Java 大数据量读取

发表于 2020-01-26 更新于 2022-09-13 分类于 Java 阅读次数：

能有多快？

在一些算法竞赛中，可能会有一些题目数据量非常大，如果使用 Java 来编写代码，如何才能读取的更快呢？

正好在 SPOJ 这个平台上有一道很合适的题目：SPOJ.com - Problem INTEST

使用 java.util.Scanner

import java.util.Scanner;

class Main {
    public static void main(String[] args) {
        Scanner scanner = new Scanner(System.in);
        int n = scanner.nextInt();
        System.out.println(n);
    }
}

使用 java.io.BufferedReader

使用 BufferedReader 配合 Integer.parseInt()、Double.parseDouble()等方法。

import java.io.BufferedReader;
import java.io.InputStreamReader;

class Main {
    public static void main(String[] args) throws Exception {
        BufferedReader bufferedReader = new BufferedReader(new InputStreamReader(System.in));
        int n = Integer.parseInt(bufferedReader.readLine());
        System.out.println(n);
    }
}

进阶版：自定义 parse

import java.io.DataInputStream;
import java.io.FileInputStream;
import java.io.IOException;

class Reader {
    final private int BUFFER_SIZE = 1 << 16;
    private DataInputStream din;
    private byte[] buffer;
    private int bufferPointer, bytesRead;

    public Reader() {
        din = new DataInputStream(System.in);
        buffer = new byte[BUFFER_SIZE];
        bufferPointer = bytesRead = 0;
    }

    public Reader(String file_name) throws IOException {
        din = new DataInputStream(new FileInputStream(file_name));
        buffer = new byte[BUFFER_SIZE];
        bufferPointer = bytesRead = 0;
    }

    public String readLine() throws IOException {
        byte[] buf = new byte[64]; // line length 
        int cnt = 0;
        int c;
        while ((c = read()) != -1) {
            if (c == '\n') {
                break;
            }
            buf[cnt++] = (byte) c;
        }
        return new String(buf, 0, cnt);
    }

    public int nextInt() throws IOException {
        int ret = 0;
        byte c = read();
        while (c <= ' ') {
            c = read();
        }
        boolean neg = (c == '-');
        if (neg) {
            c = read();
        }
        do {
            ret = ret * 10 + c - '0';
        } while ((c = read()) >= '0' && c <= '9');

        if (neg) {
            return -ret;
        }
        return ret;
    }

    public long nextLong() throws IOException {
        long ret = 0;
        byte c = read();
        while (c <= ' ') {
            c = read();
        }
        boolean neg = (c == '-');
        if (neg) {
            c = read();
        }
        do {
            ret = ret * 10 + c - '0';
        }
        while ((c = read()) >= '0' && c <= '9');
        if (neg) {
            return -ret;
        }
        return ret;
    }

    public double nextDouble() throws IOException {
        double ret = 0;
        double div = 1;
        byte c = read();
        while (c <= ' ') {
            c = read();
        }
        boolean neg = (c == '-');
        if (neg) {
            c = read();
        }

        do {
            ret = ret * 10 + c - '0';
        }
        while ((c = read()) >= '0' && c <= '9');

        if (c == '.') {
            while ((c = read()) >= '0' && c <= '9') {
                ret += (c - '0') / (div *= 10);
            }
        }

        if (neg) {
            return -ret;
        }
        return ret;
    }

    private void fillBuffer() throws IOException {
        bytesRead = din.read(buffer, bufferPointer = 0, BUFFER_SIZE);
        if (bytesRead == -1) {
            buffer[0] = -1;
        }
    }

    private byte read() throws IOException {
        if (bufferPointer == bytesRead) {
            fillBuffer();
        }
        return buffer[bufferPointer++];
    }

    public void close() throws IOException {
        if (din == null) {
            return;
        }
        din.close();
    }
}

速度对比

原因分析

为什么 java.util.Scanner 那么慢？

单行输入多个值的时候

比如

这个时候如果按照一行一行来读取数据的话，如果要把同一行的多个数据分离开，一种方法是使用 String.split() 方法，还有一种方法是使用 StringTokenizer。