原文地址：http://my.oschina.net/leejun2005/blog/120463
一、map、struct、array 这3种的用法：1、Array的使用
2、Map 的使用
3、Struct 的使用
4、数据组合 （不支持组合的复杂数据类型）
二、hive中的一些不常见函数的用法：
1、array_contains （Collection Functions）
2、get_json_object （Misc. Functions）
3、parse_url_tuple
三、ref：
目前 hive 支持的复合数据类型有以下几种：
map
(key1, value1, key2, value2, ...) Creates a map with the given key/value pairs
struct
(val1, val2, val3, ...) Creates a struct with the given field values. Struct field names will be col1, col2, ...
named_struct
(name1, val1, name2, val2, ...) Creates a struct with the given field names and values. (as of Hive 0.8.0)
array
(val1, val2, ...) Creates an array with the given elements
create_union
(tag, val1, val2, ...) Creates a union type with the value that is being pointed to by the tag parameter
一、map、struct、array 这3种的用法：
1、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
2、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 ':';
要入库的数据
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
3、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
Time taken: 13.235 seconds<span style="font-family:微软雅黑, Verdana, sans-serif, 宋体;font-size:12.5px;line-height:1.5;"> </span>
4、数据组合 （不支持组合的复杂数据类型）
LOAD DATA LOCAL INPATH '/home/hadoop/test.txt' OVERWRITE INTO TABLE test;
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 ':';
1 english:80,90,70
2 math:89,78,86
3 chinese:99,100,82
LOAD DATA LOCAL INPATH '/home/hadoop/test1.txt' OVERWRITE INTO TABLE test1;
二、hive中的一些不常见函数的用法：
常见的函数就不废话了，和标准sql类似，下面我们要聊到的基本是HQL里面专有的函数，
hive里面的函数大致分为如下几种：Built-in、Misc.、UDF、UDTF、UDAF
我们就挑几个标准SQL里没有，但是在HIVE SQL在做统计分析常用到的来说吧。
1、array_contains （Collection Functions）
这是内置的对集合进行操作的函数，用法举例：
create EXTERNAL table IF NOT EXISTS userInfo (id int,sex string, age int, name string, email string,sd string, ed string) ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' location '/hive/dw';
select * from userinfo where sex='male' and (id!=1 and id !=2 and id!=3 and id!=4 and id!=5) and age < 30;
select * from (select * from userinfo where sex='male' and !array_contains(split('1,2,3,4,5',','),cast(id as string))) tb1 where tb1.age < 30;
其中建表所用的测试数据你可以用如下链接的脚本自动生成：
http://my.oschina.net/leejun2005/blog/76631
2、get_json_object （Misc. Functions）
测试数据：
first {"store":{"fruit":[{"weight":8,"type":"apple"},{"weight":9,"type":"pear"}],"bicycle":{"price":19.951,"color":"red1"}},"email":"amy@only_for_json_udf_test.net","owner":"amy1"} third
first {"store":{"fruit":[{"weight":9,"type":"apple"},{"weight":91,"type":"pear"}],"bicycle":{"price":19.952,"color":"red2"}},"email":"amy@only_for_json_udf_test.net","owner":"amy2"} third
first {"store":{"fruit":[{"weight":10,"type":"apple"},{"weight":911,"type":"pear"}],"bicycle":{"price":19.953,"color":"red3"}},"email":"amy@only_for_json_udf_test.net","owner":"amy3"} third
create external table if not exists t_json(f1 string, f2 string, f3 string) row format delimited fields TERMINATED BY ' ' location '/test/json'
select get_json_object(t_json.f2, '$.owner') from t_json;
SELECT * from t_json where get_json_object(t_json.f2, '$.store.fruit[0].weight') = 9;
SELECT get_json_object(t_json.f2, '$.non_exist_key') FROM t_json;
这里尤其要注意UDTF的问题，官方文档有说明：
json_tuple
A new json_tuple() UDTF is introduced in hive 0.7. It takes a set of names (keys) and a JSON string, and returns a tuple of values using one function. This is much more efficient than calling GET_JSON_OBJECT to retrieve more than one key from a single JSON string. In any case where a single JSON string would be parsed more than once, your query will be more efficient if you parse it once, which is what JSON_TUPLE is for. As JSON_TUPLE is a UDTF, you will need to use the LATERAL VIEW syntax in order to achieve the same goal.
For example,
select a.timestamp, get_json_object(a.appevents, '$.eventid'), get_json_object(a.appenvets, '$.eventname') from log a;
should be changed to
select a.timestamp, b.*
from log a lateral view json_tuple(a.appevent, 'eventid', 'eventname') b as f1, f2;
UDTF(User-Defined Table-Generating Functions) 用来解决 输入一行输出多行(On-to-many maping) 的需求。
通过Lateral view可以方便的将UDTF得到的行转列的结果集合在一起提供服务，因为直接在SELECT使用UDTF会存在限制，即仅仅能包含单个字段，不光是多个UDTF，仅仅单个UDTF加上其他字段也是不可以，hive提示在UDTF中仅仅能有单一的表达式。如下：
hive> select my_test(“abcef:aa”) as qq,’abcd’ from sunwg01;
FAILED: Error in semantic analysis: Only a single expression in the SELECT clause is supported with UDTF’s
使用Lateral view可以实现上面的需求，Lateral view语法如下：
lateralView: LATERAL VIEW udtf(expression) tableAlias AS columnAlias (‘,’ columnAlias)*
fromClause: FROM baseTable (lateralView)*
hive> create table sunwg ( a array, b array )
> ROW FORMAT DELIMITED
> FIELDS TERMINATED BY ‘\t’
> COLLECTION ITEMS TERMINATED BY ‘,’;
OK
Time taken: 1.145 seconds
hive> load data local inpath ‘/home/hjl/sunwg/sunwg.txt’ overwrite into table sunwg;
Copying data from file:/home/hjl/sunwg/sunwg.txt
Loading data to table sunwg
OK
Time taken: 0.162 seconds
hive> select * from sunwg;
OK
[10,11] ["tom","mary"]
[20,21] ["kate","tim"]
Time taken: 0.069 seconds
hive>
> SELECT a, name
> FROM sunwg LATERAL VIEW explode(b) r1 AS name;
OK
[10,11] tom
[10,11] mary
[20,21] kate
[20,21] tim
Time taken: 8.497 seconds
hive> SELECT id, name
> FROM sunwg LATERAL VIEW explode(a) r1 AS id
> LATERAL VIEW explode(b) r2 AS name;
OK
10 tom
10 mary
11 tom
11 mary
20 kate
20 tim
21 kate
21 tim
Time taken: 9.687 seconds
3、parse_url_tuple
测试数据：
url1 http://facebook.com/path1/p.php?k1=v1&k2=v2#Ref1
url2 https://cwiki.apache.org/confluence/display/Hive/LanguageManual+UDF#LanguageManualUDF-getjsonobject
url3 https://www.google.com.hk/#hl=zh-CN&newwindow=1&safe=strict&q=hive+translate+example&oq=hive+translate+example&gs_l=serp.3...10174.11861.6.12051.8.8.0.0.0.0.132.883.0j7.7.0...0.0...1c.1j4.8.serp.0B9C1T_n0Hs&bav=on.2,or.&bvm=bv.44770516,d.aGc&fp=e13e41a6b9dab3f6&biw=1241&bih=589
create external table if not exists t_url(f1 string, f2 string) row format delimited fields TERMINATED BY ' ' location '/test/url';
SELECT f1, b.* FROM t_url LATERAL VIEW parse_url_tuple(f2, 'HOST', 'PATH', 'QUERY', 'QUERY:k1') b as host, path, query, query_id;
结果：
url1 facebook.com /path1/p.php k1=v1&k2=v2 v1
url2 cwiki.apache.org /confluence/display/Hive/LanguageManual+UDF NULL NULL
url3 www.google.com.hk / NULL NULL
三、ref：
http://blog.csdn.net/wf1982/article/details/7474601
http://www.cnblogs.com/ggjucheng/archive/2013/01/08/2850797.html
http://www.oratea.net/?p=650
https://cwiki.apache.org/confluence/display/Hive/LanguageManual+UDF#LanguageManualUDF-parseurltuple
https://cwiki.apache.org/confluence/display/Hive/Tutorial
http://blog.csdn.net/inte_sleeper/article/details/7196114 hive lateral view语句：列拆分成行
1693
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
