merged asterix_stabilization r620:1109
git-svn-id: https://asterixdb.googlecode.com/svn/branches/asterix_stabilization_temporal_functionality@1113 eaa15691-b419-025a-1212-ee371bd00084
diff --git a/asterix-app/src/test/resources/runtimets/queries/inverted-index-join/ngram-jaccard-inline.aql b/asterix-app/src/test/resources/runtimets/queries/inverted-index-join/ngram-jaccard-inline.aql
new file mode 100644
index 0000000..cd88072
--- /dev/null
+++ b/asterix-app/src/test/resources/runtimets/queries/inverted-index-join/ngram-jaccard-inline.aql
@@ -0,0 +1,49 @@
+/*
+ * Description : Fuzzy joins two datasets, DBLP and CSX, based on the similarity-jaccard function of their titles' 3-gram tokens.
+ * DBLP has a 3-gram index on title, and we expect the join to be transformed into an indexed nested-loop join.
+ * We test the inlining of variables that enable the select to be pushed into the join for subsequent optimization with an index.
+ * Success : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type DBLPType as closed {
+ id: int32,
+ dblpid: string,
+ title: string,
+ authors: string,
+ misc: string
+}
+
+create type CSXType as closed {
+ id: int32,
+ csxid: string,
+ title: string,
+ authors: string,
+ misc: string
+}
+
+create dataset DBLP(DBLPType) partitioned by key id;
+
+create dataset CSX(CSXType) partitioned by key id;
+
+load dataset DBLP
+using "edu.uci.ics.asterix.external.dataset.adapter.NCFileSystemAdapter"
+(("path"="nc1://data/dblp-small/dblp-small-id.txt"),("format"="delimited-text"),("delimiter"=":")) pre-sorted;
+
+load dataset CSX
+using "edu.uci.ics.asterix.external.dataset.adapter.NCFileSystemAdapter"
+(("path"="nc1://data/pub-small/csx-small-id.txt"),("format"="delimited-text"),("delimiter"=":"));
+
+create index ngram_index on DBLP(title) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-join_ngram-jaccard-inline.adm";
+
+for $a in dataset('DBLP')
+for $b in dataset('CSX')
+let $jacc := similarity-jaccard(gram-tokens($a.title, 3, false), gram-tokens($b.title, 3, false))
+where $jacc >= 0.5f and $a.id < $b.id
+order by $jacc, $a.id, $b.id
+return { "arec": $a, "brec": $b, "jacc": $jacc }
\ No newline at end of file