java 统计文本中出现概率最高的10个字符串

以前经常在CSDN博客上看别人的文章，有时是遇到难题为了寻找思路，有时则是为了偷懒，直接复制别人的源代码，所以对于写这些博客的技术大神，我都是佩服且感激的。感激于他们把我的问题分析的如此透彻明白，佩服于他们遇到问题不但自己能解决，还把思路分享给我，使我也能够受益。今天，这些‘雷锋“或者”红领巾“传递的正能量终于感动了我(实际上是teacher的作业…哎)，我也要写自己的技术博客啦，好吧，废话不多说，开始写思路！
统计字符串在某一文本出现的概率，思路上比较简单，分为以下几步：
1.读取项目的文件位置，将读出的字节流转化为字符串；
2.字符串切分，利用空格符把独处的字符串切分为字符串数组；
3.字符串统计，遍历生成字符串数组，将这些字符串数组存储为hanshMap形式，key为字符串，value为出现次数;
4.对常见的虚词或者介词进行过滤
5.对hanshMap的value排序，即可得到相应结果。
OK ，就是这么简单，剩下的可能就是有些具体代码大家会遇到点问题，所以直接贴代码：

package com.zhongcai.demo;
import java.io.BufferedReader;  
import java.io.File;  
import java.io.FileNotFoundException;  
import java.io.FileReader;  
import java.io.FileWriter;  
import java.io.IOException;  
import java.util.Collections;  
import java.util.Comparator;  
import java.util.HashMap;  
import java.util.Iterator;  
import java.util.LinkedHashMap;  
import java.util.LinkedList;  
import java.util.List;  
import java.util.Map;  

/** 
 * Author:zhangjw 
 * Date:2014/9/28 16:37 
 * function:统计一段字符串中出现频率最高的前10个词 
 *  
 * */  

public class Count {  
    public static void main(String[] args) {  
        Count c = new Count();  
        String filepath0 = new File("File").getAbsolutePath();
        System.out.println(filepath0);
        String filepath = new File("File").getAbsolutePath()+"\\in.txt";  
        String source = c.getStringFrom(filepath);  
        String[] stringArray = source.split(" ");  
        HashMap<String , Integer> map = new HashMap<String , Integer>();   
        for(int i = 0; i < stringArray.length; i++)  
        {  
             Iterator iterator = map.keySet().iterator();   
             int flag = 0;  
             while (iterator.hasNext()) {      
                 Object key = iterator.next();  
                 if(map.containsKey(stringArray[i]))  
                 {  
                        int value = map.get(stringArray[i]);  
                        value++;  
                        map.put(stringArray[i], value);  
                        flag = 1;  
                        break;  
                 }  
             }  
             if(flag == 0)  
             {  
                 map.put(stringArray[i], 1);  
             }  
        }  
        map = (HashMap<String, Integer>)new Count().sortByValue(map);  

        Iterator iterator = map.keySet().iterator();   
        int count = 0;  
        FileWriter fileWriter;  
        try {  
            fileWriter = new FileWriter(new File("File").getAbsolutePath()+"\\out.txt");  
            fileWriter.write("*************************"+"\n");  
            fileWriter.write("***频率最高的10个词语为***"+"\n");  
            fileWriter.write("*************************"+"\n");  
            while (iterator.hasNext()) {   
                Object key = iterator.next();  
                String filter = key.toString();  
                //在此处进行常见字符串的过滤  
                if(!filter.equals("would")&&!filter.equals("when")&&!filter.equals("they")&&!filter.equals("so")  
                        &&!filter.equals("I")&&!filter.equals("if")&&!filter.equals("up")&&!filter.equals("who")  
                        &&!filter.equals("been")&&!filter.equals("upon")&&!filter.equals("which")&&!filter.equals("from")  
                        &&!filter.equals("an")&&!filter.equals("my")&&!filter.equals("very")&&!filter.equals("Mr")  
                        &&!filter.equals("My")&&!filter.equals("have")&&!filter.equals("him")&&!filter.equals("no")  
                        &&!filter.equals("The")&&!filter.equals("were")&&!filter.equals("this")&&!filter.equals("all")  
                        &&!filter.equals("or")&&!filter.equals("by")&&!filter.equals("she")&&!filter.equals("as")  
                        &&!filter.equals("but")&&!filter.equals("—")&&!filter.equals("on")&&!filter.equals("be")  
                        &&!filter.equals("her")&&!filter.equals("his")&&!filter.equals("had")&&!filter.equals("for")  
                        &&!filter.equals("that")&&!filter.equals("with")&&!filter.equals("was")&&!filter.equals("at")  
                        &&!filter.equals("he")&&!filter.equals("it")&&!filter.equals("in")&&!filter.equals("of")  
                        &&!filter.equals("is")&&!filter.equals("not")&&!filter.equals("you")&&!filter.equals("me")  
                        &&!filter.equals("He")&&!filter.equals("")&&!filter.equals("and")&&!filter.equals("I")&&  
                        !filter.equals("the")&&!filter.equals("to")&&!filter.equals(" ")&&!filter.equals("a"))  
                {  

                    try {  
                        fileWriter.write("    "+String.valueOf(key.toString()+" "+map.get(key)+"次"+"\n"));  
                        System.out.println("    "+String.valueOf(key.toString()+" "+map.get(key)+"次"+"\n"));
                        count++;  
                        fileWriter.flush();  
                        if(count == 10)  
                        {  
                            fileWriter.write("************************"+"\n");  
                            fileWriter.write("****0491201:张俊伟******"+"\n");  
                            fileWriter.write("************************"+"\n");  
                            fileWriter.close();  
                            break;  
                        }  

                    } catch (IOException e) {  
                        e.printStackTrace();  
                    }  



                }  
            }  
        } catch (IOException e1) {  

            e1.printStackTrace();  
        }  


  }  



    public  Map sortByValue(Map<String, Integer> map) {    
        List list = new LinkedList(map.entrySet());    
        Collections.sort(list, new Comparator(){    
               public int compare(Object o1, Object o2) {    
                         return ((Comparable) ((Map.Entry)o2).getValue())    
                            .compareTo(((Map.Entry)o1).getValue());    
               }    
        });    
        Map result = new LinkedHashMap();    

        for (Iterator it = list.iterator(); it.hasNext();) {    
              Map.Entry entry = (Map .Entry) it.next();    
              result.put(entry.getKey(), entry.getValue());    
        }    
        return result;    

    }    

    public String getStringFrom(String filepath) {  
        File file = new File(filepath);  
        StringBuilder sb = new StringBuilder();  
        BufferedReader br;  
        try {  
            br = new BufferedReader(new FileReader(file));  
            String temp = "";  
            try {  
                while ((temp = br.readLine())!=null) {  
                    sb.append(temp+" ");  
                }  
                br.close();  
                String result = sb.toString();  
                return result;  
            } catch (IOException e) {  
                e.printStackTrace();  
            }  

        } catch (FileNotFoundException e) {  
            e.printStackTrace();  
        }  
        return null;  
    }  

}  

原文链接：http://blog.csdn.net/unexisted_/article/details/40351073