tests/test-diff-binary-file.t
author Pierre-Yves David <pierre-yves.david@octobus.net>
Fri, 05 Apr 2024 11:05:54 +0200
changeset 51576 de5bf3fe0233
parent 39707 5abc47d4ca6b
permissions -rw-r--r--
revset: stop serializing node when using "%ln" Turning hundred of thousand of node from node to hex and back can be slow… what about we stop doing it? In many case were we are using node id we should be using revision id. However this is not a good reason to have a stupidly slow implementation of "%ln". This caught my attention again because the phase discovery during push make an extensive use of "%ln" or huge set. In absolute, that phase discovery probably should use "%ld" and need to improves its algorithmic complexity, but improving "%ln" seems simple and long overdue. This greatly speeds up `hg push` on repository with many drafts. Here are some relevant poulpe benchmarks: ### data-env-vars.name = mozilla-try-2023-03-22-zstd-sparse-revlog # benchmark.name = hg.command.push # bin-env-vars.hg.flavor = default # bin-env-vars.hg.py-re2-module = default # benchmark.variants.explicit-rev = all-out-heads # benchmark.variants.issue6528 = disabled # benchmark.variants.protocol = ssh # benchmark.variants.reuse-external-delta-parent = default ## benchmark.variants.revs = any-1-extra-rev before: 44.235070 after: 20.416329 (-53.85%, -23.82) ## benchmark.variants.revs = any-100-extra-rev before: 49.234697 after: 26.519829 (-46.14%, -22.71) ### benchmark.name = hg.command.bundle # bin-env-vars.hg.flavor = default # bin-env-vars.hg.py-re2-module = default # benchmark.variants.revs = all # benchmark.variants.type = none-streamv2 ## data-env-vars.name = heptapod-public-2024-03-25-zstd-sparse-revlog before: 10.138396 after: 7.750458 (-23.55%, -2.39) ## data-env-vars.name = mercurial-public-2024-03-22-zstd-sparse-revlog before: 1.263859 after: 0.700229 (-44.60%, -0.56) ## data-env-vars.name = mozilla-try-2023-03-22-zstd-sparse-revlog before: 399.484481 after: 346.5089 (-13.26%, -52.98) ## data-env-vars.name = pypy-2024-03-22-zstd-sparse-revlog before: 4.540080 after: 3.401700 (-25.07%, -1.14) ## data-env-vars.name = tryton-public-2024-03-22-zstd-sparse-revlog before: 2.975765 after: 1.870798 (-37.13%, -1.10)

  $ hg init a
  $ cd a
  $ cp "$TESTDIR/binfile.bin" .
  $ hg add binfile.bin
  $ hg ci -m 'add binfile.bin'

  $ echo >> binfile.bin
  $ hg ci -m 'change binfile.bin'

  $ hg revert -r 0 binfile.bin
  $ hg ci -m 'revert binfile.bin'
  $ hg cp binfile.bin nonbinfile
  $ echo text > nonbinfile
  $ hg ci -m 'make non-binary copy of binary file'

  $ hg diff --nodates -r 0 -r 1
  diff -r 48b371597640 -r acea2ab458c8 binfile.bin
  Binary file binfile.bin has changed

  $ hg diff --nodates -r 0 -r 2

  $ hg diff --git -r 0 -r 1
  diff --git a/binfile.bin b/binfile.bin
  index 37ba3d1c6f17137d9c5f5776fa040caf5fe73ff9..58dc31a9e2f40f74ff3b45903f7d620b8e5b7356
  GIT binary patch
  literal 594
  zc$@)J0<HatP)<h;3K|Lk000e1NJLTq000mG000mO0ssI2kdbIM00009a7bBm000XU
  z000XU0RWnu7ytkO2XskIMF-Uh9TW;VpMjwv0005-Nkl<ZD9@FWPs=e;7{<>W$NUkd
  zX$nnYLt$-$V!?uy+1V%`z&Eh=ah|duER<4|QWhju3gb^nF*8iYobxWG-qqXl=2~5M
  z*IoDB)sG^CfNuoBmqLTVU^<;@nwHP!1wrWd`{(mHo6VNXWtyh{alzqmsH*yYzpvLT
  zLdY<T=ks|woh-`&01!ej#(xbV1f|pI*=%;d-%F*E*X#ZH`4I%6SS+$EJDE&ct=8po
  ziN#{?_j|kD%Cd|oiqds`xm@;oJ-^?NG3Gdqrs?5u*zI;{nogxsx~^|Fn^Y?Gdc6<;
  zfMJ+iF1J`LMx&A2?dEwNW8ClebzPTbIh{@$hS6*`kH@1d%Lo7fA#}N1)oN7`gm$~V
  z+wDx#)OFqMcE{s!JN0-xhG8ItAjVkJwEcb`3WWlJfU2r?;Pd%dmR+q@mSri5q9_W-
  zaR2~ECX?B2w+zELozC0s*6Z~|QG^f{3I#<`?)Q7U-JZ|q5W;9Q8i_=pBuSzunx=U;
  z9C)5jBoYw9^?EHyQl(M}1OlQcCX>lXB*ODN003Z&P17_@)3Pi=i0wb04<W?v-u}7K
  zXmmQA+wDgE!qR9o8jr`%=ab_&uh(l?R=r;Tjiqon91I2-hIu?57~@*4h7h9uORK#=
  gQItJW-{SoTm)8|5##k|m00000NkvXXu0mjf3JwksH2?qr
  

  $ hg diff --git -r 0 -r 2

  $ hg diff --config diff.nobinary=True --git -r 0 -r 1
  diff --git a/binfile.bin b/binfile.bin
  Binary file binfile.bin has changed

  $ HGPLAIN=1 hg diff --config diff.nobinary=True --git -r 0 -r 1
  diff --git a/binfile.bin b/binfile.bin
  index 37ba3d1c6f17137d9c5f5776fa040caf5fe73ff9..58dc31a9e2f40f74ff3b45903f7d620b8e5b7356
  GIT binary patch
  literal 594
  zc$@)J0<HatP)<h;3K|Lk000e1NJLTq000mG000mO0ssI2kdbIM00009a7bBm000XU
  z000XU0RWnu7ytkO2XskIMF-Uh9TW;VpMjwv0005-Nkl<ZD9@FWPs=e;7{<>W$NUkd
  zX$nnYLt$-$V!?uy+1V%`z&Eh=ah|duER<4|QWhju3gb^nF*8iYobxWG-qqXl=2~5M
  z*IoDB)sG^CfNuoBmqLTVU^<;@nwHP!1wrWd`{(mHo6VNXWtyh{alzqmsH*yYzpvLT
  zLdY<T=ks|woh-`&01!ej#(xbV1f|pI*=%;d-%F*E*X#ZH`4I%6SS+$EJDE&ct=8po
  ziN#{?_j|kD%Cd|oiqds`xm@;oJ-^?NG3Gdqrs?5u*zI;{nogxsx~^|Fn^Y?Gdc6<;
  zfMJ+iF1J`LMx&A2?dEwNW8ClebzPTbIh{@$hS6*`kH@1d%Lo7fA#}N1)oN7`gm$~V
  z+wDx#)OFqMcE{s!JN0-xhG8ItAjVkJwEcb`3WWlJfU2r?;Pd%dmR+q@mSri5q9_W-
  zaR2~ECX?B2w+zELozC0s*6Z~|QG^f{3I#<`?)Q7U-JZ|q5W;9Q8i_=pBuSzunx=U;
  z9C)5jBoYw9^?EHyQl(M}1OlQcCX>lXB*ODN003Z&P17_@)3Pi=i0wb04<W?v-u}7K
  zXmmQA+wDgE!qR9o8jr`%=ab_&uh(l?R=r;Tjiqon91I2-hIu?57~@*4h7h9uORK#=
  gQItJW-{SoTm)8|5##k|m00000NkvXXu0mjf3JwksH2?qr
  


  $ hg diff --git -r 2 -r 3
  diff --git a/binfile.bin b/nonbinfile
  copy from binfile.bin
  copy to nonbinfile
  index 37ba3d1c6f17137d9c5f5776fa040caf5fe73ff9..8e27be7d6154a1f68ea9160ef0e18691d20560dc
  GIT binary patch
  literal 5
  Mc$_OqttjCF00uV!&;S4c
  
  $ cd ..

Test text mode with extended git-style diff format
  $ hg init b
  $ cd b
  $ cat > writebin.py <<EOF
  > import sys
  > path = sys.argv[1]
  > open(path, 'wb').write(b'\x00\x01\x02\x03')
  > EOF
  $ "$PYTHON" writebin.py binfile.bin
  $ hg add binfile.bin
  $ hg ci -m 'add binfile.bin'

  $ echo >> binfile.bin
  $ hg ci -m 'change binfile.bin'

  $ hg diff --git -a -r 0 -r 1
  diff --git a/binfile.bin b/binfile.bin
  --- a/binfile.bin
  +++ b/binfile.bin
  @@ -1,1 +1,1 @@
  -\x00\x01\x02\x03 (esc)
  \ No newline at end of file
  +\x00\x01\x02\x03 (esc)

  $ HGPLAIN=1 hg diff --git -a -r 0 -r 1
  diff --git a/binfile.bin b/binfile.bin
  --- a/binfile.bin
  +++ b/binfile.bin
  @@ -1,1 +1,1 @@
  -\x00\x01\x02\x03 (esc)
  \ No newline at end of file
  +\x00\x01\x02\x03 (esc)

Test binary mode with extended git-style diff format
  $ hg diff --no-binary -r 0 -r 1
  diff -r fb45f71337ad -r 9ca112d1a3c1 binfile.bin
  Binary file binfile.bin has changed

  $ hg diff --git --no-binary -r 0 -r 1
  diff --git a/binfile.bin b/binfile.bin
  Binary file binfile.bin has changed

  $ hg diff --git --binary -r 0 -r 1
  diff --git a/binfile.bin b/binfile.bin
  index eaf36c1daccfdf325514461cd1a2ffbc139b5464..ba71a782e93f3fb63a428383706065e3ec2828e9
  GIT binary patch
  literal 5
  Mc${NkWMbw50018V5dZ)H
  
  $ hg diff --git --binary --config diff.nobinary=True -r 0 -r 1
  diff --git a/binfile.bin b/binfile.bin
  index eaf36c1daccfdf325514461cd1a2ffbc139b5464..ba71a782e93f3fb63a428383706065e3ec2828e9
  GIT binary patch
  literal 5
  Mc${NkWMbw50018V5dZ)H
  

  $ hg diff --git --binary --text -r 0 -r 1
  diff --git a/binfile.bin b/binfile.bin
  --- a/binfile.bin
  +++ b/binfile.bin
  @@ -1,1 +1,1 @@
  -\x00\x01\x02\x03 (esc)
  \ No newline at end of file
  +\x00\x01\x02\x03 (esc)

  $ cd ..