flinksql-Queries查询相关实战

  1. 分组聚合

--分组集

--GROUPING SETS() 允许你定义特定的分组方式,这样你可以选择只对感兴趣的分组进行计算。

--通过手动指定不同的分组组合,你能够灵活地控制数据的聚合结果。

--与 ROLLUP 和 CUBE 不同,GROUPING SETS 不会自动生成所有子集组合,而是只生成你指定的那些。

SELECT supplier_id, rating, COUNT(*) AS total

FROM (VALUES

('supplier1', 'product1', 4),

('supplier1', 'product2', 3),

('supplier2', 'product3', 3),

('supplier2', 'product4', 4))

AS Products(supplier_id, product_id, rating)

GROUP BY GROUPING SETS ((supplier_id, rating), (supplier_id), ());

--ROLLUP

--ROLLUP() 用于执行分层级别的聚合,主要用于需要按顺序逐层汇总数据的场景。

--与 CUBE() 不同,ROLLUP() 只生成按从左到右逐步减少维度的组合,而不是所有可能的子集组合。

--例如,ROLLUP(a, b, c) 会生成 (a, b, c), (a, b), (a), 和 (),而不会像 CUBE() 那样生成所有的可能组--合。

SELECT supplier_id, rating, COUNT(*)

FROM (VALUES

('supplier1', 'product1', 4),

('supplier1', 'product2', 3),

('supplier2', 'product3', 3),

('supplier2', 'product4', 4))

AS Products(supplier_id, product_id, rating)

GROUP BY ROLLUP (supplier_id, rating);

--立方体

--CUBE() 是一种扩展的 GROUP BY 操作,允许你针对多列进行分组聚合,并生成每种可能的维度组合的聚合结果。

--如果使用了 CUBE(a, b, c),Flink 会计算出所有 a, b, c 及其子集的组合的聚合结果。

--在数据分析和 OLAP(在线分析处理)场景中,CUBE 常用来计算多维数据的统计值。

SELECT supplier_id, rating, COUNT(*)

FROM (VALUES

('supplier1', 'product1', 4),

('supplier1', 'product2', 3),

('supplier2', 'product3', 3),

('supplier2', 'product4', 4))

AS Products(supplier_id, product_id, rating)

GROUP BY CUBE (supplier_id, rating);

  1. 窗口函数TVF

--注:不支持cdc模式,因为窗口函数只支持追加模式的,不支持update与delete操作

--模拟表

CREATE TABLE bid (

`id` string,

bidtime TIMESTAMP(3),

price DECIMAL(10, 2),

item string,

ts as bidtime,

WATERMARK FOR ts AS ts - INTERVAL '5' SECOND,

--proc_time AS PROCTIME(),

PRIMARY KEY (`id`) NOT ENFORCED

)

WITH

(

'connector' = 'jdbc',

${36},

'table-name' = 'bid'

);

--滚动窗口

-- SELECT cast(window_start as string) AS window_start, cast(window_end as string) AS window_end , SUM(price) AS total_price

-- FROM TABLE(

-- TUMBLE(TABLE bid, DESCRIPTOR(ts), INTERVAL '10' MINUTES))

-- GROUP BY window_start, window_end;

--滑动窗口

-- SELECT cast(window_start as string) AS window_start, cast(window_end as string) AS window_end , SUM(price) AS total_price

-- FROM TABLE(

-- HOP(TABLE bid, DESCRIPTOR(ts), INTERVAL '5' MINUTES, INTERVAL '10' MINUTES))

-- GROUP BY window_start, window_end;

--累计窗口

-- SELECT cast(window_start as string) AS window_start, cast(window_end as string) AS window_end , SUM(price) AS total_price

-- FROM TABLE(

-- CUMULATE(TABLE bid, DESCRIPTOR(ts), INTERVAL '5' MINUTES, INTERVAL '20' MINUTES))

-- GROUP BY window_start, window_end;

--会话窗口(不支持批处理)

SELECT window_start, window_end, item, SUM(price) AS total_price

FROM TABLE(

SESSION(TABLE bid PARTITION BY item, DESCRIPTOR(ts), INTERVAL '5' MINUTES))

GROUP BY item, window_start, window_end;

  1. 窗口聚合

CREATE TABLE bid (

`id` string,

bidtime TIMESTAMP(3),

price DECIMAL(10, 2),

item string,

supplier_id string,

ts as bidtime,

WATERMARK FOR ts AS ts - INTERVAL '5' SECOND,

--proc_time AS PROCTIME(),

PRIMARY KEY (`id`) NOT ENFORCED

)

WITH

(

'connector' = 'jdbc',

${36},

'table-name' = 'bid'

);

--分组集

-- SELECT cast(window_start as string) AS window_start, cast(window_end as string) AS window_end , supplier_id, SUM(price) AS total_price

-- FROM TABLE(

-- TUMBLE(TABLE bid, DESCRIPTOR(ts), INTERVAL '10' MINUTES))

-- GROUP BY window_start, window_end, GROUPING SETS ((supplier_id), ());

--ROLLUP

-- SELECT cast(window_start as string) AS window_start, cast(window_end as string) AS window_end , supplier_id, SUM(price) AS total_price

-- FROM TABLE(

-- TUMBLE(TABLE bid, DESCRIPTOR(ts), INTERVAL '10' MINUTES))

-- GROUP BY window_start, window_end, ROLLUP (supplier_id);

--立方体

SELECT cast(window_start as string) AS window_start, cast(window_end as string) AS window_end , supplier_id, item, SUM(price) AS total_price

FROM TABLE(

TUMBLE(TABLE bid, DESCRIPTOR(ts), INTERVAL '10' MINUTES))

GROUP BY window_start, window_end, CUBE (supplier_id, item);

  1. Over聚合

持续更新

相关推荐
java水泥工11 分钟前
师生健康信息管理系统|基于SpringBoot和Vue的师生健康信息管理系统(源码+数据库+文档)
数据库·vue.js·spring boot
chirrupy_hamal24 分钟前
PostgreSQL WAL 日志发展史 - pg7
数据库·postgresql
五颜六色的池1 小时前
my sql 常用函数及语句的执行顺序
数据库·sql
Gold Steps.1 小时前
从 “T+1” 到 “秒级”:MySQL+Flink+Doris 构建实时数据分析全链路
大数据·数据库·数据分析
花北城2 小时前
【MySQL】Oracle与MySQL,跨库数据转储
数据库·mysql·oracle
一條狗2 小时前
学习日报 20250929|数据库与缓存一致性策略的选择
redis·mysql·kafka
没有bug.的程序员2 小时前
MySQL 配置调优参数:从基础到生产级优化指南
java·数据库·mysql·优化·mysql配置调优
optimistic_chen2 小时前
【Java EE进阶 --- SpringBoot】Mybatis操作数据库(基础)
数据库·经验分享·spring boot·笔记·spring·java-ee·mybatis
支付宝小程序云2 小时前
百宝箱开放平台 ✖️ 查询信息列表
数据库
对着晚风做鬼脸3 小时前
MySQL进阶知识点(六)---- 存储引擎
数据库·mysql