jwills

#!/usr/bin/python
from org.apache.pig.scripting import *

INIT = Pig.compile("""
A = LOAD 'page_links_en.nt.bz2' using PigStorage(' ') as (url:chararray, p:chararray, link:chararray);
B = GROUP A by url;                                                                                  
C = foreach B generate group as url, 1 as pagerank, A.link as links;                                 
STORE C into '$docs_in';
""")