Optimization to regexp _CharClass: keep track of overall range of
charclass to avoid unnecessarily iterating over ranges.
Also, use the fact that IntVector is an []int to avoid method calls.
On my machine, this brings us from ~27500 ns/op to ~17500 ns/op in the benchmark I've added (it is also faster in the case where a range check
doesn't help, added a benchmark for this too.)
I'd also like to propose that "[]", and "[^]" be disallowed. They aren't useful as far as I can tell, they aren't widely supported, and they make reasoning about character classes a bit more complicated.
R=r
CC=golang-dev
https://golang.org/cl/1495041
diff --git a/src/pkg/regexp/all_test.go b/src/pkg/regexp/all_test.go
index 62dad3a..fd7ee2a 100644
--- a/src/pkg/regexp/all_test.go
+++ b/src/pkg/regexp/all_test.go
@@ -519,7 +519,7 @@
func TestNumSubexp(t *testing.T) {
for _, c := range numSubexpCases {
- re, _ := Compile(c.input)
+ re := MustCompile(c.input)
n := re.NumSubexp()
if n != c.expected {
t.Errorf("NumSubexp for %q returned %d, expected %d", c.input, n, c.expected)
@@ -530,7 +530,7 @@
func BenchmarkLiteral(b *testing.B) {
x := strings.Repeat("x", 50)
b.StopTimer()
- re, _ := Compile(x)
+ re := MustCompile(x)
b.StartTimer()
for i := 0; i < b.N; i++ {
if !re.MatchString(x) {
@@ -543,7 +543,35 @@
func BenchmarkNotLiteral(b *testing.B) {
x := strings.Repeat("x", 49)
b.StopTimer()
- re, _ := Compile("^" + x)
+ re := MustCompile("^" + x)
+ b.StartTimer()
+ for i := 0; i < b.N; i++ {
+ if !re.MatchString(x) {
+ println("no match!")
+ break
+ }
+ }
+}
+
+func BenchmarkMatchClass(b *testing.B) {
+ b.StopTimer()
+ x := strings.Repeat("xxxx", 20) + "w"
+ re := MustCompile("[abcdw]")
+ b.StartTimer()
+ for i := 0; i < b.N; i++ {
+ if !re.MatchString(x) {
+ println("no match!")
+ break
+ }
+ }
+}
+
+func BenchmarkMatchClass_InRange(b *testing.B) {
+ b.StopTimer()
+ // 'b' is betwen 'a' and 'c', so the charclass
+ // range checking is no help here.
+ x := strings.Repeat("bbbb", 20) + "c"
+ re := MustCompile("[ac]")
b.StartTimer()
for i := 0; i < b.N; i++ {
if !re.MatchString(x) {
@@ -556,7 +584,7 @@
func BenchmarkReplaceAll(b *testing.B) {
x := "abcdefghijklmnopqrstuvwxyz"
b.StopTimer()
- re, _ := Compile("[cjrw]")
+ re := MustCompile("[cjrw]")
b.StartTimer()
for i := 0; i < b.N; i++ {
re.ReplaceAllString(x, "")
