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 < 10; i++) {
writer.write(str.append("\n").toString());
}
str.append("aovnodnvds");
} catch (IOException e) {
e.printStackTrace();
}
}
}
360MB数据了,可怕……
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[] strings = new String[10];
try (BufferedReader reader = new BufferedReader(new FileReader("text.text"))) {
for (int i = 0; i < 10; i++) {
strings[i] = reader.readLine();
}
} catch (IOException e) {
e.printStackTrace();
}
long time0 = System.currentTimeMillis();
for (String s : strings) {
StringTokenizer st = new StringTokenizer(s, "#");
while (st.hasMoreTokens()) {
st.nextToken();
}
}
long time1 = System.currentTimeMillis();
for (String s : strings) {
String[] array = s.split("#");
for (String str : 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));
}
}
测试结果:
StringTokenizer的运行时间是:316
split()的运行时间是:609
文本内容×10W
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 < 100; i++) {
writer.write(str.append("\n").toString());
}
str.append("aovnodnvds");
} catch (IOException e) {
e.printStackTrace();
}
}
}
一个文件有这么地狱级别的数据量——3.96GB,太可怕了 (虽然比起大数据的数据量,这根本不算个事)
不敢一次读出来,分了100次换行读出来:
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[] strings = new String[100];
try (BufferedReader reader = new BufferedReader(new FileReader("text.text"))) {
for (int i = 0; i < 100; i++) {
strings[i] = reader.readLine();
}
} catch (IOException e) {
e.printStackTrace();
}
long time0 = System.currentTimeMillis();
for (String s : strings) {
StringTokenizer st = new StringTokenizer(s, "#");
while (st.hasMoreTokens()) {
st.nextToken();
}
}
long time1 = System.currentTimeMillis();
for (String s : strings) {
String[] array = s.split("#");
for (String str : 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));
}
}
测试结果:
StringTokenizer的运行时间是:650
split()的运行时间是:1805
对比总结
java.util.StringTokenizer是Java1.0就推出的古老API,在小数据量级显得不如split()简洁和快速。
但当数据量变大的时候,由于split()生成的数据存储在数组中,这个数组就会很大,很难操作,好在String是引用类型,否则光是开辟这么一大块空间就已经要命了……
所以,数据量很大还要读文件(显然那会儿都该是数据库了)的时候,可以使用java.util.StringTokenizer,避免使用split()再次开辟一个大数组!