大二下学期学习进度（十）

编码行数：850

编码时长：13h

发表博客数量：8

所学知识点：

统计文章中各单词出现的频率，并去掉常用单词。问题解决基本思路：先将所要读取的文件打开，先定义一个fileReader对象，用来初始化BufferedReader，new一个BufferedReader对象，将文件内容读取到缓存，定义一个字符串缓存，将字符串存放缓存中。然后按行读取，每一行读取的内容用append方法放在字符串缓存后边，再用toString()将其转化为字符串，根据".",",","?","!",":","‘","’","“","”","—",";","-"等将他们替换成空格，在根据空格分割成一个个单词放进字符串数组中，这里的方法用到Map方法，Map<String, Integer> map = new TreeMap<String, Integer>();两个参数分别代表出现的单词和其出现的次数。用for循环遍历单词数组，先统一转化成小写，在调用自定义方法judgeNouse（）去掉常见单词，用map.get方法看其出现的次数，如果为0则不重复出现则其count记为1，否则为重复出现，其count++；并

class entity11{//定义单词的实体类，便于list对象集合操作
	String danci;
	int cishu;
	public entity11(String zimu,int cishu) {
		this.danci = zimu;
		this.cishu = cishu;
	}
	public String getDanci() {
		return danci;
	}
	
	public int getCishu() {
		return cishu;
	}
	
}
public class DanciCollect {
	public static boolean judgeNouse(String str) throws IOException {//去掉常用单词的方法
		boolean flag = true;
		FileReader fr = new FileReader("judge.txt");
		BufferedReader bf = new BufferedReader(fr);
		String str1;			// 按行读取字符串
		while ((str1 = bf.readLine()) != null) {
			if(str.equals(str1)) {
				flag = false;
			}
		}
		bf.close();
		fr.close();
		
		
		return flag;	
			
	
    }  
	public static String toLowerCase(String str) {//将字符串转化成小写
		char []StringArr = str.toCharArray();
		for (int i = 0; i < StringArr.length; i++) {
			StringArr[i] = Character.toLowerCase(StringArr[i]);
		}
    	StringBuffer sb = new StringBuffer();
		for(int i = 0;i < StringArr.length;i++) {
			sb.append(StringArr[i]);
		}
		String str1 = sb.toString();
		return str1; 
		
	}
	public static void collect1() throws IOException {
		try {
			File file1 = new File("piao.txt");//定义一个file对象，用来初始化FileReader
			FileReader reader1 = new FileReader(file1);//定义一个fileReader对象，用来初始化BufferedReader
			BufferedReader bReader1 = new BufferedReader(reader1);//new一个BufferedReader对象，将文件内容读取到缓存
			StringBuilder sb1 = new StringBuilder();//定义一个字符串缓存，将字符串存放缓存中
			String s1 = "";
			while ((s1 =bReader1.readLine()) != null) {//逐行读取文件内容，不读取换行符和末尾的空格
			sb1.append(s1);//将读取的字符串添加换行符后累加p存放在缓存中
			}
			bReader1.close();
			String text = sb1.toString();
			int i=0;
			String[] array = {".",",","?","!",":","‘","’","“","”","—",";","-"};
			for (int j = 0; j < array.length; j++) {
				text = text.replace(array[j]," ");                      //将text中的array数组中包含的特殊字符用空格代替
			}
			String[] textArray = text.split(" ");                       //根据空格将text分割并存放在textArray中
			Map<String, Integer> map = new TreeMap<String, Integer>();
			Integer count = 0;//每个字母的次数
			Integer total = 0;//总共多少个字母
			while(i < textArray.length) {
				
					String str = toLowerCase(textArray[i]);
					if(!judgeNouse(str)) {
						total = total + 1;
						count = map.get(str+"");
						if (count == null) {//单词没有出现重复;
							count = 1;
						}else {//单词出现重复，count+1;
							count++;
						}
						map.put(str+"", count);
						i++;
					
					}
					else {
						i++;
					}
					
				
			  }
		
			List<entity11> result = new ArrayList<>();
			
			entity11 e = null;
			for (String str : map.keySet()) {
				e = new entity11(str,map.get(str));
				result.add(e);
			}
			result.sort((entity11 e1,entity11 e2)->{
				return e2.getCishu()-e1.getCishu();});
			System.out.println("文章共计"+total+"个单词");
			
	        
			for(int ii = 0 ; ii < result.size();ii++) {
				System.out.println(result.get(ii).getDanci()+"在文章中出现"+result.get(ii).getCishu()+"次,其频率为"+String.format("%.2f",result.get(ii).getCishu()*1.0/total));
			}
//			for(entity11 ee : result) {
//				System.out.println("单词"+ee.getDanci()+"在文章中出现"+ee.getCishu()+"次,其频率为"+String.format("%.2f",ee.getCishu()*1.0/total));
//			}
			
	
	
			
	//		for (String str : map.keySet()) {
	//			System.out.println("字母"+str+"出现"+map.get(str)+"次,其频率为:"+String.format("%.2f",map.get(str)*1.0/total));
	//		}
		} catch (FileNotFoundException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
	}
	public static void main(String args[]) throws IOException {
		try {
			DanciCollect dancicollect = new DanciCollect();
			DanciCollect.collect1();
		}catch (FileNotFoundException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
	}
}

　　

且将其单词本身字符串和出现次数count赋值给map对象map.put（）；最后将其转化成List集合，根据出现频率排序输出。源代码如下：