hgext/extdiff.py

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

# extdiff.py - external diff program support for mercurial
#
# Copyright 2006 Vadim Gelfer <[e-mail]>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

'''command to allow external programs to compare revisions

The extdiff Mercurial extension allows you to use external programs
to compare revisions, or revision with working directory. The external
diff programs are called with a configurable set of options and two
non-option arguments: paths to directories containing snapshots of
files to compare.

If there is more than one file being compared and the "child" revision
is the working directory, any modifications made in the external diff
program will be copied back to the working directory from the temporary
directory.

The extdiff extension also allows you to configure new diff commands, so
you do not need to type :hg:`extdiff -p kdiff3` always. ::

  [extdiff]
  # add new command that runs GNU diff(1) in 'context diff' mode
  cdiff = gdiff -Nprc5
  ## or the old way:
  #cmd.cdiff = gdiff
  #opts.cdiff = -Nprc5

  # add new command called meld, runs meld (no need to name twice).  If
  # the meld executable is not available, the meld tool in [merge-tools]
  # will be used, if available
  meld =

  # add new command called vimdiff, runs gvimdiff with DirDiff plugin
  # (see http://www.vim.org/scripts/script.php?script_id=102) Non
  # English user, be sure to put "let g:DirDiffDynamicDiffText = 1" in
  # your .vimrc
  vimdiff = gvim -f "+next" \\
            "+execute 'DirDiff' fnameescape(argv(0)) fnameescape(argv(1))"

Tool arguments can include variables that are expanded at runtime::

  $parent1, $plabel1 - filename, descriptive label of first parent
  $child,   $clabel  - filename, descriptive label of child revision
  $parent2, $plabel2 - filename, descriptive label of second parent
  $root              - repository root
  $parent is an alias for $parent1.

The extdiff extension will look in your [diff-tools] and [merge-tools]
sections for diff tool arguments, when none are specified in [extdiff].

::

  [extdiff]
  kdiff3 =

  [diff-tools]
  kdiff3.diffargs=--L1 '$plabel1' --L2 '$clabel' $parent $child

If a program has a graphical interface, it might be interesting to tell
Mercurial about it. It will prevent the program from being mistakenly
used in a terminal-only environment (such as an SSH terminal session),
and will make :hg:`extdiff --per-file` open multiple file diffs at once
instead of one by one (if you still want to open file diffs one by one,
you can use the --confirm option).

Declaring that a tool has a graphical interface can be done with the
``gui`` flag next to where ``diffargs`` are specified:

::

  [diff-tools]
  kdiff3.diffargs=--L1 '$plabel1' --L2 '$clabel' $parent $child
  kdiff3.gui = true

You can use -I/-X and list of file or directory names like normal
:hg:`diff` command. The extdiff extension makes snapshots of only
needed files, so running the external diff program will actually be
pretty fast (at least faster than having to compare the entire tree).
'''

from __future__ import absolute_import

import os
import re
import shutil
import stat
import subprocess

from mercurial.i18n import _
from mercurial.node import (
    nullid,
    short,
)
from mercurial import (
    archival,
    cmdutil,
    encoding,
    error,
    filemerge,
    formatter,
    pycompat,
    registrar,
    scmutil,
    util,
)
from mercurial.utils import (
    procutil,
    stringutil,
)

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

configtable = {}
configitem = registrar.configitem(configtable)

configitem(
    b'extdiff', br'opts\..*', default=b'', generic=True,
)

configitem(
    b'extdiff', br'gui\..*', generic=True,
)

configitem(
    b'diff-tools', br'.*\.diffargs$', default=None, generic=True,
)

configitem(
    b'diff-tools', br'.*\.gui$', generic=True,
)

# 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'


def snapshot(ui, repo, files, node, tmproot, listsubrepos):
    '''snapshot files as of some revision
    if not using snapshot, -I/-X does not work and recursive diff
    in tools like kdiff3 and meld displays too many files.'''
    dirname = os.path.basename(repo.root)
    if dirname == b"":
        dirname = b"root"
    if node is not None:
        dirname = b'%s.%s' % (dirname, short(node))
    base = os.path.join(tmproot, dirname)
    os.mkdir(base)
    fnsandstat = []

    if node is not None:
        ui.note(
            _(b'making snapshot of %d files from rev %s\n')
            % (len(files), short(node))
        )
    else:
        ui.note(
            _(b'making snapshot of %d files from working directory\n')
            % (len(files))
        )

    if files:
        repo.ui.setconfig(b"ui", b"archivemeta", False)

        archival.archive(
            repo,
            base,
            node,
            b'files',
            match=scmutil.matchfiles(repo, files),
            subrepos=listsubrepos,
        )

        for fn in sorted(files):
            wfn = util.pconvert(fn)
            ui.note(b'  %s\n' % wfn)

            if node is None:
                dest = os.path.join(base, wfn)

                fnsandstat.append((dest, repo.wjoin(fn), os.lstat(dest)))
    return dirname, fnsandstat


def formatcmdline(
    cmdline,
    repo_root,
    do3way,
    parent1,
    plabel1,
    parent2,
    plabel2,
    child,
    clabel,
):
    # Function to quote file/dir names in the argument string.
    # When not operating in 3-way mode, an empty string is
    # returned for parent2
    replace = {
        b'parent': parent1,
        b'parent1': parent1,
        b'parent2': parent2,
        b'plabel1': plabel1,
        b'plabel2': plabel2,
        b'child': child,
        b'clabel': clabel,
        b'root': repo_root,
    }

    def quote(match):
        pre = match.group(2)
        key = match.group(3)
        if not do3way and key == b'parent2':
            return pre
        return pre + procutil.shellquote(replace[key])

    # Match parent2 first, so 'parent1?' will match both parent1 and parent
    regex = (
        br'''(['"]?)([^\s'"$]*)'''
        br'\$(parent2|parent1?|child|plabel1|plabel2|clabel|root)\1'
    )
    if not do3way and not re.search(regex, cmdline):
        cmdline += b' $parent1 $child'
    return re.sub(regex, quote, cmdline)


def _systembackground(cmd, environ=None, cwd=None):
    ''' like 'procutil.system', but returns the Popen object directly
        so we don't have to wait on it.
    '''
    env = procutil.shellenviron(environ)
    proc = subprocess.Popen(
        procutil.tonativestr(cmd),
        shell=True,
        close_fds=procutil.closefds,
        env=procutil.tonativeenv(env),
        cwd=pycompat.rapply(procutil.tonativestr, cwd),
    )
    return proc


def _runperfilediff(
    cmdline,
    repo_root,
    ui,
    guitool,
    do3way,
    confirm,
    commonfiles,
    tmproot,
    dir1a,
    dir1b,
    dir2,
    rev1a,
    rev1b,
    rev2,
):
    # Note that we need to sort the list of files because it was
    # built in an "unstable" way and it's annoying to get files in a
    # random order, especially when "confirm" mode is enabled.
    waitprocs = []
    totalfiles = len(commonfiles)
    for idx, commonfile in enumerate(sorted(commonfiles)):
        path1a = os.path.join(dir1a, commonfile)
        label1a = commonfile + rev1a
        if not os.path.isfile(path1a):
            path1a = pycompat.osdevnull

        path1b = b''
        label1b = b''
        if do3way:
            path1b = os.path.join(dir1b, commonfile)
            label1b = commonfile + rev1b
            if not os.path.isfile(path1b):
                path1b = pycompat.osdevnull

        path2 = os.path.join(dir2, commonfile)
        label2 = commonfile + rev2

        if confirm:
            # Prompt before showing this diff
            difffiles = _(b'diff %s (%d of %d)') % (
                commonfile,
                idx + 1,
                totalfiles,
            )
            responses = _(
                b'[Yns?]'
                b'$$ &Yes, show diff'
                b'$$ &No, skip this diff'
                b'$$ &Skip remaining diffs'
                b'$$ &? (display help)'
            )
            r = ui.promptchoice(b'%s %s' % (difffiles, responses))
            if r == 3:  # ?
                while r == 3:
                    for c, t in ui.extractchoices(responses)[1]:
                        ui.write(b'%s - %s\n' % (c, encoding.lower(t)))
                    r = ui.promptchoice(b'%s %s' % (difffiles, responses))
            if r == 0:  # yes
                pass
            elif r == 1:  # no
                continue
            elif r == 2:  # skip
                break

        curcmdline = formatcmdline(
            cmdline,
            repo_root,
            do3way=do3way,
            parent1=path1a,
            plabel1=label1a,
            parent2=path1b,
            plabel2=label1b,
            child=path2,
            clabel=label2,
        )

        if confirm or not guitool:
            # Run the comparison program and wait for it to exit
            # before we show the next file.
            # This is because either we need to wait for confirmation
            # from the user between each invocation, or because, as far
            # as we know, the tool doesn't have a GUI, in which case
            # we can't run multiple CLI programs at the same time.
            ui.debug(
                b'running %r in %s\n' % (pycompat.bytestr(curcmdline), tmproot)
            )
            ui.system(curcmdline, cwd=tmproot, blockedtag=b'extdiff')
        else:
            # Run the comparison program but don't wait, as we're
            # going to rapid-fire each file diff and then wait on
            # the whole group.
            ui.debug(
                b'running %r in %s (backgrounded)\n'
                % (pycompat.bytestr(curcmdline), tmproot)
            )
            proc = _systembackground(curcmdline, cwd=tmproot)
            waitprocs.append(proc)

    if waitprocs:
        with ui.timeblockedsection(b'extdiff'):
            for proc in waitprocs:
                proc.wait()


def diffpatch(ui, repo, node1, node2, tmproot, matcher, cmdline):
    template = b'hg-%h.patch'
    # write patches to temporary files
    with formatter.nullformatter(ui, b'extdiff', {}) as fm:
        cmdutil.export(
            repo,
            [repo[node1].rev(), repo[node2].rev()],
            fm,
            fntemplate=repo.vfs.reljoin(tmproot, template),
            match=matcher,
        )
    label1 = cmdutil.makefilename(repo[node1], template)
    label2 = cmdutil.makefilename(repo[node2], template)
    file1 = repo.vfs.reljoin(tmproot, label1)
    file2 = repo.vfs.reljoin(tmproot, label2)
    cmdline = formatcmdline(
        cmdline,
        repo.root,
        # no 3way while comparing patches
        do3way=False,
        parent1=file1,
        plabel1=label1,
        # while comparing patches, there is no second parent
        parent2=None,
        plabel2=None,
        child=file2,
        clabel=label2,
    )
    ui.debug(b'running %r in %s\n' % (pycompat.bytestr(cmdline), tmproot))
    ui.system(cmdline, cwd=tmproot, blockedtag=b'extdiff')
    return 1


def diffrevs(
    ui,
    repo,
    node1a,
    node1b,
    node2,
    matcher,
    tmproot,
    cmdline,
    do3way,
    guitool,
    opts,
):

    subrepos = opts.get(b'subrepos')

    # calculate list of files changed between both revs
    st = repo.status(node1a, node2, matcher, listsubrepos=subrepos)
    mod_a, add_a, rem_a = set(st.modified), set(st.added), set(st.removed)
    if do3way:
        stb = repo.status(node1b, node2, matcher, listsubrepos=subrepos)
        mod_b, add_b, rem_b = (
            set(stb.modified),
            set(stb.added),
            set(stb.removed),
        )
    else:
        mod_b, add_b, rem_b = set(), set(), set()
    modadd = mod_a | add_a | mod_b | add_b
    common = modadd | rem_a | rem_b
    if not common:
        return 0

    # Always make a copy of node1a (and node1b, if applicable)
    # dir1a should contain files which are:
    #   * modified or removed from node1a to node2
    #   * modified or added from node1b to node2
    #     (except file added from node1a to node2 as they were not present in
    #     node1a)
    dir1a_files = mod_a | rem_a | ((mod_b | add_b) - add_a)
    dir1a = snapshot(ui, repo, dir1a_files, node1a, tmproot, subrepos)[0]
    rev1a = b'@%d' % repo[node1a].rev()
    if do3way:
        # file calculation criteria same as dir1a
        dir1b_files = mod_b | rem_b | ((mod_a | add_a) - add_b)
        dir1b = snapshot(ui, repo, dir1b_files, node1b, tmproot, subrepos)[0]
        rev1b = b'@%d' % repo[node1b].rev()
    else:
        dir1b = None
        rev1b = b''

    fnsandstat = []

    # If node2 in not the wc or there is >1 change, copy it
    dir2root = b''
    rev2 = b''
    if node2:
        dir2 = snapshot(ui, repo, modadd, node2, tmproot, subrepos)[0]
        rev2 = b'@%d' % repo[node2].rev()
    elif len(common) > 1:
        # we only actually need to get the files to copy back to
        # the working dir in this case (because the other cases
        # are: diffing 2 revisions or single file -- in which case
        # the file is already directly passed to the diff tool).
        dir2, fnsandstat = snapshot(ui, repo, modadd, None, tmproot, subrepos)
    else:
        # This lets the diff tool open the changed file directly
        dir2 = b''
        dir2root = repo.root

    label1a = rev1a
    label1b = rev1b
    label2 = rev2

    if not opts.get(b'per_file'):
        # If only one change, diff the files instead of the directories
        # Handle bogus modifies correctly by checking if the files exist
        if len(common) == 1:
            common_file = util.localpath(common.pop())
            dir1a = os.path.join(tmproot, dir1a, common_file)
            label1a = common_file + rev1a
            if not os.path.isfile(dir1a):
                dir1a = pycompat.osdevnull
            if do3way:
                dir1b = os.path.join(tmproot, dir1b, common_file)
                label1b = common_file + rev1b
                if not os.path.isfile(dir1b):
                    dir1b = pycompat.osdevnull
            dir2 = os.path.join(dir2root, dir2, common_file)
            label2 = common_file + rev2

        # Run the external tool on the 2 temp directories or the patches
        cmdline = formatcmdline(
            cmdline,
            repo.root,
            do3way=do3way,
            parent1=dir1a,
            plabel1=label1a,
            parent2=dir1b,
            plabel2=label1b,
            child=dir2,
            clabel=label2,
        )
        ui.debug(b'running %r in %s\n' % (pycompat.bytestr(cmdline), tmproot))
        ui.system(cmdline, cwd=tmproot, blockedtag=b'extdiff')
    else:
        # Run the external tool once for each pair of files
        _runperfilediff(
            cmdline,
            repo.root,
            ui,
            guitool=guitool,
            do3way=do3way,
            confirm=opts.get(b'confirm'),
            commonfiles=common,
            tmproot=tmproot,
            dir1a=os.path.join(tmproot, dir1a),
            dir1b=os.path.join(tmproot, dir1b) if do3way else None,
            dir2=os.path.join(dir2root, dir2),
            rev1a=rev1a,
            rev1b=rev1b,
            rev2=rev2,
        )

    for copy_fn, working_fn, st in fnsandstat:
        cpstat = os.lstat(copy_fn)
        # Some tools copy the file and attributes, so mtime may not detect
        # all changes.  A size check will detect more cases, but not all.
        # The only certain way to detect every case is to diff all files,
        # which could be expensive.
        # copyfile() carries over the permission, so the mode check could
        # be in an 'elif' branch, but for the case where the file has
        # changed without affecting mtime or size.
        if (
            cpstat[stat.ST_MTIME] != st[stat.ST_MTIME]
            or cpstat.st_size != st.st_size
            or (cpstat.st_mode & 0o100) != (st.st_mode & 0o100)
        ):
            ui.debug(
                b'file changed while diffing. '
                b'Overwriting: %s (src: %s)\n' % (working_fn, copy_fn)
            )
            util.copyfile(copy_fn, working_fn)

    return 1


def dodiff(ui, repo, cmdline, pats, opts, guitool=False):
    '''Do the actual diff:

    - copy to a temp structure if diffing 2 internal revisions
    - copy to a temp structure if diffing working revision with
      another one and more than 1 file is changed
    - just invoke the diff for a single file in the working dir
    '''

    cmdutil.check_at_most_one_arg(opts, b'rev', b'change')
    revs = opts.get(b'rev')
    change = opts.get(b'change')
    do3way = b'$parent2' in cmdline

    if change:
        ctx2 = scmutil.revsingle(repo, change, None)
        ctx1a, ctx1b = ctx2.p1(), ctx2.p2()
    else:
        ctx1a, ctx2 = scmutil.revpair(repo, revs)
        if not revs:
            ctx1b = repo[None].p2()
        else:
            ctx1b = repo[nullid]

    node1a = ctx1a.node()
    node1b = ctx1b.node()
    node2 = ctx2.node()

    # Disable 3-way merge if there is only one parent
    if do3way:
        if node1b == nullid:
            do3way = False

    matcher = scmutil.match(repo[node2], pats, opts)

    if opts.get(b'patch'):
        if opts.get(b'subrepos'):
            raise error.Abort(_(b'--patch cannot be used with --subrepos'))
        if opts.get(b'per_file'):
            raise error.Abort(_(b'--patch cannot be used with --per-file'))
        if node2 is None:
            raise error.Abort(_(b'--patch requires two revisions'))

    tmproot = pycompat.mkdtemp(prefix=b'extdiff.')
    try:
        if opts.get(b'patch'):
            return diffpatch(ui, repo, node1a, node2, tmproot, matcher, cmdline)

        return diffrevs(
            ui,
            repo,
            node1a,
            node1b,
            node2,
            matcher,
            tmproot,
            cmdline,
            do3way,
            guitool,
            opts,
        )

    finally:
        ui.note(_(b'cleaning up temp directory\n'))
        shutil.rmtree(tmproot)


extdiffopts = (
    [
        (
            b'o',
            b'option',
            [],
            _(b'pass option to comparison program'),
            _(b'OPT'),
        ),
        (b'r', b'rev', [], _(b'revision'), _(b'REV')),
        (b'c', b'change', b'', _(b'change made by revision'), _(b'REV')),
        (
            b'',
            b'per-file',
            False,
            _(b'compare each file instead of revision snapshots'),
        ),
        (
            b'',
            b'confirm',
            False,
            _(b'prompt user before each external program invocation'),
        ),
        (b'', b'patch', None, _(b'compare patches for two revisions')),
    ]
    + cmdutil.walkopts
    + cmdutil.subrepoopts
)


@command(
    b'extdiff',
    [(b'p', b'program', b'', _(b'comparison program to run'), _(b'CMD')),]
    + extdiffopts,
    _(b'hg extdiff [OPT]... [FILE]...'),
    helpcategory=command.CATEGORY_FILE_CONTENTS,
    inferrepo=True,
)
def extdiff(ui, repo, *pats, **opts):
    '''use external program to diff repository (or selected files)

    Show differences between revisions for the specified files, using
    an external program. The default program used is diff, with
    default options "-Npru".

    To select a different program, use the -p/--program option. The
    program will be passed the names of two directories to compare,
    unless the --per-file option is specified (see below). To pass
    additional options to the program, use -o/--option. These will be
    passed before the names of the directories or files to compare.

    When two revision arguments are given, then changes are shown
    between those revisions. If only one revision is specified then
    that revision is compared to the working directory, and, when no
    revisions are specified, the working directory files are compared
    to its parent.

    The --per-file option runs the external program repeatedly on each
    file to diff, instead of once on two directories. By default,
    this happens one by one, where the next file diff is open in the
    external program only once the previous external program (for the
    previous file diff) has exited. If the external program has a
    graphical interface, it can open all the file diffs at once instead
    of one by one. See :hg:`help -e extdiff` for information about how
    to tell Mercurial that a given program has a graphical interface.

    The --confirm option will prompt the user before each invocation of
    the external program. It is ignored if --per-file isn't specified.
    '''
    opts = pycompat.byteskwargs(opts)
    program = opts.get(b'program')
    option = opts.get(b'option')
    if not program:
        program = b'diff'
        option = option or [b'-Npru']
    cmdline = b' '.join(map(procutil.shellquote, [program] + option))
    return dodiff(ui, repo, cmdline, pats, opts)


class savedcmd(object):
    """use external program to diff repository (or selected files)

    Show differences between revisions for the specified files, using
    the following program::

        %(path)s

    When two revision arguments are given, then changes are shown
    between those revisions. If only one revision is specified then
    that revision is compared to the working directory, and, when no
    revisions are specified, the working directory files are compared
    to its parent.
    """

    def __init__(self, path, cmdline, isgui):
        # We can't pass non-ASCII through docstrings (and path is
        # in an unknown encoding anyway), but avoid double separators on
        # Windows
        docpath = stringutil.escapestr(path).replace(b'\\\\', b'\\')
        self.__doc__ %= {'path': pycompat.sysstr(stringutil.uirepr(docpath))}
        self._cmdline = cmdline
        self._isgui = isgui

    def __call__(self, ui, repo, *pats, **opts):
        opts = pycompat.byteskwargs(opts)
        options = b' '.join(map(procutil.shellquote, opts[b'option']))
        if options:
            options = b' ' + options
        return dodiff(
            ui, repo, self._cmdline + options, pats, opts, guitool=self._isgui
        )


def _gettooldetails(ui, cmd, path):
    """
    returns following things for a
    ```
    [extdiff]
    <cmd> = <path>
    ```
    entry:

    cmd: command/tool name
    path: path to the tool
    cmdline: the command which should be run
    isgui: whether the tool uses GUI or not

    Reads all external tools related configs, whether it be extdiff section,
    diff-tools or merge-tools section, or its specified in an old format or
    the latest format.
    """
    path = util.expandpath(path)
    if cmd.startswith(b'cmd.'):
        cmd = cmd[4:]
        if not path:
            path = procutil.findexe(cmd)
            if path is None:
                path = filemerge.findexternaltool(ui, cmd) or cmd
        diffopts = ui.config(b'extdiff', b'opts.' + cmd)
        cmdline = procutil.shellquote(path)
        if diffopts:
            cmdline += b' ' + diffopts
        isgui = ui.configbool(b'extdiff', b'gui.' + cmd)
    else:
        if path:
            # case "cmd = path opts"
            cmdline = path
            diffopts = len(pycompat.shlexsplit(cmdline)) > 1
        else:
            # case "cmd ="
            path = procutil.findexe(cmd)
            if path is None:
                path = filemerge.findexternaltool(ui, cmd) or cmd
            cmdline = procutil.shellquote(path)
            diffopts = False
        isgui = ui.configbool(b'extdiff', b'gui.' + cmd)
    # look for diff arguments in [diff-tools] then [merge-tools]
    if not diffopts:
        key = cmd + b'.diffargs'
        for section in (b'diff-tools', b'merge-tools'):
            args = ui.config(section, key)
            if args:
                cmdline += b' ' + args
                if isgui is None:
                    isgui = ui.configbool(section, cmd + b'.gui') or False
                break
    return cmd, path, cmdline, isgui


def uisetup(ui):
    for cmd, path in ui.configitems(b'extdiff'):
        if cmd.startswith(b'opts.') or cmd.startswith(b'gui.'):
            continue
        cmd, path, cmdline, isgui = _gettooldetails(ui, cmd, path)
        command(
            cmd,
            extdiffopts[:],
            _(b'hg %s [OPTION]... [FILE]...') % cmd,
            helpcategory=command.CATEGORY_FILE_CONTENTS,
            inferrepo=True,
        )(savedcmd(path, cmdline, isgui))


# tell hggettext to extract docstrings from these functions:
i18nfunctions = [savedcmd]