我正在将文本模式扫描仪从Python3转换为Go1.10,但惊讶的是它实际上慢了2倍。分析后,罪魁祸首在strings.Contains()
中。请参阅下面的简单基准。我想念什么吗?您能推荐一种更快的Go模式搜索算法,这种算法在这种情况下会更好吗?我不担心启动时间,相同的模式将用于扫描数百万个文件。
Py3基准:
import time
import re
RUNS = 10000
if __name__ == '__main__':
with open('data.php') as fh:
testString = fh.read()
def do():
return "576ad4f370014dfb1d0f17b0e6855f22" in testString
start = time.time()
for i in range(RUNS):
_ = do()
duration = time.time() - start
print("Python: %.2fs" % duration)
Go1.10基准测试:
package main
import (
"fmt"
"io/ioutil"
"log"
"strings"
"time"
)
const (
runs = 10000
)
func main() {
fname := "data.php"
testdata := readFile(fname)
needle := "576ad4f370014dfb1d0f17b0e6855f22"
start := time.Now()
for i := 0; i < runs; i++ {
_ = strings.Contains(testdata, needle)
}
duration := time.Now().Sub(start)
fmt.Printf("Go: %.2fs\n", duration.Seconds())
}
func readFile(fname string) string {
data, err := ioutil.ReadFile(fname)
if err != nil {
log.Fatal(err)
}
return string(data)
}
data.php
是一个528KB的文件,可以是found here。输出:
Go: 1.98s
Python: 0.84s
最佳答案
为什么Python 3(24.79s)比Go(5.47s)慢4.5倍?您得到什么结果?
Python :
$ cat contains.py
import time
import re
RUNS = 10000
if __name__ == '__main__':
# The Complete Works of William Shakespeare by William Shakespeare
# http://www.gutenberg.org/files/100/100-0.txt
file = '/home/peter/shakespeare.100-0.txt' # 'data.php'
with open(file) as fh:
testString = fh.read()
def do():
return "Means to immure herself and not be seen." in testString
start = time.time()
for i in range(RUNS):
_ = do()
duration = time.time() - start
print("Python: %.2fs" % duration)
print(do())
$ python3 --version
Python 3.6.5
$ python3 contains.py
Python: 24.79s
True
$
去:
$ cat contains.go
package main
import (
"fmt"
"io/ioutil"
"log"
"strings"
"time"
)
const (
runs = 10000
)
func main() {
// The Complete Works of William Shakespeare by William Shakespeare
// http://www.gutenberg.org/files/100/100-0.txt
fname := `/home/peter/shakespeare.100-0.txt` // "data.php"
testdata := readFile(fname)
needle := "Means to immure herself and not be seen."
start := time.Now()
for i := 0; i < runs; i++ {
_ = strings.Contains(testdata, needle)
}
duration := time.Now().Sub(start)
fmt.Printf("Go: %.2fs\n", duration.Seconds())
fmt.Println(strings.Contains(testdata, needle))
fmt.Println(strings.Index(testdata, needle))
}
func readFile(fname string) string {
data, err := ioutil.ReadFile(fname)
if err != nil {
log.Fatal(err)
}
return string(data)
}
$ go version
go version devel +5332b5e75a Tue Jul 31 15:44:37 2018 +0000 linux/amd64
$ go run contains.go
Go: 5.47s
true
5837178
$