git-commit-vandalism/t/t4209-log-pickaxe.sh

193 lines
5.0 KiB
Bash
Raw Normal View History

#!/bin/sh
test_description='log --grep/--author/--regexp-ignore-case/-S/-G'
. ./test-lib.sh
test_log () {
expect=$1
kind=$2
needle=$3
shift 3
rest=$@
case $kind in
--*)
opt=$kind=$needle
;;
*)
opt=$kind$needle
;;
esac
case $expect in
expect_nomatch)
match=nomatch
;;
*)
match=match
;;
esac
test_expect_success "log $kind${rest:+ $rest} ($match)" "
git log $rest $opt --format=%H >actual &&
test_cmp $expect actual
"
}
# test -i and --regexp-ignore-case and expect both to behave the same way
test_log_icase () {
test_log $@ --regexp-ignore-case
test_log $@ -i
}
test_expect_success setup '
>expect_nomatch &&
>file &&
git add file &&
test_tick &&
git commit -m initial &&
git rev-parse --verify HEAD >expect_initial &&
echo Picked >file &&
git add file &&
test_tick &&
git commit --author="Another Person <another@example.com>" -m second &&
git rev-parse --verify HEAD >expect_second
'
test_expect_success 'usage' '
test_expect_code 128 git log -Gregex -Sstring 2>err &&
grep "mutually exclusive" err &&
test_expect_code 128 git log -Gregex --find-object=HEAD 2>err &&
grep "mutually exclusive" err &&
test_expect_code 128 git log -Sstring --find-object=HEAD 2>err &&
grep "mutually exclusive" err
'
test_log expect_initial --grep initial
test_log expect_nomatch --grep InItial
test_log_icase expect_initial --grep InItial
test_log_icase expect_nomatch --grep initail
test_log expect_second --author Person
test_log expect_nomatch --author person
test_log_icase expect_second --author person
test_log_icase expect_nomatch --author spreon
test_log expect_nomatch -G picked
test_log expect_second -G Picked
test_log_icase expect_nomatch -G pickle
test_log_icase expect_second -G picked
test_expect_success 'log -G --textconv (missing textconv tool)' '
echo "* diff=test" >.gitattributes &&
test_must_fail git -c diff.test.textconv=missing log -Gfoo &&
rm .gitattributes
'
test_expect_success 'log -G --no-textconv (missing textconv tool)' '
echo "* diff=test" >.gitattributes &&
git -c diff.test.textconv=missing log -Gfoo --no-textconv >actual &&
test_cmp expect_nomatch actual &&
rm .gitattributes
'
test_log expect_nomatch -S picked
test_log expect_second -S Picked
test_log_icase expect_second -S picked
test_log_icase expect_nomatch -S pickle
test_log expect_nomatch -S p.cked --pickaxe-regex
test_log expect_second -S P.cked --pickaxe-regex
test_log_icase expect_second -S p.cked --pickaxe-regex
test_log_icase expect_nomatch -S p.ckle --pickaxe-regex
test_expect_success 'log -S --textconv (missing textconv tool)' '
echo "* diff=test" >.gitattributes &&
test_must_fail git -c diff.test.textconv=missing log -Sfoo &&
rm .gitattributes
'
test_expect_success 'log -S --no-textconv (missing textconv tool)' '
echo "* diff=test" >.gitattributes &&
git -c diff.test.textconv=missing log -Sfoo --no-textconv >actual &&
test_cmp expect_nomatch actual &&
rm .gitattributes
'
test_expect_success 'setup log -[GS] plain & regex' '
test_create_repo GS-plain &&
test_commit -C GS-plain --append A data.txt "a" &&
test_commit -C GS-plain --append B data.txt "a a" &&
test_commit -C GS-plain --append C data.txt "b" &&
test_commit -C GS-plain --append D data.txt "[b]" &&
test_commit -C GS-plain E data.txt "" &&
# We also include E, the deletion commit
git -C GS-plain log --grep="[ABE]" >A-to-B-then-E-log &&
git -C GS-plain log --grep="[CDE]" >C-to-D-then-E-log &&
git -C GS-plain log --grep="[DE]" >D-then-E-log &&
git -C GS-plain log >full-log
'
test_expect_success 'log -G trims diff new/old [-+]' '
git -C GS-plain log -G"[+-]a" >log &&
test_must_be_empty log &&
git -C GS-plain log -G"^a" >log &&
test_cmp log A-to-B-then-E-log
'
test_expect_success 'log -S<pat> is not a regex, but -S<pat> --pickaxe-regex is' '
git -C GS-plain log -S"a" >log &&
test_cmp log A-to-B-then-E-log &&
git -C GS-plain log -S"[a]" >log &&
test_must_be_empty log &&
git -C GS-plain log -S"[a]" --pickaxe-regex >log &&
test_cmp log A-to-B-then-E-log &&
git -C GS-plain log -S"[b]" >log &&
test_cmp log D-then-E-log &&
git -C GS-plain log -S"[b]" --pickaxe-regex >log &&
test_cmp log C-to-D-then-E-log
'
log -G: ignore binary files The -G<regex> option of log looks for the differences whose patch text contains added/removed lines that match regex. Currently -G looks also into patches of binary files (which according to [1]) is binary as well. This has a couple of issues: - It makes the pickaxe search slow. In a proprietary repository of the author with only ~5500 commits and a total .git size of ~300MB searching takes ~13 seconds $time git log -Gwave > /dev/null real 0m13,241s user 0m12,596s sys 0m0,644s whereas when we ignore binary files with this patch it takes ~4s $time ~/devel/git/git log -Gwave > /dev/null real 0m3,713s user 0m3,608s sys 0m0,105s which is a speedup of more than fourfold. - The internally used algorithm for generating patch text is based on xdiff and its states in [1] > The output format of the binary patch file is proprietary > (and binary) and it is basically a collection of copy and insert > commands [..] which means that the current format could change once the internal algorithm is changed as the format is not standardized. In addition the git binary patch format used for preparing patches for git apply is *different* from the xdiff format as can be seen by comparing git log -p -a commit 6e95bf4bafccf14650d02ab57f3affe669be10cf Author: A U Thor <author@example.com> Date: Thu Apr 7 15:14:13 2005 -0700 modify binary file diff --git a/data.bin b/data.bin index f414c84..edfeb6f 100644 --- a/data.bin +++ b/data.bin @@ -1,2 +1,4 @@ a a^@a +a +a^@a with git log --binary commit 6e95bf4bafccf14650d02ab57f3affe669be10cf Author: A U Thor <author@example.com> Date: Thu Apr 7 15:14:13 2005 -0700 modify binary file diff --git a/data.bin b/data.bin index f414c84bd3aa25fa07836bb1fb73db784635e24b..edfeb6f501[..] GIT binary patch literal 12 QcmYe~N@Pgn0zx1O01)N^ZvX%Q literal 6 NcmYe~N@Pgn0ssWg0XP5v which seems unexpected. To resolve these issues this patch makes -G<regex> ignore binary files by default. Textconv filters are supported and also -a/--text for getting the old and broken behaviour back. The -S<block of text> option of log looks for differences that changes the number of occurrences of the specified block of text (i.e. addition/deletion) in a file. As we want to keep the current behaviour, add a test to ensure it stays that way. [1]: http://www.xmailserver.org/xdiff.html Signed-off-by: Thomas Braun <thomas.braun@virtuell-zuhause.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-12-14 19:49:12 +01:00
test_expect_success 'setup log -[GS] binary & --text' '
test_create_repo GS-bin-txt &&
test_commit -C GS-bin-txt --printf A data.bin "a\na\0a\n" &&
test_commit -C GS-bin-txt --append --printf B data.bin "a\na\0a\n" &&
test_commit -C GS-bin-txt C data.bin "" &&
git -C GS-bin-txt log >full-log
log -G: ignore binary files The -G<regex> option of log looks for the differences whose patch text contains added/removed lines that match regex. Currently -G looks also into patches of binary files (which according to [1]) is binary as well. This has a couple of issues: - It makes the pickaxe search slow. In a proprietary repository of the author with only ~5500 commits and a total .git size of ~300MB searching takes ~13 seconds $time git log -Gwave > /dev/null real 0m13,241s user 0m12,596s sys 0m0,644s whereas when we ignore binary files with this patch it takes ~4s $time ~/devel/git/git log -Gwave > /dev/null real 0m3,713s user 0m3,608s sys 0m0,105s which is a speedup of more than fourfold. - The internally used algorithm for generating patch text is based on xdiff and its states in [1] > The output format of the binary patch file is proprietary > (and binary) and it is basically a collection of copy and insert > commands [..] which means that the current format could change once the internal algorithm is changed as the format is not standardized. In addition the git binary patch format used for preparing patches for git apply is *different* from the xdiff format as can be seen by comparing git log -p -a commit 6e95bf4bafccf14650d02ab57f3affe669be10cf Author: A U Thor <author@example.com> Date: Thu Apr 7 15:14:13 2005 -0700 modify binary file diff --git a/data.bin b/data.bin index f414c84..edfeb6f 100644 --- a/data.bin +++ b/data.bin @@ -1,2 +1,4 @@ a a^@a +a +a^@a with git log --binary commit 6e95bf4bafccf14650d02ab57f3affe669be10cf Author: A U Thor <author@example.com> Date: Thu Apr 7 15:14:13 2005 -0700 modify binary file diff --git a/data.bin b/data.bin index f414c84bd3aa25fa07836bb1fb73db784635e24b..edfeb6f501[..] GIT binary patch literal 12 QcmYe~N@Pgn0zx1O01)N^ZvX%Q literal 6 NcmYe~N@Pgn0ssWg0XP5v which seems unexpected. To resolve these issues this patch makes -G<regex> ignore binary files by default. Textconv filters are supported and also -a/--text for getting the old and broken behaviour back. The -S<block of text> option of log looks for differences that changes the number of occurrences of the specified block of text (i.e. addition/deletion) in a file. As we want to keep the current behaviour, add a test to ensure it stays that way. [1]: http://www.xmailserver.org/xdiff.html Signed-off-by: Thomas Braun <thomas.braun@virtuell-zuhause.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-12-14 19:49:12 +01:00
'
test_expect_success 'log -G ignores binary files' '
git -C GS-bin-txt log -Ga >log &&
log -G: ignore binary files The -G<regex> option of log looks for the differences whose patch text contains added/removed lines that match regex. Currently -G looks also into patches of binary files (which according to [1]) is binary as well. This has a couple of issues: - It makes the pickaxe search slow. In a proprietary repository of the author with only ~5500 commits and a total .git size of ~300MB searching takes ~13 seconds $time git log -Gwave > /dev/null real 0m13,241s user 0m12,596s sys 0m0,644s whereas when we ignore binary files with this patch it takes ~4s $time ~/devel/git/git log -Gwave > /dev/null real 0m3,713s user 0m3,608s sys 0m0,105s which is a speedup of more than fourfold. - The internally used algorithm for generating patch text is based on xdiff and its states in [1] > The output format of the binary patch file is proprietary > (and binary) and it is basically a collection of copy and insert > commands [..] which means that the current format could change once the internal algorithm is changed as the format is not standardized. In addition the git binary patch format used for preparing patches for git apply is *different* from the xdiff format as can be seen by comparing git log -p -a commit 6e95bf4bafccf14650d02ab57f3affe669be10cf Author: A U Thor <author@example.com> Date: Thu Apr 7 15:14:13 2005 -0700 modify binary file diff --git a/data.bin b/data.bin index f414c84..edfeb6f 100644 --- a/data.bin +++ b/data.bin @@ -1,2 +1,4 @@ a a^@a +a +a^@a with git log --binary commit 6e95bf4bafccf14650d02ab57f3affe669be10cf Author: A U Thor <author@example.com> Date: Thu Apr 7 15:14:13 2005 -0700 modify binary file diff --git a/data.bin b/data.bin index f414c84bd3aa25fa07836bb1fb73db784635e24b..edfeb6f501[..] GIT binary patch literal 12 QcmYe~N@Pgn0zx1O01)N^ZvX%Q literal 6 NcmYe~N@Pgn0ssWg0XP5v which seems unexpected. To resolve these issues this patch makes -G<regex> ignore binary files by default. Textconv filters are supported and also -a/--text for getting the old and broken behaviour back. The -S<block of text> option of log looks for differences that changes the number of occurrences of the specified block of text (i.e. addition/deletion) in a file. As we want to keep the current behaviour, add a test to ensure it stays that way. [1]: http://www.xmailserver.org/xdiff.html Signed-off-by: Thomas Braun <thomas.braun@virtuell-zuhause.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-12-14 19:49:12 +01:00
test_must_be_empty log
'
test_expect_success 'log -G looks into binary files with -a' '
git -C GS-bin-txt log -a -Ga >log &&
log -G: ignore binary files The -G<regex> option of log looks for the differences whose patch text contains added/removed lines that match regex. Currently -G looks also into patches of binary files (which according to [1]) is binary as well. This has a couple of issues: - It makes the pickaxe search slow. In a proprietary repository of the author with only ~5500 commits and a total .git size of ~300MB searching takes ~13 seconds $time git log -Gwave > /dev/null real 0m13,241s user 0m12,596s sys 0m0,644s whereas when we ignore binary files with this patch it takes ~4s $time ~/devel/git/git log -Gwave > /dev/null real 0m3,713s user 0m3,608s sys 0m0,105s which is a speedup of more than fourfold. - The internally used algorithm for generating patch text is based on xdiff and its states in [1] > The output format of the binary patch file is proprietary > (and binary) and it is basically a collection of copy and insert > commands [..] which means that the current format could change once the internal algorithm is changed as the format is not standardized. In addition the git binary patch format used for preparing patches for git apply is *different* from the xdiff format as can be seen by comparing git log -p -a commit 6e95bf4bafccf14650d02ab57f3affe669be10cf Author: A U Thor <author@example.com> Date: Thu Apr 7 15:14:13 2005 -0700 modify binary file diff --git a/data.bin b/data.bin index f414c84..edfeb6f 100644 --- a/data.bin +++ b/data.bin @@ -1,2 +1,4 @@ a a^@a +a +a^@a with git log --binary commit 6e95bf4bafccf14650d02ab57f3affe669be10cf Author: A U Thor <author@example.com> Date: Thu Apr 7 15:14:13 2005 -0700 modify binary file diff --git a/data.bin b/data.bin index f414c84bd3aa25fa07836bb1fb73db784635e24b..edfeb6f501[..] GIT binary patch literal 12 QcmYe~N@Pgn0zx1O01)N^ZvX%Q literal 6 NcmYe~N@Pgn0ssWg0XP5v which seems unexpected. To resolve these issues this patch makes -G<regex> ignore binary files by default. Textconv filters are supported and also -a/--text for getting the old and broken behaviour back. The -S<block of text> option of log looks for differences that changes the number of occurrences of the specified block of text (i.e. addition/deletion) in a file. As we want to keep the current behaviour, add a test to ensure it stays that way. [1]: http://www.xmailserver.org/xdiff.html Signed-off-by: Thomas Braun <thomas.braun@virtuell-zuhause.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-12-14 19:49:12 +01:00
test_cmp log full-log
'
test_expect_success 'log -G looks into binary files with textconv filter' '
test_when_finished "rm GS-bin-txt/.gitattributes" &&
(
cd GS-bin-txt &&
echo "* diff=bin" >.gitattributes &&
git -c diff.bin.textconv=cat log -Ga >../log
) &&
log -G: ignore binary files The -G<regex> option of log looks for the differences whose patch text contains added/removed lines that match regex. Currently -G looks also into patches of binary files (which according to [1]) is binary as well. This has a couple of issues: - It makes the pickaxe search slow. In a proprietary repository of the author with only ~5500 commits and a total .git size of ~300MB searching takes ~13 seconds $time git log -Gwave > /dev/null real 0m13,241s user 0m12,596s sys 0m0,644s whereas when we ignore binary files with this patch it takes ~4s $time ~/devel/git/git log -Gwave > /dev/null real 0m3,713s user 0m3,608s sys 0m0,105s which is a speedup of more than fourfold. - The internally used algorithm for generating patch text is based on xdiff and its states in [1] > The output format of the binary patch file is proprietary > (and binary) and it is basically a collection of copy and insert > commands [..] which means that the current format could change once the internal algorithm is changed as the format is not standardized. In addition the git binary patch format used for preparing patches for git apply is *different* from the xdiff format as can be seen by comparing git log -p -a commit 6e95bf4bafccf14650d02ab57f3affe669be10cf Author: A U Thor <author@example.com> Date: Thu Apr 7 15:14:13 2005 -0700 modify binary file diff --git a/data.bin b/data.bin index f414c84..edfeb6f 100644 --- a/data.bin +++ b/data.bin @@ -1,2 +1,4 @@ a a^@a +a +a^@a with git log --binary commit 6e95bf4bafccf14650d02ab57f3affe669be10cf Author: A U Thor <author@example.com> Date: Thu Apr 7 15:14:13 2005 -0700 modify binary file diff --git a/data.bin b/data.bin index f414c84bd3aa25fa07836bb1fb73db784635e24b..edfeb6f501[..] GIT binary patch literal 12 QcmYe~N@Pgn0zx1O01)N^ZvX%Q literal 6 NcmYe~N@Pgn0ssWg0XP5v which seems unexpected. To resolve these issues this patch makes -G<regex> ignore binary files by default. Textconv filters are supported and also -a/--text for getting the old and broken behaviour back. The -S<block of text> option of log looks for differences that changes the number of occurrences of the specified block of text (i.e. addition/deletion) in a file. As we want to keep the current behaviour, add a test to ensure it stays that way. [1]: http://www.xmailserver.org/xdiff.html Signed-off-by: Thomas Braun <thomas.braun@virtuell-zuhause.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-12-14 19:49:12 +01:00
test_cmp log full-log
'
test_expect_success 'log -S looks into binary files' '
git -C GS-bin-txt log -Sa >log &&
log -G: ignore binary files The -G<regex> option of log looks for the differences whose patch text contains added/removed lines that match regex. Currently -G looks also into patches of binary files (which according to [1]) is binary as well. This has a couple of issues: - It makes the pickaxe search slow. In a proprietary repository of the author with only ~5500 commits and a total .git size of ~300MB searching takes ~13 seconds $time git log -Gwave > /dev/null real 0m13,241s user 0m12,596s sys 0m0,644s whereas when we ignore binary files with this patch it takes ~4s $time ~/devel/git/git log -Gwave > /dev/null real 0m3,713s user 0m3,608s sys 0m0,105s which is a speedup of more than fourfold. - The internally used algorithm for generating patch text is based on xdiff and its states in [1] > The output format of the binary patch file is proprietary > (and binary) and it is basically a collection of copy and insert > commands [..] which means that the current format could change once the internal algorithm is changed as the format is not standardized. In addition the git binary patch format used for preparing patches for git apply is *different* from the xdiff format as can be seen by comparing git log -p -a commit 6e95bf4bafccf14650d02ab57f3affe669be10cf Author: A U Thor <author@example.com> Date: Thu Apr 7 15:14:13 2005 -0700 modify binary file diff --git a/data.bin b/data.bin index f414c84..edfeb6f 100644 --- a/data.bin +++ b/data.bin @@ -1,2 +1,4 @@ a a^@a +a +a^@a with git log --binary commit 6e95bf4bafccf14650d02ab57f3affe669be10cf Author: A U Thor <author@example.com> Date: Thu Apr 7 15:14:13 2005 -0700 modify binary file diff --git a/data.bin b/data.bin index f414c84bd3aa25fa07836bb1fb73db784635e24b..edfeb6f501[..] GIT binary patch literal 12 QcmYe~N@Pgn0zx1O01)N^ZvX%Q literal 6 NcmYe~N@Pgn0ssWg0XP5v which seems unexpected. To resolve these issues this patch makes -G<regex> ignore binary files by default. Textconv filters are supported and also -a/--text for getting the old and broken behaviour back. The -S<block of text> option of log looks for differences that changes the number of occurrences of the specified block of text (i.e. addition/deletion) in a file. As we want to keep the current behaviour, add a test to ensure it stays that way. [1]: http://www.xmailserver.org/xdiff.html Signed-off-by: Thomas Braun <thomas.braun@virtuell-zuhause.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-12-14 19:49:12 +01:00
test_cmp log full-log
'
test_done