统计文件中出现最频繁的前TOP个汉字(Java版)

import java.io.*;
import java.util.*;
import java.util.regex.Pattern;

public class QueryTopWordFromFile {

    public static void main(String[] args) throws IOException {
        int top = 10;
        File file = new File("C:\\nohup.out");

        BufferedReader bufferedReader = new BufferedReader(new InputStreamReader(new FileInputStream(file), "utf-8"));
        Map<String, Integer> wordsCountMap = new HashMap<>();
        String line = null;
        Pattern pattern = Pattern.compile("[\u4e00-\u9fa5]");

        int lines = 0;
        while ((line = bufferedReader.readLine()) != null) {
            lines++;
            String[] split = line.split("");
            for (String s : split) {
                wordsCountMap.merge(s, 1, Integer::sum);
            }
        }
        System.out.println("lines: " + lines);
        System.out.println(wordsCountMap);

        PriorityQueue<Map.Entry<String, Integer>> queue = new PriorityQueue<>(Comparator.comparingInt(Map.Entry::getValue));
        for (Map.Entry<String, Integer> next : wordsCountMap.entrySet()) {
            String word = next.getKey();
            if (pattern.matcher(word).matches()) {
                if (queue.size() < top) {
                    queue.add(next);
                } else if (next.getValue() > queue.peek().getValue()) {
                    queue.poll();
                    queue.add(next);
                }
            }

        }
        System.out.println("==========");
        System.out.println(queue);
    }
}