hive之自定义函数

create table tab_array(a array<int>,b array<string>)
row format delimited
fields terminated by '\t'
colloction items terminated by ',';
abc,helloworl,itcats   213123214,432312321
select a[0] from tab_array;

create table tab_map(name string,info map<string,string>)
row format delimited
fields terminated by '\t'
colloction items terminated by ';'
map keys terminated by ';';
实例数据
fengjie   age:18;size:36A;addr:usa;
furong   age:28;size:39C;addr:beijing;weight:90KG
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'
collectionitems terminated by ','
load data local inpath '/home/hadoop/hivetemp/tab_struct.txt' overwrite into table tab_struct
insert into table tab_map select name,named_struct('age',id,'tel',name,'addr',country) from tab_struct;

cli shell
hive -S -e 'select country,count(*) from tab_ext'>~/soft/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)

package cn.itcas.hive.udf;

import java.util.HashMap;

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

public class PhoneToArea extends UDF {
    
    
    private static HashMap<String,String> map=new HashMap<String,String>();
    static{
        map.put("136","beijing");
        map.put("137","tianjing");
        map.put("138","nanjing");
        map.put("139","shanghai");
        map.put("188","tokyo");
    }
    
    //transform phoneNo To specificAreaName
    public String evaluate(String phoneNum){
        String area=map.get(phoneNum.substring(0, 3));
        return area==null?"huoxing":area;
    }
    //sum the flow
    public int evaluate(int upFlow,int downFlow){
        
        return upFlow+downFlow;
    }

}
//方法必须是public 否者吊用不了这个方法

打成hiveutil.jar
[root@hadoop04 hive-0.12.0]# mv ~/Desktop/hiveutil.jar ~/soft
hive> add jar /root/soft/hiveutil.jar
    > ;
Added /root/soft/hiveutil.jar to class path
Added resource: /root/soft/hiveutil.jar

hive> create temporary function areasum as 'cn.itcas.hive.udf.PhoneToArea'
    > ;
OK
Time taken: 0.006 seconds
[root@hadoop04 soft]# vi flow.data
13198530807,220,300
13233231222,330,450
13333231222,330,450
13433231222,330,450
13533231222,330,450
13633231222,330,450
13833231222,330,450
13933231222,330,450
18633231222,330,450
13233231222,330,450


hive> create table t_flow(phonenbr string ,upflow int,downflow int)
    > row format delimited
    > fields terminated by ',';
OK
Time taken: 14.112 seconds
hive> load data local inpath '/root/soft/flow.data' into table t_flow;
Copying data from file:/root/soft/flow.data
Copying file: file:/root/soft/flow.data
Loading data to table default.t_flow
Table default.t_flow stats: [num_partitions: 0, num_files: 1, num_rows: 0, total_size: 201, raw_data_size: 0]
OK
Time taken: 1.509 seconds
hive> select * from t_flow;
OK
13198530807     220     300
13233231222     330     450
13333231222     330     450
13433231222     330     450
13533231222     330     450
13633231222     330     450
13833231222     330     450
13933231222     330     450
18633231222     330     450
13233231222     330     450
        NULL    NULL
Time taken: 0.76 seconds, Fetched: 11 row(s)

hive> select phonenbr,areasum(phonenbr),areasum(upflow,downflow) from t_flow;
若出错quit之后再运行
13198530807     huoxing 520
13233231222     huoxing 780
13333231222     huoxing 780
13433231222     huoxing 780
13533231222     huoxing 780
13633231222     beijing 780
13833231222     nanjing 780
13933231222     shanghai        780
18633231222     huoxing 780
13233231222     huoxing 780