搜索学习--Lucene中搜索的排序、范围区间搜索、分页搜索、多条件搜索

水深无声 2022-06-05 12:38 256阅读 0赞

### 依赖 ###

<dependency>
                    <groupId>org.apache.lucene</groupId>
                    <artifactId>lucene-core</artifactId>
                    <version>4.7.2</version>
                </dependency>
    
            
            <dependency>
                <groupId>org.apache.lucene</groupId>
                <artifactId>lucene-queryparser</artifactId>
                <version>4.7.2</version>
            </dependency>
    
            
            <dependency>
                <groupId>org.apache.lucene</groupId>
                <artifactId>lucene-analyzers-common</artifactId>
                <version>4.7.2</version>
            </dependency>
    
            
            <dependency>
                <groupId>org.apache.lucene</groupId>
                <artifactId>lucene-highlighter</artifactId>
                <version>4.7.2</version>
            </dependency>

### 建立索引 ###

> 本次增加了Float、Int类型的域

package top.yuyufeng.learn.lucene.demo2;
    
    /**
     * @author yuyufeng
     * @date 2017/11/21
     */
    
    import org.apache.lucene.analysis.Analyzer;
    import org.apache.lucene.analysis.standard.StandardAnalyzer;
    import org.apache.lucene.document.*;
    import org.apache.lucene.index.CorruptIndexException;
    import org.apache.lucene.index.IndexWriter;
    import org.apache.lucene.index.IndexWriterConfig;
    import org.apache.lucene.store.Directory;
    import org.apache.lucene.store.LockObtainFailedException;
    import org.apache.lucene.store.SimpleFSDirectory;
    import org.apache.lucene.util.Version;
    
    import java.io.File;
    import java.io.IOException;
    
    /**
     * @author yuyufeng
     * @date 2017/11/21
     */
    public class LuceneIndexDemo {
        public static void main(String[] args) {
            // 建立5条索引
            String content = "10月11日杭州云栖大会上，马云表达了对新建成的阿里巴巴全球研究院—阿里巴巴达摩院的愿景，希望达摩院二十年内成为世界第一大经济体，服务世界二十亿人，创造一亿个工作岗位。";
            Long createTime = System.currentTimeMillis();
            String id = createTime + "";
            int readCount =10;
            float score =9.5f;
            index(content, createTime, id, readCount, score);
    
    
            content = "中国互联网界，阿里巴巴被认为是技术实力最弱的公司。我确实不懂技术，承认不懂技术不丢人，不懂装懂才丢人。";
            createTime = System.currentTimeMillis();
            id = createTime + "";
            readCount =3;
            score =9.7f;
            index(content, createTime, id, readCount, score);
    
            content = "阿里巴巴未来二十年的目标是打造世界第五大经济体，不是我们狂妄，而是世界需要这么一个经济体，也一定会有这么一个经济体。";
            createTime = System.currentTimeMillis();
            id = createTime + "";
            readCount =69;
            score =5.6f;
            index(content, createTime, id, readCount, score);
    
            content = "达摩院一定也必须要超越英特尔，必须超越微软，必须超越IBM，因为我们生于二十一世纪，我们是有机会后发优势的。";
            createTime = System.currentTimeMillis();
            id = createTime + "";
            readCount =38;
            score =4.7f;
            index(content, createTime, id, readCount, score);
    
            content = "阿里巴巴有很多争议，似乎无处不在，我还真想不出有什么东西是我们不做的。互联网是一种思想，是一种技术革命，不应该有界限。跨界乐趣无穷。我觉得阿里巴巴的跨界还不错";
            createTime = System.currentTimeMillis();
            id = createTime + "";
            readCount =73;
            score =1.7f;
            index(content, createTime, id, readCount, score);
    
        }
    
        private static void index(String content, Long createTime, String id, int readCount, float score) {
            // 实例化IKAnalyzer分词器
            Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_47);
    
            Directory directory = null;
            IndexWriter iwriter;
            try {
                // 索引目录
                directory = new SimpleFSDirectory(new File("D://test/lucene_index_blog"));
    
                // 配置IndexWriterConfig
                IndexWriterConfig iwConfig = new IndexWriterConfig(Version.LUCENE_47, analyzer);
                iwConfig.setOpenMode(IndexWriterConfig.OpenMode.CREATE_OR_APPEND);
                iwriter = new IndexWriter(directory, iwConfig);
                // 写入索引
                Document doc = new Document();
    
                doc.add(new StringField("ID", id, Field.Store.YES));
                doc.add(new TextField("content", content, Field.Store.YES));
                doc.add(new LongField("createTime", createTime, Field.Store.YES));
                doc.add(new IntField("readCount", readCount, Field.Store.YES));
                doc.add(new FloatField("score", score, Field.Store.YES));
                iwriter.addDocument(doc);
                iwriter.close();
                System.out.println("建立索引成功:" + id);
            } catch (CorruptIndexException e) {
                e.printStackTrace();
            } catch (LockObtainFailedException e) {
                e.printStackTrace();
            } catch (IOException e) {
                e.printStackTrace();
            } finally {
                if (directory != null) {
                    try {
                        directory.close();
                    } catch (IOException e) {
                        e.printStackTrace();
                    }
                }
            }
        }
    }

### 搜索排序 ###

### 范围搜索 ###

> 查询score范围在1~5之间的文档，对于上面的代码中的Query进行改造

Query query = NumericRangeQuery.newFloatRange("score",1f,5f,true,true);

### 对搜索结果的分页 ###

### 多条件查询 ###

> BooleanClause.Occur

<table> 
 <thead> 
  <tr> 
   <th>组合方式</th> 
   <th>结果</th> 
  </tr> 
 </thead> 
 <tbody> 
  <tr> 
   <td>MUST和MUST</td> 
   <td>取得连个查询子句的交集。</td> 
  </tr> 
  <tr> 
   <td>MUST和MUST_NOT</td> 
   <td>表示查询结果中不能包含MUST_NOT所对应得查询子句的检索结果。</td> 
  </tr> 
  <tr> 
   <td>SHOULD与MUST_NOT</td> 
   <td>连用时，功能同MUST和MUST_NOT。</td> 
  </tr> 
  <tr> 
   <td>SHOULD与MUST</td> 
   <td>结果为MUST子句的检索结果,但是SHOULD可影响排序</td> 
  </tr> 
  <tr> 
   <td>SHOULD与SHOULD</td> 
   <td>表示“或”关系，最终检索结果为所有检索子句的并集</td> 
  </tr> 
  <tr> 
   <td>MUST_NOT和MUST_NOT</td> 
   <td>无意义，检索无结果</td> 
  </tr> 
 </tbody> 
</table>