【Java】split()和java.util.StringTokenizer分割字符串的性能比较

原始版本

import java.io.FileOutputStream;
import java.io.IOException;
import java.io.OutputStreamWriter;

public class StringGenerator {
    public static void main(String[] args) {
        try (OutputStreamWriter writer = new OutputStreamWriter(new FileOutputStream("text.text"))) {
            StringBuilder str = new StringBuilder();
            str.append("afiaongaoncanivnrfbnavoiadnvonvoron#".repeat(1000));
            str.append("aovnodnvds");
            writer.write(str.toString());
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
}

文件写进去了：

看看能不能读出来：

读的出来，那就正式测试吧：

import java.io.BufferedReader;
import java.io.FileReader;
import java.io.IOException;
import java.util.StringTokenizer;

public class SplitTest {
    public static void main(String[] args) {
        String str = "";
        try (BufferedReader reader = new BufferedReader(new FileReader("text.text"))) {
            str = reader.readLine();
        } catch (IOException e) {
            e.printStackTrace();
        }
        long time0 = System.currentTimeMillis();
        StringTokenizer st = new StringTokenizer(str, "#");
        while (st.hasMoreTokens()) {
            st.nextToken();
        }
        long time1 = System.currentTimeMillis();
        String[] array = str.split("#");
        for (String s : array) {}
        long time2 = System.currentTimeMillis();
        System.out.println("StringTokenizer的运行时间是：" + (time1-time0));
        System.out.println("split()的运行时间是：" + (time2-time1));
    }
}

运行结果：

StringTokenizer的运行时间是：9
split()的运行时间是：0

文本内容×10

import java.io.FileOutputStream;
import java.io.IOException;
import java.io.OutputStreamWriter;

public class StringGenerator {
    public static void main(String[] args) {
        try (OutputStreamWriter writer = new OutputStreamWriter(new FileOutputStream("text.text"))) {
            StringBuilder str = new StringBuilder();
            str.append("afiaongaoncanivnrfbnavoiadnvonvoron#".repeat(10000));
            str.append("aovnodnvds");
            writer.write(str.toString());
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
}

运行结果：

StringTokenizer的运行时间是：10
split()的运行时间是：0

文本内容×100

import java.io.FileOutputStream;
import java.io.IOException;
import java.io.OutputStreamWriter;

public class StringGenerator {
    public static void main(String[] args) {
        try (OutputStreamWriter writer = new OutputStreamWriter(new FileOutputStream("text.text"))) {
            StringBuilder str = new StringBuilder();
            str.append("afiaongaoncanivnrfbnavoiadnvonvoron#".repeat(100000));
            str.append("aovnodnvds");
            writer.write(str.toString());
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
}

看看这3.6MB的文件吧…… 运行结果：

StringTokenizer的运行时间是：20
split()的运行时间是：10

文本内容×1000

import java.io.FileOutputStream;
import java.io.IOException;
import java.io.OutputStreamWriter;

public class StringGenerator {
    public static void main(String[] args) {
        try (OutputStreamWriter writer = new OutputStreamWriter(new FileOutputStream("text.text"))) {
            StringBuilder str = new StringBuilder();
            str.append("afiaongaoncanivnrfbnavoiadnvonvoron#".repeat(1000000));
            str.append("aovnodnvds");
            writer.write(str.toString());
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
}

惨绝人寰的36M： 运行结果：

StringTokenizer的运行时间是：90
split()的运行时间是：140

文本内容×10000

这个时候虚拟机就有点顶不住，我忘了是1W倍还是10W倍数据，反正基本在GB级别的时候，虚拟机就崩了……

试着调了虚拟机，也没啥用，就试着不在一次写入，而是改成分批次写入，每次都是追加模式……

import java.io.FileWriter;
import java.io.IOException;

public class StringGenerator {
    public static void main(String[] args) {
        try (FileWriter writer = new FileWriter("text.text", true)) {
            StringBuilder str = new StringBuilder();
            str.append("afiaongaoncanivnrfbnavoiadnvonvoron#".repeat(1000000));
            for (int i = 0; i