[原创]基于apache Lucene的mp3搜索器
前些日子找机器上的一首老歌时，费了些周折，后想到既然这些mp3有自己的标签信息，为何不利用起来呢？笔者就尝试用Lucene实现，分两部分，Mp3Indexer.java是创建索引的，mp3search.jsp是搜索mp3的页面。
下面是Mp3Indexer.java的代码。
package mp3indexer;
import java.io.*;
import java.text.*;
import java.util.*;
import org.apache.lucene.analysis.cjk.*;
import org.apache.lucene.document.*;
import org.apache.lucene.index.*;
public class Mp3Indexer
{
public final static String mp3Path="d:\\mp3";//mp3所在目录
public final static String indexPath="c:\\mp3Indexer";//索引存放目录
public static void main(String[] args) throws ClassNotFoundException, IOException{
try {
IndexWriter writer = new IndexWriter(indexPath, new CJKAnalyzer(), true);
indexMp3s(writer, new File(mp3Path));
System.out.println("优化中....");
writer.optimize();
writer.close();
} catch (Exception e) {
System.out.println(e.getMessage());
}
}
public static void indexMp3s(IndexWriter writer, File file) throws Exception {
if (file.isDirectory()) {
String[] files = file.list();
for (int i = 0; i < files.length; i++) {
indexMp3s(writer, new File(file, files[i]));
}
}
else if (file.getPath().endsWith(".mp3")) { //只对 MP3 文件做索引
System.out.print("正在处理文件:" + file + " ....");
// Add mp3 file ....
Document doc = new Document();
doc.add(Field.Text("name", file.getName())); //索引文件名
doc.add(Field.UnIndexed("modified", DateFormat.getDateTimeInstance().format(new Date(file.lastModified())))); //索引最后修改时间
doc.add(Field.Text("size",""+NumberFormat.getNumberInstance().format(file.length()/1048576.0)+"MB")); //索引最后修改时间
FileReader fReader = new FileReader(file);
java.io.RandomAccessFile r=new RandomAccessFile(file,"r");
r.seek(file.length()-128);
byte[] bt=new byte[127];
r.read(bt);
String labelInfo=new String(bt,"GB2312");
System.out.println(labelInfo);
if (labelInfo.startsWith("TAG")) {
doc.add(Field.Text("comment", labelInfo));
}
System.out.println("[处理完成]");
r.close();
fReader.close();
writer.addDocument(doc);
} //end else if
}
} //end class
|
本类阅读TOP10