blob: fc899bcf77f1ade28a4f0ad74b8090983ac678f4 [file] [log] [blame]
Yingyi Bu391f09e2015-10-29 13:49:39 -07001/*
2 * Licensed to the Apache Software Foundation (ASF) under one
3 * or more contributor license agreements. See the NOTICE file
4 * distributed with this work for additional information
5 * regarding copyright ownership. The ASF licenses this file
6 * to you under the Apache License, Version 2.0 (the
7 * "License"); you may not use this file except in compliance
8 * with the License. You may obtain a copy of the License at
9 *
10 * http://www.apache.org/licenses/LICENSE-2.0
11 *
12 * Unless required by applicable law or agreed to in writing,
13 * software distributed under the License is distributed on an
14 * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
15 * KIND, either express or implied. See the License for the
16 * specific language governing permissions and limitations
17 * under the License.
18 */
19
20drop database "fj-dblp-csx" if exists;
21create database "fj-dblp-csx";
22
23use "fj-dblp-csx";
24
25
26create type "fj-dblp-csx".DBLPType as
27{
28 id : int32,
29 dblpid : string,
30 title : string,
31 authors : string,
32 misc : string
33}
34
35create type "fj-dblp-csx".CSXType as
36{
37 id : int32,
38 csxid : string,
39 title : string,
40 authors : string,
41 misc : string
42}
43
44create nodegroup group1 if not exists on
45 nc1,
46 nc2
47;
48create table DBLP(DBLPType) primary key id on group1;
49
50create table CSX(CSXType) primary key id on group1;
51
52write output to nc1:"rttest/fj-dblp-csx.adm"
53select element {'idDBLP':idDBLP,'idCSX':idCSX}
54from DBLP as paperDBLP,
55 tokensDBLP as prefixTokenDBLP,
56 CSX as paperCSX,
57 tokensCSX as prefixTokenCSX
58with idDBLP as paperDBLP.id,
59 unrankedTokensDBLP as "fj-dblp-csx"."counthashed-word-tokens"(paperDBLP.title),
60 tokensDBLP as (
61 select element i
62 from unrankedTokensDBLP as token,
63 (
64 select element paper.title
65 from DBLP as paper
66 ) as tokenRanked at i
67 where (token = tokenRanked)
68 order by i
69 ),
70 idCSX as paperCSX.id,
71 unrankedTokensCSX as "fj-dblp-csx"."counthashed-word-tokens"(paperCSX.title),
72 tokensCSX as (
73 select element i
74 from unrankedTokensCSX as token,
75 (
76 select element paper.title
77 from DBLP as paper
78 ) as tokenRanked at i
79 where (token = tokenRanked)
80 order by i
81 )
82where (prefixTokenDBLP = prefixTokenCSX)
83group by idDBLP as idDBLP,idCSX as idCSX
84order by idDBLP,idCSX
85;