尚硅谷大数据技术之Hive（新）第10章 Hive实战之谷粒影音

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;

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

load data inpath "/gulivideo/user/2008/0903" into table gulivideo_user_ori;

insert into table gulivideo_orc select * from gulivideo_ori;

insert into table gulivideo_user_orc select * from gulivideo_user_ori;