

from .i18n import _
from . import (
    encoding,
    error,
    pycompat,
    util,
    wireprototypes,
    wireprotov1server,
    wireprotov2server,
)
from .interfaces import util as interfaceutil
from .utils import (
    cborutil,
    compression,
)

stringio = util.stringio

urlerr = util.urlerr
urlreq = util.urlreq

HTTP_OK = 200

HGTYPE = b'application/mercurial-0.1'
HGTYPE2 = b'application/mercurial-0.2'
HGERRTYPE = b'application/hg-error'

SSHV1 = wireprototypes.SSHV1
SSHV2 = wireprototypes.SSHV2


def decodevaluefromheaders(req, headerprefix):
    """Decode a long value from multiple HTTP request headers.

    Returns the value as a bytes, not a str.
    """
    chunks = []
    i = 1
    while True:
        v = req.headers.get(b'%s-%d' % (headerprefix, i))
        if v is None:
            break
        chunks.append(pycompat.bytesurl(v))
        i += 1

    return b''.join(chunks)


@interfaceutil.implementer(wireprototypes.baseprotocolhandler)
class httpv1protocolhandler(object):
    def __init__(self, req, ui, checkperm):
        self._req = req
        self._ui = ui
        self._checkperm = checkperm
        self._protocaps = None

    @property
    def name(self):
        return b'http-v1'

    def getargs(self, args):
        knownargs = self._args()
        data = {}
        keys = args.split()
        for k in keys:
            if k == b'*':
                star = {}
                for key in knownargs.keys():
                    if key != b'cmd' and key not in keys:
                        star[key] = knownargs[key][0]
                data[b'*'] = star
            else:
                data[k] = knownargs[k][0]
        return [data[k] for k in keys]

    def _args(self):
        args = self._req.qsparams.asdictoflists()
        postlen = int(self._req.headers.get(b'X-HgArgs-Post', 0))
        if postlen:
            args.update(
                urlreq.parseqs(
                    self._req.bodyfh.read(postlen), keep_blank_values=True
                )
            )
            return args

        argvalue = decodevaluefromheaders(self._req, b'X-HgArg')
        args.update(urlreq.parseqs(argvalue, keep_blank_values=True))
        return args

    def getprotocaps(self):
        if self._protocaps is None:
            value = decodevaluefromheaders(self._req, b'X-HgProto')
            self._protocaps = set(value.split(b' '))
        return self._protocaps

    def getpayload(self):
        # Existing clients *always* send Content-Length.
        length = int(self._req.headers[b'Content-Length'])

        # If httppostargs is used, we need to read Content-Length
        # minus the amount that was consumed by args.
        length -= int(self._req.headers.get(b'X-HgArgs-Post', 0))
        return util.filechunkiter(self._req.bodyfh, limit=length)

    @contextlib.contextmanager
    def mayberedirectstdio(self):
        oldout = self._ui.fout
        olderr = self._ui.ferr

        out = util.stringio()

        try:
            self._ui.fout = out
            self._ui.ferr = out
            yield out
        finally:
            self._ui.fout = oldout
            self._ui.ferr = olderr

    def client(self):
        return b'remote:%s:%s:%s' % (
            self._req.urlscheme,
            urlreq.quote(self._req.remotehost or b''),
            urlreq.quote(self._req.remoteuser or b''),
        )

    def addcapabilities(self, repo, caps):
        caps.append(b'batch')

        caps.append(
            b'httpheader=%d' % repo.ui.configint(b'server', b'maxhttpheaderlen')
        )
        if repo.ui.configbool(b'experimental', b'httppostargs'):
            caps.append(b'httppostargs')

        # FUTURE advertise 0.2rx once support is implemented
        # FUTURE advertise minrx and mintx after consulting config option
        caps.append(b'httpmediatype=0.1rx,0.1tx,0.2tx')

        compengines = wireprototypes.supportedcompengines(
            repo.ui, compression.SERVERROLE
        )
        if compengines:
            comptypes = b','.join(
                urlreq.quote(e.wireprotosupport().name) for e in compengines
            )
            caps.append(b'compression=%s' % comptypes)

        return caps

    def checkperm(self, perm):
        return self._checkperm(perm)


# This method exists mostly so that extensions like remotefilelog can
# disable a kludgey legacy method only over http. As of early 2018,
# there are no other known users, so with any luck we can discard this
# hook if remotefilelog becomes a first-party extension.
def iscmd(cmd):
    return cmd in wireprotov1server.commands


def handlewsgirequest(rctx, req, res, checkperm):
    """Possibly process a wire protocol request.

    If the current request is a wire protocol request, the request is
    processed by this function.

    ``req`` is a ``parsedrequest`` instance.
    ``res`` is a ``wsgiresponse`` instance.

    Returns a bool indicating if the request was serviced. If set, the caller
    should stop processing the request, as a response has already been issued.
    """
    # Avoid cycle involving hg module.
    from .hgweb import common as hgwebcommon

    repo = rctx.repo

    # HTTP version 1 wire protocol requests are denoted by a "cmd" query
    # string parameter. If it isn't present, this isn't a wire protocol
    # request.
    if b'cmd' not in req.qsparams:
        return False

    cmd = req.qsparams[b'cmd']

    # The "cmd" request parameter is used by both the wire protocol and hgweb.
    # While not all wire protocol commands are available for all transports,
    # if we see a "cmd" value that resembles a known wire protocol command, we
    # route it to a protocol handler. This is better than routing possible
    # wire protocol requests to hgweb because it prevents hgweb from using
    # known wire protocol commands and it is less confusing for machine
    # clients.
    if not iscmd(cmd):
        return False

    # The "cmd" query string argument is only valid on the root path of the
    # repo. e.g. ``/?cmd=foo``, ``/repo?cmd=foo``. URL paths within the repo
    # like ``/blah?cmd=foo`` are not allowed. So don't recognize the request
    # in this case. We send an HTTP 404 for backwards compatibility reasons.
    if req.dispatchpath:
        res.status = hgwebcommon.statusmessage(404)
        res.headers[b'Content-Type'] = HGTYPE
        # TODO This is not a good response to issue for this request. This
        # is mostly for BC for now.
        res.setbodybytes(b'0\n%s\n' % b'Not Found')
        return True

    proto = httpv1protocolhandler(
        req, repo.ui, lambda perm: checkperm(rctx, req, perm)
    )

    # The permissions checker should be the only thing that can raise an
    # ErrorResponse. It is kind of a layer violation to catch an hgweb
    # exception here. So consider refactoring into a exception type that
    # is associated with the wire protocol.
    try:
        _callhttp(repo, req, res, proto, cmd)
    except hgwebcommon.ErrorResponse as e:
        for k, v in e.headers:
            res.headers[k] = v
        res.status = hgwebcommon.statusmessage(e.code, pycompat.bytestr(e))
        # TODO This response body assumes the failed command was
        # "unbundle." That assumption is not always valid.
        res.setbodybytes(b'0\n%s\n' % pycompat.bytestr(e))

    return True


def _availableapis(repo):
    apis = set()

    # Registered APIs are made available via config options of the name of
    # the protocol.
    for k, v in API_HANDLERS.items():
        section, option = v[b'config']
        if repo.ui.configbool(section, option):
            apis.add(k)

    return apis


def handlewsgiapirequest(rctx, req, res, checkperm):
    """Handle requests to /api/*."""
    assert req.dispatchparts[0] == b'api'

    repo = rctx.repo

    # This whole URL space is experimental for now. But we want to
    # reserve the URL space. So, 404 all URLs if the feature isn't enabled.
    if not repo.ui.configbool(b'experimental', b'web.apiserver'):
        res.status = b'404 Not Found'
        res.headers[b'Content-Type'] = b'text/plain'
        res.setbodybytes(_(b'Experimental API server endpoint not enabled'))
        return

    # The URL space is /api/<protocol>/*. The structure of URLs under varies
    # by <protocol>.

    availableapis = _availableapis(repo)

    # Requests to /api/ list available APIs.
    if req.dispatchparts == [b'api']:
        res.status = b'200 OK'
        res.headers[b'Content-Type'] = b'text/plain'
        lines = [
            _(
                b'APIs can be accessed at /api/<name>, where <name> can be '
                b'one of the following:\n'
            )
        ]
        if availableapis:
            lines.extend(sorted(availableapis))
        else:
            lines.append(_(b'(no available APIs)\n'))
        res.setbodybytes(b'\n'.join(lines))
        return

    proto = req.dispatchparts[1]

    if proto not in API_HANDLERS:
        res.status = b'404 Not Found'
        res.headers[b'Content-Type'] = b'text/plain'
        res.setbodybytes(
            _(b'Unknown API: %s\nKnown APIs: %s')
            % (proto, b', '.join(sorted(availableapis)))
        )
        return

    if proto not in availableapis:
        res.status = b'404 Not Found'
        res.headers[b'Content-Type'] = b'text/plain'
        res.setbodybytes(_(b'API %s not enabled\n') % proto)
        return

    API_HANDLERS[proto][b'handler'](
        rctx, req, res, checkperm, req.dispatchparts[2:]
    )


# Maps API name to metadata so custom API can be registered.
# Keys are:
#
# config
#    Config option that controls whether service is enabled.
# handler
#    Callable receiving (rctx, req, res, checkperm, urlparts) that is called
#    when a request to this API is received.
# apidescriptor
#    Callable receiving (req, repo) that is called to obtain an API
#    descriptor for this service. The response must be serializable to CBOR.
API_HANDLERS = {
    wireprotov2server.HTTP_WIREPROTO_V2: {
        b'config': (b'experimental', b'web.api.http-v2'),
        b'handler': wireprotov2server.handlehttpv2request,
        b'apidescriptor': wireprotov2server.httpv2apidescriptor,
    },
}


def _httpresponsetype(ui, proto, prefer_uncompressed):
    """Determine the appropriate response type and compression settings.

    Returns a tuple of (mediatype, compengine, engineopts).
    """
    # Determine the response media type and compression engine based
    # on the request parameters.

    if b'0.2' in proto.getprotocaps():
        # All clients are expected to support uncompressed data.
        if prefer_uncompressed:
            return HGTYPE2, compression._noopengine(), {}

        # Now find an agreed upon compression format.
        compformats = wireprotov1server.clientcompressionsupport(proto)
        for engine in wireprototypes.supportedcompengines(
            ui, compression.SERVERROLE
        ):
            if engine.wireprotosupport().name in compformats:
                opts = {}
                level = ui.configint(b'server', b'%slevel' % engine.name())
                if level is not None:
                    opts[b'level'] = level

                return HGTYPE2, engine, opts

        # No mutually supported compression format. Fall back to the
        # legacy protocol.

    # Don't allow untrusted settings because disabling compression or
    # setting a very high compression level could lead to flooding
    # the server's network or CPU.
    opts = {b'level': ui.configint(b'server', b'zliblevel')}
    return HGTYPE, util.compengines[b'zlib'], opts


def processcapabilitieshandshake(repo, req, res, proto):
    """Called during a ?cmd=capabilities request.

    If the client is advertising support for a newer protocol, we send
    a CBOR response with information about available services. If no
    advertised services are available, we don't handle the request.
    """
    # Fall back to old behavior unless the API server is enabled.
    if not repo.ui.configbool(b'experimental', b'web.apiserver'):
        return False

    clientapis = decodevaluefromheaders(req, b'X-HgUpgrade')
    protocaps = decodevaluefromheaders(req, b'X-HgProto')
    if not clientapis or not protocaps:
        return False

    # We currently only support CBOR responses.
    protocaps = set(protocaps.split(b' '))
    if b'cbor' not in protocaps:
        return False

    descriptors = {}

    for api in sorted(set(clientapis.split()) & _availableapis(repo)):
        handler = API_HANDLERS[api]

        descriptorfn = handler.get(b'apidescriptor')
        if not descriptorfn:
            continue

        descriptors[api] = descriptorfn(req, repo)

    v1caps = wireprotov1server.dispatch(repo, proto, b'capabilities')
    assert isinstance(v1caps, wireprototypes.bytesresponse)

    m = {
        # TODO allow this to be configurable.
        b'apibase': b'api/',
        b'apis': descriptors,
        b'v1capabilities': v1caps.data,
    }

    res.status = b'200 OK'
    res.headers[b'Content-Type'] = b'application/mercurial-cbor'
    res.setbodybytes(b''.join(cborutil.streamencode(m)))

    return True


def _callhttp(repo, req, res, proto, cmd):
    # Avoid cycle involving hg module.
    from .hgweb import common as hgwebcommon

    def genversion2(gen, engine, engineopts):
        # application/mercurial-0.2 always sends a payload header
        # identifying the compression engine.
        name = engine.wireprotosupport().name
        assert 0 < len(name) < 256
        yield struct.pack(b'B', len(name))
        yield name

        for chunk in gen:
            yield chunk

    def setresponse(code, contenttype, bodybytes=None, bodygen=None):
        if code == HTTP_OK:
            res.status = b'200 Script output follows'
        else:
            res.status = hgwebcommon.statusmessage(code)

        res.headers[b'Content-Type'] = contenttype

        if bodybytes is not None:
            res.setbodybytes(bodybytes)
        if bodygen is not None:
            res.setbodygen(bodygen)

    if not wireprotov1server.commands.commandavailable(cmd, proto):
        setresponse(
            HTTP_OK,
            HGERRTYPE,
            _(
                b'requested wire protocol command is not available over '
                b'HTTP'
            ),
        )
        return

    proto.checkperm(wireprotov1server.commands[cmd].permission)

    # Possibly handle a modern client wanting to switch protocols.
    if cmd == b'capabilities' and processcapabilitieshandshake(
        repo, req, res, proto
    ):

        return

    rsp = wireprotov1server.dispatch(repo, proto, cmd)

    if isinstance(rsp, bytes):
        setresponse(HTTP_OK, HGTYPE, bodybytes=rsp)
    elif isinstance(rsp, wireprototypes.bytesresponse):
        setresponse(HTTP_OK, HGTYPE, bodybytes=rsp.data)
    elif isinstance(rsp, wireprototypes.streamreslegacy):
        setresponse(HTTP_OK, HGTYPE, bodygen=rsp.gen)
    elif isinstance(rsp, wireprototypes.streamres):
        gen = rsp.gen

        # This code for compression should not be streamres specific. It
        # is here because we only compress streamres at the moment.
        mediatype, engine, engineopts = _httpresponsetype(
            repo.ui, proto, rsp.prefer_uncompressed
        )
        gen = engine.compressstream(gen, engineopts)

        if mediatype == HGTYPE2:
            gen = genversion2(gen, engine, engineopts)

        setresponse(HTTP_OK, mediatype, bodygen=gen)
    elif isinstance(rsp, wireprototypes.pushres):
        rsp = b'%d\n%s' % (rsp.res, rsp.output)
        setresponse(HTTP_OK, HGTYPE, bodybytes=rsp)
    elif isinstance(rsp, wireprototypes.pusherr):
        rsp = b'0\n%s\n' % rsp.res
        res.drain = True
        setresponse(HTTP_OK, HGTYPE, bodybytes=rsp)
    elif isinstance(rsp, wireprototypes.ooberror):
        setresponse(HTTP_OK, HGERRTYPE, bodybytes=rsp.message)
    else:
        raise error.ProgrammingError(b'hgweb.protocol internal failure', rsp)


def _sshv1respondbytes(fout, value):
    """Send a bytes response for protocol version 1."""
    fout.write(b'%d\n' % len(value))
    fout.write(value)
    fout.flush()


def _sshv1respondstream(fout, source):
    write = fout.write
    for chunk in source.gen:
        write(chunk)
    fout.flush()


def _sshv1respondooberror(fout, ferr, rsp):
    ferr.write(b'%s\n-\n' % rsp)
    ferr.flush()
    fout.write(b'\n')
    fout.flush()


@interfaceutil.implementer(wireprototypes.baseprotocolhandler)
class sshv1protocolhandler(object):
    """Handler for requests services via version 1 of SSH protocol."""

    def __init__(self, ui, fin, fout):
        self._ui = ui
        self._fin = fin
        self._fout = fout
        self._protocaps = set()

    @property
    def name(self):
        return wireprototypes.SSHV1

    def getargs(self, args):
        data = {}
        keys = args.split()
        for n in pycompat.xrange(len(keys)):
            argline = self._fin.readline()[:-1]
            arg, l = argline.split()
            if arg not in keys:
                raise error.Abort(_(b"unexpected parameter %r") % arg)
            if arg == b'*':
                star = {}
                for k in pycompat.xrange(int(l)):
                    argline = self._fin.readline()[:-1]
                    arg, l = argline.split()
                    val = self._fin.read(int(l))
                    star[arg] = val
                data[b'*'] = star
            else:
                val = self._fin.read(int(l))
                data[arg] = val
        return [data[k] for k in keys]

    def getprotocaps(self):
        return self._protocaps

    def getpayload(self):
        # We initially send an empty response. This tells the client it is
        # OK to start sending data. If a client sees any other response, it
        # interprets it as an error.
        _sshv1respondbytes(self._fout, b'')

        # The file is in the form:
        #
        # <chunk size>\n<chunk>
        # ...
        # 0\n
        count = int(self._fin.readline())
        while count:
            yield self._fin.read(count)
            count = int(self._fin.readline())

    @contextlib.contextmanager
    def mayberedirectstdio(self):
        yield None

    def client(self):
        client = encoding.environ.get(b'SSH_CLIENT', b'').split(b' ', 1)[0]
        return b'remote:ssh:' + client

    def addcapabilities(self, repo, caps):
        if self.name == wireprototypes.SSHV1:
            caps.append(b'protocaps')
        caps.append(b'batch')
        return caps

    def checkperm(self, perm):
        pass


class sshv2protocolhandler(sshv1protocolhandler):
    """Protocol handler for version 2 of the SSH protocol."""

    @property
    def name(self):
        return wireprototypes.SSHV2

    def addcapabilities(self, repo, caps):
        return caps


def _runsshserver(ui, repo, fin, fout, ev):
    # This function operates like a state machine of sorts. The following
    # states are defined:
    #
    # protov1-serving
    #    Server is in protocol version 1 serving mode. Commands arrive on
    #    new lines. These commands are processed in this state, one command
    #    after the other.
    #
    # protov2-serving
    #    Server is in protocol version 2 serving mode.
    #
    # upgrade-initial
    #    The server is going to process an upgrade request.
    #
    # upgrade-v2-filter-legacy-handshake
    #    The protocol is being upgraded to version 2. The server is expecting
    #    the legacy handshake from version 1.
    #
    # upgrade-v2-finish
    #    The upgrade to version 2 of the protocol is imminent.
    #
    # shutdown
    #    The server is shutting down, possibly in reaction to a client event.
    #
    # And here are their transitions:
    #
    # protov1-serving -> shutdown
    #    When server receives an empty request or encounters another
    #    error.
    #
    # protov1-serving -> upgrade-initial
    #    An upgrade request line was seen.
    #
    # upgrade-initial -> upgrade-v2-filter-legacy-handshake
    #    Upgrade to version 2 in progress. Server is expecting to
    #    process a legacy handshake.
    #
    # upgrade-v2-filter-legacy-handshake -> shutdown
    #    Client did not fulfill upgrade handshake requirements.
    #
    # upgrade-v2-filter-legacy-handshake -> upgrade-v2-finish
    #    Client fulfilled version 2 upgrade requirements. Finishing that
    #    upgrade.
    #
    # upgrade-v2-finish -> protov2-serving
    #    Protocol upgrade to version 2 complete. Server can now speak protocol
    #    version 2.
    #
    # protov2-serving -> protov1-serving
    #    Ths happens by default since protocol version 2 is the same as
    #    version 1 except for the handshake.

    state = b'protov1-serving'
    proto = sshv1protocolhandler(ui, fin, fout)
    protoswitched = False

    while not ev.is_set():
        if state == b'protov1-serving':
            # Commands are issued on new lines.
            request = fin.readline()[:-1]

            # Empty lines signal to terminate the connection.
            if not request:
                state = b'shutdown'
                continue

            # It looks like a protocol upgrade request. Transition state to
            # handle it.
            if request.startswith(b'upgrade '):
                if protoswitched:
                    _sshv1respondooberror(
                        fout,
                        ui.ferr,
                        b'cannot upgrade protocols multiple times',
                    )
                    state = b'shutdown'
                    continue

                state = b'upgrade-initial'
                continue

            available = wireprotov1server.commands.commandavailable(
                request, proto
            )

            # This command isn't available. Send an empty response and go
            # back to waiting for a new command.
            if not available:
                _sshv1respondbytes(fout, b'')
                continue

            rsp = wireprotov1server.dispatch(repo, proto, request)
            repo.ui.fout.flush()
            repo.ui.ferr.flush()

            if isinstance(rsp, bytes):
                _sshv1respondbytes(fout, rsp)
            elif isinstance(rsp, wireprototypes.bytesresponse):
                _sshv1respondbytes(fout, rsp.data)
            elif isinstance(rsp, wireprototypes.streamres):
                _sshv1respondstream(fout, rsp)
            elif isinstance(rsp, wireprototypes.streamreslegacy):
                _sshv1respondstream(fout, rsp)
            elif isinstance(rsp, wireprototypes.pushres):
                _sshv1respondbytes(fout, b'')
                _sshv1respondbytes(fout, b'%d' % rsp.res)
            elif isinstance(rsp, wireprototypes.pusherr):
                _sshv1respondbytes(fout, rsp.res)
            elif isinstance(rsp, wireprototypes.ooberror):
                _sshv1respondooberror(fout, ui.ferr, rsp.message)
            else:
                raise error.ProgrammingError(
                    b'unhandled response type from '
                    b'wire protocol command: %s' % rsp
                )

        # For now, protocol version 2 serving just goes back to version 1.
        elif state == b'protov2-serving':
            state = b'protov1-serving'
            continue

        elif state == b'upgrade-initial':
            # We should never transition into this state if we've switched
            # protocols.
            assert not protoswitched
            assert proto.name == wireprototypes.SSHV1

            # Expected: upgrade <token> <capabilities>
            # If we get something else, the request is malformed. It could be
            # from a future client that has altered the upgrade line content.
            # We treat this as an unknown command.
            try:
                token, caps = request.split(b' ')[1:]
            except ValueError:
                _sshv1respondbytes(fout, b'')
                state = b'protov1-serving'
                continue

            # Send empty response if we don't support upgrading protocols.
            if not ui.configbool(b'experimental', b'sshserver.support-v2'):
                _sshv1respondbytes(fout, b'')
                state = b'protov1-serving'
                continue

            try:
                caps = urlreq.parseqs(caps)
            except ValueError:
                _sshv1respondbytes(fout, b'')
                state = b'protov1-serving'
                continue

            # We don't see an upgrade request to protocol version 2. Ignore
            # the upgrade request.
            wantedprotos = caps.get(b'proto', [b''])[0]
            if SSHV2 not in wantedprotos:
                _sshv1respondbytes(fout, b'')
                state = b'protov1-serving'
                continue

            # It looks like we can honor this upgrade request to protocol 2.
            # Filter the rest of the handshake protocol request lines.
            state = b'upgrade-v2-filter-legacy-handshake'
            continue

        elif state == b'upgrade-v2-filter-legacy-handshake':
            # Client should have sent legacy handshake after an ``upgrade``
            # request. Expected lines:
            #
            #    hello
            #    between
            #    pairs 81
            #    0000...-0000...

            ok = True
            for line in (b'hello', b'between', b'pairs 81'):
                request = fin.readline()[:-1]

                if request != line:
                    _sshv1respondooberror(
                        fout,
                        ui.ferr,
                        b'malformed handshake protocol: missing %s' % line,
                    )
                    ok = False
                    state = b'shutdown'
                    break

            if not ok:
                continue

            request = fin.read(81)
            if request != b'%s-%s' % (b'0' * 40, b'0' * 40):
                _sshv1respondooberror(
                    fout,
                    ui.ferr,
                    b'malformed handshake protocol: '
                    b'missing between argument value',
                )
                state = b'shutdown'
                continue

            state = b'upgrade-v2-finish'
            continue

        elif state == b'upgrade-v2-finish':
            # Send the upgrade response.
            fout.write(b'upgraded %s %s\n' % (token, SSHV2))
            servercaps = wireprotov1server.capabilities(repo, proto)
            rsp = b'capabilities: %s' % servercaps.data
            fout.write(b'%d\n%s\n' % (len(rsp), rsp))
            fout.flush()

            proto = sshv2protocolhandler(ui, fin, fout)
            protoswitched = True

            state = b'protov2-serving'
            continue

        elif state == b'shutdown':
            break

        else:
            raise error.ProgrammingError(
                b'unhandled ssh server state: %s' % state
            )


class sshserver(object):
    def __init__(self, ui, repo, logfh=None):
        self._ui = ui
        self._repo = repo
        self._fin, self._fout = ui.protectfinout()

        # Log write I/O to stdout and stderr if configured.
        if logfh:
            self._fout = util.makeloggingfileobject(
                logfh, self._fout, b'o', logdata=True
            )
            ui.ferr = util.makeloggingfileobject(
                logfh, ui.ferr, b'e', logdata=True
            )

    def serve_forever(self):
        self.serveuntil(threading.Event())
        self._ui.restorefinout(self._fin, self._fout)

    def serveuntil(self, ev):
        """Serve until a threading.Event is set."""
        _runsshserver(self._ui, self._repo, self._fin, self._fout, ev)