1. 字符串长度函数:length
语法: length(string A)
返回值: int
说明:返回字符串A的长度
举例:
hive> select length('abcedfg') from student;
7
hive> select length(null) from student;
NULL
2. 字符串反转函数:reverse
语法: reverse(string A)
返回值: string
说明:返回字符串A的反转结果
举例:
hive> select reverse('abcedfg') from student;
gfdecba
hive> select reverse('12345') from student;
54321
3. 字符串连接函数:concat
语法: concat(string A, string B…)
返回值: string
说明:返回输入字符串连接后的结果,支持任意个输入字符串
举例:
hive> select concat('a','b','c') from student;
abc
4. 带分隔符字符串连接函数:concat_ws
语法: concat_ws(string SEP, string A, string B…)
返回值: string
说明:返回输入字符串连接后的结果,SEP表示各个字符串间的分隔符
举例:
hive> select concat_ws(',','abc','def','gh') from student;
abc,def,gh
hive> select concat_ws('-','abc','def','gh') from student;
abc-def-gh
5. 字符串截取函数:substr,substring
语法: substr(string A, int start),substring(string A, int start)
返回值: string
说明:返回字符串A从start位置到结尾的字符串
举例:
--从第三个字符截到最后
hive> select substr('abcde',3) from student;
cde
--从第零个字符截到最后
hive> select substr('abcde',0) from student;
abcde
--从第零个字符开始截两个字符
hive> select substr('abcde',0,2) from student;
ab
hive> select substr('abcde',-1) from student; (和ORACLE相同)
e
hive> select substr('abcde',-2) from student;(和ORACLE相同)
de
6. 字符串截取函数:substr,substring
语法: substr(string A, int start, int len),substring(string A, int start, int len)
返回值: string
说明:返回字符串A从start位置开始,长度为len的字符串
举例:
--从第二个字符开始截三个字符
hive> select substr('abcde',2,3) from student;
bcd
hive> select substr('abcde',3,2) from student;
cd
hive> select substring('abcde',3,2) from student;
cd
hive>select substring('abcde',-2,2) from student;
de
7. 字符串转大写函数:upper,ucase
语法: upper(string A) ucase(string A)
返回值: string
说明:返回字符串A的大写格式
举例:
hive> select upper('abSEd') from student;
ABSED
hive> select ucase('abSEd') from student;
ABSED
8. 字符串转小写函数:lower,lcase
语法: lower(string A) lcase(string A)
返回值: string
说明:返回字符串A的小写格式
举例:
hive> select lower('abSEd') from student;
absed
hive> select lcase('abSEd') from student;
absed
9. 去空格函数:trim
语法: trim(string A)
返回值: string
说明:去除字符串两边的空格
举例:
hive> select trim(' abc ') from student;
abc
hive> select trim(' a b c ') from student;
a b c
10. 左边去空格函数:ltrim
语法: ltrim(string A)
返回值: string
说明:去除字符串左边的空格
举例:
hive> select ltrim(' a b c ') from student;
a b c
11. 右边去空格函数:rtrim
语法: rtrim(string A)
返回值: string
说明:去除字符串右边的空格
举例:
hive> select rtrim(' a b c ') from student;
a b c
12. 正则表达式替换函数:regexp_replace
语法: regexp_replace(string A, string B, string C)
返回值: string
说明:将字符串A中的符合java正则表达式B的部分替换为C。注意,在有些情况下要使用转义字符,类似oracle中的regexp_replace函数。
举例:
hive> select regexp_replace('foobar', 'oo|ar', '') from student;
fb
hive> select regexp_replace('123456', '.', '_') from student;
______
hive> select regexp_replace('123456', '1|3|5', '_') from student;
_2_4_6
13. 正则表达式解析函数:regexp_extract
语法: regexp_extract(string subject, string pattern, int index)
返回值: string
说明:将字符串subject按照pattern正则表达式的规则拆分,返回index指定的字符。
举例:
hive> select regexp_extract('foothebar', 'foo(.*?)(bar)', 1) from student;
the
hive> select regexp_extract('foothebar', 'foo(.*?)(bar)', 2) from student;
bar
hive> select regexp_extract('foothebar', 'foo(.*?)(bar)', 0) from student;
Foothebar
hive> select regexp_extract('4.2.3.','\\d.+',0) from student;
4.2.3.
hive> select regexp_extract('4.2.3.','\\d',0) from student;
4
hive> select regexp_extract('4.2.3.','\\d+',0) from student;
4
hive> select regexp_extract('4.2.3.','\\d.\\d.\\d',0) from student;
4.2.3
hive> select regexp_extract('4.2.3.','.\\d.',0) from student;
.2.
--注意,在有些情况下要使用转义字符,下面的等号要用双竖线转义,这是java正则表达式的规则。
select data_field,
regexp_extract(data_field,'.*?bgStart\\=([^&]+)',1) as aaa,
regexp_extract(data_field,'.*?contentLoaded_headStart\\=([^&]+)',1) as bbb,
regexp_extract(data_field,'.*?AppLoad2Req\\=([^&]+)',1) as ccc
from pt_nginx_loginlog_st
where pt = '2012-03-26' limit 2;
14. URL解析函数:parse_url
语法: parse_url(string urlString, string partToExtract [, string keyToExtract])
返回值: string
说明:返回URL中指定的部分。 的有效值为:HOST, PATH, QUERY, REF, PROTOCOL, AUTHORITY, FILE, and USERINFO.
举例:
hive> select parse_url('https://facebook.com/path1/p.php?k1=v1&k2=v2#Ref1', 'HOST') from student;
facebook.com
hive> select parse_url('https://facebook.com/path1/p.php?k1=v1&k2=v2#Ref1', 'QUERY', 'k1') from student;
v1
hive> select parse_url('https://facebook.com/path1/p.php?k1=v1&k2=v2#Ref1', 'PATH') from student;
/path1/p.php
hive> select parse_url('https://facebook.com/path1/p.php?k1=v1&k2=v2#Ref1', 'QUERY') from student;
k1=v1&k2=v2
hive> select parse_url('https://facebook.com/path1/p.php?k1=v1&k2=v2#Ref1', 'REF') from student;
Ref1
hive> select parse_url('https://facebook.com/path1/p.php?k1=v1&k2=v2#Ref1', 'PROTOCOL') from student;
http
hive> select parse_url('https://facebook.com/path1/p.php?k1=v1&k2=v2#Ref1', 'AUTHORITY') from student;
facebook.com
hive> select parse_url('https://facebook.com/path1/p.php?k1=v1&k2=v2#Ref1', 'FILE') from student;
/path1/p.php?k1=v1&k2=v2
hive> select parse_url('https://facebook.com/path1/p.php?k1=v1&k2=v2#Ref1', 'USERINFO') from student;
NULL
15. json解析函数:get_json_object
语法: get_json_object(string json_string, string path)
返回值: string
说明:解析json的字符串json_string,返回path指定的内容。如果输入的json字符串无效,那么返回NULL。
举例:
{
"store": {
"fruit": \[
{
"weight": 8,
"type": "apple"
},
{
"weight": 9,
"type": "pear"
}
],
"bicycle": {
"price": 19.95,
"color": "red"
}
},
"email": "amy@only_for_json_udf_test.net",
"owner": "amy"
}
--获取最顶层的标签
hive> select get_json_object('{"store":{"fruit":\[{"weight":8,"type":"apple"},{"weight":9,"type":"pear"}],"bicycle":{"price":19.95,"color":"red"}},"email":"amy@only_for_json_udf_test.net", "owner":"amy"}','$.owner') from student;
Amy
--获取最顶层的标签
hive> select get_json_object('{"store":{"fruit":\[{"weight":8,"type":"apple"},{"weight":9,"type":"pear"}],"bicycle":{"price":19.95,"color":"red"}},"email":"amy@only_for_json_udf_test.net", "owner":"amy"}','$.store') from student;
{"fruit":[{"weight":8,"type":"apple"},{"weight":9,"type":"pear"}],"bicycle":{"price":19.95,"color":"red"}}
--获得二层标签
hive> select get_json_object('{"store":{"fruit":\[{"weight":8,"type":"apple"},{"weight":9,"type":"pear"}],"bicycle":{"price":19.95,"color":"red"}},"email":"amy@only_for_json_udf_test.net", "owner":"amy"}','$.store.fruit') from student;
[{"weight":8,"type":"apple"},{"weight":9,"type":"pear"}]
--获得三层标签
hive> select get_json_object('{"store":{"fruit":\[{"weight":8,"type":"apple"},{"weight":9,"type":"pear"}],"bicycle":{"price":19.95,"color":"red"}},"email":"amy@only_for_json_udf_test.net", "owner":"amy"}','$.store.fruit.type') from student;
["apple","pear"]
--跨层获取标签(不通过一层获取二层)
hive> select get_json_object('{"store":{"fruit":\[{"weight":8,"type":"apple"},{"weight":9,"type":"pear"}],"bicycle":{"price":19.95,"color":"red"}},"email":"amy@only_for_json_udf_test.net", "owner":"amy"}','$.bicyle.price') from student;
NULL
--获取最底层标签
hive> select get_json_object('{"store":{"fruit":\[{"weight":8,"type":"apple"},{"weight":9,"type":"pear"}],"bicycle":{"price":19.95,"color":"red"}},"email":"amy@only_for_json_udf_test.net", "owner":"amy"}','$.store.bicycle.price') from student;
19.95
16. 空格字符串函数:space
语法: space(int n)
返回值: string
说明:返回长度为n的字符串
举例:
hive> select space(10) from student;
(10个空格)
hive> select length(space(10)) from student;
10
17. 重复字符串函数:repeat
语法: repeat(string str, int n)
返回值: string
说明:返回重复n次后的str字符串
举例:
hive> select repeat('abc|',5) from student;
abc|abc|abc|abc|abc|
18. 首字符ascii函数:ascii
语法: ascii(string str)
返回值: int
说明:返回字符串str第一个字符的ascii码
举例:
hive> select ascii('abcde') from student;
97
19. 左补足函数:lpad
语法: lpad(string str, int len, string pad)
返回值: string
说明:将str进行用pad进行左补足到len位
举例:
hive> select lpad('abc',10,'td') from student;
tdtdtdtabc
--注意:与GP,ORACLE不同,pad 不能默认
hive> select lpad('abc',4,'td') from student;
tabc
20. 右补足函数:rpad
语法: rpad(string str, int len, string pad)
返回值: string
说明:将str进行用pad进行右补足到len位
举例:
hive> select rpad('abc',10,'td') from student;
abctdtdtdt
21. 分割字符串函数: split
语法: split(string str, string pat)
返回值: array
说明: 按照pat字符串分割str,会返回分割后的字符串数组
举例:
hive> select split('abt,cdt,ef',',') from student;
["abt","cdt","ef"]
22. 集合查找函数: find_in_set
语法: find_in_set(string str, string strList)
返回值: int
说明: 返回str在strlist第一次出现的位置,strlist是用逗号分割的字符串。如果没有找该str字符,则返回0
举例:
hive> select find_in_set('ab','ef,ab,de') from student;
2
hive> select find_in_set('at','ef,ab,de') from student;
0
23.查找字符串在某个字符串当中的开始位置 instr
语法:instr(string str string str2);
返回值: int
说明:返回 str2在str 中的开始位置,两个参数有一个为null则返回null
hive> select instr("abcd" "ab");
0