lucene入门实例

全文检索技术在文档管理方面应用非常广泛，lucene是apache里面的一个子项目。

全文检索，主要几个过程，创建索引文件、检索、通过索引查找相关文件。

通过一个简单的入门实例来理解lucene的处理过程。

1、为文件创建索引

package cn.com.raul.lucene; import java.io.File; import java.io.FileReader; import java.io.IOException; import java.util.Date; import junit.framework.TestCase; 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; import org.apache.lucene.store.FSDirectory; import org.apache.lucene.util.Version; /** * 创建索引 * * @author Administrator * */ public class IndexWork extends TestCase { private static String INDEX_DIR = "D:\\index";// 索引存放目录 private static String DATA_DIR = "D:\\hibernate\\";// 文件存放的目录 public void testLucene() throws Exception { long start = new Date().getTime(); int numIndexed = index(new File(INDEX_DIR), new File(DATA_DIR));//调用index方法 long end = new Date().getTime(); System.out.println("Indexing " + numIndexed + " files took " + (end - start) + " milliseconds"); } /** * * @param indexFile * 索引文件 * @param dataFile * 待索引文件 * @return */ public static int index(File indexFile, File dataDir) throws Exception { if (!indexFile.exists()) { indexFile.mkdir() ; } if (!dataDir.exists()) { throw new IOException("文件不存在"); } IndexWriter writer = new IndexWriter(FSDirectory.open(indexFile), new StandardAnalyzer(Version.LUCENE_30), true, IndexWriter.MaxFieldLength.LIMITED); indexDirectory(writer, dataDir); int numIndexed = writer.numDocs(); writer.optimize(); writer.close(); return numIndexed; } /** * 取出文件并循环索引 * * @param writer * @param dataDir * @throws IOException */ public static void indexDirectory(IndexWriter writer, File dataDir) throws IOException { File[] fileList = dataDir.listFiles(); for (int i = 0; i < fileList.length; i++) { File f = fileList[i]; if (f.isDirectory()) { indexDirectory(writer, f); // recurse } else if (f.getName().endsWith(".java")) { indexFile(writer, f); } } } /** * 对单个文件进行索引 * * @param writer * @param f */ public static void indexFile(IndexWriter writer, File f) throws IOException { if (f.isHidden() || !f.exists() || !f.canRead()) { return; } System.out.println("Indexing " + f.getCanonicalPath()); Document doc = new Document(); doc.add(new Field("contents", new FileReader(f)));// 有变化的地方 doc.add(new Field("filename", f.getCanonicalPath(), Field.Store.YES, Field.Index.ANALYZED));// 有变化的地方 writer.addDocument(doc); } }

2、检索文档

package cn.com.raul.lucene; import java.io.File; import java.util.Date; import junit.framework.TestCase; import org.apache.lucene.analysis.standard.StandardAnalyzer; import org.apache.lucene.document.Document; 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.TopScoreDocCollector; import org.apache.lucene.store.FSDirectory; import org.apache.lucene.util.Version; /** * 查询 * * @author Administrator * */ public class SearcheWork extends TestCase { private static String INDEX_DIR = "D:\\index\\";// 索引所在的路径 private static String KEYWORD = "insert";// 关键词 private static int TOP_NUM = 10;// 显示前10条结果 public void testSearch() throws Exception { search(new File(INDEX_DIR), KEYWORD); } public static void search(File indexDir, String q) throws Exception { IndexSearcher is = new IndexSearcher(FSDirectory.open(indexDir), true); String field = "contents"; QueryParser parser = new QueryParser(Version.LUCENE_30, field, new StandardAnalyzer(Version.LUCENE_30));// 有变化的地方 Query query = parser.parse(q); TopScoreDocCollector collector = TopScoreDocCollector.create(TOP_NUM, false); long start = new Date().getTime();// start time is.search(query, collector); ScoreDoc[] hits = collector.topDocs().scoreDocs; System.out.println(hits.length); for (int i = 0; i < hits.length; i++) { Document doc = is.doc(hits[i].doc);// new method is.doc() System.out.println(doc.getField("filename") + " " + hits[i].toString() + " "); } long end = new Date().getTime();// end time System.out.println("Found " + collector.getTotalHits() + " document(s) (in " + (end - start) + " milliseconds) that matched query '" + q + "':"); } }

Indexing D:\hibernate\CommonDao.java
Indexing D:\hibernate\HibernateDao.java
Indexing D:\hibernate\SimpleHibernateDao.java
Indexing 3 files took 467 milliseconds

1
stored,indexed,tokenized<filename:D:\hibernate\SimpleHibernateDao.java> doc=2 score=0.046585027
Found 1 document(s) (in 31 milliseconds) that matched query 'insert':