blob: 2898058d5b6b1dbab15a63dab610bdf2ec0a3c45 [file] [log] [blame]
drop dataverse fj-dblp-csx if exists;
create dataverse fj-dblp-csx;
use dataverse fj-dblp-csx;
create type DBLPType as open {
id: int32,
dblpid: string,
title: string,
authors: string,
misc: string
}
create type CSXType as open {
id: int32,
csxid: 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;
create dataset CSX(CSXType) partitioned by key id on group1;
write output to nc1:'rttest/fj-dblp-csx.adm';
for $paperDBLP in dataset('DBLP')
let $idDBLP := $paperDBLP.id
let $unrankedTokensDBLP := counthashed-word-tokens($paperDBLP.title)
let $tokensDBLP :=
for $token in $unrankedTokensDBLP
for $tokenRanked at $i in
//
// -- - Stage 1 - --
//
// for $paper in dataset('DBLP')
// for $token in counthashed-word-tokens($paper.title)
// group by $tokenGroupped := $token with $paper
// order by count($paper), $tokenGroupped
// return $tokenGroupped
for $paper in dataset('DBLP')
return $paper.title
where $token = $tokenRanked
order by $i
return $i
for $prefixTokenDBLP in $tokensDBLP
for $paperCSX in dataset('CSX')
let $idCSX := $paperCSX.id
let $unrankedTokensCSX := counthashed-word-tokens($paperCSX.title)
let $tokensCSX :=
for $token in $unrankedTokensCSX
for $tokenRanked at $i in
//
// -- - Stage 1 - --
//
// for $paper in dataset('DBLP')
// for $token in counthashed-word-tokens($paper.title)
// group by $tokenGroupped := $token with $paper
// order by count($paper), $tokenGroupped
// return $tokenGroupped
for $paper in dataset('DBLP')
return $paper.title
where $token = $tokenRanked
order by $i
return $i
for $prefixTokenCSX in $tokensCSX
where $prefixTokenDBLP = $prefixTokenCSX
group by $idDBLP := $idDBLP, $idCSX := $idCSX with $paperDBLP
order by $idDBLP, $idCSX
return {'idDBLP': $idDBLP, 'idCSX': $idCSX}