模拟生成数据

CREATE TABLE ods_station_log (base_station_id int,   -- 基站IDevent_type      int,   -- 事件类型: connect/disconnectevent_time      TIMESTAMP_LTZ(3), -- 事件时间WATERMARK FOR event_time AS event_time - INTERVAL '5' SECOND -- 允许5秒乱序
) WITH ('connector' = 'datagen',-- 基站ID生成规则（BS001 ~ BS100）'fields.base_station_id.kind' = 'random','fields.base_station_id.min' = '1','fields.base_station_id.max' = '2',-- 事件类型随机生成（50%概率为 connect/disconnect）'fields.event_type.kind' = 'random','fields.event_type.min' = '0','fields.event_type.max' = '1',-- 事件时间生成规则（模拟1小时数据，每秒10条）'fields.event_time.kind' = 'random','fields.event_time.max-past' = '1000s',-- 控制数据生成速率'rows-per-second' = '1'
);

需求： 基站与服务器长连接，每次连接和断开都会上报数据，统计过去一小时每个基站断开次数和时长
思路：

CREATE TEMPORARY VIEW disconnect_records2 AS
SELECTbase_station_id,connect_time,disconnect_time,TIMESTAMPDIFF(SECOND, connect_time, disconnect_time) AS duration
FROM ods_station_log
MATCH_RECOGNIZE (PARTITION BY base_station_idORDER BY event_timeMEASURESe_connect.event_time AS connect_time,e_disconnect.event_time AS disconnect_timeONE ROW PER MATCHAFTER MATCH SKIP PAST LAST ROWPATTERN (e_connect e_disconnect) DEFINEe_connect AS e_connect.event_type = 1,e_disconnect AS e_disconnect.event_type = 0
);