lead

lag

FIRST_VALUE

LAST_VALUE

RANK

ROW_NUMBER

DENSE_RANK

CUME_DIST

PERCENT_RANK

NTILE

java_method(class,method [,arg1 [,arg2])reflect(class,method [,arg1 [,arg2..]])hash(a1 [,a2...])

lateralView: LATERAL VIEW udtf(expression) tableAlias AS columnAlias (‘,‘ columnAlias)*  fromClause: FROM baseTable (lateralView)*  

create table employee(

id string,

money double,

type string)row format delimited 

fields terminated by ‘\t‘ 

lines terminated by ‘\n‘ 

stored as textfile;

load data local inpath '/home/tuzq/software/hivedata/employee.txt' into table employee;

优先级依次为NOT AND OR

select cast(1.5 as int);

if(con,‘‘,‘‘);

hive (default)> select if(2>1,‘YES‘,‘NO‘);

YES

case when con then ‘‘ when con then ‘‘ else  ‘‘ end (‘‘里面类型要一样)

get_json_object(json 解析函数，用来处理json，必须是json格式)select get_json_object(‘{"name":"jack","age":"20"}‘,‘$.name‘);

parse_url(string urlString, string partToExtract [, string keyToExtract])

select parse_url(‘http://facebook.com/path1/p.php?k1=v1&k2=v2#Ref1‘, ‘HOST‘) from

employee limit 1;

hive> select concat(‘abc‘,‘def’,‘gh‘) from lxw_dual;

abcdefgh

concat_ws(string SEP, array<string>)

举例：

hive> select concat_ws(‘,‘,‘abc‘,‘def‘,‘gh‘) from lxw_dual;

abc,def,gh

列出该字段所有不重复的值，相当于去重

collect_set(id)  //返回的是数组

列出该字段所有的值，列出来不去重 

collect_list(id)   //返回的是数组

select collect_set(id) from taborder;

求和

sum(money)

统计列数

count(*)

select sum(num),count(*) from taborder;

first_value(第一行值)

first_value(money) over (partition by id order by money)

select ch,num,first_value(num) over (partition by ch order by num) from taborder;

rows between 1 preceding and 1 following (当前行以及当前行的前一行与后一行)

hive (liguodong)> select ch,num,first_value(num) over (partition by ch order by num ROWS BETWEEN 2 PRECEDING AND CURRENT ROW) from taborder;

last_value 最后一行值

hive (liguodong)> select ch,num,last_value(num) over (partition by ch) from taborder;

 lead

 去当前行后面的第二行的值

 lead(money,2) over (order by money)

 lag 

 去当前行前面的第二行的值

 lag(money,2) over (order by money)

 ```

 ```

 select ch, num, lead(num,2) over (order by num) from taborder;

 select ch, num, lag(num,2) over (order by num) from taborder;

rank() over(partition by id order by money)

select ch, num, rank() over(partition by ch order by num) as rank from taborder;

select ch, num, dense_rank() over(partition by ch order by num) as dense_rank from taborder;

cume_dist (相同值的最大行号/行数)

cume_dist() over (partition by id order by money)

percent_rank (相同值的最小行号-1)/(行数-1)

第一个总是从0开始

percent_rank() over (partition by id order by money)

 select ch,num,cume_dist() over (partition by ch order by num) as cume_dist,

 percent_rank() over (partition by ch order by num) as percent_rank

 from taborder;

 ntile分片 

 ntile(2) over (order by money desc)  分两份 

 select ch,num,ntile(2) over (order by num desc) from taborder;

select id,java_method("java.lang,Math","sqrt",cast(id as double)) as sqrt from hiveTest;

 select id,adid 

 from employee 

 lateral view explode(split(type,‘B‘)) tt as adid;

 explode 把一列转成多行

hive (liguodong)>  select id,adid

                >  from hiveDemo

                >  lateral view explode(split(str,‘,‘)) tt as adid;

hive> select regexp_replace(‘foobar‘, ‘oo|ar‘, ‘‘) from lxw_dual;

fb

hive> select regexp_replace(‘979|7.10.80|8684‘, ‘.*\\|(.*)‘,1) from hiveDemo limit 1;

hive> select regexp_replace(‘979|7.10.80|8684‘, ‘(.*?)\\|(.*)‘,1) from hiveDemo limit 1;