use test03;
// 桶表 辅助表
create table b_tb1(
id bigint,
name string,
love array<string>)
row format delimited fields terminated by '\t';
//导入数据
load data local inpath '/data/log/tong.txt' into table b_tb1
//分通表(clusted by 指定按那个列分桶,sorted by指定排序方式)
create table tongb_tb2(
id bigint,
name string,
love array<string>)
clustered by(id) sorted by(id desc) into 3 buckets
row format delimited fields terminated by '\t'
collection items terminated by ',';
//插入数据。插入数据是也要指定分桶字段,按key对桶数量取摸,此时reduce数量和桶数量设为一致(set mapreduce.job.reduces=3)(cluster by等同于distribute by+sort by)
//cluster by默认为升序
insert into table tongb_tb2
select id,name,love from b_tb1 cluster by(id);