vlambda博客
学习文章列表

 <dependencies> <dependency> <groupId>junit</groupId> <artifactId>junit</artifactId> <version>4.8.2</version> </dependency>
 <dependency> <groupId>org.apache.lucene</groupId> <artifactId>lucene-core</artifactId> <version>7.7.3</version> </dependency>
 <dependency> <groupId>org.apache.lucene</groupId> <artifactId>lucene-queryparser</artifactId> <version>7.7.3</version> </dependency>
 <dependency> <groupId>org.apache.lucene</groupId> <artifactId>lucene-analyzers-common</artifactId> <version>7.7.3</version> </dependency>
 <dependency> <groupId>commons-io</groupId> <artifactId>commons-io</artifactId> <version>2.5</version> </dependency> <dependency> <groupId>com.github.magese</groupId> <artifactId>ik-analyzer</artifactId> <version>7.7.1</version> </dependency> </dependencies>

 @Test public void testCreateIndex() throws Exception{ //1.采集数据 List<Book> bookList = new ArrayList<>(); Book booka = new Book(); booka.setId(1); booka.setDesc("Lucene Core is a Java library providing powerful indexing and search features, as well as spellchecking, hit highlighting and advanced analysis/tokenization capabilities. The PyLucene sub project provides Python bindings for Lucene Core. "); booka.setName("Lucene"); booka.setPrice(100.45f); bookList.add(booka);
 Book bookb = new Book(); bookb.setId(11); bookb.setDesc("Solr is highly scalable, providing fully fault tolerant distributed indexing, search and analytics. It exposes Lucene's features through easy to use JSON/HTTP interfaces or native clients for Java and other languages. "); bookb.setName("Solr"); bookb.setPrice(320.45f); bookList.add(bookb); Book bookc = new Book(); bookc.setId(21); bookc.setDesc("The Apache Hadoop software library is a framework that allows for the distributed processing of large data sets across clusters of computers using simple programming models."); bookc.setName("Hadoop"); bookc.setPrice(620.45f); bookList.add(bookc); //2.创建Document 文档对象 List<Document> documents = new ArrayList<>(); for (Book book:bookList){ Document document = new Document(); // 给document 添加Field document.add(new TextField("id",book.getId().toString(),Field.Store.YES)); document.add(new TextField("name",book.getName(),Field.Store.YES)); document.add(new TextField("price",book.getPrice().toString(),Field.Store.YES)); document.add(new TextField("desc",book.getDesc(),Field.Store.YES)); documents.add(document); }

 //3.创建Analyzer 分词器 对文档进行分词 Analyzer analyzer = new StandardAnalyzer(); // 创建Directory 和 IndexWriterConfig 对象 Directory directory = FSDirectory.open(Paths.get("D:/lucene/index")); IndexWriterConfig indexWriterConfig = new IndexWriterConfig(analyzer); // 4.创建IndexWriter 写入对象 IndexWriter indexWriter = new IndexWriter(directory,indexWriterConfig); // 添加文档对象 for (Document doc : documents) { indexWriter.addDocument(doc); } // 释放资源 indexWriter.close(); }

 @Test public void testSearchIndex()throws Exception {
 //1.创建Query 搜索对象 // 创建分词器 Analyzer analyzer = new StandardAnalyzer(); // 创建搜索解析器 QueryParser queryParser = new QueryParser("id", analyzer); // 创建搜索对象 Query query = queryParser.parse("desc:java OR name:solr"); //2.创建Directory 流对象 指定索引库位置 //Directory directory = FSDirectory.open(Paths.get("D:/lucene/index")); //Directory directory = SimpleFSDirectory.open(Paths.get("D:/lucene/index")); //Directory directory = NIOFSDirectory.open(Paths.get("D:/lucene/index")); Directory directory = MMapDirectory.open(Paths.get("D:/lucene/index")); //3.创建索引读取对象 IndexReader indexReader = DirectoryReader.open(directory); //4.创建索引搜索对象 IndexSearcher indexSearcher = new IndexSearcher(indexReader); indexSearcher.setSimilarity(new ClassicSimilarity()); System.out.println(indexSearcher.getSimilarity(true)); // indexSearcher.setSimilarity(indexSearcher.getSimilarity(false));
 //5.执行搜索 返回结果集 TopDocs TopDocs topDocs = indexSearcher.search(query, 2); System.out.println("查询到的数据总条数:" + topDocs.totalHits); // 获取排序的文档 ScoreDoc[] docs = topDocs.scoreDocs; //6.解析结果集 for (ScoreDoc scoreDoc : docs) { // 获取文档id int docID = scoreDoc.doc; Document doc = indexSearcher.doc(docID); System.out.println("score:" + scoreDoc.score);
 System.out.println("docId:" + docID); System.out.println("bookId:" + doc.get("id")); System.out.println("name:" + doc.get("name")); System.out.println("price:" + doc.get("price")); System.out.println("desc:" + doc.get("desc")); System.out.println(); } indexReader.close(); }

ClassicSimilarity查询到的数据总条数:2score:1.9506836docId:1bookId:11name:Solrprice:320.45desc:Solr is highly scalable, providing fully fault tolerant distributed indexing, search and analytics. It exposes Lucene's features through easy to use JSON/HTTP interfaces or native clients for Java and other languages. 
score:0.2575364docId:0bookId:1name:Luceneprice:100.45desc:Lucene Core is a Java library providing powerful indexing and search features, as well as spellchecking, hit highlighting and advanced analysis/tokenization capabilities. The PyLucene sub project provides Python bindings for Lucene Core.