blob: ef83284153efdcbfd1b42db64e8ac1cf2de01e7a [file] [log] [blame]
register $JAR_PATH
define CountEach datafu.pig.bags.CountEach();
data = LOAD 'input' AS (data: bag {T: tuple(v1:chararray)});
data2 = FOREACH data GENERATE CountEach(data) as counted;
describe data2;
data3 = FOREACH data2 {
ordered = ORDER counted BY count DESC;
GENERATE ordered;
}
describe data3
STORE data3 INTO 'output';