|
A = load 'mobydick.txt';
|
|
B = foreach A generate flatten(TOKENIZE((chararray)$0)) as word;
|
|
C = filter B by word matches '\\w+';
|
|
D = group C by word;
|
|
E = foreach D generate COUNT(C) as count, group as word;
|
|
F = order E by count desc;
|
|
-- one comment
|
|
/* another comment */
|
|
dump F;
|