Mercurial > public > mercurial-scm > hg-stable
view rust/hg-core/src/filepatterns.rs @ 45907:06b64fabf91c
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 | 26114bd6ec60 |
children | 777c3d231913 |
line wrap: on
line source
// filepatterns.rs // // Copyright 2019 Raphaël Gomès <rgomes@octobus.net> // // This software may be used and distributed according to the terms of the // GNU General Public License version 2 or any later version. //! Handling of Mercurial-specific patterns. use crate::{ utils::{ files::{canonical_path, get_bytes_from_path, get_path_from_bytes}, hg_path::{path_to_hg_path_buf, HgPathBuf, HgPathError}, SliceExt, }, FastHashMap, PatternError, }; use lazy_static::lazy_static; use regex::bytes::{NoExpand, Regex}; use std::fs::File; use std::io::Read; use std::ops::Deref; use std::path::{Path, PathBuf}; use std::vec::Vec; lazy_static! { static ref RE_ESCAPE: Vec<Vec<u8>> = { let mut v: Vec<Vec<u8>> = (0..=255).map(|byte| vec![byte]).collect(); let to_escape = b"()[]{}?*+-|^$\\.&~# \t\n\r\x0b\x0c"; for byte in to_escape { v[*byte as usize].insert(0, b'\\'); } v }; } /// These are matched in order const GLOB_REPLACEMENTS: &[(&[u8], &[u8])] = &[(b"*/", b"(?:.*/)?"), (b"*", b".*"), (b"", b"[^/]*")]; /// Appended to the regexp of globs const GLOB_SUFFIX: &[u8; 7] = b"(?:/|$)"; #[derive(Debug, Copy, Clone, PartialEq, Eq)] pub enum PatternSyntax { /// A regular expression Regexp, /// Glob that matches at the front of the path RootGlob, /// Glob that matches at any suffix of the path (still anchored at /// slashes) Glob, /// a path relative to repository root, which is matched recursively Path, /// A path relative to cwd RelPath, /// an unrooted glob (*.rs matches Rust files in all dirs) RelGlob, /// A regexp that needn't match the start of a name RelRegexp, /// A path relative to repository root, which is matched non-recursively /// (will not match subdirectories) RootFiles, /// A file of patterns to read and include Include, /// A file of patterns to match against files under the same directory SubInclude, } /// Transforms a glob pattern into a regex fn glob_to_re(pat: &[u8]) -> Vec<u8> { let mut input = pat; let mut res: Vec<u8> = vec![]; let mut group_depth = 0; while let Some((c, rest)) = input.split_first() { input = rest; match c { b'*' => { for (source, repl) in GLOB_REPLACEMENTS { if let Some(rest) = input.drop_prefix(source) { input = rest; res.extend(*repl); break; } } } b'?' => res.extend(b"."), b'[' => { match input.iter().skip(1).position(|b| *b == b']') { None => res.extend(b"\\["), Some(end) => { // Account for the one we skipped let end = end + 1; res.extend(b"["); for (i, b) in input[..end].iter().enumerate() { if *b == b'!' && i == 0 { res.extend(b"^") } else if *b == b'^' && i == 0 { res.extend(b"\\^") } else if *b == b'\\' { res.extend(b"\\\\") } else { res.push(*b) } } res.extend(b"]"); input = &input[end + 1..]; } } } b'{' => { group_depth += 1; res.extend(b"(?:") } b'}' if group_depth > 0 => { group_depth -= 1; res.extend(b")"); } b',' if group_depth > 0 => res.extend(b"|"), b'\\' => { let c = { if let Some((c, rest)) = input.split_first() { input = rest; c } else { c } }; res.extend(&RE_ESCAPE[*c as usize]) } _ => res.extend(&RE_ESCAPE[*c as usize]), } } res } fn escape_pattern(pattern: &[u8]) -> Vec<u8> { pattern .iter() .flat_map(|c| RE_ESCAPE[*c as usize].clone()) .collect() } pub fn parse_pattern_syntax( kind: &[u8], ) -> Result<PatternSyntax, PatternError> { match kind { b"re:" => Ok(PatternSyntax::Regexp), b"path:" => Ok(PatternSyntax::Path), b"relpath:" => Ok(PatternSyntax::RelPath), b"rootfilesin:" => Ok(PatternSyntax::RootFiles), b"relglob:" => Ok(PatternSyntax::RelGlob), b"relre:" => Ok(PatternSyntax::RelRegexp), b"glob:" => Ok(PatternSyntax::Glob), b"rootglob:" => Ok(PatternSyntax::RootGlob), b"include:" => Ok(PatternSyntax::Include), b"subinclude:" => Ok(PatternSyntax::SubInclude), _ => Err(PatternError::UnsupportedSyntax( String::from_utf8_lossy(kind).to_string(), )), } } /// Builds the regex that corresponds to the given pattern. /// If within a `syntax: regexp` context, returns the pattern, /// otherwise, returns the corresponding regex. fn _build_single_regex(entry: &IgnorePattern) -> Vec<u8> { let IgnorePattern { syntax, pattern, .. } = entry; if pattern.is_empty() { return vec![]; } match syntax { PatternSyntax::Regexp => pattern.to_owned(), PatternSyntax::RelRegexp => { // The `regex` crate accepts `**` while `re2` and Python's `re` // do not. Checking for `*` correctly triggers the same error all // engines. if pattern[0] == b'^' || pattern[0] == b'*' || pattern.starts_with(b".*") { return pattern.to_owned(); } [&b".*"[..], pattern].concat() } PatternSyntax::Path | PatternSyntax::RelPath => { if pattern == b"." { return vec![]; } [escape_pattern(pattern).as_slice(), b"(?:/|$)"].concat() } PatternSyntax::RootFiles => { let mut res = if pattern == b"." { vec![] } else { // Pattern is a directory name. [escape_pattern(pattern).as_slice(), b"/"].concat() }; // Anything after the pattern must be a non-directory. res.extend(b"[^/]+$"); res } PatternSyntax::RelGlob => { let glob_re = glob_to_re(pattern); if let Some(rest) = glob_re.drop_prefix(b"[^/]*") { [b".*", rest, GLOB_SUFFIX].concat() } else { [b"(?:.*/)?", glob_re.as_slice(), GLOB_SUFFIX].concat() } } PatternSyntax::Glob | PatternSyntax::RootGlob => { [glob_to_re(pattern).as_slice(), GLOB_SUFFIX].concat() } PatternSyntax::Include | PatternSyntax::SubInclude => unreachable!(), } } const GLOB_SPECIAL_CHARACTERS: [u8; 7] = [b'*', b'?', b'[', b']', b'{', b'}', b'\\']; /// TODO support other platforms #[cfg(unix)] pub fn normalize_path_bytes(bytes: &[u8]) -> Vec<u8> { if bytes.is_empty() { return b".".to_vec(); } let sep = b'/'; let mut initial_slashes = bytes.iter().take_while(|b| **b == sep).count(); if initial_slashes > 2 { // POSIX allows one or two initial slashes, but treats three or more // as single slash. initial_slashes = 1; } let components = bytes .split(|b| *b == sep) .filter(|c| !(c.is_empty() || c == b".")) .fold(vec![], |mut acc, component| { if component != b".." || (initial_slashes == 0 && acc.is_empty()) || (!acc.is_empty() && acc[acc.len() - 1] == b"..") { acc.push(component) } else if !acc.is_empty() { acc.pop(); } acc }); let mut new_bytes = components.join(&sep); if initial_slashes > 0 { let mut buf: Vec<_> = (0..initial_slashes).map(|_| sep).collect(); buf.extend(new_bytes); new_bytes = buf; } if new_bytes.is_empty() { b".".to_vec() } else { new_bytes } } /// Wrapper function to `_build_single_regex` that short-circuits 'exact' globs /// that don't need to be transformed into a regex. pub fn build_single_regex( entry: &IgnorePattern, ) -> Result<Option<Vec<u8>>, PatternError> { let IgnorePattern { pattern, syntax, .. } = entry; let pattern = match syntax { PatternSyntax::RootGlob | PatternSyntax::Path | PatternSyntax::RelGlob | PatternSyntax::RootFiles => normalize_path_bytes(&pattern), PatternSyntax::Include | PatternSyntax::SubInclude => { return Err(PatternError::NonRegexPattern(entry.clone())) } _ => pattern.to_owned(), }; if *syntax == PatternSyntax::RootGlob && !pattern.iter().any(|b| GLOB_SPECIAL_CHARACTERS.contains(b)) { Ok(None) } else { let mut entry = entry.clone(); entry.pattern = pattern; Ok(Some(_build_single_regex(&entry))) } } lazy_static! { static ref SYNTAXES: FastHashMap<&'static [u8], &'static [u8]> = { let mut m = FastHashMap::default(); m.insert(b"re".as_ref(), b"relre:".as_ref()); m.insert(b"regexp".as_ref(), b"relre:".as_ref()); m.insert(b"glob".as_ref(), b"relglob:".as_ref()); m.insert(b"rootglob".as_ref(), b"rootglob:".as_ref()); m.insert(b"include".as_ref(), b"include:".as_ref()); m.insert(b"subinclude".as_ref(), b"subinclude:".as_ref()); m }; } #[derive(Debug)] pub enum PatternFileWarning { /// (file path, syntax bytes) InvalidSyntax(PathBuf, Vec<u8>), /// File path NoSuchFile(PathBuf), } pub fn parse_pattern_file_contents<P: AsRef<Path>>( lines: &[u8], file_path: P, warn: bool, ) -> Result<(Vec<IgnorePattern>, Vec<PatternFileWarning>), PatternError> { let comment_regex = Regex::new(r"((?:^|[^\\])(?:\\\\)*)#.*").unwrap(); #[allow(clippy::trivial_regex)] let comment_escape_regex = Regex::new(r"\\#").unwrap(); let mut inputs: Vec<IgnorePattern> = vec![]; let mut warnings: Vec<PatternFileWarning> = vec![]; let mut current_syntax = b"relre:".as_ref(); for (line_number, mut line) in lines.split(|c| *c == b'\n').enumerate() { let line_number = line_number + 1; let line_buf; if line.contains(&b'#') { if let Some(cap) = comment_regex.captures(line) { line = &line[..cap.get(1).unwrap().end()] } line_buf = comment_escape_regex.replace_all(line, NoExpand(b"#")); line = &line_buf; } let mut line = line.trim_end(); if line.is_empty() { continue; } if let Some(syntax) = line.drop_prefix(b"syntax:") { let syntax = syntax.trim(); if let Some(rel_syntax) = SYNTAXES.get(syntax) { current_syntax = rel_syntax; } else if warn { warnings.push(PatternFileWarning::InvalidSyntax( file_path.as_ref().to_owned(), syntax.to_owned(), )); } continue; } let mut line_syntax: &[u8] = ¤t_syntax; for (s, rels) in SYNTAXES.iter() { if let Some(rest) = line.drop_prefix(rels) { line_syntax = rels; line = rest; break; } if let Some(rest) = line.drop_prefix(&[s, &b":"[..]].concat()) { line_syntax = rels; line = rest; break; } } inputs.push(IgnorePattern::new( parse_pattern_syntax(&line_syntax).map_err(|e| match e { PatternError::UnsupportedSyntax(syntax) => { PatternError::UnsupportedSyntaxInFile( syntax, file_path.as_ref().to_string_lossy().into(), line_number, ) } _ => e, })?, &line, &file_path, )); } Ok((inputs, warnings)) } pub fn read_pattern_file<P: AsRef<Path>>( file_path: P, warn: bool, ) -> Result<(Vec<IgnorePattern>, Vec<PatternFileWarning>), PatternError> { let mut f = match File::open(file_path.as_ref()) { Ok(f) => Ok(f), Err(e) => match e.kind() { std::io::ErrorKind::NotFound => { return Ok(( vec![], vec![PatternFileWarning::NoSuchFile( file_path.as_ref().to_owned(), )], )) } _ => Err(e), }, }?; let mut contents = Vec::new(); f.read_to_end(&mut contents)?; Ok(parse_pattern_file_contents(&contents, file_path, warn)?) } /// Represents an entry in an "ignore" file. #[derive(Debug, Eq, PartialEq, Clone)] pub struct IgnorePattern { pub syntax: PatternSyntax, pub pattern: Vec<u8>, pub source: PathBuf, } impl IgnorePattern { pub fn new( syntax: PatternSyntax, pattern: &[u8], source: impl AsRef<Path>, ) -> Self { Self { syntax, pattern: pattern.to_owned(), source: source.as_ref().to_owned(), } } } pub type PatternResult<T> = Result<T, PatternError>; /// Wrapper for `read_pattern_file` that also recursively expands `include:` /// patterns. /// /// `subinclude:` is not treated as a special pattern here: unraveling them /// needs to occur in the "ignore" phase. pub fn get_patterns_from_file( pattern_file: impl AsRef<Path>, root_dir: impl AsRef<Path>, ) -> PatternResult<(Vec<IgnorePattern>, Vec<PatternFileWarning>)> { let (patterns, mut warnings) = read_pattern_file(&pattern_file, true)?; let patterns = patterns .into_iter() .flat_map(|entry| -> PatternResult<_> { let IgnorePattern { syntax, pattern, .. } = &entry; Ok(match syntax { PatternSyntax::Include => { let inner_include = root_dir.as_ref().join(get_path_from_bytes(&pattern)); let (inner_pats, inner_warnings) = get_patterns_from_file( &inner_include, root_dir.as_ref(), )?; warnings.extend(inner_warnings); inner_pats } _ => vec![entry], }) }) .flatten() .collect(); Ok((patterns, warnings)) } /// Holds all the information needed to handle a `subinclude:` pattern. pub struct SubInclude { /// Will be used for repository (hg) paths that start with this prefix. /// It is relative to the current working directory, so comparing against /// repository paths is painless. pub prefix: HgPathBuf, /// The file itself, containing the patterns pub path: PathBuf, /// Folder in the filesystem where this it applies pub root: PathBuf, } impl SubInclude { pub fn new( root_dir: impl AsRef<Path>, pattern: &[u8], source: impl AsRef<Path>, ) -> Result<SubInclude, HgPathError> { let normalized_source = normalize_path_bytes(&get_bytes_from_path(source)); let source_root = get_path_from_bytes(&normalized_source); let source_root = source_root.parent().unwrap_or_else(|| source_root.deref()); let path = source_root.join(get_path_from_bytes(pattern)); let new_root = path.parent().unwrap_or_else(|| path.deref()); let prefix = canonical_path(&root_dir, &root_dir, new_root)?; Ok(Self { prefix: path_to_hg_path_buf(prefix).and_then(|mut p| { if !p.is_empty() { p.push(b'/'); } Ok(p) })?, path: path.to_owned(), root: new_root.to_owned(), }) } } /// Separate and pre-process subincludes from other patterns for the "ignore" /// phase. pub fn filter_subincludes( ignore_patterns: &[IgnorePattern], root_dir: impl AsRef<Path>, ) -> Result<(Vec<SubInclude>, Vec<&IgnorePattern>), HgPathError> { let mut subincludes = vec![]; let mut others = vec![]; for ignore_pattern in ignore_patterns.iter() { let IgnorePattern { syntax, pattern, source, } = ignore_pattern; if *syntax == PatternSyntax::SubInclude { subincludes.push(SubInclude::new(&root_dir, pattern, &source)?); } else { others.push(ignore_pattern) } } Ok((subincludes, others)) } #[cfg(test)] mod tests { use super::*; use pretty_assertions::assert_eq; #[test] fn escape_pattern_test() { let untouched = br#"!"%',/0123456789:;<=>@ABCDEFGHIJKLMNOPQRSTUVWXYZ_`abcdefghijklmnopqrstuvwxyz"#; assert_eq!(escape_pattern(untouched), untouched.to_vec()); // All escape codes assert_eq!( escape_pattern(br#"()[]{}?*+-|^$\\.&~# \t\n\r\v\f"#), br#"\(\)\[\]\{\}\?\*\+\-\|\^\$\\\\\.\&\~\#\ \\t\\n\\r\\v\\f"# .to_vec() ); } #[test] fn glob_test() { assert_eq!(glob_to_re(br#"?"#), br#"."#); assert_eq!(glob_to_re(br#"*"#), br#"[^/]*"#); assert_eq!(glob_to_re(br#"**"#), br#".*"#); assert_eq!(glob_to_re(br#"**/a"#), br#"(?:.*/)?a"#); assert_eq!(glob_to_re(br#"a/**/b"#), br#"a/(?:.*/)?b"#); assert_eq!(glob_to_re(br#"[a*?!^][^b][!c]"#), br#"[a*?!^][\^b][^c]"#); assert_eq!(glob_to_re(br#"{a,b}"#), br#"(?:a|b)"#); assert_eq!(glob_to_re(br#".\*\?"#), br#"\.\*\?"#); } #[test] fn test_parse_pattern_file_contents() { let lines = b"syntax: glob\n*.elc"; assert_eq!( parse_pattern_file_contents(lines, Path::new("file_path"), false) .unwrap() .0, vec![IgnorePattern::new( PatternSyntax::RelGlob, b"*.elc", Path::new("file_path") )], ); let lines = b"syntax: include\nsyntax: glob"; assert_eq!( parse_pattern_file_contents(lines, Path::new("file_path"), false) .unwrap() .0, vec![] ); let lines = b"glob:**.o"; assert_eq!( parse_pattern_file_contents(lines, Path::new("file_path"), false) .unwrap() .0, vec![IgnorePattern::new( PatternSyntax::RelGlob, b"**.o", Path::new("file_path") )] ); } #[test] fn test_build_single_regex() { assert_eq!( build_single_regex(&IgnorePattern::new( PatternSyntax::RelGlob, b"rust/target/", Path::new("") )) .unwrap(), Some(br"(?:.*/)?rust/target(?:/|$)".to_vec()), ); assert_eq!( build_single_regex(&IgnorePattern::new( PatternSyntax::Regexp, br"rust/target/\d+", Path::new("") )) .unwrap(), Some(br"rust/target/\d+".to_vec()), ); } #[test] fn test_build_single_regex_shortcut() { assert_eq!( build_single_regex(&IgnorePattern::new( PatternSyntax::RootGlob, b"", Path::new("") )) .unwrap(), None, ); assert_eq!( build_single_regex(&IgnorePattern::new( PatternSyntax::RootGlob, b"whatever", Path::new("") )) .unwrap(), None, ); assert_eq!( build_single_regex(&IgnorePattern::new( PatternSyntax::RootGlob, b"*.o", Path::new("") )) .unwrap(), Some(br"[^/]*\.o(?:/|$)".to_vec()), ); } }