Lucene practice

阅读更多

1.simply practice the lucene api for search document and data, post code first

lucene version :2.2.0

set up the index of files

java 代码

package com.aaron.lucene;

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 demonstrate the process of creating index with Lucene for text
 * files
 */
public class TxtFileIndexer {
    public static void main(String[] args) throws Exception {
        // indexDir is the directory that hosts Lucene's index files
        File indexDir = new File("C:/bin/lucence/Index");
        // dataDir is the directory that hosts the text files that to be indexed
        File dataDir = new File("C:/bin/lucence/Data");
        Analyzer luceneAnalyzer = new StandardAnalyzer();
        File[] dataFiles = dataDir.listFiles();
        IndexWriter indexWriter = new IndexWriter(indexDir, luceneAnalyzer,
                true);
        long startTime = new Date().getTime();
        for (int i = 0; i < dataFiles.length; i++) {
            if (dataFiles[i].isFile()
                    && dataFiles[i].getName().endsWith(".txt")) {
                System.out.println("Indexing file "
                        + dataFiles[i].getCanonicalPath());
                Document document = new Document();
                Reader txtReader = new FileReader(dataFiles[i]);

                document.add(new Field("path", dataFiles[i].getPath(),
                        Field.Store.YES, Field.Index.UN_TOKENIZED));
                document.add(new Field("contents", txtReader));
                indexWriter.addDocument(document);
            }
        }
        indexWriter.optimize();
        indexWriter.close();
        long endTime = new Date().getTime();

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

Search key word

java 代码

package com.aaron.lucene;

import java.io.File;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.Hits;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.store.FSDirectory;

/**
 * This class is used to demonstrate the
 * process of searching on an existing
 * Lucene index
 *
 */
public class TextFileSearcher {
    public static void main(String[] args) throws Exception {
        String queryStr = "lucene";
        //This is the directory that hosts the Lucene index
        File indexDir = new File("C:/bin/lucence/Index");
        FSDirectory directory = FSDirectory.getDirectory(indexDir);
        IndexSearcher searcher = new IndexSearcher(directory);
        if (!indexDir.exists()) {
            System.out.println("The Lucene index is not exist");
            return;
        }
        Term term = new Term("contents", queryStr.toLowerCase());
        TermQuery luceneQuery = new TermQuery(term);
        Hits hits = searcher.search(luceneQuery);
        for (int i = 0; i < hits.length(); i++) {
            Document document = hits.doc(i);
            System.out.println("File: " + document.get("path"));
        }
    }
}