blob: 60773891ce3c2e2b19dc8cc8f8259d8ff406286c [file] [log] [blame]
drop dataverse test if exists;
create dataverse test;
use dataverse test;
create type DBLPType as closed {
id: int32,
dblpid: string,
title: string,
authors: string,
misc: string
}
create nodegroup group1 if not exists on nc1, nc2;
create dataset DBLP(DBLPType)
partitioned by key id on group1;
load dataset DBLP
using "edu.uci.ics.asterix.external.dataset.adapter.NCFileSystemAdapter"
(("path"="nc1://data/dblp-small/dblp-small-id.txt"),("format"="delimited-text"),("delimiter"=":")) pre-sorted;
create index ngram_index on DBLP(authors) type fuzzy ngram(3);
write output to nc1:"rttest/index-selection_fuzzy-inverted-index-ngram-edit-distance.adm";
for $o in dataset('DBLP')
let $ed := edit-distance-check($o.authors, "Amihay Motro", 1)
where $ed[0]
return $o