Lucene创建索引、查询索引入门案例

女爷i 2021-11-29 11:20 384阅读 0赞

## 一、环境搭建 ##

1.新建java-project工程，导入以下三个jar包。  
commons-io-2.2.jar  
lucene-analyzers-common-7.4.0.jar  
lucene-core-7.4.0.jar  
2. 新建索引保存的文件夹。例如：I:\\Lucene\\index  
3. 新建一个文件目录，包含一些测试文本文档。例如目录为：I:\\Lucene\\index

## 二、创建索引 ##

/**
         * 创建一个Director对象，指定索引库的位置
         * 基于Director对象，创建IndexWriter对象
         * 读取磁盘上的文件，为每个文件创建一个文档对象
         * 向文档对象中添加域
         * 把文档对象写入索引库
         * 关闭IndexWriter对象
         *
         */
        @Test
        public void createIndex() throws Exception{
            //把索引库保存在磁盘
            Directory directory = FSDirectory.open(new File("I:\\Lucene\\index").toPath());
    
            IndexWriter indexWriter = new IndexWriter(directory,new IndexWriterConfig());
    
            File dir = new File("I:\\Lucene\\searchsource");
    
            File[] files = dir.listFiles();
    
            for (File file:
                 files) {
    
                String filename = file.getName();
    
                String filepath = file.getPath();
    
                String content = FileUtils.readFileToString(file,"utf8");
    
                long size = FileUtils.sizeOf(file);
    
                Field fieldName = new TextField("name",filename, Field.Store.YES);
    
                Field fieldPath = new TextField("path",filepath, Field.Store.YES);
    
                Field fieldContent = new TextField("content",content, Field.Store.YES);
    
                Field fieldSize = new TextField("size",size+"", Field.Store.YES);
    
                Document document = new Document();
                document.add(fieldName);
                document.add(fieldPath);
                document.add(fieldContent);
                document.add(fieldSize);
    
                indexWriter.addDocument(document);
            }
    
            indexWriter.close();
    
        }

## 三、查询索引 ##

/**
         * 查询索引
         *
         */
        @Test
        public void searchIndex() throws Exception{
    
            Directory directory = FSDirectory.open(new File("I:\\黑马学习\\Lucene\\index").toPath());
    
            IndexReader indexReader = DirectoryReader.open(directory);
    
            IndexSearcher indexSearcher = new IndexSearcher(indexReader);
    
            Query query = new TermQuery(new Term("content","spring"));
    
            TopDocs topDocs = indexSearcher.search(query, 10);
    
            ScoreDoc[] scoreDocs = topDocs.scoreDocs;
    
            for (ScoreDoc scoreDoc:
                 scoreDocs) {
    
                int docId = scoreDoc.doc;
    
                Document document = indexSearcher.doc(docId);
    
                System.out.println(document.getField("name"));
    
    
            }
    
            indexReader.close();
    
    
        }

## 四、查看分析器的分词效果 ##

@Test
        public void testTokenStream() throws Exception{
    
            Analyzer analyzer = new StandardAnalyzer();
    
            TokenStream tokenStream = analyzer.tokenStream("","the spring Framework is ...");
    
            CharTermAttribute charTermAttribute = tokenStream.addAttribute(CharTermAttribute.class);
    
            tokenStream.reset();
    
            while (tokenStream.incrementToken()){
                System.out.println(charTermAttribute.toString());
            }
            tokenStream.close();
        }