建立索引源代码

时间：2007-07-31 来源：sdwsyjp

package test; import java.io.File;
import java.io.FileReader;
import java.io.IOException;
import java.util.Date; 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;
public class Indexer { /**
* @param args
*/
public static void main(String[] args) {
  // TODO Auto-generated method stub
  //创建索引文件和要索引文件所在的目录
  File indexDir = new File(Constants.INDEX_STORE_PATH);//调用Constants中的常量
  File dataDir = new File(Constants.INDEX_FILE_PATH);
  //获取建立索引开始的时间
  long start =new Date().getTime();
  int numIndexed = 0;
  try {
   numIndexed = index(indexDir,dataDir);返回要索引文件的数量
  } catch (IOException e) {
   // TODO Auto-generated catch block
   e.printStackTrace();
  }
  long end = new Date().getTime();
  System.out.print("Indexing"+ numIndexed + "files took"
    + (end - start) + "milliseconds");//计算整个索引过程所需要的时间
   } private static int index(File indexDir, File dataDir) throws IOException{
  // TODO Auto-generated method stub
  if(!dataDir.exists() || !dataDir.isDirectory())
  {
   throw new IOException(dataDir + "does not exit or" +
     "is not a directory");
  }   //第一个参数是索引文件存放目录，第二个参数是分析器（可选），第三个参数确定是否覆盖原有索引，建立此对象对索引进行写操作。
  IndexWriter writer = new IndexWriter(indexDir,new StandardAnalyzer(),true);
  writer.setUseCompoundFile(false);//使用复合文件？
  indexDirectory(writer,dataDir);
  int numIndexed = writer.docCount();
  writer.optimize();//进行优化
  writer.close();//关闭writer对象
  return numIndexed;
} //对文件夹和文件查找遍历。 private static void indexDirectory(IndexWriter writer, File dataDir)
  throws IOException{
  // TODO Auto-generated method stub
  File[] files = dataDir.listFiles();
  for(int i = 0;i<files.length;i++)
  {
   File f = files[i];
   if(f.isDirectory())
   {
    indexDirectory(writer,f);
   }
   else if(f.getName().endsWith(".txt"))
   {
    indexFile(writer,f);
   }
  }

} private static void indexFile(IndexWriter writer, File f) throws IOException{
  // TODO Auto-generated method stub
  if(f.isHidden() || !f.exists() || !f.canRead())
  {
   return;
  }
  System.out.println("Indexing" + f.getCanonicalPath()); //最主要的部分
  Document doc = new Document();
  Field fieldContents = new Field("contents", new FileReader(f));//得到文本的内容域
  doc.add(fieldContents);
  Field fieldName = new Field("name",f.getCanonicalPath(),Field.Store.YES,Field.Index.UN_TOKENIZED);//得到文本的路径名称，不同的内容会有不同的操作方法（四种）
  doc.add(fieldName);
  writer.addDocument(doc); } }