<dependency>
    <groupId>org.apache.lucene</groupId>
    <artifactId>lucene-core</artifactId>
    <version>8.5.2</version>
</dependency>
<dependency>
    <groupId>org.apache.lucene</groupId>
    <artifactId>lucene-queryparser</artifactId>
    <version>8.5.2</version>
</dependency>
<dependency>
    <groupId>org.apache.lucene</groupId>
    <artifactId>lucene-analyzers-common</artifactId>
    <version>8.5.2</version>
</dependency>
<dependency>
    <groupId>org.apache.lucene</groupId>
    <artifactId>lucene-analyzers-smartcn</artifactId>
    <version>8.5.2</version>
</dependency>

@Test
public void testAnalyzer() throws IOException {
    String chinese = "中华人民共和国简称中国，是一个有13亿人口的国家";
    Analyzer analyzer = new SmartChineseAnalyzer();
    TokenStream tokenStream = analyzer.tokenStream(chinese, new StringReader(chinese));
    tokenStream.reset();
    CharTermAttribute attribute = tokenStream.getAttribute(CharTermAttribute.class);
    System.out.println("分词结果：");
    while (tokenStream.incrementToken()) {
        System.out.print(attribute.toString() + "|");
    }
    analyzer.close();
}

@Test
public void testIndex() throws IOException {
    List<String> titleList = Lists.newArrayList("中国房企洛杉矶丑闻：百万美元行贿案遭曝光", "2025年之前美国不会退出WTO了",
            "特朗普退出总统竞选？");
    List<String> contentList = Lists.newArrayList(
            "据调查，惠泽尔从中国房企手里收取了超过150万美元的现金贿赂，合人民币超过1000万元。",
            "美国特朗普政府上台以来，每隔几月，便总要传出有关“美国要退出世贸组织（WTO）”的消息。那么究竟美国能不能退出WTO？",
            "“共和党的操盘手首次提出了这样的可能性”，即川普总统可能会退出2020年总统竞选");

    Path indexPath = Paths.get("indexDir");
    Directory dir = FSDirectory.open(indexPath);

    // 设置新闻ID索引并存储
    FieldType idType = new FieldType();
    idType.setIndexOptions(IndexOptions.DOCS);
    idType.setStored(true);

    // 设置新闻标题索引文档、此项频率、位移信息、偏移量，存储并词条化
    FieldType titleType = new FieldType();
    titleType.setIndexOptions(IndexOptions.DOCS_AND_FREQS_AND_POSITIONS_AND_OFFSETS);
    titleType.setStored(true);
    titleType.setTokenized(true);

    FieldType contentType = new FieldType();
    contentType.setIndexOptions(IndexOptions.DOCS_AND_FREQS_AND_POSITIONS_AND_OFFSETS);
    contentType.setStored(true);
    contentType.setTokenized(true);
    contentType.setStoreTermVectors(true);
    contentType.setStoreTermVectorOffsets(true);
    contentType.setStoreTermVectorPayloads(true);
    contentType.setStoreTermVectorPositions(true);

    Analyzer analyzer = new SmartChineseAnalyzer();
    IndexWriterConfig indexWriterConfig = new IndexWriterConfig(analyzer);
    indexWriterConfig.setOpenMode(IndexWriterConfig.OpenMode.CREATE);
    IndexWriter indexWriter = new IndexWriter(dir, indexWriterConfig);

    for (int i = 0; i < titleList.size(); i++) {
        Document doc = new Document();
        doc.add(new Field("id", Integer.toString(i + 1), idType));
        doc.add(new Field("title", titleList.get(i), titleType));
        doc.add(new Field("content", contentList.get(i), contentType));
        indexWriter.addDocument(doc);
    }
    indexWriter.commit();
    indexWriter.close();
    dir.close();
}

@Test
public void testSearch() throws Exception {
    Path indexPath = Paths.get("indexDir");
    Directory dir = FSDirectory.open(indexPath);
    IndexReader reader = DirectoryReader.open(dir);
    IndexSearcher searcher = new IndexSearcher(reader);
    Analyzer analyzer = new SmartChineseAnalyzer();
    QueryParser parser = new QueryParser("title", analyzer);
    parser.setDefaultOperator(QueryParser.Operator.AND);
    Query query = parser.parse("房企");
    System.out.println("query : " + query.toString());

    TopDocs topDocs = searcher.search(query, 10);
    for (ScoreDoc sd : topDocs.scoreDocs) {
        Document doc = searcher.doc(sd.doc);
        System.out.println("docId: " + sd.doc);
        System.out.println("id: " + doc.get("id"));
        System.out.println("title: " + doc.get("title"));
        System.out.println("content: " + doc.get("content"));
        System.out.println("文档评分：" + sd.score);
    }
}

@Data
@Builder
@Document(indexName = "news_test")
public class EsNewsEntity {

    @Id
    private String id;
    private String title;
    private String content;

    @DateTimeFormat(pattern = "yyyy-MM-dd")
    @JsonFormat(pattern = "yyyy-MM-dd", timezone = "GMT+8")
    private Date time;
}

public interface EsNewsRepository extends ElasticsearchRepository<EsNewsEntity, String> {
}

@Test
public void testEs() {
    EsNewsEntity newsEntity = EsNewsEntity.builder().id("1").title("韩国男星")
            .content("我很喜欢大神、金钟国、光洙").time(DateTime.now().toDate()).build();
    esNewsRepository.save(newsEntity);

    newsEntity = EsNewsEntity.builder().id("2").title("特大暴雨")
            .content("特大暴雨夜袭四川冕宁:山洪摧毁村庄 一家5口遇难").time(DateTime.now().toDate()).build();
    esNewsRepository.save(newsEntity);

    newsEntity = EsNewsEntity.builder().id("3").title("韩国男星")
            .content("韩国男星身材管理多严格？金秀贤 Rain有八块腹肌").time(DateTime.now().toDate()).build();
    esNewsRepository.save(newsEntity);

    System.out.println("es save ...");
}