Java實現(xiàn)統(tǒng)計文檔中關鍵字出現(xiàn)的次數(shù)

更新時間：2022年05月12日 09:31:35 作者：錯過了時間

這篇文章主要為大家分享了利用Java語言實現(xiàn)統(tǒng)計關鍵字在文檔中出現(xiàn)的次數(shù)的方法，文中的示例代碼講解詳細，感興趣的小伙伴可以了解一下

1.實現(xiàn)URL文檔的拷貝

import java.util.Scanner;
import java.util.regex.Pattern;
import java.net.*;
import java.io.*;
import javax.swing.*;
import javax.swing.UIManager;
import java.awt.*;
import javax.swing.plaf.FontUIResource;
public class TestURL {

	static String getUserKeyWords=null;  //獲取用戶選擇的關鍵詞

	public static void main(String[] args) {
		File copyfile=new File("D:/newTest.txt");
		InputStream in=null;
		BufferedReader br=null;    //字符流寫入
		BufferedWriter out=null;   //字符流寫出
		String urladdress=null;  //獲取用戶輸入的URL地址
		
		try
		{	
			UIManager.put("JOptionPane.messageFont",new FontUIResource(new Font("宋體",Font.BOLD,20)));
			String getUserURL=JOptionPane.showInputDialog(null,"URL地址：\n","輸入URL地址",JOptionPane.PLAIN_MESSAGE);
			String urlAddr=getUserURL.substring(getUserURL.lastIndexOf("/"));
			copyfile=new File("D:/"+urlAddr);
			getUserKeyWords=JOptionPane.showInputDialog(null,"關鍵字查詢：\n","關鍵字",JOptionPane.PLAIN_MESSAGE); 
			//URL url=new URL("http://news.cctv.com/2019/06/19/ARTIhqziOpWz2COTyHFW063b190619.shtml");  //獲取URL地址
			URL url=new URL(getUserURL);  //獲取URL地址
			HttpURLConnection urlC=(HttpURLConnection)url.openConnection();  //由URL獲取URLConnection對象
			in=urlC.getInputStream();  //獲取urlC的輸入流
			br=new BufferedReader(new InputStreamReader(in,"UTF-8"));  //將url默認的字節(jié)流轉成字符流,并以UTF-8的格式寫入文檔
			out=new BufferedWriter(new FileWriter(copyfile));  //將獲取的信息寫入到TestURL文檔中
			String length=null;
			while ((length=br.readLine())!=null)
			{
				out.write(Html2Text(length));
				out.newLine();
			}
		}
		catch (Exception e)
		{
			e.getMessage();
		}finally{
			System.out.println("拷貝完成！");
			try{
			if (in!=null){in.close();}
			if (out!=null){out.close();}
			if (br!=null){br.close();}
			}catch(Exception ee){
				ee.getMessage();
			}
		}


		TextFileSearch search = new TextFileSearch();
		search.SearchKeyword(copyfile, getUserKeyWords);
	}   //程序到這就結束了 ，下面是不同方法實現(xiàn)對html的剔除功能，可以忽略

	//從html中提取純文本  ，這部分其實沒什么用，最開始想截取html中的字符串，后面檢查也沒啥用，就沒刪除，保留著
	public static String Html2Text(String inputString) {
		String htmlStr = inputString; // 含html標簽的字符串
		String textStr = "";
		java.util.regex.Pattern p_script;
		java.util.regex.Matcher m_script;
		java.util.regex.Pattern p_style;
		java.util.regex.Matcher m_style;
		java.util.regex.Pattern p_html;
		java.util.regex.Matcher m_html;
		try {
			String regEx_script = "<[\\s]*?script[^>]*?>[\\s\\S]*?<[\\s]*?\\/[\\s]*?script[\\s]*?>"; // 定義script的正則表達式{或<script[^>]*?>[\\s\\S]*?<\\/script>
	        String regEx_style = "<[\\s]*?style[^>]*?>[\\s\\S]*?<[\\s]*?\\/[\\s]*?style[\\s]*?>"; // 定義style的正則表達式{或<style[^>]*?>[\\s\\S]*?<\\/style>
	        String regEx_html = "<[^>]+>"; // 定義HTML標簽的正則表達式
	        p_script = Pattern.compile(regEx_script, Pattern.CASE_INSENSITIVE);
	        m_script = p_script.matcher(htmlStr);
	        htmlStr = m_script.replaceAll(""); // 過濾script標簽
	        p_style = Pattern.compile(regEx_style, Pattern.CASE_INSENSITIVE);
	        m_style = p_style.matcher(htmlStr);
	        htmlStr = m_style.replaceAll(""); // 過濾style標簽
	        p_html = Pattern.compile(regEx_html, Pattern.CASE_INSENSITIVE);
	        m_html = p_html.matcher(htmlStr);
	        htmlStr = m_html.replaceAll(""); // 過濾html標簽
	        textStr = htmlStr;
	    } catch (Exception e) {System.err.println("Html2Text: " + e.getMessage()); }
		//剔除空格行
		textStr=textStr.replaceAll("[ ]+", " ");
		textStr=textStr.replaceAll("(?m)^\\s*$(\\n|\\r\\n)", "");
		return textStr;// 返回文本字符串
	}

	 /*//從html中提取純文本，這個部分是簡易實現(xiàn)html剔除，只能部分篩選
	 public static String stripHT(String strHtml){
		 String txtcontent = strHtml.replaceAll("</?[^>]+>", ""); //剔出<html>的標簽  
         txtcontent = txtcontent.replaceAll("<a>\\s*|\t|\r|\n</a>", "");//去除字符串中的空格,回車,換行符,制表符  
         return txtcontent;
    }*/



/* //這個是利用java自帶的類實現(xiàn)html剔除功能，基本上沒怎么用，這部分可以忽略
import java.io.*;
import javax.swing.text.html.*;
import javax.swing.text.html.parser.*;
 
public class Html2Text extends HTMLEditorKit.ParserCallback {
	 StringBuffer s;
 
	 public Html2Text() {}
 
	 public void parse(Reader in) throws IOException {
	   s = new StringBuffer();
	   ParserDelegator delegator = new ParserDelegator();
	   // the third parameter is TRUE to ignore charset directive
	   delegator.parse(in, this, Boolean.TRUE);
	 }
 
	 public void handleText(char[] text, int pos) {
	   s.append(text);
	 }
 
	 public String getText() {
	   return s.toString();
	 }
 
	 public static void main (String[] args) {
	   try {
	     // the HTML to convert
		 //Reader in=new StringReader("string");	
	     FileReader in = new FileReader("java-new.html");
	     Html2Text parser = new Html2Text();
	     parser.parse(in);
	     in.close();
	     System.out.println(parser.getText());
	   }
	   catch (Exception e) {
	     e.printStackTrace();
	   }
	 }
}*/
	
}

2.實現(xiàn)關鍵詞在文檔的查詢功能

import java.io.Closeable;
import java.io.File;
import java.io.FileReader;
import java.io.IOException;
import java.io.LineNumberReader;
import javax.swing.UIManager;
import javax.swing.*;
import java.awt.*;
import javax.swing.plaf.FontUIResource;
 
/**
 * 對文本文件的關鍵詞進行搜索
 */
public class TextFileSearch {
	TestURL tt;
	public void SearchKeyword(File file,String keyword) {
		//參數(shù)校驗
		verifyParam(file, keyword);
		
		//行讀取
		LineNumberReader lineReader = null;
		try {
			lineReader = new LineNumberReader(new FileReader(file));
			String readLine = null;
			int times = 0;//出現(xiàn)的次數(shù)
			while((readLine =lineReader.readLine()) != null){  
				//判斷每一行中,出現(xiàn)關鍵詞的次數(shù)
				int index = 0; //獲得readLine的對象值
				int next = 0;  //定義開始查找關鍵字的序列號
				//int times = 0;//出現(xiàn)的次數(shù)
				//判斷次數(shù)
				while((index = readLine.indexOf(keyword,next)) != -1) {  //從每行的第0個索引開始遍歷關鍵字
					next = index + keyword.length();  //下一次的遍歷序號為序列號+關鍵字長度
					times++;//次數(shù)加1
				}
				/*if(times > 0) {
					//System.out.println("第"+ lineReader.getLineNumber() +"行" + "出現(xiàn) "+keyword+" 次數(shù): "+times);	
				}*/
			}
			if (times>0)
			{
				UIManager.put("JOptionPane.messageFont",new FontUIResource(new Font("宋體",Font.BOLD,20)));
				JOptionPane.showMessageDialog(null,"關鍵字"+"@"+tt.getUserKeyWords+"@"+"共有"+times+"個");
			}
		} catch (IOException e) {
			e.printStackTrace();
		} finally {
			//關閉流
			close(lineReader);
		}
	}
 
	/**
	 * 參數(shù)校驗
	 */
	private void verifyParam(File file, String keyword) {
		//對參數(shù)進行校驗證
		if(file == null ){
			throw new NullPointerException("the file is null");
		}
		if(keyword == null || keyword.trim().equals("")){
			throw new NullPointerException("the keyword is null or \"\" ");
		}
		
		if(!file.exists()) {
			throw new RuntimeException("the file is not exists");
		}
		//非目錄
		if(file.isDirectory()){
			throw new RuntimeException("the file is a directory,not a file");
		}
		
		//可讀取
		if(!file.canRead()) {
			throw new RuntimeException("the file can't read");
		}
	}
	
	/**
	 * 關閉流
	 */
	private void close(Closeable able){
		if(able != null){
			try {
				able.close();
			} catch (IOException e) {
				e.printStackTrace();
				able = null;
			}
		}
	}
 
}