基本概念

hive> select regexp_replace('Hÿelloä íworlãd','[^a-zA-Z ]','');
OK
Hello world

演示

从整个表中删除不需要的字符并将其导出到文件。

create table t (i int,s1 string,s2 string);
insert into t values (1,'Hÿelloä','íworlãd'),(2,'ãGããood','Byÿe');

select * from t;

+---+---------+---------+
| i | s1      | s2      |
+---+---------+---------+
| 1 | Hÿelloä | íworlãd |
| 2 | ãGããood | Byÿe    |
+---+---------+---------+

create external table t_ext (rec string) 
row format delimited 
fields terminated by '0' 
location '/user/hive/warehouse/t'
;

insert overwrite local directory '/tmp/t_ext'
select  regexp_replace(regexp_replace(rec,'[^a-zA-Z0-9 \\01]',''),'\\x01','<--->') 
from    t_ext
;

! ls /tmp/t_ext
;

000000_0

! cat /tmp/t_ext/000000_0
;

1<--->Hello<--->world
2<--->Good<--->Bye

只要您的表只包含“基本”类型（没有结构、数组、Map等），这种方法就可以工作。
我真的把信封推到这里了。

演示

create table t (i int, dt date, str string, ts timestamp, bl boolean);

insert into t select 1,current_date,'Hello world',current_timestamp,true;

select * from t;

+-----+------------+-------------+-------------------------+------+
| t.i |    t.dt    |    t.str    |          t.ts           | t.bl |
+-----+------------+-------------+-------------------------+------+
|   1 | 2017-03-14 | Hello world | 2017-03-14 14:37:28.889 | true |
+-----+------------+-------------+-------------------------+------+

select  regexp_replace
        (   
            printf(concat('%s',repeat('$$%s',field(unhex(1),*,unhex(1))-2)),*)
           ,'(\\$\\$)|[^a-zA-Z0-9 -]'
           ,'$1'
        )

from    t
;

1$$2017-03-14$$hello world$$2017-03-14 143728.889$$真实