SQL++ parser:
1. refactored asterix-aql to become asterix-lang-common and asterix-lang-aql, where the former is the common part for different languages;
2. added asterix-lang-sqlpp on top of asterix-lang-common;
3. ported parser tests, optimizer tests and runtime tests in asterix-app to their sql++ version, and added parser tests for all the queries.
Change-Id: Ie5af4e3b692ca017ec047a1ba3b404a51beb3a2e
Reviewed-on: https://asterix-gerrit.ics.uci.edu/466
Tested-by: Jenkins <jenkins@fulliautomatix.ics.uci.edu>
Reviewed-by: Till Westmann <tillw@apache.org>
diff --git a/asterix-app/src/test/resources/optimizerts/queries_sqlpp/split-materialization-above-join.sqlpp b/asterix-app/src/test/resources/optimizerts/queries_sqlpp/split-materialization-above-join.sqlpp
new file mode 100644
index 0000000..07ccedc
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries_sqlpp/split-materialization-above-join.sqlpp
@@ -0,0 +1,82 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied. See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+
+drop database fuzzyjoin if exists;
+create database fuzzyjoin;
+
+use fuzzyjoin;
+
+
+create type fuzzyjoin.DBLPType as
+{
+ id : int32,
+ dblpid : string,
+ title : string,
+ authors : string,
+ misc : string
+}
+
+create table DBLP(DBLPType) primary key id;
+
+set "import-private-functions" "true";
+
+select element {'left':paperLeft,'right':paperRight,'sim':ridpair.sim}
+from DBLP as paperLeft,
+ DBLP as paperRight,
+ (
+ select element {'idLeft':idLeft,'idRight':idRight,'sim':sim[0]}
+ from DBLP as paperLeft,
+ fuzzyjoin."subset-collection"(tokensLeft,0,fuzzyjoin."prefix-len-jaccard"(lenLeft,0.500000f)) as prefixTokenLeft,
+ DBLP as paperRight,
+ fuzzyjoin."subset-collection"(tokensRight,0,fuzzyjoin."prefix-len-jaccard"(lenRight,0.500000f)) as prefixTokenRight
+ with lenLeft as fuzzyjoin.len(fuzzyjoin."counthashed-word-tokens"(paperLeft.title)),
+ tokensLeft as (
+ select element i
+ from fuzzyjoin."counthashed-word-tokens"(paperLeft.title) as tokenUnranked,
+ (
+ select element tokenGroupped
+ from DBLP as paper,
+ fuzzyjoin."counthashed-word-tokens"(paper.title) as token
+ group by token as tokenGroupped
+ order by fuzzyjoin.count(paper),tokenGroupped
+ ) as tokenRanked at i
+ where (tokenUnranked = tokenRanked)
+ order by i
+ ),
+ lenRight as fuzzyjoin.len(fuzzyjoin."counthashed-word-tokens"(paperRight.title)),
+ tokensRight as (
+ select element i
+ from fuzzyjoin."counthashed-word-tokens"(paperRight.title) as tokenUnranked,
+ (
+ select element tokenGroupped
+ from DBLP as paper,
+ fuzzyjoin."counthashed-word-tokens"(paper.title) as token
+ group by token as tokenGroupped
+ order by fuzzyjoin.count(paper),tokenGroupped
+ ) as tokenRanked at i
+ where (tokenUnranked = tokenRanked)
+ order by i
+ ),
+ sim as fuzzyjoin."similarity-jaccard-prefix"(lenLeft,tokensLeft,lenRight,tokensRight,prefixTokenLeft,0.500000f)
+ where ((prefixTokenLeft = prefixTokenRight) and ((sim >= 0.500000f) and (paperLeft.id < paperRight.id)))
+ group by paperLeft.id as idLeft,paperRight.id as idRight
+) as ridpair
+where ((ridpair.idLeft = paperLeft.id) and (ridpair.idRight = paperRight.id))
+order by paperLeft.id,paperRight.id
+;