lucene_7.1_demo

最新推荐文章于 2024-09-20 08:52:16 发布

liu975123

最新推荐文章于 2024-09-20 08:52:16 发布

阅读量3.7k

点赞数

CC 4.0 BY-SA版权

分类专栏： lucene入门demo 文章标签： lucene 入门 maven

本文链接：https://blog.youkuaiyun.com/liu975123/article/details/78294715

lucene入门demo 专栏收录该内容

1 篇文章

订阅专栏

本文介绍如何使用 Lucene 7.1 进行全文检索的应用演示，包括基于实体和文件创建索引的方法，并展示了如何进行简单查询。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

lucene 7.1 demo

1、基于maven；废话不多说，如下

<dependencies>
    <dependency>
        <groupId>org.apache.lucene</groupId>
        <artifactId>lucene-core</artifactId>
        <version>7.1.0</version>
    </dependency>

    <dependency>
        <groupId>org.apache.lucene</groupId>
        <artifactId>lucene-analyzers-smartcn</artifactId>
        <version>7.1.0</version>
    </dependency>

    <dependency>
        <groupId>org.apache.lucene</groupId>
        <artifactId>lucene-queryparser</artifactId>
        <version>7.1.0</version>
    </dependency>

    <dependency>
        <groupId>org.apache.lucene</groupId>
        <artifactId>lucene-highlighter</artifactId>
        <version>7.1.0</version>
    </dependency>
    <dependency>
        <groupId>junit</groupId>
        <artifactId>junit</artifactId>
        <version>4.12</version>
    </dependency>

</dependencies>

2、IndexWriter（可以是实体，也可以是读取的文件）

2.1实体

@Test
public void add() throws IOException {

    Article article = new Article();
    article.setId(1);
    article.setTitle("Lucene全文检索");
    article.setContent("Lucene是apache软件基金会4 jakarta项目组的一个子项目，是一个开放源代码的全文检索引擎工具包，但它不是一个完整的全文检索引擎，而是一个全文检索引擎的架构，提供了完整的查询引擎和索引引擎，部分文本分析引擎（英文与德文两种西方语言）。");

    final Path path = Paths.get("./article/");

    Directory directory = FSDirectory.open(path);
    Analyzer analyzer = new StandardAnalyzer();

    IndexWriterConfig indexWriterConfig = new IndexWriterConfig(analyzer);
    indexWriterConfig.setOpenMode(IndexWriterConfig.OpenMode.CREATE);

    IndexWriter indexWriter = new IndexWriter(directory, indexWriterConfig);

    Document document = new Document();
    document.add(new TextField("id", article.getId().toString(), Field.Store.YES));
    document.add(new TextField("title", article.getTitle(), Field.Store.YES));
    document.add(new TextField("content", article.getContent(), Field.Store.YES));

    indexWriter.addDocument(document);
    indexWriter.close();

}

2.2 文件

@Test
public void addFile() throws IOException {

    final Path path = Paths.get("./article/");

    Directory directory = FSDirectory.open(path);
    Analyzer analyzer = new StandardAnalyzer();

    IndexWriterConfig indexWriterConfig = new IndexWriterConfig(analyzer);
    indexWriterConfig.setOpenMode(IndexWriterConfig.OpenMode.CREATE);

    IndexWriter indexWriter = new IndexWriter(directory, indexWriterConfig);
    BufferedReader bufferedReader = new BufferedReader(new FileReader(new File("e:/2017_10_17.stderrout.log")));
    String content = "";
    while ((content = bufferedReader.readLine())!=null){
        System.out.println(content);
        Document document = new Document();
        document.add(new TextField("logs", content, Field.Store.YES));
        indexWriter.addDocument(document);
    }

    indexWriter.close();

}

3、Search（查询）

@Test
    public void SearchFiles() throws IOException, ParseException {
//        String queryString = "全文检索";
        String queryString  = "error";

        //多条件
//        Query q = MultiFieldQueryParser.parse(new String[]{},new String[]{},new StandardAnalyzer());

        final Path path = Paths.get("./article/");
        Directory directory = FSDirectory.open(path);
        Analyzer analyzer = new StandardAnalyzer();

        IndexReader indexReader = DirectoryReader.open(directory);
        IndexSearcher indexSearcher = new IndexSearcher(indexReader);

        //单条件
        QueryParser queryParser = new QueryParser("logs",analyzer);
        Query query = queryParser.parse(queryString);

        TopDocs topDocs = indexSearcher.search(query,10);

        long conut = topDocs.totalHits;
        System.out.println("检索总条数："+conut);
        ScoreDoc[] scoreDocs = topDocs.scoreDocs;
        for (ScoreDoc scoreDoc : scoreDocs) {
            Document document = indexSearcher.doc(scoreDoc.doc);
            System.out.print("相关度："+scoreDoc.score+"-----time:"+document.get("time"));
            System.out.println(document.get("logs"));
        }
    }