深入 Lucene 索引机制

package lucene.index;

import java.io.File;
import java.io.FileReader;
import java.io.Reader;
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;

/**
 * This class demonstrates the process of creating an index with Lucene 
 * for text files in a directory.
 */
public class TextFileIndexer {
 public static void main(String[] args) throws Exception{
   //fileDir is the directory that contains the text files to be indexed
   File   fileDir  = new File("C:\\files_to_index ");

   //indexDir is the directory that hosts Lucene's index files
   File   indexDir = new File("C:\\luceneIndex");
   Analyzer luceneAnalyzer = new StandardAnalyzer();
   IndexWriter indexWriter = new IndexWriter(indexDir,luceneAnalyzer,true);
   File[] textFiles  = fileDir.listFiles();
   long startTime = new Date().getTime();

   //Add documents to the index
   for(int i = 0; i < textFiles.length; i++){
     if(textFiles[i].isFile() >> textFiles[i].getName().endsWith(".txt")){
       System.out.println("File " + textFiles[i].getCanonicalPath() 
              + " is being indexed");
       Reader textReader = new FileReader(textFiles[i]);
       Document document = new Document();
       document.add(Field.Text("content",textReader));
       document.add(Field.Text("path",textFiles[i].getPath()));
       indexWriter.addDocument(document);
     }
   }

   indexWriter.optimize();
   indexWriter.close();
   long endTime = new Date().getTime();

   System.out.println("It took " + (endTime - startTime) 
              + " milliseconds to create an index for the files in the directory "
              + fileDir.getPath());
  }
}

Analyzer luceneAnalyzer = new StandardAnalyzer();

IndexWriter indexWriter = new IndexWriter(indexDir,luceneAnalyzer,true);

Document document = new Document();
document.add(Field.Text("content",textReader));
document.add(Field.Text("path",textFiles[i].getPath()));
indexWriter.addDocument(document);

indexWriter.close();

File   indexDir = new File("C:\\luceneIndex");
IndexReader ir = IndexReader.open(indexDir);
ir.delete(1);
ir.delete(new Term("path","C:\\file_to_index\lucene.txt"));
ir.close();

File   indexDir = new File("C:\\luceneIndex");
IndexReader ir = IndexReader.open(indexDir);
ir.undeleteAll();
ir.close();

File   indexDir = new File("C:\\luceneIndex");
Analyzer luceneAnalyzer = new StandardAnalyzer();
IndexWriter indexWriter = new IndexWriter(indexDir,luceneAnalyzer,false);
indexWriter.optimize();
indexWriter.close();

/**
 * This class demonstrates how to improve the indexing performance 
 * by adjusting the parameters provided by IndexWriter.
 */
public class AdvancedTextFileIndexer  {
  public static void main(String[] args) throws Exception{
    //fileDir is the directory that contains the text files to be indexed
    File   fileDir  = new File("C:\\files_to_index");

    //indexDir is the directory that hosts Lucene's index files
    File   indexDir = new File("C:\\luceneIndex");
    Analyzer luceneAnalyzer = new StandardAnalyzer();
    File[] textFiles  = fileDir.listFiles();
    long startTime = new Date().getTime();

    int mergeFactor = 10;
    int minMergeDocs = 10;
    int maxMergeDocs = Integer.MAX_VALUE;
    IndexWriter indexWriter = new IndexWriter(indexDir,luceneAnalyzer,true);        
    indexWriter.mergeFactor = mergeFactor;
    indexWriter.minMergeDocs = minMergeDocs;
    indexWriter.maxMergeDocs = maxMergeDocs;

    //Add documents to the index
    for(int i = 0; i < textFiles.length; i++){
      if(textFiles[i].isFile() >> textFiles[i].getName().endsWith(".txt")){
        Reader textReader = new FileReader(textFiles[i]);
        Document document = new Document();
        document.add(Field.Text("content",textReader));
        document.add(Field.Keyword("path",textFiles[i].getPath()));
        indexWriter.addDocument(document);
      }
    }

    indexWriter.optimize();
    indexWriter.close();
    long endTime = new Date().getTime();

    System.out.println("MergeFactor: " + indexWriter.mergeFactor);
    System.out.println("MinMergeDocs: " + indexWriter.minMergeDocs);
    System.out.println("MaxMergeDocs: " + indexWriter.maxMergeDocs);
    System.out.println("Document number: " + textFiles.length);
    System.out.println("Time consumed: " + (endTime - startTime) + " milliseconds");
  }
}

int mergeFactor = 10;
int minMergeDocs = 10;
int maxMergeDocs = Integer.MAX_VALUE;
IndexWriter indexWriter = new IndexWriter(indexDir,luceneAnalyzer,true);        
indexWriter.mergeFactor = mergeFactor;
indexWriter.minMergeDocs = minMergeDocs;
indexWriter.maxMergeDocs = maxMergeDocs;