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 CSX(CSXType) | |
primary key id on group1; | |
load dataset CSX | |
using "org.apache.asterix.external.dataset.adapter.NCFileSystemAdapter" | |
(("path"="nc1://data/fuzzyjoin/pub/csx-id.txt"),("format"="delimited-text"),("delimiter"=":")) pre-sorted; | |