Java之统计字符串频率

本文主要是通过Java来实现统计txt文件当中的字符出现频率。

1. 主要使用的是map来进行存储（map访问速度很快，去重方便）
2. 另外对map进行了按value排序的功能（默认可以按key排序）
3. 然也涉及到文件的读取等，直接上代码：

import java.io.File;
import java.io.*;
import java.util.*;
import java.util.Map.Entry;

public class StringTest1 {



    public static Map<String,Integer> ComputeString(String filePath){

        Map<String,Integer> map = new HashMap<String,Integer>();

        //读取文件
        try{
            String encoding = "UTF-8";
            File file = new File(filePath);
            if(file.isFile() && file.exists()){
                InputStreamReader read = new InputStreamReader(
                        new FileInputStream(file),encoding);
                BufferedReader bufferedReader = new BufferedReader(read);
                String lineTxt = null;

                while((lineTxt = bufferedReader.readLine())!=null){
                    for(int i = 1 ; i < lineTxt.length() ; i++){
                        String temp = lineTxt.substring(i-1,i);
                        boolean k = false;
                        //将字符输入到map当中保存
                        for(String key:map.keySet()){
                            if(key.equals(temp)){
                                map.put(key, (int)map.get(key)+1);
                                k = true;
                                break;
                            }   
                        }
                        if(!k){
                            map.put(temp, 1);
                        }
                    }
                }
                read.close();
                return map;
            }else{
                System.out.println("cant find the file!");
            }
        }catch(Exception e){
            System.out.println("read file error!");
            e.printStackTrace();
        }

        return map;
    }


    //对map按照value来排序
    public static Map<String,Integer> sortMapByvalue(Map<String, Integer> oriMap){
        if(oriMap == null || oriMap.isEmpty()){
            return null;
        }
        Map<String,Integer> sortedMap = new LinkedHashMap<String, Integer>();
        List<Map.Entry<String, Integer>> entryList = new ArrayList<Map.Entry<String,Integer>>(
                oriMap.entrySet());

        Collections.sort(entryList, new MapValueComparator());

        Iterator<Map.Entry<String, Integer>> iter = entryList.iterator();
        Map.Entry<String, Integer> tmpEntry = null;
        while(iter.hasNext()){
            tmpEntry = iter.next();
            sortedMap.put(tmpEntry.getKey(), tmpEntry.getValue());
        }
        return sortedMap;
    }

    //排序的具体函数
    public static class MapValueComparator implements Comparator<Map.Entry<String,Integer>>{
        @Override
        public int compare(Entry<String, Integer> me1, Entry<String,Integer> me2){
            return me2.getValue().compareTo(me1.getValue());
        }
    }

    //清除字符
    public static Map<String,Integer> ClearClip(Map<String,Integer> oriMap){
        String[] clip = new String[]{"0" , "1" , "2" , "3" , "4" , "5" , "6" , "7" , "8" , "9"," ","。","，","?",",","."
                ,"？",""};


        Iterator<String> it = oriMap.keySet().iterator();
        while(it.hasNext()){
            String key = it.next().toString().trim();
            for(int i = 0 ; i < clip.length ; i++){
                if(key.equals(clip[i])){

                    it.remove();
                    break;
                }
            }

        }

        /*
        for(String key:oriMap.keySet()){
            for(int i = 0 ; i < clip.length ; i++){
                if(key.toString().equals(clip[i])){
                    oriMap.remove(key);
                    break;
                }
            }
        }
        */
        return oriMap;
    }

    public static void main(String []args){
        Map<String,Integer> answerMap = new HashMap<String,Integer>();

        String FilePath = "D:\\eclipse\\WebJava2\\poem.txt";


        answerMap = ComputeString(FilePath);



        answerMap = sortMapByvalue(answerMap);

        answerMap = ClearClip(answerMap);
        int i = 1;
        for(String key:answerMap.keySet()){
            if(i <= 20){
                System.out.println("我的出现次数排名为: " + i + " key= " + key + " value= "+ answerMap.get(key));
                i++;
            }else{
                break;
            }

        }
    }
}