hive2.2.0及之后的版本支持使用merge into 语法,使用源表数据批量目标表的数据。使用该功能还需做如下配置
set hive.support.concurrency = true;
set hive.enforce.bucketing = true;
set hive.exec.dynamic.partition.mode = nonstrict;
set hive.txn.manager = org.apache.hadoop.hive.ql.lockmgr.DbTxnManager;
set hive.compactor.initiator.on = true;
set hive.compactor.worker.threads = 1;
set hive.auto.convert.join=false;
set hive.merge.cardinality.check=false; -- 目标表中出现重复匹配时要设置该参数才行
Hive对使用Update功能的表有特定的语法要求, 语法要求如下:
(1)要执行Update的表中, 建表时必须带有buckets(分桶)属性
(2)要执行Update的表中, 需要指定格式,其余格式目前赞不支持, 如:parquet格式, 目前只支持ORCFileformat和AcidOutputFormat
(3)要执行Update的表中, 建表时必须指定参数(‘transactional’ = true);
DROP TABLE IF EXISTS dim_date_10000;
create table dim_date_10000(
date_key string comment'如:2018-08-08'
,day int comment'日(1~31)'
,month int comment'月,如:8'
,month_name string comment'月名称,如:8月'
,year int comment'年,如:2018'
,year_month int comment'年月,如201808'
,week_of_year string comment'年内第几周 2018-1'
,week int comment'周(1~7)'
,week_name string comment'周,如星期三'
,quarter int comment'季(1~4)'
)
CLUSTERED BY (date_key) INTO 10 buckets
ROW FORMAT DELIMITED FIELDS TERMINATED BY ','
STORED AS orc
TBLPROPERTIES('transactional'='true');
对比在hive1.1.0 使用overwrite ,hive2.3.5使用merge into的方式 ,对不同量级的数据进行更新时的语法及效率。
之前hive表实现更新操作的步骤
insert overwrite table dim_date_100w
-- 旧的改变了的数据
select t2.date_key,t2.day,t2.month,t2.month_name,t2.year,t2.year_month,t2.week_of_year,t2.week,t2.week_name,1001 as quarter
from dim_date_100w t1
join dim_date_1w t2 on t1.date_key=t2.date_key
-- 旧的不变的数据
union all
select t1.*
from dim_date_100w t1
left join dim_date_1w t2 on t1.date_key=t2.date_key
where t2.date_key is null
-- 新增的数据
union all
select t1.*
from dim_date_1w t1
left join dim_date_100w t2 on t1.date_key=t2.date_key
where t2.date_key is null
;
MERGE INTO dim_date_100w AS T USING dim_date_1w AS S
ON t.date_key=s.date_key
WHEN MATCHED THEN
UPDATE SET quarter=1001 --关联上,变化的数据
WHEN NOT MATCHED THEN
INSERT --S 没关联上的 新增的数据
VALUES(S.date_key,S.day,S.month,S.month_name,S.year,S.year_month,S.week_of_year,S.week,S.week_name,S.quarter);
MERGE INTO <target table> AS T USING <source expression/table> AS S
ON <``boolean` `expression1>
WHEN MATCHED [AND <``boolean` `expression2>] THEN UPDATE SET <set clause list>
WHEN MATCHED [AND <``boolean` `expression3>] THEN DELETE
WHEN NOT MATCHED [AND <``boolean` `expression4>] THEN INSERT VALUES<value list>