view mercurial/templatefilters.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 7333e8bb9781
children 89a2afe31e82
line wrap: on
line source

# templatefilters.py - common template expansion filters
#
# Copyright 2005-2008 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 os
import re
import time

from .i18n import _
from . import (
    encoding,
    error,
    node,
    pycompat,
    registrar,
    smartset,
    templateutil,
    url,
    util,
)
from .utils import (
    cborutil,
    dateutil,
    stringutil,
)

urlerr = util.urlerr
urlreq = util.urlreq

# filters are callables like:
#   fn(obj)
# with:
#   obj - object to be filtered (text, date, list and so on)
filters = {}

templatefilter = registrar.templatefilter(filters)


@templatefilter(b'addbreaks', intype=bytes)
def addbreaks(text):
    """Any text. Add an XHTML "<br />" tag before the end of
    every line except the last.
    """
    return text.replace(b'\n', b'<br/>\n')


agescales = [
    (b"year", 3600 * 24 * 365, b'Y'),
    (b"month", 3600 * 24 * 30, b'M'),
    (b"week", 3600 * 24 * 7, b'W'),
    (b"day", 3600 * 24, b'd'),
    (b"hour", 3600, b'h'),
    (b"minute", 60, b'm'),
    (b"second", 1, b's'),
]


@templatefilter(b'age', intype=templateutil.date)
def age(date, abbrev=False):
    """Date. Returns a human-readable date/time difference between the
    given date/time and the current date/time.
    """

    def plural(t, c):
        if c == 1:
            return t
        return t + b"s"

    def fmt(t, c, a):
        if abbrev:
            return b"%d%s" % (c, a)
        return b"%d %s" % (c, plural(t, c))

    now = time.time()
    then = date[0]
    future = False
    if then > now:
        future = True
        delta = max(1, int(then - now))
        if delta > agescales[0][1] * 30:
            return b'in the distant future'
    else:
        delta = max(1, int(now - then))
        if delta > agescales[0][1] * 2:
            return dateutil.shortdate(date)

    for t, s, a in agescales:
        n = delta // s
        if n >= 2 or s == 1:
            if future:
                return b'%s from now' % fmt(t, n, a)
            return b'%s ago' % fmt(t, n, a)


@templatefilter(b'basename', intype=bytes)
def basename(path):
    """Any text. Treats the text as a path, and returns the last
    component of the path after splitting by the path separator.
    For example, "foo/bar/baz" becomes "baz" and "foo/bar//" becomes "".
    """
    return os.path.basename(path)


def _tocborencodable(obj):
    if isinstance(obj, smartset.abstractsmartset):
        return list(obj)
    return obj


@templatefilter(b'cbor')
def cbor(obj):
    """Any object. Serializes the object to CBOR bytes."""
    # cborutil is stricter about type than json() filter
    obj = pycompat.rapply(_tocborencodable, obj)
    return b''.join(cborutil.streamencode(obj))


@templatefilter(b'commondir')
def commondir(filelist):
    """List of text. Treats each list item as file name with /
    as path separator and returns the longest common directory
    prefix shared by all list items.
    Returns the empty string if no common prefix exists.

    The list items are not normalized, i.e. "foo/../bar" is handled as
    file "bar" in the directory "foo/..". Leading slashes are ignored.

    For example, ["foo/bar/baz", "foo/baz/bar"] becomes "foo" and
    ["foo/bar", "baz"] becomes "".
    """

    def common(a, b):
        if len(a) > len(b):
            a = b[: len(a)]
        elif len(b) > len(a):
            b = b[: len(a)]
        if a == b:
            return a
        for i in pycompat.xrange(len(a)):
            if a[i] != b[i]:
                return a[:i]
        return a

    try:
        if not filelist:
            return b""
        dirlist = [f.lstrip(b'/').split(b'/')[:-1] for f in filelist]
        if len(dirlist) == 1:
            return b'/'.join(dirlist[0])
        a = min(dirlist)
        b = max(dirlist)
        # The common prefix of a and b is shared with all
        # elements of the list since Python sorts lexicographical
        # and [1, x] after [1].
        return b'/'.join(common(a, b))
    except TypeError:
        raise error.ParseError(_(b'argument is not a list of text'))


@templatefilter(b'count')
def count(i):
    """List or text. Returns the length as an integer."""
    try:
        return len(i)
    except TypeError:
        raise error.ParseError(_(b'not countable'))


@templatefilter(b'dirname', intype=bytes)
def dirname(path):
    """Any text. Treats the text as a path, and strips the last
    component of the path after splitting by the path separator.
    """
    return os.path.dirname(path)


@templatefilter(b'domain', intype=bytes)
def domain(author):
    """Any text. Finds the first string that looks like an email
    address, and extracts just the domain component. Example: ``User
    <user@example.com>`` becomes ``example.com``.
    """
    f = author.find(b'@')
    if f == -1:
        return b''
    author = author[f + 1 :]
    f = author.find(b'>')
    if f >= 0:
        author = author[:f]
    return author


@templatefilter(b'email', intype=bytes)
def email(text):
    """Any text. Extracts the first string that looks like an email
    address. Example: ``User <user@example.com>`` becomes
    ``user@example.com``.
    """
    return stringutil.email(text)


@templatefilter(b'escape', intype=bytes)
def escape(text):
    """Any text. Replaces the special XML/XHTML characters "&", "<"
    and ">" with XML entities, and filters out NUL characters.
    """
    return url.escape(text.replace(b'\0', b''), True)


para_re = None
space_re = None


def fill(text, width, initindent=b'', hangindent=b''):
    '''fill many paragraphs with optional indentation.'''
    global para_re, space_re
    if para_re is None:
        para_re = re.compile(b'(\n\n|\n\\s*[-*]\\s*)', re.M)
        space_re = re.compile(br'  +')

    def findparas():
        start = 0
        while True:
            m = para_re.search(text, start)
            if not m:
                uctext = encoding.unifromlocal(text[start:])
                w = len(uctext)
                while w > 0 and uctext[w - 1].isspace():
                    w -= 1
                yield (
                    encoding.unitolocal(uctext[:w]),
                    encoding.unitolocal(uctext[w:]),
                )
                break
            yield text[start : m.start(0)], m.group(1)
            start = m.end(1)

    return b"".join(
        [
            stringutil.wrap(
                space_re.sub(b' ', stringutil.wrap(para, width)),
                width,
                initindent,
                hangindent,
            )
            + rest
            for para, rest in findparas()
        ]
    )


@templatefilter(b'fill68', intype=bytes)
def fill68(text):
    """Any text. Wraps the text to fit in 68 columns."""
    return fill(text, 68)


@templatefilter(b'fill76', intype=bytes)
def fill76(text):
    """Any text. Wraps the text to fit in 76 columns."""
    return fill(text, 76)


@templatefilter(b'firstline', intype=bytes)
def firstline(text):
    """Any text. Returns the first line of text."""
    try:
        return text.splitlines(True)[0].rstrip(b'\r\n')
    except IndexError:
        return b''


@templatefilter(b'hex', intype=bytes)
def hexfilter(text):
    """Any text. Convert a binary Mercurial node identifier into
    its long hexadecimal representation.
    """
    return node.hex(text)


@templatefilter(b'hgdate', intype=templateutil.date)
def hgdate(text):
    """Date. Returns the date as a pair of numbers: "1157407993
    25200" (Unix timestamp, timezone offset).
    """
    return b"%d %d" % text


@templatefilter(b'isodate', intype=templateutil.date)
def isodate(text):
    """Date. Returns the date in ISO 8601 format: "2009-08-18 13:00
    +0200".
    """
    return dateutil.datestr(text, b'%Y-%m-%d %H:%M %1%2')


@templatefilter(b'isodatesec', intype=templateutil.date)
def isodatesec(text):
    """Date. Returns the date in ISO 8601 format, including
    seconds: "2009-08-18 13:00:13 +0200". See also the rfc3339date
    filter.
    """
    return dateutil.datestr(text, b'%Y-%m-%d %H:%M:%S %1%2')


def indent(text, prefix, firstline=b''):
    '''indent each non-empty line of text after first with prefix.'''
    lines = text.splitlines()
    num_lines = len(lines)
    endswithnewline = text[-1:] == b'\n'

    def indenter():
        for i in pycompat.xrange(num_lines):
            l = lines[i]
            if l.strip():
                yield prefix if i else firstline
            yield l
            if i < num_lines - 1 or endswithnewline:
                yield b'\n'

    return b"".join(indenter())


@templatefilter(b'json')
def json(obj, paranoid=True):
    """Any object. Serializes the object to a JSON formatted text."""
    if obj is None:
        return b'null'
    elif obj is False:
        return b'false'
    elif obj is True:
        return b'true'
    elif isinstance(obj, (int, pycompat.long, float)):
        return pycompat.bytestr(obj)
    elif isinstance(obj, bytes):
        return b'"%s"' % encoding.jsonescape(obj, paranoid=paranoid)
    elif isinstance(obj, type(u'')):
        raise error.ProgrammingError(
            b'Mercurial only does output with bytes: %r' % obj
        )
    elif util.safehasattr(obj, b'keys'):
        out = [
            b'"%s": %s'
            % (encoding.jsonescape(k, paranoid=paranoid), json(v, paranoid))
            for k, v in sorted(pycompat.iteritems(obj))
        ]
        return b'{' + b', '.join(out) + b'}'
    elif util.safehasattr(obj, b'__iter__'):
        out = [json(i, paranoid) for i in obj]
        return b'[' + b', '.join(out) + b']'
    raise error.ProgrammingError(b'cannot encode %r' % obj)


@templatefilter(b'lower', intype=bytes)
def lower(text):
    """Any text. Converts the text to lowercase."""
    return encoding.lower(text)


@templatefilter(b'nonempty', intype=bytes)
def nonempty(text):
    """Any text. Returns '(none)' if the string is empty."""
    return text or b"(none)"


@templatefilter(b'obfuscate', intype=bytes)
def obfuscate(text):
    """Any text. Returns the input text rendered as a sequence of
    XML entities.
    """
    text = pycompat.unicode(
        text, pycompat.sysstr(encoding.encoding), r'replace'
    )
    return b''.join([b'&#%d;' % ord(c) for c in text])


@templatefilter(b'permissions', intype=bytes)
def permissions(flags):
    if b"l" in flags:
        return b"lrwxrwxrwx"
    if b"x" in flags:
        return b"-rwxr-xr-x"
    return b"-rw-r--r--"


@templatefilter(b'person', intype=bytes)
def person(author):
    """Any text. Returns the name before an email address,
    interpreting it as per RFC 5322.
    """
    return stringutil.person(author)


@templatefilter(b'revescape', intype=bytes)
def revescape(text):
    """Any text. Escapes all "special" characters, except @.
    Forward slashes are escaped twice to prevent web servers from prematurely
    unescaping them. For example, "@foo bar/baz" becomes "@foo%20bar%252Fbaz".
    """
    return urlreq.quote(text, safe=b'/@').replace(b'/', b'%252F')


@templatefilter(b'rfc3339date', intype=templateutil.date)
def rfc3339date(text):
    """Date. Returns a date using the Internet date format
    specified in RFC 3339: "2009-08-18T13:00:13+02:00".
    """
    return dateutil.datestr(text, b"%Y-%m-%dT%H:%M:%S%1:%2")


@templatefilter(b'rfc822date', intype=templateutil.date)
def rfc822date(text):
    """Date. Returns a date using the same format used in email
    headers: "Tue, 18 Aug 2009 13:00:13 +0200".
    """
    return dateutil.datestr(text, b"%a, %d %b %Y %H:%M:%S %1%2")


@templatefilter(b'short', intype=bytes)
def short(text):
    """Changeset hash. Returns the short form of a changeset hash,
    i.e. a 12 hexadecimal digit string.
    """
    return text[:12]


@templatefilter(b'shortbisect', intype=bytes)
def shortbisect(label):
    """Any text. Treats `label` as a bisection status, and
    returns a single-character representing the status (G: good, B: bad,
    S: skipped, U: untested, I: ignored). Returns single space if `text`
    is not a valid bisection status.
    """
    if label:
        return label[0:1].upper()
    return b' '


@templatefilter(b'shortdate', intype=templateutil.date)
def shortdate(text):
    """Date. Returns a date like "2006-09-18"."""
    return dateutil.shortdate(text)


@templatefilter(b'slashpath', intype=bytes)
def slashpath(path):
    """Any text. Replaces the native path separator with slash."""
    return util.pconvert(path)


@templatefilter(b'splitlines', intype=bytes)
def splitlines(text):
    """Any text. Split text into a list of lines."""
    return templateutil.hybridlist(text.splitlines(), name=b'line')


@templatefilter(b'stringescape', intype=bytes)
def stringescape(text):
    return stringutil.escapestr(text)


@templatefilter(b'stringify', intype=bytes)
def stringify(thing):
    """Any type. Turns the value into text by converting values into
    text and concatenating them.
    """
    return thing  # coerced by the intype


@templatefilter(b'stripdir', intype=bytes)
def stripdir(text):
    """Treat the text as path and strip a directory level, if
    possible. For example, "foo" and "foo/bar" becomes "foo".
    """
    dir = os.path.dirname(text)
    if dir == b"":
        return os.path.basename(text)
    else:
        return dir


@templatefilter(b'tabindent', intype=bytes)
def tabindent(text):
    """Any text. Returns the text, with every non-empty line
    except the first starting with a tab character.
    """
    return indent(text, b'\t')


@templatefilter(b'upper', intype=bytes)
def upper(text):
    """Any text. Converts the text to uppercase."""
    return encoding.upper(text)


@templatefilter(b'urlescape', intype=bytes)
def urlescape(text):
    """Any text. Escapes all "special" characters. For example,
    "foo bar" becomes "foo%20bar".
    """
    return urlreq.quote(text)


@templatefilter(b'user', intype=bytes)
def userfilter(text):
    """Any text. Returns a short representation of a user name or email
    address."""
    return stringutil.shortuser(text)


@templatefilter(b'emailuser', intype=bytes)
def emailuser(text):
    """Any text. Returns the user portion of an email address."""
    return stringutil.emailuser(text)


@templatefilter(b'utf8', intype=bytes)
def utf8(text):
    """Any text. Converts from the local character encoding to UTF-8."""
    return encoding.fromlocal(text)


@templatefilter(b'xmlescape', intype=bytes)
def xmlescape(text):
    text = (
        text.replace(b'&', b'&amp;')
        .replace(b'<', b'&lt;')
        .replace(b'>', b'&gt;')
        .replace(b'"', b'&quot;')
        .replace(b"'", b'&#39;')
    )  # &apos; invalid in HTML
    return re.sub(b'[\x00-\x08\x0B\x0C\x0E-\x1F]', b' ', text)


def websub(text, websubtable):
    """:websub: Any text. Only applies to hgweb. Applies the regular
    expression replacements defined in the websub section.
    """
    if websubtable:
        for regexp, format in websubtable:
            text = regexp.sub(format, text)
    return text


def loadfilter(ui, extname, registrarobj):
    """Load template filter from specified registrarobj
    """
    for name, func in pycompat.iteritems(registrarobj._table):
        filters[name] = func


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