hgext/releasenotes.py
author Pierre-Yves David <pierre-yves.david@octobus.net>
Mon, 02 Nov 2020 11:03:56 +0100
changeset 45892 06b64fabf91c
parent 45055 4c1b4805db57
child 46113 59fa3890d40a
permissions -rw-r--r--
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

# Copyright 2017-present Gregory Szorc <gregory.szorc@gmail.com>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

"""generate release notes from commit messages (EXPERIMENTAL)

It is common to maintain files detailing changes in a project between
releases. Maintaining these files can be difficult and time consuming.
The :hg:`releasenotes` command provided by this extension makes the
process simpler by automating it.
"""

from __future__ import absolute_import

import difflib
import errno
import re

from mercurial.i18n import _
from mercurial.pycompat import open
from mercurial import (
    cmdutil,
    config,
    error,
    minirst,
    node,
    pycompat,
    registrar,
    scmutil,
    util,
)
from mercurial.utils import (
    procutil,
    stringutil,
)

cmdtable = {}
command = registrar.command(cmdtable)

try:
    import fuzzywuzzy.fuzz as fuzz

    fuzz.token_set_ratio
except ImportError:
    fuzz = None

# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
# extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
# be specifying the version(s) of Mercurial they are tested with, or
# leave the attribute unspecified.
testedwith = b'ships-with-hg-core'

DEFAULT_SECTIONS = [
    (b'feature', _(b'New Features')),
    (b'bc', _(b'Backwards Compatibility Changes')),
    (b'fix', _(b'Bug Fixes')),
    (b'perf', _(b'Performance Improvements')),
    (b'api', _(b'API Changes')),
]

RE_DIRECTIVE = re.compile(br'^\.\. ([a-zA-Z0-9_]+)::\s*([^$]+)?$')
RE_ISSUE = br'\bissue ?[0-9]{4,6}(?![0-9])\b'

BULLET_SECTION = _(b'Other Changes')


class parsedreleasenotes(object):
    def __init__(self):
        self.sections = {}

    def __contains__(self, section):
        return section in self.sections

    def __iter__(self):
        return iter(sorted(self.sections))

    def addtitleditem(self, section, title, paragraphs):
        """Add a titled release note entry."""
        self.sections.setdefault(section, ([], []))
        self.sections[section][0].append((title, paragraphs))

    def addnontitleditem(self, section, paragraphs):
        """Adds a non-titled release note entry.

        Will be rendered as a bullet point.
        """
        self.sections.setdefault(section, ([], []))
        self.sections[section][1].append(paragraphs)

    def titledforsection(self, section):
        """Returns titled entries in a section.

        Returns a list of (title, paragraphs) tuples describing sub-sections.
        """
        return self.sections.get(section, ([], []))[0]

    def nontitledforsection(self, section):
        """Returns non-titled, bulleted paragraphs in a section."""
        return self.sections.get(section, ([], []))[1]

    def hastitledinsection(self, section, title):
        return any(t[0] == title for t in self.titledforsection(section))

    def merge(self, ui, other):
        """Merge another instance into this one.

        This is used to combine multiple sources of release notes together.
        """
        if not fuzz:
            ui.warn(
                _(
                    b"module 'fuzzywuzzy' not found, merging of similar "
                    b"releasenotes is disabled\n"
                )
            )

        for section in other:
            existingnotes = converttitled(
                self.titledforsection(section)
            ) + convertnontitled(self.nontitledforsection(section))
            for title, paragraphs in other.titledforsection(section):
                if self.hastitledinsection(section, title):
                    # TODO prompt for resolution if different and running in
                    # interactive mode.
                    ui.write(
                        _(b'%s already exists in %s section; ignoring\n')
                        % (title, section)
                    )
                    continue

                incoming_str = converttitled([(title, paragraphs)])[0]
                if section == b'fix':
                    issue = getissuenum(incoming_str)
                    if issue:
                        if findissue(ui, existingnotes, issue):
                            continue

                if similar(ui, existingnotes, incoming_str):
                    continue

                self.addtitleditem(section, title, paragraphs)

            for paragraphs in other.nontitledforsection(section):
                if paragraphs in self.nontitledforsection(section):
                    continue

                incoming_str = convertnontitled([paragraphs])[0]
                if section == b'fix':
                    issue = getissuenum(incoming_str)
                    if issue:
                        if findissue(ui, existingnotes, issue):
                            continue

                if similar(ui, existingnotes, incoming_str):
                    continue

                self.addnontitleditem(section, paragraphs)


class releasenotessections(object):
    def __init__(self, ui, repo=None):
        if repo:
            sections = util.sortdict(DEFAULT_SECTIONS)
            custom_sections = getcustomadmonitions(repo)
            if custom_sections:
                sections.update(custom_sections)
            self._sections = list(pycompat.iteritems(sections))
        else:
            self._sections = list(DEFAULT_SECTIONS)

    def __iter__(self):
        return iter(self._sections)

    def names(self):
        return [t[0] for t in self._sections]

    def sectionfromtitle(self, title):
        for name, value in self._sections:
            if value == title:
                return name

        return None


def converttitled(titledparagraphs):
    """
    Convert titled paragraphs to strings
    """
    string_list = []
    for title, paragraphs in titledparagraphs:
        lines = []
        for para in paragraphs:
            lines.extend(para)
        string_list.append(b' '.join(lines))
    return string_list


def convertnontitled(nontitledparagraphs):
    """
    Convert non-titled bullets to strings
    """
    string_list = []
    for paragraphs in nontitledparagraphs:
        lines = []
        for para in paragraphs:
            lines.extend(para)
        string_list.append(b' '.join(lines))
    return string_list


def getissuenum(incoming_str):
    """
    Returns issue number from the incoming string if it exists
    """
    issue = re.search(RE_ISSUE, incoming_str, re.IGNORECASE)
    if issue:
        issue = issue.group()
    return issue


def findissue(ui, existing, issue):
    """
    Returns true if issue number already exists in notes.
    """
    if any(issue in s for s in existing):
        ui.write(_(b'"%s" already exists in notes; ignoring\n') % issue)
        return True
    else:
        return False


def similar(ui, existing, incoming_str):
    """
    Returns true if similar note found in existing notes.
    """
    if len(incoming_str.split()) > 10:
        merge = similaritycheck(incoming_str, existing)
        if not merge:
            ui.write(
                _(b'"%s" already exists in notes file; ignoring\n')
                % incoming_str
            )
            return True
        else:
            return False
    else:
        return False


def similaritycheck(incoming_str, existingnotes):
    """
    Returns false when note fragment can be merged to existing notes.
    """
    # fuzzywuzzy not present
    if not fuzz:
        return True

    merge = True
    for bullet in existingnotes:
        score = fuzz.token_set_ratio(incoming_str, bullet)
        if score > 75:
            merge = False
            break
    return merge


def getcustomadmonitions(repo):
    ctx = repo[b'.']
    p = config.config()

    def read(f, sections=None, remap=None):
        if f in ctx:
            data = ctx[f].data()
            p.parse(f, data, sections, remap, read)
        else:
            raise error.Abort(
                _(b".hgreleasenotes file \'%s\' not found") % repo.pathto(f)
            )

    if b'.hgreleasenotes' in ctx:
        read(b'.hgreleasenotes')
    return p[b'sections']


def checkadmonitions(ui, repo, directives, revs):
    """
    Checks the commit messages for admonitions and their validity.

    .. abcd::

       First paragraph under this admonition

    For this commit message, using `hg releasenotes -r . --check`
    returns: Invalid admonition 'abcd' present in changeset 3ea92981e103

    As admonition 'abcd' is neither present in default nor custom admonitions
    """
    for rev in revs:
        ctx = repo[rev]
        admonition = re.search(RE_DIRECTIVE, ctx.description())
        if admonition:
            if admonition.group(1) in directives:
                continue
            else:
                ui.write(
                    _(b"Invalid admonition '%s' present in changeset %s\n")
                    % (admonition.group(1), ctx.hex()[:12])
                )
                sim = lambda x: difflib.SequenceMatcher(
                    None, admonition.group(1), x
                ).ratio()

                similar = [s for s in directives if sim(s) > 0.6]
                if len(similar) == 1:
                    ui.write(_(b"(did you mean %s?)\n") % similar[0])
                elif similar:
                    ss = b", ".join(sorted(similar))
                    ui.write(_(b"(did you mean one of %s?)\n") % ss)


def _getadmonitionlist(ui, sections):
    for section in sections:
        ui.write(b"%s: %s\n" % (section[0], section[1]))


def parsenotesfromrevisions(repo, directives, revs):
    notes = parsedreleasenotes()

    for rev in revs:
        ctx = repo[rev]

        blocks, pruned = minirst.parse(
            ctx.description(), admonitions=directives
        )

        for i, block in enumerate(blocks):
            if block[b'type'] != b'admonition':
                continue

            directive = block[b'admonitiontitle']
            title = block[b'lines'][0].strip() if block[b'lines'] else None

            if i + 1 == len(blocks):
                raise error.Abort(
                    _(
                        b'changeset %s: release notes directive %s '
                        b'lacks content'
                    )
                    % (ctx, directive)
                )

            # Now search ahead and find all paragraphs attached to this
            # admonition.
            paragraphs = []
            for j in range(i + 1, len(blocks)):
                pblock = blocks[j]

                # Margin blocks may appear between paragraphs. Ignore them.
                if pblock[b'type'] == b'margin':
                    continue

                if pblock[b'type'] == b'admonition':
                    break

                if pblock[b'type'] != b'paragraph':
                    repo.ui.warn(
                        _(
                            b'changeset %s: unexpected block in release '
                            b'notes directive %s\n'
                        )
                        % (ctx, directive)
                    )

                if pblock[b'indent'] > 0:
                    paragraphs.append(pblock[b'lines'])
                else:
                    break

            # TODO consider using title as paragraph for more concise notes.
            if not paragraphs:
                repo.ui.warn(
                    _(b"error parsing releasenotes for revision: '%s'\n")
                    % node.hex(ctx.node())
                )
            if title:
                notes.addtitleditem(directive, title, paragraphs)
            else:
                notes.addnontitleditem(directive, paragraphs)

    return notes


def parsereleasenotesfile(sections, text):
    """Parse text content containing generated release notes."""
    notes = parsedreleasenotes()

    blocks = minirst.parse(text)[0]

    def gatherparagraphsbullets(offset, title=False):
        notefragment = []

        for i in range(offset + 1, len(blocks)):
            block = blocks[i]

            if block[b'type'] == b'margin':
                continue
            elif block[b'type'] == b'section':
                break
            elif block[b'type'] == b'bullet':
                if block[b'indent'] != 0:
                    raise error.Abort(_(b'indented bullet lists not supported'))
                if title:
                    lines = [l[1:].strip() for l in block[b'lines']]
                    notefragment.append(lines)
                    continue
                else:
                    lines = [[l[1:].strip() for l in block[b'lines']]]

                    for block in blocks[i + 1 :]:
                        if block[b'type'] in (b'bullet', b'section'):
                            break
                        if block[b'type'] == b'paragraph':
                            lines.append(block[b'lines'])
                    notefragment.append(lines)
                    continue
            elif block[b'type'] != b'paragraph':
                raise error.Abort(
                    _(b'unexpected block type in release notes: %s')
                    % block[b'type']
                )
            if title:
                notefragment.append(block[b'lines'])

        return notefragment

    currentsection = None
    for i, block in enumerate(blocks):
        if block[b'type'] != b'section':
            continue

        title = block[b'lines'][0]

        # TODO the parsing around paragraphs and bullet points needs some
        # work.
        if block[b'underline'] == b'=':  # main section
            name = sections.sectionfromtitle(title)
            if not name:
                raise error.Abort(
                    _(b'unknown release notes section: %s') % title
                )

            currentsection = name
            bullet_points = gatherparagraphsbullets(i)
            if bullet_points:
                for para in bullet_points:
                    notes.addnontitleditem(currentsection, para)

        elif block[b'underline'] == b'-':  # sub-section
            if title == BULLET_SECTION:
                bullet_points = gatherparagraphsbullets(i)
                for para in bullet_points:
                    notes.addnontitleditem(currentsection, para)
            else:
                paragraphs = gatherparagraphsbullets(i, True)
                notes.addtitleditem(currentsection, title, paragraphs)
        else:
            raise error.Abort(_(b'unsupported section type for %s') % title)

    return notes


def serializenotes(sections, notes):
    """Serialize release notes from parsed fragments and notes.

    This function essentially takes the output of ``parsenotesfromrevisions()``
    and ``parserelnotesfile()`` and produces output combining the 2.
    """
    lines = []

    for sectionname, sectiontitle in sections:
        if sectionname not in notes:
            continue

        lines.append(sectiontitle)
        lines.append(b'=' * len(sectiontitle))
        lines.append(b'')

        # First pass to emit sub-sections.
        for title, paragraphs in notes.titledforsection(sectionname):
            lines.append(title)
            lines.append(b'-' * len(title))
            lines.append(b'')

            for i, para in enumerate(paragraphs):
                if i:
                    lines.append(b'')
                lines.extend(
                    stringutil.wrap(b' '.join(para), width=78).splitlines()
                )

            lines.append(b'')

        # Second pass to emit bullet list items.

        # If the section has titled and non-titled items, we can't
        # simply emit the bullet list because it would appear to come
        # from the last title/section. So, we emit a new sub-section
        # for the non-titled items.
        nontitled = notes.nontitledforsection(sectionname)
        if notes.titledforsection(sectionname) and nontitled:
            # TODO make configurable.
            lines.append(BULLET_SECTION)
            lines.append(b'-' * len(BULLET_SECTION))
            lines.append(b'')

        for paragraphs in nontitled:
            lines.extend(
                stringutil.wrap(
                    b' '.join(paragraphs[0]),
                    width=78,
                    initindent=b'* ',
                    hangindent=b'  ',
                ).splitlines()
            )

            for para in paragraphs[1:]:
                lines.append(b'')
                lines.extend(
                    stringutil.wrap(
                        b' '.join(para),
                        width=78,
                        initindent=b'  ',
                        hangindent=b'  ',
                    ).splitlines()
                )

            lines.append(b'')

    if lines and lines[-1]:
        lines.append(b'')

    return b'\n'.join(lines)


@command(
    b'releasenotes',
    [
        (
            b'r',
            b'rev',
            b'',
            _(b'revisions to process for release notes'),
            _(b'REV'),
        ),
        (
            b'c',
            b'check',
            False,
            _(b'checks for validity of admonitions (if any)'),
            _(b'REV'),
        ),
        (
            b'l',
            b'list',
            False,
            _(b'list the available admonitions with their title'),
            None,
        ),
    ],
    _(b'hg releasenotes [-r REV] [-c] FILE'),
    helpcategory=command.CATEGORY_CHANGE_NAVIGATION,
)
def releasenotes(ui, repo, file_=None, **opts):
    """parse release notes from commit messages into an output file

    Given an output file and set of revisions, this command will parse commit
    messages for release notes then add them to the output file.

    Release notes are defined in commit messages as ReStructuredText
    directives. These have the form::

       .. directive:: title

          content

    Each ``directive`` maps to an output section in a generated release notes
    file, which itself is ReStructuredText. For example, the ``.. feature::``
    directive would map to a ``New Features`` section.

    Release note directives can be either short-form or long-form. In short-
    form, ``title`` is omitted and the release note is rendered as a bullet
    list. In long form, a sub-section with the title ``title`` is added to the
    section.

    The ``FILE`` argument controls the output file to write gathered release
    notes to. The format of the file is::

       Section 1
       =========

       ...

       Section 2
       =========

       ...

    Only sections with defined release notes are emitted.

    If a section only has short-form notes, it will consist of bullet list::

       Section
       =======

       * Release note 1
       * Release note 2

    If a section has long-form notes, sub-sections will be emitted::

       Section
       =======

       Note 1 Title
       ------------

       Description of the first long-form note.

       Note 2 Title
       ------------

       Description of the second long-form note.

    If the ``FILE`` argument points to an existing file, that file will be
    parsed for release notes having the format that would be generated by this
    command. The notes from the processed commit messages will be *merged*
    into this parsed set.

    During release notes merging:

    * Duplicate items are automatically ignored
    * Items that are different are automatically ignored if the similarity is
      greater than a threshold.

    This means that the release notes file can be updated independently from
    this command and changes should not be lost when running this command on
    that file. A particular use case for this is to tweak the wording of a
    release note after it has been added to the release notes file.

    The -c/--check option checks the commit message for invalid admonitions.

    The -l/--list option, presents the user with a list of existing available
    admonitions along with their title. This also includes the custom
    admonitions (if any).
    """

    opts = pycompat.byteskwargs(opts)
    sections = releasenotessections(ui, repo)

    cmdutil.check_incompatible_arguments(opts, b'list', [b'rev', b'check'])

    if opts.get(b'list'):
        return _getadmonitionlist(ui, sections)

    rev = opts.get(b'rev')
    revs = scmutil.revrange(repo, [rev or b'not public()'])
    if opts.get(b'check'):
        return checkadmonitions(ui, repo, sections.names(), revs)

    incoming = parsenotesfromrevisions(repo, sections.names(), revs)

    if file_ is None:
        ui.pager(b'releasenotes')
        return ui.write(serializenotes(sections, incoming))

    try:
        with open(file_, b'rb') as fh:
            notes = parsereleasenotesfile(sections, fh.read())
    except IOError as e:
        if e.errno != errno.ENOENT:
            raise

        notes = parsedreleasenotes()

    notes.merge(ui, incoming)

    with open(file_, b'wb') as fh:
        fh.write(serializenotes(sections, notes))


@command(b'debugparsereleasenotes', norepo=True)
def debugparsereleasenotes(ui, path, repo=None):
    """parse release notes and print resulting data structure"""
    if path == b'-':
        text = procutil.stdin.read()
    else:
        with open(path, b'rb') as fh:
            text = fh.read()

    sections = releasenotessections(ui, repo)

    notes = parsereleasenotesfile(sections, text)

    for section in notes:
        ui.write(_(b'section: %s\n') % section)
        for title, paragraphs in notes.titledforsection(section):
            ui.write(_(b'  subsection: %s\n') % title)
            for para in paragraphs:
                ui.write(_(b'    paragraph: %s\n') % b' '.join(para))

        for paragraphs in notes.nontitledforsection(section):
            ui.write(_(b'  bullet point:\n'))
            for para in paragraphs:
                ui.write(_(b'    paragraph: %s\n') % b' '.join(para))