spring-data-elasticsearch 3.2.4 实现桶bucket排序去重，实现指定字段的聚合搜索

一、背景

es索引有一个文档CourseIndex，下面是示意:

在搜索的时候，搜索条件包括creatorId列表，grade列表，subject列表等，且它们不是固定的字典，而是从文档CourseIndex的已有数据中获取。

假使上面的数据，搜索条件分别是：

creatorId列表

• 1002
• 1003
• 1004

grade列表

• 2
• 3
• 4

subject列表

• 70
• 80
• 90

总结一下需求，对es文档的数据进行桶bucket排序，以达到去重效果。

下面将介绍如何使用spring-data-elasticsearch 3.2.4实现对指定字段的聚合搜索。

pom.xml引入jar包

    <dependency>
        <groupId>org.springframework.boot</groupId>
        <artifactId>spring-boot-starter-data-elasticsearch</artifactId>
    </dependency>
        
    <dependency>
      <groupId>org.springframework.data</groupId>
      <artifactId>spring-data-elasticsearch</artifactId>
      <version>3.2.4.RELEASE</version>
    </dependency>

二、CourseIndexAggrService.java

import lombok.RequiredArgsConstructor;
import org.elasticsearch.index.query.BoolQueryBuilder;
import org.elasticsearch.index.query.QueryBuilders;
import org.elasticsearch.search.aggregations.Aggregation;
import org.elasticsearch.search.aggregations.AggregationBuilders;
import org.elasticsearch.search.aggregations.bucket.terms.ParsedLongTerms;
import org.elasticsearch.search.aggregations.bucket.terms.Terms;
import org.elasticsearch.search.aggregations.bucket.terms.TermsAggregationBuilder;
import org.springframework.data.elasticsearch.core.ElasticsearchRestTemplate;
import org.springframework.data.elasticsearch.core.aggregation.AggregatedPage;
import org.springframework.data.elasticsearch.core.query.NativeSearchQueryBuilder;
import org.springframework.stereotype.Component;

import java.util.ArrayList;
import java.util.List;

/**
 * @author xxx
 */
@Component
@RequiredArgsConstructor
public class CourseIndexAggrService {
    private final ElasticsearchRestTemplate elasticsearchRestTemplate;
    private final CommonConfig commonConfig;
    private static final String UNIQUE_FIELD = "unique_field";

    // 需要进行桶排序的字段
    public static final String CREATOR_ID = "creatorId";
    public static final String GRADE = "grade";
    public static final String SUBJECT = "subject";

    public List<String> findUniqueField(String uniqueField) {
        NativeSearchQueryBuilder queryBuilder = new NativeSearchQueryBuilder();
        BoolQueryBuilder boolQueryBuilder = QueryBuilders.boolQuery();
        //TODO 这里boolQueryBuilder是一个空的查询条件
        // 过滤掉已逻辑删除的记录 
        // boolQueryBuilder.filter(QueryBuilders.termQuery("deleted", 0));
        queryBuilder.withQuery(boolQueryBuilder);

        TermsAggregationBuilder termsAgg = AggregationBuilders.terms(UNIQUE_FIELD).field(uniqueField);

        queryBuilder.addAggregation(termsAgg);
        // idx_courseIndex是索引名
        queryBuilder.withIndices("idx_courseIndex");

        // CourseIndex是es文档类，见下文
        AggregatedPage<CourseIndex> resultPage = elasticsearchRestTemplate.queryForPage(queryBuilder.build(), CourseIndex.class);

        Aggregation aggregation = resultPage.getAggregation(UNIQUE_FIELD);

        ParsedLongTerms terms = (ParsedLongTerms) aggregation;

        // 获取桶
        final List<? extends Terms.Bucket> buckets = terms.getBuckets();

        // 提取唯一值
        List<String> uniqueUserIds = new ArrayList<>();
        for (Terms.Bucket bucket : buckets) {
            uniqueUserIds.add(bucket.getKeyAsString());
        }

        return uniqueUserIds;
    }
}

三、CourseIndex.java

这里略去了无关本文的字段。

import lombok.Data;
import org.springframework.data.elasticsearch.annotations.Document;
import org.springframework.data.elasticsearch.annotations.Field;
import org.springframework.data.elasticsearch.annotations.FieldType;

import javax.persistence.Id;
import java.io.Serializable;
import java.util.Set;

/**
 * 课程索引.
 * <p>
 * 索引检索条件，并非所有的字段
 * </p>
 *
 * @author xxx
 */
@Data
@Document(indexName = "#{commonConfig.courseIdx}", type = "_doc", shards = 1, refreshInterval = "-1")
public class CourseIndex implements Serializable {
    @Id
    private String id;

    /**
     * 课程或讲次编号
     */
    @Field(type = FieldType.Keyword)
    private String no;

    /**
     * 创建者ID
     */
    @Field(type = FieldType.Long)
    private long creatorId;

    /**
     * 课程或讲次名称
     */
    @Field(type = FieldType.Text)
    private String name;

    /**
     * 科目
     */
    @Field(type = FieldType.Integer)
    private int subject;

    /**
     * 年级
     */
    @Field(type = FieldType.Integer)
    private int grade;
}

四、使用

// 查询创建者creatorId列表
final List<Long> userIds = courseIndexAggrService.findUniqueField(CREATOR_ID).stream().map(v -> Long.parseLong(v)).collect(Collectors.toList());

// 查询年级grade列表
final List<Integer> grades = courseIndexAggrService.findUniqueField(GRADE).stream().map(v -> Integer.parseInt(v)).collect(Collectors.toList());

// 查询科目subject列表
final List<Integer> subjects = courseIndexAggrService.findUniqueField(SUBJECT).stream().map(v -> Integer.parseInt(v)).collect(Collectors.toList());