hive之行轉列和列轉行

1、列轉行

user_basic_info:

id	name
1	a
2	b
3	c
4	d

user_address;

name	address
a	add1
a	add2
b	add3
c	add4
d	add5

user_info

id	name	address
1	a	add1,add2
2	b	add3
3	c	add4
4	d	add5

建表語句：

create table  user_basic_info(
id string,
name string
)ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' ;   --指定每一行中的字段用\t 作分隔符，

create table user_address(name string, address string)
ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' ;   --指定每一行中的字段用\t 作分隔符，

create table user_info(
id   string,
name   string ,
address array<string>
)
ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' 
COLLECTION ITEMS TERMINATED BY ',' ;--集合按照指定分割符號分割

導入數據：

load data local inpath '/usr/local/hive/user_basic_info_file' into table user_basic_info;  
load data local inpath '/usr/local/hive/user_address_file' into table user_address;

列轉行，並將數據插入到表 user_info中

insert  overwrite  table  user_info  
select max(ubi.id), ubi.name,   collect_set(ua.address)  as address from  user_basic_info  ubi 
join  user_address  ua on ubi.name=ua.name group by ubi.name;

2、行轉列

建立新表  user_info2

create table user_info2(
id string,
name string,
address string)
ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t'  ;

行轉列語句：

insert into user_info2  select id, name, add 
from user_info ui lateral view explode(ui.address) adtable as add;