Hive中复杂数据类型介绍及使用

hive 复杂数据类型

在Hive中如何使用符合数据结构 maps，array，structs

Array的使用

创建数据库表，以array作为数据类型

create table  person(name string, work_locations array<string> )
ROW FORMAT DELIMITED
FIELDS TERMINATED BY '\t'
COLLECTION ITEMS TERMINATED BY ',';

数据

biansutao beijing,shanghai,tianjin,hangzhou
linan changchu,chengdu,wuhan

入库数据

LOAD DATA LOCAL INPATH '/home/Hadoop/person.txt' OVERWRITE INTO TABLE person;

查询

hive> select * from person;
biansutao    ["beijing","shanghai","tianjin","hangzhou"]
linan  ["changchu","chengdu","wuhan"]
Time taken: 0.355 seconds
 
hive> select name from person;
linan
biansutao
Time taken: 12.397 seconds
 
hive> select work_locations[0] from person;
changchu
beijing
Time taken: 13.214 seconds
 
hive> select work_locations from person;
["changchu","chengdu","wuhan"]
["beijing","shanghai","tianjin","hangzhou"]
Time taken: 13.755 seconds
 
hive> select work_locations[3] from person;
NULL
hangzhou
Time taken: 12.722 seconds
 
hive> select work_locations[4] from person;
NULL
NULL
Time taken: 15.958 seconds

Map的使用

创建数据库表

create table score(
    name string, 
    score map<string,int> 
)
ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t'
COLLECTION ITEMS TERMINATED BY ','
MAP KEYS TERMINATED BY ':';

数据

biansutao ‘数学’:80,‘语文’:89,‘英语’:95
jobs ‘语文’:60,‘数学’:80,‘英语’:99

入库数据

LOAD DATA LOCAL INPATH '/home/hadoop/score.txt' OVERWRITE INTO TABLE score;

查询

hive> select * from score;
biansutao    {"数学":80,"语文":89,"英语":95}
jobs   {"语文":60,"数学":80,"英语":99}
Time taken: 0.665 seconds

hive> select name from score;
jobs
biansutao
Time taken: 19.778 seconds

hive> select t.score from score t;
{"语文":60,"数学":80,"英语":99}
{"数学":80,"语文":89,"英语":95}
Time taken: 19.353 seconds

hive> select t.score['语文'] from score t;
60
89
Time taken: 13.054 seconds

hive> select t.score['英语'] from score t;
99
95
Time taken: 13.769 seconds

Struct的使用

创建数据表

CREATE TABLE test(id int,course struct<course:string,score:int> )
ROW FORMAT DELIMITED
FIELDS TERMINATED BY '\t'
COLLECTION ITEMS TERMINATED BY ',';

数据

1 english,80
2 math,89
3 chinese,95

入库

LOAD DATA LOCAL INPATH '/home/hadoop/test.txt' OVERWRITE INTO TABLE test;

查询

hive> select * from test;
OK
1    {"course":"english","score":80}
2    {"course":"math","score":89}
3    {"course":"chinese","score":95}
Time taken: 0.275 seconds
hive> select course from test;
{"course":"english","score":80}
{"course":"math","score":89}
{"course":"chinese","score":95}
Time taken: 44.968 seconds

select t.course.course from test t; 
english
math
chinese
Time taken: 15.827 seconds

hive> select t.course.score from test t;
80
89
95

4 数据组合（不支持组合的复杂数据类型）

建表语句 -> Map中嵌套ARRAY

create table test1(id int,a MAP<STRING,ARRAY<STRING>>)
row format delimited fields terminated by '\t' 
collection items terminated by ','
MAP KEYS TERMINATED BY ':';

数据

1 english:80,90,70
2 math:89,78,86
3 chinese:99,100,82

加载数据

LOAD DATA LOCAL INPATH '/home/hadoop/test1.txt' OVERWRITE INTO TABLE test1;