use dataverse fuzzy1; | |
declare type DBLPType as open { | |
id: int32, | |
dblpid: string, | |
title: string, | |
authors: string, | |
misc: string | |
} | |
declare nodegroup group1 on rainbow-01, rainbow-02, rainbow-03, | |
rainbow-04, rainbow-05; | |
declare dataset DBLP(DBLPType) | |
partitioned by key id on group1; | |
write output to rainbow-01:"/home/hyracks/out.txt"; | |
for $x in dataset('DBLP') | |
let $ed := edit-distance($x.authors, "Michael Carey") | |
where $ed <= 3 | |
order by $ed, $x.authors | |
return { "edit-distance":$ed, "authors":$x.authors, "title":$x.title } |