在了解本文内容前,必须先了解ES DSL查询和ES 聚合查询,ES基于查询结果的聚合分为两种,第一种类似与关系型数据库中的Having语法,第二种类似于关系型数据库中先where在group by的语法,本文主要分析先查询后聚合场景
演示数据从ES 聚合查询获取
1、先查询后聚合
现在需要统计价格在50到500价格范围区间的所有食物,并按照标签进行聚合查询,代码如下:
GET food/_search { "query": { "range": { "Price": { "gte": 50, "lte": 500 } } }, "aggs": { "tags_bucket": { "terms": { "field": "Tags.keyword", "order": { "_count": "asc" } } } } }
搜索结果如下:
{ "took" : 5, "timed_out" : false, "_shards" : { "total" : 3, "successful" : 3, "skipped" : 0, "failed" : 0 }, "hits" : { "total" : { "value" : 3, "relation" : "eq" }, "max_score" : 1.0, "hits" : [ { "_index" : "food", "_id" : "5", "_score" : 1.0, "_source" : { "CreateTime" : "2022-07-09 13:11:11", "Desc" : "榴莲 非常好吃 很贵 吃一个相当于吃一只老母鸡", "Level" : "高级水果", "Name" : "榴莲", "Price" : 100.11, "Tags" : [ "贵", "水果", "营养" ], "Type" : "水果" } }, { "_index" : "food", "_id" : "3", "_score" : 1.0, "_source" : { "CreateTime" : "2022-06-07 13:11:11", "Desc" : "芦笋来自国外进口的蔬菜,西餐标配", "Level" : "中等蔬菜", "Name" : "芦笋", "Price" : 66.11, "Tags" : [ "有点贵", "国外", "绿色蔬菜", "营养价值高" ], "Type" : "蔬菜" } }, { "_index" : "food", "_id" : "6", "_score" : 1.0, "_source" : { "CreateTime" : "2022-07-08 13:11:11", "Desc" : "猫砂王榴莲 榴莲中的战斗机", "Level" : "高级水果", "Name" : "猫砂王榴莲", "Price" : 300.11, "Tags" : [ "超级贵", "进口", "水果", "非常好吃" ], "Type" : "水果" } } ] }, "aggregations" : { "tags_bucket" : { "doc_count_error_upper_bound" : 0, "sum_other_doc_count" : 0, "buckets" : [ { "key" : "国外", "doc_count" : 1 }, { "key" : "有点贵", "doc_count" : 1 }, { "key" : "绿色蔬菜", "doc_count" : 1 }, { "key" : "营养", "doc_count" : 1 }, { "key" : "营养价值高", "doc_count" : 1 }, { "key" : "贵", "doc_count" : 1 }, { "key" : "超级贵", "doc_count" : 1 }, { "key" : "进口", "doc_count" : 1 }, { "key" : "非常好吃", "doc_count" : 1 }, { "key" : "水果", "doc_count" : 2 } ] } } }
hits中是按照query查询的结果集,下面是根据query的结果集进行的聚合查询.
2、先聚合后查询(注意这里不是having语法,而是查询聚合里面的详情) 通过post_filter实现
现在需要查询价格范围在50到500之间,按照标签分组之后,标签包含营养的记录数据,代码如下:
GET food/_search { "query": { "range": { "Price": { "gte": 50, "lte": 500 } } }, "aggs": { "tags_bucket":{ "terms": { "field": "Tags.keyword" } } }, "post_filter": { "term": { "Tags.keyword": "营养" } } }
搜索结果如下:
{ "took" : 41, "timed_out" : false, "_shards" : { "total" : 3, "successful" : 3, "skipped" : 0, "failed" : 0 }, "hits" : { "total" : { "value" : 1, "relation" : "eq" }, "max_score" : 1.0, "hits" : [ { "_index" : "food", "_id" : "5", "_score" : 1.0, "_source" : { "CreateTime" : "2022-07-09 13:11:11", "Desc" : "榴莲 非常好吃 很贵 吃一个相当于吃一只老母鸡", "Level" : "高级水果", "Name" : "榴莲", "Price" : 100.11, "Tags" : [ "贵", "水果", "营养" ], "Type" : "水果" } } ] }, "aggregations" : { "tags_bucket" : { "doc_count_error_upper_bound" : 0, "sum_other_doc_count" : 0, "buckets" : [ { "key" : "水果", "doc_count" : 2 }, { "key" : "国外", "doc_count" : 1 }, { "key" : "有点贵", "doc_count" : 1 }, { "key" : "绿色蔬菜", "doc_count" : 1 }, { "key" : "营养", "doc_count" : 1 }, { "key" : "营养价值高", "doc_count" : 1 }, { "key" : "贵", "doc_count" : 1 }, { "key" : "超级贵", "doc_count" : 1 }, { "key" : "进口", "doc_count" : 1 }, { "key" : "非常好吃", "doc_count" : 1 } ] } } }
3、取消查询条件,嵌套查询
现在需要统计指定范围内食品的平均值、最大值等等,最后需要带上一个所有食品的平均值.这个时候计算所有食品的平均值不能受限于查询条件,实现方式如下:
GET food/_search { "query": { "range": { "Price": { "gte": 50, "lte": 500 } } }, "aggs": { "price_avg":{ "avg": { "field": "Price" } }, "price_max":{ "max": { "field": "Price" } }, "price_min":{ "min": { "field": "Price" } }, "all_price_avg":{ "global": {}, "aggs": { "price_avg":{ "avg": { "field": "Price" } } } } } }
搜索结果如下:
{ "took" : 6, "timed_out" : false, "_shards" : { "total" : 3, "successful" : 3, "skipped" : 0, "failed" : 0 }, "hits" : { "total" : { "value" : 3, "relation" : "eq" }, "max_score" : 1.0, "hits" : [ { "_index" : "food", "_id" : "5", "_score" : 1.0, "_source" : { "CreateTime" : "2022-07-09 13:11:11", "Desc" : "榴莲 非常好吃 很贵 吃一个相当于吃一只老母鸡", "Level" : "高级水果", "Name" : "榴莲", "Price" : 100.11, "Tags" : [ "贵", "水果", "营养" ], "Type" : "水果" } }, { "_index" : "food", "_id" : "3", "_score" : 1.0, "_source" : { "CreateTime" : "2022-06-07 13:11:11", "Desc" : "芦笋来自国外进口的蔬菜,西餐标配", "Level" : "中等蔬菜", "Name" : "芦笋", "Price" : 66.11, "Tags" : [ "有点贵", "国外", "绿色蔬菜", "营养价值高" ], "Type" : "蔬菜" } }, { "_index" : "food", "_id" : "6", "_score" : 1.0, "_source" : { "CreateTime" : "2022-07-08 13:11:11", "Desc" : "猫砂王榴莲 榴莲中的战斗机", "Level" : "高级水果", "Name" : "猫砂王榴莲", "Price" : 300.11, "Tags" : [ "超级贵", "进口", "水果", "非常好吃" ], "Type" : "水果" } } ] }, "aggregations" : { "all_price_avg" : { "doc_count" : 6, "price_avg" : { "value" : 83.44333092371623 } }, "price_min" : { "value" : 66.11000061035156 }, "price_avg" : { "value" : 155.44332885742188 }, "price_max" : { "value" : 300.1099853515625 } } }
这里通过 "global": {}来实现取消查询条件