pig使用记录

--如何进入PIG 的local模式

pig -x local

--读出bbb文件内容，并将文件第一列的内容打印在屏幕上

A = load '/home/flankwang/download/bbbb' using PigStorage('|') as (f1:chararray,f2:chararray);

B = foreach A generate f1;--B = foreach A generate $0;这是又一种写法，一样的

dump B;

--记录中包含元组的情况

cat data;
(3,8,9) (4,5,6)
(1,4,7) (3,7,5)
(2,5,8) (9,5,8)

A = load '/home/flankwang/download/data' using PigStorage(' ') AS (t1:tuple(t1a,t1b,t1c),t2:tuple(t2a,t2b,t2c));

B = foreach A generate t1.t1a,t2.t2a;
dump B;

--分组

cat ccc

1 1 2
1 2 3
1 3 4
2 1 5
2 2 4
2 3 6
2 4 9

 A = load '/home/flankwang/download/ccc' using PigStorage(' ') AS (f1:int,f2:int,f3:int);

 B = group A by f1;
dump B;