private Directory directory; private IndexReader indexReader; private IndexSearcher indexSearcher; @Before public void setUp() throws IOException { //索引存放的位置，设置在当前目录中 directory = FSDirectory.open(Paths.get("indexDir/")); //创建索引的读取器 indexReader = DirectoryReader.open(directory); //创建一个索引的查找器，来检索索引库 indexSearcher = new IndexSearcher(indexReader); } @After public void tearDown() throws Exception { indexReader.close(); } ** * 执行查询，并打印查询到的记录数 * * @param query * @throws IOException */ public void executeQuery(Query query) throws IOException { TopDocs topDocs = indexSearcher.search(query, 100); //打印查询到的记录数 System.out.println("总共查询到" + topDocs.totalHits + "个文档"); for (ScoreDoc scoreDoc : topDocs.scoreDocs) { //取得对应的文档对象 Document document = indexSearcher.doc(scoreDoc.doc); System.out.println("id：" + document.get("id")); System.out.println("title：" + document.get("title")); System.out.println("content：" + document.get("content")); } } /** * 分词打印 * * @param analyzer * @param text * @throws IOException */ public void printAnalyzerDoc(Analyzer analyzer, String text) throws IOException { TokenStream tokenStream = analyzer.tokenStream("content", new StringReader(text)); CharTermAttribute charTermAttribute = tokenStream.addAttribute(CharTermAttribute.class); try { tokenStream.reset(); while (tokenStream.incrementToken()) { System.out.println(charTermAttribute.toString()); } tokenStream.end(); } finally { tokenStream.close(); analyzer.close(); } }
创建索引
@Test public void indexWriterTest() throws IOException { long start = System.currentTimeMillis(); //索引存放的位置，设置在当前目录中 Directory directory = FSDirectory.open(Paths.get("indexDir/")); //在 6.6 以上版本中 version 不再是必要的，并且，存在无参构造方法，可以直接使用默认的 StandardAnalyzer 分词器。 Version version = Version.LUCENE_7_1_0; //Analyzer analyzer = new StandardAnalyzer(); // 标准分词器，适用于英文 //Analyzer analyzer = new SmartChineseAnalyzer();//中文分词 //Analyzer analyzer = new ComplexAnalyzer();//中文分词 //Analyzer analyzer = new IKAnalyzer();//中文分词 Analyzer analyzer = new IKAnalyzer();//中文分词 //创建索引写入配置 IndexWriterConfig indexWriterConfig = new IndexWriterConfig(analyzer); //创建索引写入对象 IndexWriter indexWriter = new IndexWriter(directory, indexWriterConfig); //创建Document对象，存储索引 Document doc = new Document(); int id = 1; //将字段加入到doc中 doc.add(new IntPoint("id", id)); doc.add(new StringField("title", "Spark", Field.Store.YES)); doc.add(new TextField("content", "Apache Spark 是专为大规模数据处理而设计的快速通用的计算引擎", Field.Store.YES)); doc.add(new StoredField("id", id)); //将doc对象保存到索引库中 indexWriter.addDocument(doc); indexWriter.commit(); //关闭流 indexWriter.close(); long end = System.currentTimeMillis(); System.out.println("索引花费了" + (end - start) + " 毫秒"); }
响应
17:58:14.655 [main] DEBUG org.wltea.analyzer.dic.Dictionary - 加载扩展词典：ext.dic 17:58:14.660 [main] DEBUG org.wltea.analyzer.dic.Dictionary - 加载扩展停止词典：stopword.dic 索引花费了879 毫秒
删除文档
@Test public void deleteDocumentsTest() throws IOException { //Analyzer analyzer = new StandardAnalyzer(); // 标准分词器，适用于英文 //Analyzer analyzer = new SmartChineseAnalyzer();//中文分词 //Analyzer analyzer = new ComplexAnalyzer();//中文分词 //Analyzer analyzer = new IKAnalyzer();//中文分词 Analyzer analyzer = new IKAnalyzer();//中文分词 //创建索引写入配置 IndexWriterConfig indexWriterConfig = new IndexWriterConfig(analyzer); //创建索引写入对象 IndexWriter indexWriter = new IndexWriter(directory, indexWriterConfig); // 删除title中含有关键词“Spark”的文档 long count = indexWriter.deleteDocuments(new Term("title", "Spark")); // 除此之外IndexWriter还提供了以下方法： // DeleteDocuments(Query query):根据Query条件来删除单个或多个Document // DeleteDocuments(Query[] queries):根据Query条件来删除单个或多个Document // DeleteDocuments(Term term):根据Term来删除单个或多个Document // DeleteDocuments(Term[] terms):根据Term来删除单个或多个Document // DeleteAll():删除所有的Document //使用IndexWriter进行Document删除操作时，文档并不会立即被删除，而是把这个删除动作缓存起来，当IndexWriter.Commit()或IndexWriter.Close()时，删除操作才会被真正执行。 indexWriter.commit(); indexWriter.close(); System.out.println("删除完成:" + count); }
响应
删除完成:1
更新文档