Java、统计文本文件中单词的出现频率

 

package set;

import java.io.File;
import java.io.IOException;
import java.util.Map;
import java.util.Scanner;
import java.util.Set;
import java.util.TreeMap;

public class Exercise21_08 {
    public static void main(String[] args) throws IOException {
        if (args.length != 1) {
            System.out.println("Invalid length");
        } else {
            File file = new File(args[0]);
            if (!file.exists())
                System.out.println("File " + file + "does not exist");
            else
                countWordOccurrence(file);
        }

    }

    /** 统计文件中单词出现频率 */
    public static void countWordOccurrence(File file) throws IOException {
        Map<String, Integer> map = new TreeMap<>(); //树映射表
        try(Scanner input = new Scanner(file)) {
            while (input.hasNextLine()) {
                String text = input.nextLine();
                String[] words = text.split("[ ,.:;'\"{}()?\\[\\]]");

                for (int i = 0; i < words.length; i++) {
                    String key = words[i].toLowerCase().trim();

                    //添加单词
                    if (key.length() > 0 && Character.isLetter(key.charAt(0))) {
                        if (!map.containsKey(key))
                            map.put(key, 1);
                        else
                            map.put(key, map.get(key)+1);
                    }
                }
            }

            Set<Map.Entry<String, Integer>> entrySet = map.entrySet();
            for (Map.Entry<String, Integer> entry: entrySet)    //输出单词和数目
                System.out.println(String.format("%-10d%10s", entry.getValue(), entry.getKey()));
        }
    }
}