hive> create database hadoop;
hive> use hadoop;

hive> create table t_order(id int,name string,container string,price double)
    > row format delimited                                                  
    > fields terminated by ‘\t‘;

//array 
create table tab_array(a array<int>,b array<string>)
row format delimited
fields terminated by ‘\t‘　　//使用\t分割字段
collection items terminated by ‘,‘;　　//使用,分割数组元素

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‘　　　　//使用\t分割字段
collection items terminated by ‘,‘　　//使用，分割map元素
map keys terminated by ‘:‘;　　//使用：分割每个map的key和value

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; 

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;

[hadoop@hadoopH1 ~]$ cat order.txt 
00001001        iphone5 32G     4999
00001002        iphone6S        128G    9999
00001003        xiaomi6x        32G     2999
00001004        honor   32G     3999

load data local inpath ‘/home/hadoop/order.txt‘ into table t_order;

[hadoop@hadoopH1 ~]$ cat order_1.txt 
00002001        redmi   32G     3999
00002002        geli    128G    1999
00002003        xiami6x 32G     999
00002004        huawei  32G     3999

load data local inpath ‘/home/hadoop/ip.txt‘ into table tab_ext;

load data inpath ‘hdfs://ns1/aa/bb/data.log‘ into table tab_user;

insert overwrite table tab_ip_seq select * from tab_ext;

select * from t_order;

 select count(*) from t_order;

CREATE EXTERNAL TABLE tab_ip_ext(id int, name string,
     ip STRING,
     country STRING)
 ROW FORMAT DELIMITED FIELDS TERMINATED BY ‘,‘
 STORED AS TEXTFILE　　#数据表存储格式为TEXT文本
 LOCATION ‘/external/user‘;　　#从hdfs中其他文件目录/external/user下引入数据

CREATE TABLE t_order_sel
   AS
SELECT id new_id, name new_name, price new_price
FROM t_order
SORT BY new_id;

partition分区，可以使用建表字段，也可以使用其他字段。

建表使用partition进行分区，数据插入也需要指定分区进行存放

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‘);

show partitions tab_ip_part;

alter table tab_ip change id id_alter string;　　修改字段
ALTER TABLE tab_cts ADD PARTITION (partCol = ‘dt‘) location ‘/external/hive/dt‘;　　修改添加分区

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); 

hive -S -e ‘select country,count(*) from tab_ext‘ > /home/hadoop/hivetemp/e.txt  

select getarea(phoneNB),upflow,downflow from t_flow

1389990045    239    300
1385566005    229    435
1385566005    192    256
1389990045    23    84
1390876045    682    432
1385566005    134    300
1390876045    378    656
1390876045    346    123
1389990045    78    352

1389990045    beijing    239    300
1385566005    nanjin    229    435
1385566005    nanjin    192    256
1389990045    beijing    23    84
1390876045    shenyang    682    432
1385566005    nanjin    134    300
1390876045    shenyang    378    656
1390876045    shenyang    346    123
1389990045    beijing    78    352

1.实现Java类，定义上述函数逻辑。转化为jar包，上传到hive的lib中
2.在hive中创建一个函数getarea,和jar包中的自定义java类建立关联

package cn.hadoop.hive;

import java.util.HashMap;

import org.apache.hadoop.hive.ql.exec.UDF;

public class phoneNBToArea extends UDF{
    public static HashMap<String,String> areamap = new HashMap<>();
    
    static {
        areamap.put("1389", "beijing");
        areamap.put("1385", "nanjin");
        areamap.put("1390", "shenyang");
    }
    
    public String evaluate(String phoneNB) {　　//需要重载该方法
        String result = areamap.get(phoneNB.substring(0, 4))==null?(phoneNB+"    nowhere"):(phoneNB+"    "+areamap.get(phoneNB.substring(0, 4)));
        return result;
    }
}

hive> add jar /home/hadoop/hive.jar;
hive> create temporary function getarea as ‘cn.hadoop.hive.phoneNBToArea‘;

create table t_flow(phoneNB string,upflow int,download int)
row format delimited
fields terminated by ‘\t‘;

load data local inpath ‘/home/hadoop/flow.txt‘ into table t_flow;

select getarea(phoneNB),upflow,download from t_flow;