exp/html: add some tokenizer and parser benchmarks.

$GOROOT/src/pkg/exp/html/testdata/go1.html is an execution of the
$GOROOT/doc/go1.html template by godoc.

Sample numbers on my linux,amd64 desktop:
BenchmarkParser	     500	   4699198 ns/op	  16.63 MB/s
--- BENCH: BenchmarkParser
        parse_test.go:409: 1 iterations, 14653 mallocs per iteration
        parse_test.go:409: 100 iterations, 14651 mallocs per iteration
        parse_test.go:409: 500 iterations, 14651 mallocs per iteration
BenchmarkRawLevelTokenizer	    2000	    904957 ns/op	  86.37 MB/s
--- BENCH: BenchmarkRawLevelTokenizer
        token_test.go:657: 1 iterations, 28 mallocs per iteration
        token_test.go:657: 100 iterations, 28 mallocs per iteration
        token_test.go:657: 2000 iterations, 28 mallocs per iteration
BenchmarkLowLevelTokenizer	    2000	   1134300 ns/op	  68.91 MB/s
--- BENCH: BenchmarkLowLevelTokenizer
        token_test.go:657: 1 iterations, 41 mallocs per iteration
        token_test.go:657: 100 iterations, 41 mallocs per iteration
        token_test.go:657: 2000 iterations, 41 mallocs per iteration
BenchmarkHighLevelTokenizer	    1000	   2096179 ns/op	  37.29 MB/s
--- BENCH: BenchmarkHighLevelTokenizer
        token_test.go:657: 1 iterations, 6616 mallocs per iteration
        token_test.go:657: 100 iterations, 6616 mallocs per iteration
        token_test.go:657: 1000 iterations, 6616 mallocs per iteration

R=rsc
CC=andybalholm, golang-dev, r
https://golang.org/cl/6257067

Author: nigeltao

src/pkg/exp/html/parse_test.go

@@ -11,8 +11,10 @@ import (
 	"flag"
 	"fmt"
 	"io"
+	"io/ioutil"
 	"os"
 	"path/filepath"
+	"runtime"
 	"sort"
 	"strings"
 	"testing"
@@ -386,3 +388,23 @@ var renderTestBlacklist = map[string]bool{
 	// A <plaintext> element can't have anything after it in HTML.
 	`<table><plaintext><td>`: true,
 }
+
+func BenchmarkParser(b *testing.B) {
+	buf, err := ioutil.ReadFile("testdata/go1.html")
+	if err != nil {
+		b.Fatalf("could not read testdata/go1.html: %v", err)
+	}
+	b.SetBytes(int64(len(buf)))
+	runtime.GC()
+	var ms runtime.MemStats
+	runtime.ReadMemStats(&ms)
+	mallocs := ms.Mallocs
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		Parse(bytes.NewBuffer(buf))
+	}
+	b.StopTimer()
+	runtime.ReadMemStats(&ms)
+	mallocs = ms.Mallocs - mallocs
+	b.Logf("%d iterations, %d mallocs per iteration\n", b.N, int(mallocs)/b.N)
+}