java读取文件统计一串英文出现频率最高的单词或字母

java读取文件统计一串英文出现频率最高的单词或字母

1.java统计一串英文出现频率最高的单词

package count;

import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;
import java.util.Map;

public class Count {
    public static void main(String[] args) {
        long start = System.currentTimeMillis();
	
	BufferedReader reader = new BufferedReader(new FileReader(
                "D:\\main.txt"));
        StringBuffer buffer = new StringBuffer();
        String line = null;
        while ((line = reader.readLine()) != null) {
            buffer.append(line);
        }
	reader.close();
        String str = = buffer.toString();
        str = str.replace(',', ' ');//将逗号用空格替换
        str = str.replace('.', ' ');//将句号用空格替换

        String[] strings = str.split("\\s+");   // “\\s+”代表一个或多个空格，是正则表达式
//      String[] strings = str.split(" +"); // “ +”在我的机器上也能代表一个或多个空格

        Map<String, Integer> map = new HashMap<String, Integer>();
        List<String> list = new ArrayList<String>();//存储每个不重复的单词

        for(String s : strings){
            if(map.containsKey(s)){//如果map中已经包含该单词，则将其个数+1
                int x = map.get(s);
                x++;
                map.put(s, x);
            }else{  //如果map中没用包含该单词，代表该单词第一次出现，则将其放入map并将个数设置为1
                map.put(s, 1);
                list.add(s);//将其添加到list中，代表它是一个新出现的单词
            }
        }

        int max=0;//记录出现次数最多的那个单词的出现次数
        String maxString = null;//记录出现次数最多的那个单词的值
        /*
         * 从list中取出每个单词，在map中查找其出现次数
         * 并没有真正排序，而只是记录下出现次数最多的那个单词
         */
        for(String s : list){
            int x = map.get(s);
            if(x>max){
                maxString = s;
                max = x;
            }
        }

        System.out.println(maxString);

        long end = System.currentTimeMillis();

        System.out.println("共耗时：" + (end - start) + "毫秒");
    }
}

2.java统计一串英文出现频率最高的字母

package com.algorithm.interview;
 
import java.io.BufferedReader;
import java.io.File;
import java.io.FileReader;
import java.util.Collections;
import java.util.HashMap;
import java.util.LinkedList;
import java.util.List;
import java.util.Map;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
 
public class Frequency {
    public void count() throws Exception {
        File file = new File("D:\\main.txt");
        FileReader fileReader = new FileReader(file);
        BufferedReader reader = new BufferedReader(fileReader);
        StringBuilder builder = new StringBuilder();
        String line = "";
        while ((line = reader.readLine()) != null) {
            builder.append(line);
        }
        Pattern pattern = Pattern.compile("[a-zA-Z]+");
        String content = builder.toString();
        Matcher matcher = pattern.matcher(content);
        Map<String, Integer> map = new HashMap<String, Integer>();
        String word = "";
        Integer times = 0;
        while (matcher.find()) {
            word = matcher.group();
            if (map.containsKey(word)) {
                times = map.get(word);
                map.put(word, times+1);
            } else {
                map.put(word, 1);
            }
        }
        List<Map.Entry<String, Integer>> list = new LinkedList<Map.Entry<String, Integer>>(
                map.entrySet());// put Entry to List
        Compare compare = new Compare();//rewrite Comparator
        for (int i = 0; i < 5; i++) {
            Map.Entry<String, Integer> entry = Collections.max(list, compare);// max
            String key = entry.getKey();
            Integer value = entry.getValue();
            int index = list.indexOf(entry);//get max's index
            System.out.println(key + " " + value);
            list.remove(index);//remove max
 
        }
    }
 
    public static void main(String[] args) {
 
        try {
            Frequency frequency = new Frequency();
            frequency.count();
        } catch (Exception e) {
            e.printStackTrace();
        }
    }
}

3.java统计一串英文单词字数并排序

import java.util.ArrayList; 
import java.util.Collections; 
import java.util.Comparator; 
import java.util.HashMap; 
import java.util.List; 
import java.util.Map; 
import java.util.StringTokenizer; 
import java.util.Map.Entry; 
 
 
 
public class wordCount { 
public static void main(String arg[]){ 
    int wordCount=0;      //用于统计单词的总个数 
    Map<String,Integer> map=new HashMap<String,Integer>();//用于统计各个单词的个数，排序 
    String sentence="hello,my name is Tom,what is your name?he said:\"my name is John\""; 
    StringTokenizer token=new StringTokenizer(sentence);//这个类会将字符串分解成一个个的标记 
    while(token.hasMoreTokens()){                      //循环遍历 
        wordCount++;                                   
        String word=token.nextToken(", ?.!:\"\"''\n");  //括号里的字符的含义是说按照,空格 ? . : "" '' \n去分割，如果这里你没明确要求，即括号里为空，则默认按照空格，制表符，新行符和回车符去分割 
        if(map.containsKey(word)){     //HashMap不允许重复的key，所以利用这个特性，去统计单词的个数 
            int count=map.get(word); 
            map.put(word, count+1);     //如果HashMap已有这个单词，则设置它的数量加1 
        } 
        else 
            map.put(word, 1);          //如果没有这个单词，则新填入，数量为1 
    } 
    System.out.println("总共单词数："+wordCount); 
    sort(map);                        //调用排序的方法，排序并输出！ 
} 
public static void sort(Map<String,Integer> map){ 
    List<Map.Entry<String, Integer>> infoIds = new ArrayList<Map.Entry<String, Integer>>(map.entrySet());  
    Collections.sort(infoIds, new Comparator<Map.Entry<String, Integer>>() {    
        public int compare(Map.Entry<String, Integer> o1, Map.Entry<String, Integer> o2) {    
            return (o2.getValue() - o1.getValue());    
        }    
}); //排序 
    for (int i = 0; i < infoIds.size(); i++) {   //输出 
        Entry<String, Integer> id = infoIds.get(i); 
    System.out.println(id.getKey()+":"+id.getValue()); 
        } 
} 
}