lucene全文检索word内容

创建索引 Lucene 3.0+

package test;

import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.util.Date;

import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.DateTools;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.SimpleFSDirectory;
import org.apache.lucene.util.Version;
import org.apache.poi.hwpf.extractor.WordExtractor;
/**
 * 创建索引 Lucene 3.0+
 * @author Administrator
 *
 */
public class LuceneTest {

	/**
	 * @param args
	 * @throws IOException 
	 */
	public static void main(String[] args) throws IOException {
		//保存索引文件的地方
		String indexDir = "D:\\indexDir";
		//将要搜索word文件的地方
		String dateDir = "D:\\dateDir";
		IndexWriter indexWriter = null;
		//创建Directory对象
		Directory dir = new SimpleFSDirectory(new File(indexDir));
		//创建IndexWriter对象,第一个参数是Directory,第二个是分词器,第三个表示是否是创建,如果为false为在此基础上面修改,第四表示表示分词的最大值，比如说new MaxFieldLength(2)，就表示两个字一分，一般用IndexWriter.MaxFieldLength.LIMITED 
		indexWriter = new IndexWriter(dir,new StandardAnalyzer(Version.LUCENE_30),true,IndexWriter.MaxFieldLength.UNLIMITED);
		File[] files = new File(dateDir).listFiles();
		for (int i = 0; i < files.length; i++) {
			Document doc = new Document();
			InputStream in = new FileInputStream(files[i]);
			WordExtractor w = new WordExtractor(in);
			//创建Field对象，并放入doc对象中
			doc.add(new Field("contents", w.getText(),Field.Store.YES,Field.Index.ANALYZED)); 
			doc.add(new Field("filename", files[i].getName(), 
								Field.Store.YES, Field.Index.NOT_ANALYZED));
			doc.add(new Field("indexDate",DateTools.dateToString(new Date(), DateTools.Resolution.DAY),Field.Store.YES,Field.Index.NOT_ANALYZED));
			//写入IndexWriter
			indexWriter.addDocument(doc);
		}
		//查看IndexWriter里面有多少个索引
		System.out.println("numDocs"+indexWriter.numDocs());
		indexWriter.close();
		
	}

}

搜索索引 Lucene 3.0+

package test;

import java.io.File;
import java.io.IOException;

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.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.SimpleFSDirectory;
import org.apache.lucene.util.Version;
/**
 * 搜索索引 Lucene 3.0+
 * @author Administrator
 *
 */
public class LuceneSearch {

	public static void main(String[] args) throws IOException, ParseException {
		//保存索引文件的地方
		String indexDir = "D:\\indexDir";
		Directory dir = new SimpleFSDirectory(new File(indexDir));
		//创建 IndexSearcher对象，相比IndexWriter对象，这个参数就要提供一个索引的目录就行了
		IndexSearcher indexSearch = new IndexSearcher(dir);
		//创建QueryParser对象,第一个参数表示Lucene的版本,第二个表示搜索Field的字段,第三个表示搜索使用分词器
		QueryParser queryParser = new QueryParser(Version.LUCENE_30,
				"contents", new StandardAnalyzer(Version.LUCENE_30));
		//生成Query对象
		Query query = queryParser.parse("高铁");
		//搜索结果 TopDocs里面有scoreDocs[]数组，里面保存着索引值
		TopDocs hits = indexSearch.search(query, 10);
		//hits.totalHits表示一共搜到多少个
		System.out.println("找到了"+hits.totalHits+"个");
		//循环hits.scoreDocs数据，并使用indexSearch.doc方法把Document还原，再拿出对应的字段的值
		for (int i = 0; i < hits.scoreDocs.length; i++) {
			ScoreDoc sdoc = hits.scoreDocs[i];
			Document doc = indexSearch.doc(sdoc.doc);
			System.out.println(doc.get("filename"));			
		}		
		indexSearch.close();
	}
}

用到的jar包：

lucene-core-3.0.3.jar

poi-3.7-20101029.jar

poi-ooxml-3.7-20101029.jar

poi-ooxml-schemas-3.7-20101029.jar

poi-scratchpad-3.7-20101029.jar