Hive读取复杂的数据类型（Array，Map，Struct）
1.数组
数据文件 hive_array.txt,Array(1,2,3,4) 装的数据类型是一样的
zhnagsan PEK,SHA,HAK,NKG
lisi CTU,CKG,XIY,CSX创建表：
create table hive_array(name string, work_locations array)
row format delimited fields terminated by '\t'
COLLECTION ITEMS TERMINATED BY ','; 加载数据：load data local inpath '/home/hadoop/testdata/hive_array.txt' into table hive_array;
查询数据：
+------------------+----------------------------+--+
| hive_array.name | hive_array.work_locations |
+------------------+----------------------------+--+
| zhnagsan | ["PEK","SHA","HAK","NKG"] |
| lisi | ["CTU","CKG","XIY","CSX"] |
+------------------+----------------------------+--+
2 rows selected (0.233 seconds)
0: jdbc:hive2://hadoop002:10000/test>
查询数组字段的第一个值：work_locations[index] : index from zero
0: jdbc:hive2://hadoop002:10000/test> select name,work_locations[0] from hive_array;
+-----------+------+--+
| name | _c1 |
+-----------+------+--+
| zhnagsan | PEK |
| lisi | CTU |
+-----------+------+--+
2 rows selected (0.103 seconds)
0: jdbc:hive2://hadoop002:10000/test> select name,size(work_locations) from hive_array;
+-----------+------+--+
| name | _c1 |
+-----------+------+--+
| zhnagsan | 4 |
| lisi | 4 |
+-----------+------+--+
2 rows selected (0.096 seconds)
0: jdbc:hive2://hadoop002:10000/test> select name from hive_array where array_contains(work_locations,'PEK');
+-----------+--+
| name |
+-----------+--+
| zhnagsan |
+-----------+--+
1 row selected (0.075 seconds)
2.Map
数据文件hive_map.txt
1,zhangsan,father:laozhang#mother:xiaohuang#brother:xiaohu,55
2,lisi,father:laoli#mother:xiaoxu#brother:xiaoqiang,44
3,wangwu,father:laowang#mother:xiaoliu#sister:wanghua,33
4,zhaoliu,father:xiaozhao#mother:xiaozhu,22建表并加载数据
hive (test)> create table hive_map(id int,name string, members map, age int)
> row format delimited fields terminated by ','
> COLLECTION ITEMS TERMINATED BY '#'
> MAP KEYS TERMINATED BY ':';
OK
Time taken: 0.305 seconds
hive (test)> load data local inpath '/home/hadoop/testdata/hive_map.txt' into table hive_map;
Loading data to table test.hive_map
Table test.hive_map stats: [numFiles=1, totalSize=218]
OK
Time taken: 0.398 seconds
查询数据
hive (test)> select * from hive_map;
OK
hive_map.id hive_map.name hive_map.members hive_map.age
1 zhangsan {"father":"laozhang","mother":"xiaohuang","brother":"xiaohu"} 55
2 lisi {"father":"laoli","mother":"xiaoxu","brother":"xiaoqiang"} 44
3 wangwu {"father":"laowang","mother":"xiaoliu","sister":"wanghua"} 33
4 zhaoliu {"father":"xiaozhao","mother":"xiaozhu"} 22
Time taken: 0.2 seconds, Fetched: 4 row(s)
hive (test)> select id,name,age,members["father"],members["sister"] from hive_map;
OK
id name age _c3 _c4
1 zhangsan 55 laozhang NULL
2 lisi 44 laoli NULL
3 wangwu 33 laowang wanghua
4 zhaoliu 22 xiaozhao NULL
Time taken: 0.096 seconds, Fetched: 4 row(s)
hive (test)> select id,map_keys(members),size(members) from hive_map;
OK
id _c1 _c2
1 ["father","mother","brother"] 3
2 ["father","mother","brother"] 3
3 ["father","mother","sister"] 3
4 ["father","mother"] 2
Time taken: 0.046 seconds, Fetched: 4 row(s)
hive (test)> select id,name,age,members from hive_map where array_contains(map_keys(members),'brother');
OK
id name age members
1 zhangsan 55 {"father":"laozhang","mother":"xiaohuang","brother":"xiaohu"}
2 lisi 44 {"father":"laoli","mother":"xiaoxu","brother":"xiaoqiang"}
Time taken: 0.054 seconds, Fetched: 2 row(s)
hive (test)> 3.Struct
数据文件 hive_struct.txt
192.168.1.1#zhangsan:40
192.168.1.2#lisi:30
192.168.1.3#wangwu:20创建表并加载数据
hive (test)> create table hive_struct(ip string, userinfo struct)
> row format delimited fields terminated by '#'
> COLLECTION ITEMS TERMINATED BY ':';
OK
Time taken: 0.068 seconds
hive (test)> load data local inpath '/home/hadoop/testdata/hive_struct.txt' into hive_struct;
FAILED: ParseException line 1:68 missing TABLE at 'hive_struct' near ''
hive (test)> load data local inpath '/home/hadoop/testdata/hive_struct.txt' into table hive_struct; 查询数据
Time taken: 0.172 seconds
hive (test)> select * from hive_struct;
OK
hive_struct.ip hive_struct.userinfo
192.168.1.1 {"name":"zhangsan","age":40}
192.168.1.2 {"name":"lisi","age":30}
192.168.1.3 {"name":"wangwu","age":20}
Time taken: 0.044 seconds, Fetched: 3 row(s)
hive (test)> select ip,userinfo.name,userinfo.age from hive_struct;
OK
ip name age
192.168.1.1 zhangsan 40
192.168.1.2 lisi 30
192.168.1.3 wangwu 20
Time taken: 0.032 seconds, Fetched: 3 row(s)