03准备工作

1.创建表

1.1 所需表

	gulivideo_ori，gulivideo_user_ori，
	gulivideo_orc，gulivideo_user_orc。

1.2 代码

	create table gulivideo_ori(
		videoId string, 
		uploader string, 
		age int, 
		category array<string>, 
		length int, 
		views int, 
		rate float, 
		ratings int, 
		comments int,
		relatedId array<string>)
	row format delimited 
	fields terminated by "\t"
	collection items terminated by "&"
	stored as textfile;

	create table gulivideo_user_ori(
		uploader string,
		videos int,
		friends int)
	row format delimited 
	fields terminated by "\t" 
	stored as textfile;
	
	create table gulivideo_orc(
		videoId string, 
		uploader string, 
		age int, 
		category array<string>, 
		length int, 
		views int, 
		rate float, 
		ratings int, 
		comments int,
		relatedId array<string>)
	clustered by (uploader) into 8 buckets 
	row format delimited fields terminated by "\t" 
	collection items terminated by "&" 
	stored as orc;

	create table gulivideo_user_orc(
		uploader string,
		videos int,
		friends int)
	row format delimited 
	fields terminated by "\t" 
	stored as orc;
	
1.3 将原始数据插入到orc中

2.导入ETL后的数据

load data inpath "/gulivideo/output/video/2008/0222" into table gulivideo_ori;
load data inpath "/gulivideo/user/2008/0903" 		 into table gulivideo_user_ori;

3.向ORC表插入数据

insert into table gulivideo_orc 		select * from gulivideo_ori;
insert into table gulivideo_user_orc 	select * from gulivideo_user_ori;