lucene

最新推荐文章于 2024-04-09 02:46:04 发布

strugglejiaxin

最新推荐文章于 2024-04-09 02:46:04 发布

阅读量152

点赞数

本文链接：https://blog.csdn.net/strugglejiaxin/article/details/102952699

版权

Lucene是一套用于全文检索和搜寻的开源程序库。

Lucene提供了一个简单却强大的应用程序接口（API），能够做全文索引和搜寻，在Java开发环境里Lucene是一个成熟的免费开放源代码工具

Lucene并不是现成的搜索引擎产品，但可以用来制作搜索引擎产品

Lucene、Solr、Elasticsearch关系

Lucene：底层的API，工具包

Solr：基于Lucene开发的企业级的搜索引擎产品

Elasticsearch：基于Lucene开发的企业级的搜索引擎产品

Lucene的基本使用
使用Lucene的API来实现对索引的增（创建索引）、删（删除索引）、改（修改索引）、查（搜索数据）。

创建索引

文档Document：数据库中一条具体的记录

字段Field：数据库中的每个字段

目录对象Directory：物理存储位置

写出器的配置对象：需要分词器和lucene的版本

创建文件步骤

//1 创建文档对象
//2 创建存储目录
//3 创建分词器
//4 创建索引写入器的配置对象
//5 创建索引写入器对象
//6 将文档交给索引写入器
//7 提交
//8 关闭

创建只有一条文档的文件

//创建索引
    @Test
    public void testCreate(){
        try {
            //1、创建文档对象
        Document document = new Document();
        //创建并添加字段信息。参数：字段的名称，字段的值，是否存储，Store.YES代表存储到文档列表
        StringField id = new StringField("id", "1", Field.Store.YES);
        document.add(id);
        //title字段需要用TextField，即创建索引又会被分词。StringField会创建索引，但是不会被分词
        TextField textField = new TextField("title", "谷歌之父跳槽facebook", Field.Store.YES);
        document.add(textField);
        //2、索引目录类，指定索引在目录中的位置
        FSDirectory directory = FSDirectory.open(new File("d:/lucenedata"));
      //3、创建分词器对象
            IKAnalyzer analyzer = new IKAnalyzer();
            //4、索引写出工具的配置对象
            IndexWriterConfig conf = new IndexWriterConfig(Version.LATEST,analyzer);
            conf.setOpenMode(IndexWriterConfig.OpenMode.CREATE);
            //5、创建索引的写出工具类。参数：索引的目录和配置信息
            IndexWriter indexWriter = new IndexWriter(directory,conf);
            //6、把文档交给IndexWriter
            indexWriter.addDocument(document);
            //7、提交
            indexWriter.commit();
            //8、关闭
            indexWriter.close();

        } catch (IOException e) {
        }
    }

创建多条文档的文件

 @Test
    public void testCreate2(){
        try {
            //1、创建文档对象
        ArrayList<Document> documents = new ArrayList<Document>();
        Document document = new Document();
        document.add(new StringField("id","1",Field.Store.YES));
        document.add(new TextField("title","谷歌之父跳槽facebook",Field.Store.YES));
        documents.add(document);

        Document document2 = new Document();
        document2.add(new StringField("id","2",Field.Store.YES));
        document2.add(new TextField("title","谷歌之父跳槽facebook",Field.Store.YES));
        documents.add(document2);

        Document document3 = new Document();
        document3.add(new StringField("id","3",Field.Store.YES));
        document3.add(new TextField("title","谷歌地图创始人拉斯离开谷歌加盟Facebook",Field.Store.YES));
        documents.add(document3);

        Document document4 = new Document();
        document4.add(new StringField("id","4",Field.Store.YES));
        document4.add(new TextField("title","谷歌地图之父跳槽Facebook与Wave项目取消有关",Field.Store.YES));
        documents.add(document4);

        Document document5 = new Document();
        document5.add(new StringField("id","5",Field.Store.YES));
        document5.add(new TextField("title","谷歌地图之父拉斯加盟社交网站Facebook",Field.Store.YES));
        documents.add(document5);
//2、索引目录类，指定索引在目录中的位置
            FSDirectory dir = FSDirectory.open(new File("d:/lucenedata"));
            //3、创建分词器对象
            //4、索引写出工具的配置对象
            IndexWriterConfig conf = new IndexWriterConfig(Version.LATEST, new IKAnalyzer());
            conf.setOpenMode(IndexWriterConfig.OpenMode.CREATE);
            //5、创建索引的写出工具类。参数：索引的目录和配置信息
            IndexWriter indexWriter = new IndexWriter(dir,conf);
            //6、把文档交给IndexWriter
            indexWriter.addDocument(document);
            indexWriter.addDocuments(documents);
            //7、提交
            indexWriter.commit();
            //8、关闭
            indexWriter.close();



        } catch (IOException e) {
            e.printStackTrace();
        }
    }

查询

  @Test
    public void testSearch(){
        try {

            // 索引目录对象
            FSDirectory directory = FSDirectory.open(new File("d:/lucenedata"));
            // 索引读取工具
            DirectoryReader reader = DirectoryReader.open(directory);

            // 索引搜索工具
            IndexSearcher searcher = new IndexSearcher(reader);
            // 创建查询解析器,两个参数：默认要查询的字段的名称，分词器
            QueryParser parser = new QueryParser("title", new IKAnalyzer());
            // 创建查询对象
            Query query = parser.parse("跳槽");
            // 搜索数据,两个参数：查询条件对象要查询的最大结果条数
            // 返回的结果是 按照匹配度排名得分前N名的文档信息（包含查询到的总条数信息、所有符合条件的文档的编号信息）。

            TopDocs topDocs = searcher.search(query, 10);
            // 获取总条数
            int totalHits = topDocs.totalHits;
            System.out.println(totalHits);
            ScoreDoc[] scoreDocs = topDocs.scoreDocs;
            for (ScoreDoc scoreDoc : scoreDocs){

                // 取出文档编号
                int docID = scoreDoc.doc;
                // 根据编号去找文档
                Document doc = reader.document(docID);
                String id = doc.get("id");
                // 取出文档得分
                String title = doc.get("title");
                System.out.println(id + title);
            }

        } catch (IOException e) {
            e.printStackTrace();
        } catch (ParseException e) {
            e.printStackTrace();
        }

    }

高亮显示

@Test
    public  void testHighLighting(){
        try {
            FSDirectory directory = FSDirectory.open(new File("d:/lucenedata"));
            DirectoryReader reader = DirectoryReader.open(directory);
            IndexSearcher searcher = new IndexSearcher(reader);
            QueryParser parser = new QueryParser("title",new IKAnalyzer());
            Query query = parser.parse("谷歌地图");
            SimpleHTMLFormatter formatter = new SimpleHTMLFormatter("<body>","</body>");
            QueryScorer scorer = new QueryScorer(query);
            Highlighter highlighter = new Highlighter(formatter, scorer);
            TopDocs topDocs = searcher.search(query, 10);
            System.out.println("本次搜索共" + topDocs.totalHits + "条数据");
            ScoreDoc[] scoreDocs = topDocs.scoreDocs;
            for (ScoreDoc scoreDoc : scoreDocs){
                int docID = scoreDoc.doc;
                Document doc = reader.document(docID);
                System.out.println("id:" + doc.get("id"));

                String title = doc.get("title");
                String hTitle = highlighter.getBestFragment(new IKAnalyzer(), "title", title);
                System.out.println("title:" + hTitle);
                System.out.println("得分：" + scoreDoc.score);
            }


        } catch (IOException e) {
            e.printStackTrace();
        } catch (ParseException e) {
            e.printStackTrace();
        } catch (InvalidTokenOffsetsException e) {
            e.printStackTrace();
        }

    }

排序

//排序
    @Test
    public void testSortQuery () {

        try {
            FSDirectory directory = FSDirectory.open(new File("d:/lucenedata"));
            DirectoryReader reader = DirectoryReader.open(directory);
            IndexSearcher searcher = new IndexSearcher(reader);
            QueryParser parser = new QueryParser("title", new IKAnalyzer());
            Query query = parser.parse("谷歌地图");
            Sort sort = new Sort(new SortField("id", SortField.Type.LONG, true));
            TopDocs topDocs = searcher.search(query, 10,sort);
            System.out.println("本次搜索共" + topDocs.totalHits + "条数据");
            ScoreDoc[] scoreDocs = topDocs.scoreDocs;
            for (ScoreDoc scoreDoc :scoreDocs){
                int docID = scoreDoc.doc;
                Document doc = reader.document(docID);
                System.out.println("id:" + doc.get("id"));
                System.out.println("title" + doc.get("title"));

            }


        } catch (IOException e) {
            e.printStackTrace();
        } catch (ParseException e) {
            e.printStackTrace();
        }


    }

分页

@Test
    public void testPageQuery (){
        int pageSize = 2;
        int pageNum = 3;
        int start = (pageNum - 1) * pageSize;
        int end = start + pageSize;
        try {
            FSDirectory directory = FSDirectory.open(new File("d:/lucenedata"));
            DirectoryReader reader = DirectoryReader.open(directory);
            IndexSearcher searcher = new IndexSearcher(reader);
            QueryParser parser = new QueryParser("title",new IKAnalyzer());
            Query query = parser.parse("谷歌地图");
            Sort sort = new Sort(new SortField("id", SortField.Type.LONG, false));
            TopDocs topDocs = searcher.search(query, end, sort);
            System.out.println("本次共搜索到" + topDocs.totalHits + "条数据");
            ScoreDoc[] scoreDocs = topDocs.scoreDocs;
            for (int i = start; i < end; i++){
                ScoreDoc scoreDoc = scoreDocs[i];
                int docID = scoreDoc.doc;
                Document doc = reader.document(docID);
                System.out.println("id:" + doc.get("id"));
                System.out.println("title" + doc.get("title"));

            }
        } catch (IOException e) {
            e.printStackTrace();
        } catch (ParseException e) {
            e.printStackTrace();
        }
    }