blob: f7dcf0eccbf57caf1c66d58cb93e0e7cd53c8298 [file] [log] [blame]
use dataverse fuzzy1;
declare type CSXType as open {
id: int32,
csxid: string,
title: string,
authors: string,
misc: string
}
declare nodegroup group1 on nc1, nc2;
declare dataset CSXSmall(CSXType)
partitioned by key id on group1;
load dataset CSXSmall
using "edu.uci.ics.asterix.external.dataset.adapter.NCFileSystemAdapter"
(("path"="nc1://data/fuzzyjoin/pub-small/csx-small-id.txt"),("format"="delimited-text"),("delimiter"=":")) pre-sorted;