HQL（Hive query language）常用语句

set hive.cli.print.header=true;


CREATE TABLE page_view(viewTime INT, userid BIGINT,
     page_url STRING, referrer_url STRING,
     ip STRING COMMENT 'IP Address of the User')
 COMMENT 'This is the page view table'
 PARTITIONED BY(dt STRING, country STRING)
 ROW FORMAT DELIMITED
   FIELDS TERMINATED BY '\001'
STORED AS SEQUENCEFILE;


//sequencefile
create table tab_ip_seq(id int,name string,ip string,country string) 
    row format delimited
    fields terminated by ','
    stored as sequencefile;
    
//使用select语句来批量插入数据
insert overwrite table tab_ip_seq select * from tab_ext;




//create & load
create table tab_ip(id int,name string,ip string,country string) 
    row format delimited
    fields terminated by ','
    stored as textfile;
    
//从本地导入数据到hive的表中（实质就是将文件上传到hdfs中hive管理目录下）
load data local inpath '/home/hadoop/ip.txt' into table tab_ext;


//从hdfs上导入数据到hive表中（实质就是将文件从原始目录移动到hive管理的目录下）
load data inpath 'hdfs://ns1/aa/bb/data.log' into table tab_user;




//external外部表
CREATE EXTERNAL TABLE tab_ip_ext(id int, name string,
     ip STRING,
     country STRING)
 ROW FORMAT DELIMITED FIELDS TERMINATED BY ','
 STORED AS TEXTFILE
 LOCATION '/external/user';
 


// CTAS  根据select语句建表结构
CREATE TABLE tab_ip_ctas
   AS
SELECT id new_id, name new_name, ip new_ip,country new_country
FROM tab_ip_ext
SORT BY new_id;




//CLUSTER <--相对高级一点，你可以放在有精力的时候才去学习>
create table tab_ip_cluster(id int,name string,ip string,country string)
clustered by(id) into 3 buckets;


load data local inpath '/home/hadoop/ip.txt' overwrite into table tab_ip_cluster;
set hive.enforce.bucketing=true;
insert into table tab_ip_cluster select * from tab_ip;


select * from tab_ip_cluster tablesample(bucket 2 out of 3 on id); 






//PARTITION  分区表
create table tab_ip_part(id int,name string,ip string,country string) 
    partitioned by (year string)
    row format delimited fields terminated by ',';
    
load data local inpath '/home/hadoop/data.log' overwrite into table tab_ip_part
     partition(year='1990');
    
    
load data local inpath '/home/hadoop/data2.log' overwrite into table tab_ip_part
     partition(year='2000');


select * from tab_ip_part;


select * from tab_ip_part  where part_flag='part2';
select count(*) from tab_ip_part  where part_flag='part2';




alter table tab_ip change id id_alter string;
ALTER TABLE tab_cts ADD PARTITION (partCol = 'dt') location '/external/hive/dt';


show partitions tab_ip_part;


//insert from select   通过select语句批量插入数据到别的表
create table tab_ip_like like tab_ip;
insert overwrite table tab_ip_like
    select * from tab_ip;
   
//write to hdfs  将结果写入到hdfs的文件中
insert overwrite local directory '/home/hadoop/hivetemp/test.txt' select * from tab_ip_part where part_flag='part1';    
insert overwrite directory '/hiveout.txt' select * from tab_ip_part where part_flag='part1';


//cli shell  通过shell执行hive的hql语句
hive -S -e 'select country,count(*) from tab_ext' > /home/hadoop/hivetemp/e.txt  


select * from tab_ext sort by id desc limit 5;


select a.ip,b.book from tab_ext a join tab_ip_book b on(a.name=b.name);




//array 
create table tab_array(a array<int>,b array<string>)
row format delimited
fields terminated by '\t'
collection items terminated by ',';


select a[0] from tab_array;
select * from tab_array where array_contains(b,'word');
insert into table tab_array select array(0),array(name,ip) from tab_ext t; 


//map
create table tab_map(name string,info map<string,string>)
row format delimited
fields terminated by '\t'
collection items terminated by ','
map keys terminated by ':';


load data local inpath '/home/hadoop/hivetemp/tab_map.txt' overwrite into table tab_map;
insert into table tab_map select name,map('name',name,'ip',ip) from tab_ext; 


//struct
create table tab_struct(name string,info struct<age:int,tel:string,addr:string>)
row format delimited
fields terminated by '\t'
collection items terminated by ','


load data local inpath '/home/hadoop/hivetemp/tab_st.txt' overwrite into table tab_struct;
insert into table tab_struct select name,named_struct('age',id,'tel',name,'addr',country) from tab_ext;






//UDF
select if(id=1,first,no-first),name from tab_ext;


hive>add jar /home/hadoop/myudf.jar;
hive>CREATE TEMPORARY FUNCTION fanyi AS 'cn.itcast.hive.Fanyi';
select id,name,ip,fanyi(country) from tab_ip_ext;