blob: 7598987886ff6cca9755912a78d417680bc02ce3 [file] [log] [blame]
drop dataverse fuzzyjoin if exists;
create dataverse fuzzyjoin;
use dataverse fuzzyjoin;
create type UserType as open {
uid: int32,
name: string,
lottery_numbers: [int32],
interests: {{string}}
}
create dataset Users(UserType) partitioned by key uid;
load dataset Users
using "edu.uci.ics.asterix.external.dataset.adapter.NCFileSystemAdapter"
(("path"="nc1://data/users-visitors-small/users.json"),("format"="adm"));
write output to nc1:'rttest/fuzzyjoin_user-int-aqlplus_1.adm';
set simthreshold '.5f';
for $user in dataset('Users')
for $user2 in dataset('Users')
where $user.interests ~= $user2.interests and $user.uid < $user2.uid
order by $user.uid, $user2.uid
return { 'user': $user, 'user2': $user2 }