Elasticsearch：对一些字段进行聚合入门

秒速五厘米 2024-03-24 10:49 102阅读 0赞

聚合（aggregations）可以实现对文档数据的统计、分析、运算。聚合常见的有三类：

*  桶（Bucket）聚合：用来对文档做分组
    
     *  TermAggregation：按照文档字段值分组Date
     *  Histogram：按照日期阶梯分组，例如一周为一组，或者一月为一组
 *  度量（Metric）聚合：用以计算一些值，比如：最大值、最小值、平均值等
    
     *  Avg：求平均值
     *  Max：求最大值
     *  Min：求最小值
     *  Stats：同时求max、min、avg、sum等
 *  管道（pipeline）聚合：其它聚合的结果为基础做聚合

参与聚合的字段类型必须是：

*  keyword
 *  数值
 *  日期
 *  布尔

import org.apache.http.HttpHost;
    import org.elasticsearch.client.RestClient;
    import org.elasticsearch.client.RestHighLevelClient;
     
    @Configuration
    public class ElasticsearchConfig {
     
     
        @Bean
        public RestHighLevelClient restHighLevelClient(){
            return new RestHighLevelClient(RestClient.builder(
                    HttpHost.create("http://192.168.150.101:9200")
            ));
        }
    }

@Data
    public class Demo {
    
        private String brand;
        private String city;
        private String starName;
    }

import org.elasticsearch.action.search.SearchRequest;
    import org.elasticsearch.action.search.SearchResponse;
    import org.elasticsearch.client.RestHighLevelClient;
    import org.elasticsearch.search.aggregations.AggregationBuilders;
    import org.elasticsearch.search.aggregations.Aggregations;
    import org.elasticsearch.search.aggregations.bucket.terms.Terms;
    
    @Service
    public class DemoService extends ServiceImpl<DemoMapper, Demo> implements IDemoService {
    
        @Autowired
        private RestHighLevelClient restHighLevelClient;
    
        @Override
        public Map<String, List<String>> getFilters(RequestParams params) {
            
            try {
                // 1.准备请求
                SearchRequest request = new SearchRequest("demo");
                // 2.请求参数
                // 2.2.size
                request.source().size(0);
                // 2.3.聚合
                buildAggregations(request);
                // 3.发出请求
                SearchResponse response = restHighLevelClient.search(request, RequestOptions.DEFAULT);
                // 4.解析结果
                Aggregations aggregations = response.getAggregations();
                Map<String, List<String>> filters = new HashMap<>(3);
                // 4.1.解析品牌
                List<String> brandList = getAggregationByName(aggregations, "brandAgg");
                filters.put("brand", brandList);
                // 4.2.解析城市
                List<String> cityList = getAggregationByName(aggregations, "cityAgg");
                filters.put("city", cityList);
                // 4.3.解析星级
                List<String> starList = getAggregationByName(aggregations, "starAgg");
                filters.put("starName", starList);
    
                return filters;
            } catch (IOException e) {
                throw new RuntimeException(e);
            }
        }
    
        private void buildAggregations(SearchRequest request) {
            request.source().aggregation(
                    AggregationBuilders.terms("brandAgg").field("brand").size(100));
            request.source().aggregation(
                    AggregationBuilders.terms("cityAgg").field("city").size(100));
            request.source().aggregation(
                    AggregationBuilders.terms("starAgg").field("starName").size(100));
        }
        
    
        private List<String> getAggregationByName(Aggregations aggregations, String aggName) {
            // 4.1.根据聚合名称，获取聚合结果
            Terms terms = aggregations.get(aggName);
            // 4.2.获取buckets
            List<? extends Terms.Bucket> buckets = terms.getBuckets();
            // 4.3.遍历
            List<String> list = new ArrayList<>(buckets.size());
            for (Terms.Bucket bucket : buckets) {
                String brandName = bucket.getKeyAsString();
                list.add(brandName);
            }
            return list;
        }
    }