perf: add a comparison test of log --grep regex engines

Add a very basic performance comparison test comparing the POSIX
basic, extended and perl engines with patterns matching log messages
via --grep=<pattern>.

    $ GIT_PERF_REPEAT_COUNT=10 GIT_PERF_LARGE_REPO=~/g/linux ./run p4220-log-grep-engines.sh
    [...]
    Test                                                  this tree
    ---------------------------------------------------------------------
    4220.1: basic log --grep='how.to'                     6.22(6.00+0.21)
    4220.2: extended log --grep='how.to'                  6.23(5.98+0.23)
    4220.3: perl log --grep='how.to'                      6.07(5.79+0.25)
    4220.5: basic log --grep='^how to'                    6.19(5.93+0.22)
    4220.6: extended log --grep='^how to'                 6.19(5.93+0.23)
    4220.7: perl log --grep='^how to'                     6.14(5.88+0.24)
    4220.9: basic log --grep='[how] to'                   6.96(6.65+0.28)
    4220.10: extended log --grep='[how] to'               6.96(6.69+0.24)
    4220.11: perl log --grep='[how] to'                   6.95(6.58+0.33)
    4220.13: basic log --grep='\(e.t[^ ]*\|v.ry\) rare'   7.10(6.80+0.27)
    4220.14: extended log --grep='(e.t[^ ]*|v.ry) rare'   7.07(6.80+0.26)
    4220.15: perl log --grep='(e.t[^ ]*|v.ry) rare'       7.70(7.46+0.22)
    4220.17: basic log --grep='m\(ú\|u\)lt.b\(æ\|y\)te'   6.12(5.87+0.24)
    4220.18: extended log --grep='m(ú|u)lt.b(æ|y)te'      6.14(5.84+0.26)
    4220.19: perl log --grep='m(ú|u)lt.b(æ|y)te'          6.16(5.93+0.20)

With -i:

    $ GIT_PERF_REPEAT_COUNT=10 GIT_PERF_LARGE_REPO=~/g/linux GIT_PERF_4220_LOG_OPTS=' -i' ./run p4220-log-grep-engines.sh
    [...]
    Test                                                     this tree
    ------------------------------------------------------------------------
    4220.1: basic log -i --grep='how.to'                     6.74(6.41+0.32)
    4220.2: extended log -i --grep='how.to'                  6.78(6.55+0.22)
    4220.3: perl log -i --grep='how.to'                      6.06(5.77+0.28)
    4220.5: basic log -i --grep='^how to'                    6.80(6.57+0.22)
    4220.6: extended log -i --grep='^how to'                 6.83(6.52+0.29)
    4220.7: perl log -i --grep='^how to'                     6.16(5.94+0.20)
    4220.9: basic log -i --grep='[how] to'                   7.87(7.61+0.24)
    4220.10: extended log -i --grep='[how] to'               7.85(7.57+0.27)
    4220.11: perl log -i --grep='[how] to'                   7.03(6.75+0.25)
    4220.13: basic log -i --grep='\(e.t[^ ]*\|v.ry\) rare'   8.68(8.41+0.25)
    4220.14: extended log -i --grep='(e.t[^ ]*|v.ry) rare'   8.80(8.44+0.28)
    4220.15: perl log -i --grep='(e.t[^ ]*|v.ry) rare'       7.85(7.56+0.26)
    4220.17: basic log -i --grep='m\(ú\|u\)lt.b\(æ\|y\)te'   6.94(6.68+0.24)
    4220.18: extended log -i --grep='m(ú|u)lt.b(æ|y)te'      7.04(6.76+0.24)
    4220.19: perl log -i --grep='m(ú|u)lt.b(æ|y)te'          6.26(5.92+0.29)

See commit ("perf: add a comparison test of grep regex engines",
2017-04-19) for details on the machine the above test run was executed
on.

Before commit ("log: make --regexp-ignore-case work with
--perl-regexp", 2017-05-20) this test will almost definitely
fail (depending on the repo) if passed the -i option, since it wasn't
properly supported under PCRE.

Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 53 insertions, 0 deletions

diff --git a/t/perf/p4220-log-grep-engines.sh b/t/perf/p4220-log-grep-engines.sh
new file mode 100755
index 0000000000..2bc47ded4d
--- /dev/null
+++ b/t/perf/p4220-log-grep-engines.sh
@@ -0,0 +1,53 @@
+#!/bin/sh
+
+test_description="Comparison of git-log's --grep regex engines
+
+Set GIT_PERF_4220_LOG_OPTS in the environment to pass options to
+git-grep. Make sure to include a leading space,
+e.g. GIT_PERF_4220_LOG_OPTS=' -i'. Some options to try:
+
+	-i
+	--invert-grep
+	-i --invert-grep
+"
+
+. ./perf-lib.sh
+
+test_perf_large_repo
+test_checkout_worktree
+
+for pattern in \
+	'how.to' \
+	'^how to' \
+	'[how] to' \
+	'\(e.t[^ ]*\|v.ry\) rare' \
+	'm\(ú\|u\)lt.b\(æ\|y\)te'
+do
+	for engine in basic extended perl
+	do
+		if test $engine != "basic"
+		then
+			# Poor man's basic -> extended converter.
+			pattern=$(echo $pattern | sed 's/\\//g')
+		fi
+		if test $engine = "perl" && ! test_have_prereq PCRE
+		then
+			prereq="PCRE"
+		else
+			prereq=""
+		fi
+		test_perf $prereq "$engine log$GIT_PERF_4220_LOG_OPTS --grep='$pattern'" "
+			git -c grep.patternType=$engine log --pretty=format:%h$GIT_PERF_4220_LOG_OPTS --grep='$pattern' >'out.$engine' || :
+		"
+	done
+
+	test_expect_success "assert that all engines found the same for$GIT_PERF_4220_LOG_OPTS '$pattern'" '
+		test_cmp out.basic out.extended &&
+		if test_have_prereq PCRE
+		then
+			test_cmp out.basic out.perl
+		fi
+	'
+done
+
+test_done