From 3966a6a0a18cfe9d0437e33618a103ae940df8e8 Mon Sep 17 00:00:00 2001
From: Eng Zer Jun <engzerjun@gmail.com>
Date: Sat, 10 Aug 2024 01:09:53 +0800
Subject: [PATCH] lib/regex: use string version of regexp methods to reduce
 allocs (#1614)

Both `(*Regexp).Match` and `(*Regexp).FindAllSubmatchIndex` have
string-based equivalents: `(*Regexp).MatchString` and
`(*Regexp).FindAllStringSubmatchIndex`. We should use the string version
to avoid unnecessary `[]byte` conversions.

Benchmark:

var regex = regexp.MustCompile("foo.*")

func BenchmarkMatch(b *testing.B) {
	for i := 0; i < b.N; i++ {
		if match := regex.Match([]byte("foo bar baz")); !match {
			b.Fail()
		}
	}
}

func BenchmarkMatchString(b *testing.B) {
	for i := 0; i < b.N; i++ {
		if match := regex.MatchString("foo bar baz"); !match {
			b.Fail()
		}
	}
}

func BenchmarkFindAllSubmatchIndex(b *testing.B) {
	for i := 0; i < b.N; i++ {
		if match := regex.FindAllSubmatchIndex([]byte("foo bar baz"), -1); len(match) == 0 {
			b.Fail()
		}
	}
}

func BenchmarkFindAllStringSubmatchIndex(b *testing.B) {
	for i := 0; i < b.N; i++ {
		if match := regex.FindAllStringSubmatchIndex("foo bar baz", -1); len(match) == 0 {
			b.Fail()
		}
	}
}

goos: linux
goarch: amd64
pkg: github.com/johnkerl/miller/pkg/lib
cpu: AMD Ryzen 7 PRO 4750U with Radeon Graphics
BenchmarkMatch-16                         	 2198350	       517.5 ns/op	      16 B/op	       1 allocs/op
BenchmarkMatchString-16                   	 3143605	       371.5 ns/op	       0 B/op	       0 allocs/op
BenchmarkFindAllSubmatchIndex-16          	  921711	      1199 ns/op	     273 B/op	       3 allocs/op
BenchmarkFindAllStringSubmatchIndex-16    	 1212321	       981.0 ns/op	     257 B/op	       2 allocs/op
PASS
coverage: 0.0% of statements
ok  	github.com/johnkerl/miller/pkg/lib	6.576s

Signed-off-by: Eng Zer Jun <engzerjun@gmail.com>
---
 pkg/lib/regex.go | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/pkg/lib/regex.go b/pkg/lib/regex.go
index af0a188059..d8d5511674 100644
--- a/pkg/lib/regex.go
+++ b/pkg/lib/regex.go
@@ -202,7 +202,7 @@ func regexCompiledSubOrGsub(
 	replacementCaptureMatrix [][]int,
 	breakOnFirst bool,
 ) string {
-	matrix := regex.FindAllSubmatchIndex([]byte(input), -1)
+	matrix := regex.FindAllStringSubmatchIndex(input, -1)
 	if matrix == nil || len(matrix) == 0 {
 		return input
 	}
@@ -290,7 +290,7 @@ func RegexCompiledMatchSimple(
 	input string,
 	regex *regexp.Regexp,
 ) bool {
-	return regex.Match([]byte(input))
+	return regex.MatchString(input)
 }
 
 // RegexStringMatchWithMapResults implements much of the `strmatchx` DSL function.  This returns
@@ -320,7 +320,7 @@ func RegexCompiledMatchWithMapResults(
 	starts := make([]int, 0, 10)
 	ends := make([]int, 0, 10)
 
-	matrix := regex.FindAllSubmatchIndex([]byte(input), -1)
+	matrix := regex.FindAllStringSubmatchIndex(input, -1)
 	if matrix == nil || len(matrix) == 0 {
 		return false, captures, starts, ends
 	}
@@ -406,7 +406,7 @@ func RegexCompiledMatchWithCaptures(
 	input string,
 	regex *regexp.Regexp,
 ) (bool, []string) {
-	matrix := regex.FindAllSubmatchIndex([]byte(input), -1)
+	matrix := regex.FindAllStringSubmatchIndex(input, -1)
 	if matrix == nil || len(matrix) == 0 {
 		// Set all captures to ""
 		return false, make([]string, 10)
@@ -474,7 +474,7 @@ func ReplacementHasCaptures(
 	matrix [][]int,
 ) {
 	if captureDetector.MatchString(replacement) {
-		return true, captureSplitter.FindAllSubmatchIndex([]byte(replacement), -1)
+		return true, captureSplitter.FindAllStringSubmatchIndex(replacement, -1)
 	} else {
 		return false, nil
 	}