Lucene V3.0.2搜索例子

Lucene3.0开始已经完全抛弃了2.x使用的Hits类，转而使用TopDocs，TopFieldDocs。本例演示了如何使用这两个类进行搜索。

 

package index; 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.document.Field; import org.apache.lucene.document.Field.Index; import org.apache.lucene.document.Field.Store; import org.apache.lucene.index.CorruptIndexException; import org.apache.lucene.index.IndexWriter; import org.apache.lucene.index.IndexWriter.MaxFieldLength; 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.Searcher; import org.apache.lucene.search.Sort; import org.apache.lucene.search.SortField; import org.apache.lucene.search.TopDocs; import org.apache.lucene.search.TopFieldDocs; import org.apache.lucene.store.FSDirectory; import org.apache.lucene.store.LockObtainFailedException; import org.apache.lucene.util.Version; public class SearchTest { /** * 建索引<br> * 一共4个Document，每个文档两个Field：text,size。text存放内容，size用于排序 * * @throws CorruptIndexException * @throws LockObtainFailedException * @throws IOException */ private static void build() throws CorruptIndexException, LockObtainFailedException, IOException { IndexWriter writer = new IndexWriter(FSDirectory.open(new File("index")), new StandardAnalyzer(Version.LUCENE_30), true, MaxFieldLength.LIMITED); Document document = new Document(); document.add(new Field("text", "google", Store.YES, Index.ANALYZED)); document.add(new Field("size", "1", Store.YES, Index.NOT_ANALYZED_NO_NORMS)); writer.addDocument(document); document = new Document(); document.add(new Field("text", "google earth apache", Store.YES, Index.ANALYZED)); document.add(new Field("size", "2", Store.YES, Index.NOT_ANALYZED_NO_NORMS)); writer.addDocument(document); document = new Document(); document.add(new Field("text", "baidu earth", Store.YES, Index.ANALYZED)); document.add(new Field("size", "3", Store.YES, Index.NOT_ANALYZED_NO_NORMS)); writer.addDocument(document); document = new Document(); document.add(new Field("text", "baidu earth apache", Store.YES, Index.ANALYZED)); document.add(new Field("size", "4", Store.YES, Index.NOT_ANALYZED_NO_NORMS)); writer.addDocument(document); writer.optimize(); writer.close(); } /** * lucene3.0已经没有返回Hits的方法，使用返回TopDocs的方法进行搜索 * * @param keyword * 要搜索的关键词 * @throws CorruptIndexException * @throws IOException * @throws ParseException */ private static void searchWithTopDocs(String keyword) throws CorruptIndexException, IOException, ParseException { QueryParser parser = new QueryParser(Version.LUCENE_30, "text", new StandardAnalyzer(Version.LUCENE_30)); IndexSearcher searcher = new IndexSearcher(FSDirectory.open(new File("index"))); TopDocs topDocs = searcher.search(parser.parse(keyword), 10);// 取前10个搜索结果，如果没有这么多，就取实际大小 ScoreDoc[] scoreDocs = topDocs.scoreDocs;// 获取ScoreDoc System.out.println("hits:" + topDocs.totalHits); for (ScoreDoc scoreDoc : scoreDocs) { int docNum = scoreDoc.doc;// 文档编号 Document doc = searcher.doc(docNum); String text = doc.get("text"); String size = doc.get("size"); float score = scoreDoc.score;// 评分 System.out.println(text + " " + size + " " + score); } } /** * 对命中文档进行排序的搜索，也不再返回Hits，而是返回TopFieldDocs * * @param keyword * 要搜索的关键词 * @throws CorruptIndexException * @throws IOException * @throws ParseException */ private static void searchWithSort(String keyword) throws CorruptIndexException, IOException, ParseException { QueryParser parser = new QueryParser(Version.LUCENE_30, "text", new StandardAnalyzer(Version.LUCENE_30)); Searcher searcher = new IndexSearcher(FSDirectory.open(new File("index"))); Query query = parser.parse(keyword); SortField sortField = new SortField("size", SortField.INT, true);// 需要排序的字段 TopFieldDocs topFieldDocs = searcher.search(query, null, 10, new Sort(sortField));// 第二个参数是过滤器，此例中不需要 ScoreDoc[] socDocs = topFieldDocs.scoreDocs; System.out.println("hits:" + topFieldDocs.totalHits); for (ScoreDoc scoreDoc : socDocs) { int docNum = scoreDoc.doc; Document doc = searcher.doc(docNum); String text = doc.get("text"); String size = doc.get("size"); float score = scoreDoc.score;// 评分,这里的评分不可用,分值都是NaN System.out.println(text + " " + size + " " + score); } } public static void main(String[] args) throws CorruptIndexException, LockObtainFailedException, IOException, ParseException { build(); String keyword = "google"; searchWithTopDocs(keyword); System.out.println("---------"); searchWithSort(keyword); } }