[求助]文本检索功能实现
提示: 作者被禁止或删除 内容自动屏蔽
回复 楼主 txing521
package com.lch.test;import java.awt.Font;
import java.awt.event.ActionEvent;
import java.awt.event.ActionListener;
import java.util.ArrayList;
import java.util.List;
import javax.swing.JButton;
import javax.swing.JComboBox;
import javax.swing.JFrame;
import javax.swing.JLabel;
import javax.swing.JPanel;
import javax.swing.JScrollPane;
import javax.swing.JTextArea;
import javax.swing.JTextField;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.queryParser.ParseException;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.Hits;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
public class FindFrame extends JFrame
{
public FindFrame()
{
this.setTitle("文本挖掘");
this.setSize(600, 400);
this.setLocationRelativeTo(null);
this.setDefaultCloseOperation(JFrame.EXIT_ON_CLOSE);
this.add(new FindPanel());
}
public static void main(String[] args) throws Exception
{
TextFileIndexer t = new TextFileIndexer();
TextFileIndexer.s(args);
FindFrame frame=new FindFrame();
frame.setVisible(true);
}
}
class FindPanel extends JPanel
{
private JLabel findLabel, pathLabel;
private JTextField findField, showPathField;
private JComboBox pathBox;
private JTextArea resultArea;
private JButton findButton;
public FindPanel()
{
this.setLayout(null);
findLabel=new JLabel("请输入关键字");
findLabel.setFont(new Font("仿宋", Font.BOLD, 20));
findLabel.setSize(200, 60);
findLabel.setLocation(10, 10);
findField=new JTextField();
findField.setSize(200, 25);
findField.setLocation(10, 55);
pathLabel=new JLabel("在这里寻找");
pathLabel.setFont(new Font("仿宋", Font.BOLD, 20));
pathLabel.setSize(200, 60);
pathLabel.setLocation(10, 65);
String[] pathString={ "d:\\s\\1.txt", "d:\\s\\2.txt", "d:\\s\\3.txt",
"d:\\s\\4.txt", "d:\\s\\5.txt", "d:\\s\\6.txt", "d:\\s\\7.txt",
"d:\\s\\8.txt"};
pathBox=new JComboBox(pathString);
pathBox.setSize(200, 25);
pathBox.setLocation(10, 110);
findButton=new JButton("搜索");
findButton.setFont(new Font("仿宋", Font.BOLD, 15));
findButton.setSize(80, 30);
findButton.setLocation(65, 145);
resultArea=new JTextArea();
resultArea.setEnabled(false);
resultArea.setFont(new Font("宋体", Font.PLAIN, 20));
JScrollPane area=new JScrollPane(resultArea);
area.setSize(350, 330);
area.setLocation(220, 10);
showPathField=new JTextField();
showPathField.setEditable(false);
showPathField.setSize(600, 25);
showPathField.setLocation(0, 340);
this.add(findLabel);
this.add(findField);
this.add(pathLabel);
this.add(pathBox);
this.add(findButton);
this.add(area);
this.add(showPathField);
findButton.addActionListener(new ActionListener(){
public void actionPerformed(ActionEvent arg0)
{
resultArea.setText(null); //清空文本区
//线程
new Thread()
{
public void run()
{
try {
listfile();
} catch (Exception e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
}.start();
}
});
}
//构建一个取得抽象路径名数组的方法
public void listfile() throws Exception
{
Hits hits = null;
// 搜索内容自己换
String queryString = "";
String pathBoxText = "";
queryString = findField.getText();
if(queryString.equals("")){
return;
}
int selectInt = pathBox.getSelectedIndex() + 1;
System.out.println(selectInt);
pathBoxText = (String)pathBox.getSelectedItem();
//System.out.println(pathBoxText);
Query query = null;
IndexSearcher searcher = new IndexSearcher("d:\\index"+selectInt); // 这里注意索引存放的路径
System.out.println("正在搜索目录d:\\index"+selectInt);
Analyzer analyzer = new StandardAnalyzer();
try {
QueryParser qp = new QueryParser("body", analyzer);
/**
* 建索引的时候我们指定了body建立为内容，我们搜索的时候也是针对body的，所以 QueryParser qp = new
* QueryParser("body", analyzer); 这句和建立索引时候 Field FieldBody = new
* Field("body", temp, Field.Store.YES, Field.Index.TOKENIZED,
* Field.TermVector.WITH_POSITIONS_OFFSETS); 的这句的"body"是对应的。
*/
query = qp.parse(queryString);
} catch (ParseException e) {
System.out.println("异常");
}
if (searcher != null) {
hits = searcher.search(query);
if (hits.length() > 0) {
System.out.println("找到:" + hits.length() + " 个结果!");
List<String> list = new ArrayList<String>();
for (int i = 0; i < hits.length(); i++) {// 输出搜索信息
Document document = hits.doc(i);
list.add(document.get("body"));
list.add(document.get("path"));
// System.out.println("contents：" + document.get("body"));
// 同样原理这里的document.get("body")就是取得建立在索引文件里面的额body的所有内容
// 你若想输出文件路径就用document.get("path")就可以了
}
StringBuffer sb = new StringBuffer();
sb.append("找到:" + hits.length() + " 个结果!"+"\n");
for (int i = 0; i < list.size(); i++) {
sb.append(list.get(i));
sb.append("\n");
}
resultArea.setText(sb.toString());
} else {
System.out.println("0个结果!");
}
}
}
/* public static String readTxt(String path) {
StringBuffer content = new StringBuffer("");// 文档内容
try {
FileReader reader = new FileReader(path);
BufferedReader br = new BufferedReader(reader);
String s1 = null;
while ((s1 = br.readLine()) != null) {
content.append(s1 + "\r");
}
br.close();
reader.close();
} catch (IOException e) {
e.printStackTrace();
}
return content.toString().trim();
}
*/
}
***********************************************************************************
***********************************************************************************
***********************************************************************************
package com.lch.test;
import
import
import
import
import java.util.Date;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexWriter;
/**
*
*/
/**
* @author lijieli_2
*
*/
public class TextFileIndexer {
/**
* @param args
*/
public static void s(String[] args) throws Exception { /* 指明要索引文件夹的位置,这里是d盘的s文件夹下 */
//File[] textFiles = fileDir.listFiles();
long startTime = new Date().getTime();
// 增加document到索引去
System.out.println("File正在被索引.");
/*
* 注意要变的就是这里，路径和读取文件的方法
*/
String[] paths = { "d:\\s\\1.txt", "d:\\s\\2.txt", "d:\\s\\3.txt",
"d:\\s\\4.txt", "d:\\s\\5.txt", "d:\\s\\6.txt", "d:\\s\\7.txt",
"d:\\s\\8.txt", };
int i = 1;
for (String path : paths) {
File fileDir = new File("d:\\s");
/* 这里放索引文件的位置 */
File indexDir = new File("d:\\index" + i);
System.out.println("创建索引目录为d:\\index" + i );
i++;
Analyzer luceneAnalyzer = new StandardAnalyzer();
IndexWriter indexWriter = new IndexWriter(indexDir, luceneAnalyzer,
true);
String temp = readTxt(path);
// String path ="d:\\s\\index.htm";
// String temp = ReadFile.readHtml(path);
Document document = new Document();
Field FieldPath = new Field("path", path, Field.Store.YES,
Field.Index.NO);
Field FieldBody = new Field("body", temp, Field.Store.YES,
Field.Index.TOKENIZED,
Field.TermVector.WITH_POSITIONS_OFFSETS);
document.add(FieldPath);
document.add(FieldBody);
indexWriter.addDocument(document);
indexWriter.optimize();
indexWriter.close();
}
// optimize()方法是对索引进行优化
// // 测试一下索引的时间
// long endTime = new Date().getTime();
// System.out.println("这花费了" + (endTime - startTime) + " 毫秒来把文档增加到索引里面去!"
// + fileDir.getPath());
}
public static String readTxt(String path) {
StringBuffer content = new StringBuffer("");// 文档内容
try {
FileReader reader = new FileReader(path);
BufferedReader br = new BufferedReader(reader);
String s1 = null;
while ((s1 = br.readLine()) != null) {
content.append(s1 + "\r");
}
br.close();
reader.close();
} catch (IOException e) {
e.printStackTrace();
}
return content.toString().trim();
}
}
***********************************************************************************
***********************************************************************************
思路：1. 建立的索引的时候就分开建立，可能我这么写的方法效率有点低。
2. 其他的几个问题，不值得我去做。
3. 要不是对这个问题感兴趣，不会回答你的问题。今天才注册！