Mercurial > public > mercurial-scm > hg
view mercurial/parser.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 | 0fc8b066928a |
children | 89a2afe31e82 |
line wrap: on
line source
# parser.py - simple top-down operator precedence parser for mercurial # # Copyright 2010 Matt Mackall <mpm@selenic.com> # # This software may be used and distributed according to the terms of the # GNU General Public License version 2 or any later version. # see http://effbot.org/zone/simple-top-down-parsing.htm and # http://eli.thegreenplace.net/2010/01/02/top-down-operator-precedence-parsing/ # for background # takes a tokenizer and elements # tokenizer is an iterator that returns (type, value, pos) tuples # elements is a mapping of types to binding strength, primary, prefix, infix # and suffix actions # an action is a tree node name, a tree label, and an optional match # __call__(program) parses program into a labeled tree from __future__ import absolute_import, print_function from .i18n import _ from . import ( error, pycompat, util, ) from .utils import stringutil class parser(object): def __init__(self, elements, methods=None): self._elements = elements self._methods = methods self.current = None def _advance(self): """advance the tokenizer""" t = self.current self.current = next(self._iter, None) return t def _hasnewterm(self): """True if next token may start new term""" return any(self._elements[self.current[0]][1:3]) def _match(self, m): """make sure the tokenizer matches an end condition""" if self.current[0] != m: raise error.ParseError( _(b"unexpected token: %s") % self.current[0], self.current[2] ) self._advance() def _parseoperand(self, bind, m=None): """gather right-hand-side operand until an end condition or binding met""" if m and self.current[0] == m: expr = None else: expr = self._parse(bind) if m: self._match(m) return expr def _parse(self, bind=0): token, value, pos = self._advance() # handle prefix rules on current token, take as primary if unambiguous primary, prefix = self._elements[token][1:3] if primary and not (prefix and self._hasnewterm()): expr = (primary, value) elif prefix: expr = (prefix[0], self._parseoperand(*prefix[1:])) else: raise error.ParseError(_(b"not a prefix: %s") % token, pos) # gather tokens until we meet a lower binding strength while bind < self._elements[self.current[0]][0]: token, value, pos = self._advance() # handle infix rules, take as suffix if unambiguous infix, suffix = self._elements[token][3:] if suffix and not (infix and self._hasnewterm()): expr = (suffix, expr) elif infix: expr = (infix[0], expr, self._parseoperand(*infix[1:])) else: raise error.ParseError(_(b"not an infix: %s") % token, pos) return expr def parse(self, tokeniter): """generate a parse tree from tokens""" self._iter = tokeniter self._advance() res = self._parse() token, value, pos = self.current return res, pos def eval(self, tree): """recursively evaluate a parse tree using node methods""" if not isinstance(tree, tuple): return tree return self._methods[tree[0]](*[self.eval(t) for t in tree[1:]]) def __call__(self, tokeniter): """parse tokens into a parse tree and evaluate if methods given""" t = self.parse(tokeniter) if self._methods: return self.eval(t) return t def splitargspec(spec): """Parse spec of function arguments into (poskeys, varkey, keys, optkey) >>> splitargspec(b'') ([], None, [], None) >>> splitargspec(b'foo bar') ([], None, ['foo', 'bar'], None) >>> splitargspec(b'foo *bar baz **qux') (['foo'], 'bar', ['baz'], 'qux') >>> splitargspec(b'*foo') ([], 'foo', [], None) >>> splitargspec(b'**foo') ([], None, [], 'foo') """ optkey = None pre, sep, post = spec.partition(b'**') if sep: posts = post.split() if not posts: raise error.ProgrammingError(b'no **optkey name provided') if len(posts) > 1: raise error.ProgrammingError(b'excessive **optkey names provided') optkey = posts[0] pre, sep, post = pre.partition(b'*') pres = pre.split() posts = post.split() if sep: if not posts: raise error.ProgrammingError(b'no *varkey name provided') return pres, posts[0], posts[1:], optkey return [], None, pres, optkey def buildargsdict(trees, funcname, argspec, keyvaluenode, keynode): """Build dict from list containing positional and keyword arguments Arguments are specified by a tuple of ``(poskeys, varkey, keys, optkey)`` where - ``poskeys``: list of names of positional arguments - ``varkey``: optional argument name that takes up remainder - ``keys``: list of names that can be either positional or keyword arguments - ``optkey``: optional argument name that takes up excess keyword arguments If ``varkey`` specified, all ``keys`` must be given as keyword arguments. Invalid keywords, too few positional arguments, or too many positional arguments are rejected, but missing keyword arguments are just omitted. """ poskeys, varkey, keys, optkey = argspec kwstart = next( (i for i, x in enumerate(trees) if x and x[0] == keyvaluenode), len(trees), ) if kwstart < len(poskeys): raise error.ParseError( _(b"%(func)s takes at least %(nargs)d positional arguments") % {b'func': funcname, b'nargs': len(poskeys)} ) if not varkey and kwstart > len(poskeys) + len(keys): raise error.ParseError( _(b"%(func)s takes at most %(nargs)d positional arguments") % {b'func': funcname, b'nargs': len(poskeys) + len(keys)} ) args = util.sortdict() # consume positional arguments for k, x in zip(poskeys, trees[:kwstart]): args[k] = x if varkey: args[varkey] = trees[len(args) : kwstart] else: for k, x in zip(keys, trees[len(args) : kwstart]): args[k] = x # remainder should be keyword arguments if optkey: args[optkey] = util.sortdict() for x in trees[kwstart:]: if not x or x[0] != keyvaluenode or x[1][0] != keynode: raise error.ParseError( _(b"%(func)s got an invalid argument") % {b'func': funcname} ) k = x[1][1] if k in keys: d = args elif not optkey: raise error.ParseError( _(b"%(func)s got an unexpected keyword argument '%(key)s'") % {b'func': funcname, b'key': k} ) else: d = args[optkey] if k in d: raise error.ParseError( _( b"%(func)s got multiple values for keyword " b"argument '%(key)s'" ) % {b'func': funcname, b'key': k} ) d[k] = x[2] return args def unescapestr(s): try: return stringutil.unescapestr(s) except ValueError as e: # mangle Python's exception into our format raise error.ParseError(pycompat.bytestr(e).lower()) def _prettyformat(tree, leafnodes, level, lines): if not isinstance(tree, tuple): lines.append((level, stringutil.pprint(tree))) elif tree[0] in leafnodes: rs = map(stringutil.pprint, tree[1:]) lines.append((level, b'(%s %s)' % (tree[0], b' '.join(rs)))) else: lines.append((level, b'(%s' % tree[0])) for s in tree[1:]: _prettyformat(s, leafnodes, level + 1, lines) lines[-1:] = [(lines[-1][0], lines[-1][1] + b')')] def prettyformat(tree, leafnodes): lines = [] _prettyformat(tree, leafnodes, 0, lines) output = b'\n'.join((b' ' * l + s) for l, s in lines) return output def simplifyinfixops(tree, targetnodes): """Flatten chained infix operations to reduce usage of Python stack >>> from . import pycompat >>> def f(tree): ... s = prettyformat(simplifyinfixops(tree, (b'or',)), (b'symbol',)) ... print(pycompat.sysstr(s)) >>> f((b'or', ... (b'or', ... (b'symbol', b'1'), ... (b'symbol', b'2')), ... (b'symbol', b'3'))) (or (symbol '1') (symbol '2') (symbol '3')) >>> f((b'func', ... (b'symbol', b'p1'), ... (b'or', ... (b'or', ... (b'func', ... (b'symbol', b'sort'), ... (b'list', ... (b'or', ... (b'or', ... (b'symbol', b'1'), ... (b'symbol', b'2')), ... (b'symbol', b'3')), ... (b'negate', ... (b'symbol', b'rev')))), ... (b'and', ... (b'symbol', b'4'), ... (b'group', ... (b'or', ... (b'or', ... (b'symbol', b'5'), ... (b'symbol', b'6')), ... (b'symbol', b'7'))))), ... (b'symbol', b'8')))) (func (symbol 'p1') (or (func (symbol 'sort') (list (or (symbol '1') (symbol '2') (symbol '3')) (negate (symbol 'rev')))) (and (symbol '4') (group (or (symbol '5') (symbol '6') (symbol '7')))) (symbol '8'))) """ if not isinstance(tree, tuple): return tree op = tree[0] if op not in targetnodes: return (op,) + tuple(simplifyinfixops(x, targetnodes) for x in tree[1:]) # walk down left nodes taking each right node. no recursion to left nodes # because infix operators are left-associative, i.e. left tree is deep. # e.g. '1 + 2 + 3' -> (+ (+ 1 2) 3) -> (+ 1 2 3) simplified = [] x = tree while x[0] == op: l, r = x[1:] simplified.append(simplifyinfixops(r, targetnodes)) x = l simplified.append(simplifyinfixops(x, targetnodes)) simplified.append(op) return tuple(reversed(simplified)) def _buildtree(template, placeholder, replstack): if template == placeholder: return replstack.pop() if not isinstance(template, tuple): return template return tuple(_buildtree(x, placeholder, replstack) for x in template) def buildtree(template, placeholder, *repls): """Create new tree by substituting placeholders by replacements >>> _ = (b'symbol', b'_') >>> def f(template, *repls): ... return buildtree(template, _, *repls) >>> f((b'func', (b'symbol', b'only'), (b'list', _, _)), ... ('symbol', '1'), ('symbol', '2')) ('func', ('symbol', 'only'), ('list', ('symbol', '1'), ('symbol', '2'))) >>> f((b'and', _, (b'not', _)), (b'symbol', b'1'), (b'symbol', b'2')) ('and', ('symbol', '1'), ('not', ('symbol', '2'))) """ if not isinstance(placeholder, tuple): raise error.ProgrammingError(b'placeholder must be a node tuple') replstack = list(reversed(repls)) r = _buildtree(template, placeholder, replstack) if replstack: raise error.ProgrammingError(b'too many replacements') return r def _matchtree(pattern, tree, placeholder, incompletenodes, matches): if pattern == tree: return True if not isinstance(pattern, tuple) or not isinstance(tree, tuple): return False if pattern == placeholder and tree[0] not in incompletenodes: matches.append(tree) return True if len(pattern) != len(tree): return False return all( _matchtree(p, x, placeholder, incompletenodes, matches) for p, x in zip(pattern, tree) ) def matchtree(pattern, tree, placeholder=None, incompletenodes=()): """If a tree matches the pattern, return a list of the tree and nodes matched with the placeholder; Otherwise None >>> def f(pattern, tree): ... m = matchtree(pattern, tree, _, {b'keyvalue', b'list'}) ... if m: ... return m[1:] >>> _ = (b'symbol', b'_') >>> f((b'func', (b'symbol', b'ancestors'), _), ... (b'func', (b'symbol', b'ancestors'), (b'symbol', b'1'))) [('symbol', '1')] >>> f((b'func', (b'symbol', b'ancestors'), _), ... (b'func', (b'symbol', b'ancestors'), None)) >>> f((b'range', (b'dagrange', _, _), _), ... (b'range', ... (b'dagrange', (b'symbol', b'1'), (b'symbol', b'2')), ... (b'symbol', b'3'))) [('symbol', '1'), ('symbol', '2'), ('symbol', '3')] The placeholder does not match the specified incomplete nodes because an incomplete node (e.g. argument list) cannot construct an expression. >>> f((b'func', (b'symbol', b'ancestors'), _), ... (b'func', (b'symbol', b'ancestors'), ... (b'list', (b'symbol', b'1'), (b'symbol', b'2')))) The placeholder may be omitted, but which shouldn't match a None node. >>> _ = None >>> f((b'func', (b'symbol', b'ancestors'), None), ... (b'func', (b'symbol', b'ancestors'), (b'symbol', b'0'))) """ if placeholder is not None and not isinstance(placeholder, tuple): raise error.ProgrammingError(b'placeholder must be a node tuple') matches = [tree] if _matchtree(pattern, tree, placeholder, incompletenodes, matches): return matches def parseerrordetail(inst): """Compose error message from specified ParseError object """ if inst.location is not None: return _(b'at %d: %s') % (inst.location, inst.message) else: return inst.message class alias(object): """Parsed result of alias""" def __init__(self, name, args, err, replacement): self.name = name self.args = args self.error = err self.replacement = replacement # whether own `error` information is already shown or not. # this avoids showing same warning multiple times at each # `expandaliases`. self.warned = False class basealiasrules(object): """Parsing and expansion rule set of aliases This is a helper for fileset/revset/template aliases. A concrete rule set should be made by sub-classing this and implementing class/static methods. It supports alias expansion of symbol and function-call styles:: # decl = defn h = heads(default) b($1) = ancestors($1) - ancestors(default) """ # typically a config section, which will be included in error messages _section = None # tag of symbol node _symbolnode = b'symbol' def __new__(cls): raise TypeError(b"'%s' is not instantiatable" % cls.__name__) @staticmethod def _parse(spec): """Parse an alias name, arguments and definition""" raise NotImplementedError @staticmethod def _trygetfunc(tree): """Return (name, args) if tree is a function; otherwise None""" raise NotImplementedError @classmethod def _builddecl(cls, decl): """Parse an alias declaration into ``(name, args, errorstr)`` This function analyzes the parsed tree. The parsing rule is provided by ``_parse()``. - ``name``: of declared alias (may be ``decl`` itself at error) - ``args``: list of argument names (or None for symbol declaration) - ``errorstr``: detail about detected error (or None) >>> sym = lambda x: (b'symbol', x) >>> symlist = lambda *xs: (b'list',) + tuple(sym(x) for x in xs) >>> func = lambda n, a: (b'func', sym(n), a) >>> parsemap = { ... b'foo': sym(b'foo'), ... b'$foo': sym(b'$foo'), ... b'foo::bar': (b'dagrange', sym(b'foo'), sym(b'bar')), ... b'foo()': func(b'foo', None), ... b'$foo()': func(b'$foo', None), ... b'foo($1, $2)': func(b'foo', symlist(b'$1', b'$2')), ... b'foo(bar_bar, baz.baz)': ... func(b'foo', symlist(b'bar_bar', b'baz.baz')), ... b'foo(bar($1, $2))': ... func(b'foo', func(b'bar', symlist(b'$1', b'$2'))), ... b'foo($1, $2, nested($1, $2))': ... func(b'foo', (symlist(b'$1', b'$2') + ... (func(b'nested', symlist(b'$1', b'$2')),))), ... b'foo("bar")': func(b'foo', (b'string', b'bar')), ... b'foo($1, $2': error.ParseError(b'unexpected token: end', 10), ... b'foo("bar': error.ParseError(b'unterminated string', 5), ... b'foo($1, $2, $1)': func(b'foo', symlist(b'$1', b'$2', b'$1')), ... } >>> def parse(expr): ... x = parsemap[expr] ... if isinstance(x, Exception): ... raise x ... return x >>> def trygetfunc(tree): ... if not tree or tree[0] != b'func' or tree[1][0] != b'symbol': ... return None ... if not tree[2]: ... return tree[1][1], [] ... if tree[2][0] == b'list': ... return tree[1][1], list(tree[2][1:]) ... return tree[1][1], [tree[2]] >>> class aliasrules(basealiasrules): ... _parse = staticmethod(parse) ... _trygetfunc = staticmethod(trygetfunc) >>> builddecl = aliasrules._builddecl >>> builddecl(b'foo') ('foo', None, None) >>> builddecl(b'$foo') ('$foo', None, "invalid symbol '$foo'") >>> builddecl(b'foo::bar') ('foo::bar', None, 'invalid format') >>> builddecl(b'foo()') ('foo', [], None) >>> builddecl(b'$foo()') ('$foo()', None, "invalid function '$foo'") >>> builddecl(b'foo($1, $2)') ('foo', ['$1', '$2'], None) >>> builddecl(b'foo(bar_bar, baz.baz)') ('foo', ['bar_bar', 'baz.baz'], None) >>> builddecl(b'foo($1, $2, nested($1, $2))') ('foo($1, $2, nested($1, $2))', None, 'invalid argument list') >>> builddecl(b'foo(bar($1, $2))') ('foo(bar($1, $2))', None, 'invalid argument list') >>> builddecl(b'foo("bar")') ('foo("bar")', None, 'invalid argument list') >>> builddecl(b'foo($1, $2') ('foo($1, $2', None, 'at 10: unexpected token: end') >>> builddecl(b'foo("bar') ('foo("bar', None, 'at 5: unterminated string') >>> builddecl(b'foo($1, $2, $1)') ('foo', None, 'argument names collide with each other') """ try: tree = cls._parse(decl) except error.ParseError as inst: return (decl, None, parseerrordetail(inst)) if tree[0] == cls._symbolnode: # "name = ...." style name = tree[1] if name.startswith(b'$'): return (decl, None, _(b"invalid symbol '%s'") % name) return (name, None, None) func = cls._trygetfunc(tree) if func: # "name(arg, ....) = ...." style name, args = func if name.startswith(b'$'): return (decl, None, _(b"invalid function '%s'") % name) if any(t[0] != cls._symbolnode for t in args): return (decl, None, _(b"invalid argument list")) if len(args) != len(set(args)): return ( name, None, _(b"argument names collide with each other"), ) return (name, [t[1] for t in args], None) return (decl, None, _(b"invalid format")) @classmethod def _relabelargs(cls, tree, args): """Mark alias arguments as ``_aliasarg``""" if not isinstance(tree, tuple): return tree op = tree[0] if op != cls._symbolnode: return (op,) + tuple(cls._relabelargs(x, args) for x in tree[1:]) assert len(tree) == 2 sym = tree[1] if sym in args: op = b'_aliasarg' elif sym.startswith(b'$'): raise error.ParseError(_(b"invalid symbol '%s'") % sym) return (op, sym) @classmethod def _builddefn(cls, defn, args): """Parse an alias definition into a tree and marks substitutions This function marks alias argument references as ``_aliasarg``. The parsing rule is provided by ``_parse()``. ``args`` is a list of alias argument names, or None if the alias is declared as a symbol. >>> from . import pycompat >>> parsemap = { ... b'$1 or foo': (b'or', (b'symbol', b'$1'), (b'symbol', b'foo')), ... b'$1 or $bar': ... (b'or', (b'symbol', b'$1'), (b'symbol', b'$bar')), ... b'$10 or baz': ... (b'or', (b'symbol', b'$10'), (b'symbol', b'baz')), ... b'"$1" or "foo"': ... (b'or', (b'string', b'$1'), (b'string', b'foo')), ... } >>> class aliasrules(basealiasrules): ... _parse = staticmethod(parsemap.__getitem__) ... _trygetfunc = staticmethod(lambda x: None) >>> builddefn = aliasrules._builddefn >>> def pprint(tree): ... s = prettyformat(tree, (b'_aliasarg', b'string', b'symbol')) ... print(pycompat.sysstr(s)) >>> args = [b'$1', b'$2', b'foo'] >>> pprint(builddefn(b'$1 or foo', args)) (or (_aliasarg '$1') (_aliasarg 'foo')) >>> try: ... builddefn(b'$1 or $bar', args) ... except error.ParseError as inst: ... print(pycompat.sysstr(parseerrordetail(inst))) invalid symbol '$bar' >>> args = [b'$1', b'$10', b'foo'] >>> pprint(builddefn(b'$10 or baz', args)) (or (_aliasarg '$10') (symbol 'baz')) >>> pprint(builddefn(b'"$1" or "foo"', args)) (or (string '$1') (string 'foo')) """ tree = cls._parse(defn) if args: args = set(args) else: args = set() return cls._relabelargs(tree, args) @classmethod def build(cls, decl, defn): """Parse an alias declaration and definition into an alias object""" repl = efmt = None name, args, err = cls._builddecl(decl) if err: efmt = _(b'bad declaration of %(section)s "%(name)s": %(error)s') else: try: repl = cls._builddefn(defn, args) except error.ParseError as inst: err = parseerrordetail(inst) efmt = _(b'bad definition of %(section)s "%(name)s": %(error)s') if err: err = efmt % { b'section': cls._section, b'name': name, b'error': err, } return alias(name, args, err, repl) @classmethod def buildmap(cls, items): """Parse a list of alias (name, replacement) pairs into a dict of alias objects""" aliases = {} for decl, defn in items: a = cls.build(decl, defn) aliases[a.name] = a return aliases @classmethod def _getalias(cls, aliases, tree): """If tree looks like an unexpanded alias, return (alias, pattern-args) pair. Return None otherwise. """ if not isinstance(tree, tuple): return None if tree[0] == cls._symbolnode: name = tree[1] a = aliases.get(name) if a and a.args is None: return a, None func = cls._trygetfunc(tree) if func: name, args = func a = aliases.get(name) if a and a.args is not None: return a, args return None @classmethod def _expandargs(cls, tree, args): """Replace _aliasarg instances with the substitution value of the same name in args, recursively. """ if not isinstance(tree, tuple): return tree if tree[0] == b'_aliasarg': sym = tree[1] return args[sym] return tuple(cls._expandargs(t, args) for t in tree) @classmethod def _expand(cls, aliases, tree, expanding, cache): if not isinstance(tree, tuple): return tree r = cls._getalias(aliases, tree) if r is None: return tuple( cls._expand(aliases, t, expanding, cache) for t in tree ) a, l = r if a.error: raise error.Abort(a.error) if a in expanding: raise error.ParseError( _(b'infinite expansion of %(section)s "%(name)s" detected') % {b'section': cls._section, b'name': a.name} ) # get cacheable replacement tree by expanding aliases recursively expanding.append(a) if a.name not in cache: cache[a.name] = cls._expand( aliases, a.replacement, expanding, cache ) result = cache[a.name] expanding.pop() if a.args is None: return result # substitute function arguments in replacement tree if len(l) != len(a.args): raise error.ParseError( _(b'invalid number of arguments: %d') % len(l) ) l = [cls._expand(aliases, t, [], cache) for t in l] return cls._expandargs(result, dict(zip(a.args, l))) @classmethod def expand(cls, aliases, tree): """Expand aliases in tree, recursively. 'aliases' is a dictionary mapping user defined aliases to alias objects. """ return cls._expand(aliases, tree, [], {})