Merged asterix_lsm_stabilization upto r1547 git-svn-id: https://asterixdb.googlecode.com/svn/trunk/asterix@1622 eaa15691-b419-025a-1212-ee371bd00084

commit: 5ee049d45ea3aa9e6317cd59063e2e0b4f2d4d4c [log] [tgz]
author: vinayakb <vinayakb@eaa15691-b419-025a-1212-ee371bd00084> Sat Apr 06 21:21:29 2013 +0000
committer: vinayakb <vinayakb@eaa15691-b419-025a-1212-ee371bd00084> Sat Apr 06 21:21:29 2013 +0000
tree: 8f8ff948c7f4786d5950fdbc75c56fa5027f2e97
parent: a13f242d1b42dd3e21079c5ace934ae20ecae218 [diff]
diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-equi-join-multipred.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-equi-join-multipred.aql
new file mode 100644
index 0000000..f235220
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-equi-join-multipred.aql

@@ -0,0 +1,48 @@
+/*
+ * Description    : Equi joins two datasets, Customers and Orders, based on the customer id.
+ *                  Given the 'indexnl' hint we expect the join to be transformed
+ *                  into an indexed nested-loop join using Customers' primary index.
+ *                  We expect the additional predicates to be put into a select above the 
+ *                  primary index search.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  lastorder: {
+    oid: int32,
+    total: float
+  }
+}
+
+create type OrderType as closed {
+  oid: int32,
+  cid: int32,
+  orderstatus: string,
+  orderpriority: string,
+  clerk: string,
+  total: float
+}
+
+create dataset Customers(CustomerType) primary key cid;
+create dataset Orders(OrderType) primary key oid;
+
+write output to nc1:"rttest/btree-index-join_primary-equi-join-multipred.adm";
+
+for $c in dataset('Customers')
+for $o in dataset('Orders')
+where $c.cid /*+ indexnl */ = $o.cid and $c.name < $o.orderstatus and $c.age < $o.cid
+return {"customer":$c, "order": $o} 

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-equi-join-neg_01.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-equi-join-neg_01.aql
new file mode 100644
index 0000000..8e8324f
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-equi-join-neg_01.aql

@@ -0,0 +1,29 @@
+/*
+ * Description  : This is a negative test, mis-spelt/incorrect HINT should result in
+ *                a plan not using an indexed-nested loops join strategy. We expect a hash join. 
+ * Expected Res : Success
+ * Date         : 29th November 2012
+ */
+
+drop dataverse test1 if exists;
+create dataverse test1;
+
+create type test1.TestType as open {
+          key1: int32,
+          key2: int32,
+          fname : string,
+          lname : string
+}
+
+create dataset test1.DsOne(TestType) primary key key1;
+create dataset test1.DsTwo(TestType) primary key key1;
+
+// Please note content enclosed in the comment in the predicate is the HINT to the optimizer
+
+write output to nc1:"rttest/btree-index-join_primary-equi-join-neg_01.adm";
+
+for $x in dataset('test1.DsOne')
+for $y in dataset('test1.DsTwo')
+where $x.key1 /*+ index */ = $y.key2
+return $x
+

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-equi-join-neg_02.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-equi-join-neg_02.aql
new file mode 100644
index 0000000..8a62332
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-equi-join-neg_02.aql

@@ -0,0 +1,29 @@
+/*
+ * Description  : This is a negative test, mis-spelt/incorrect HINT should result in
+ *                a plan not using an indexed-nested loops join strategy. We expect a hash join. 
+ * Expected Res : Success
+ * Date         : 29th November 2012
+ */
+
+drop dataverse test1 if exists;
+create dataverse test1;
+
+create type test1.TestType as open {
+          key1: int32,
+          key2: int32,
+          fname : string,
+          lname : string
+}
+
+create dataset test1.DsOne(TestType) primary key key1;
+create dataset test1.DsTwo(TestType) primary key key1;
+
+// Please note content enclosed in the comment in the predicate is the HINT to the optimizer
+
+write output to nc1:"rttest/btree-index-join_primary-equi-join-neg_02.adm";
+
+for $x in dataset('test1.DsOne')
+for $y in dataset('test1.DsTwo')
+where $x.key2 /*+ index */ = $y.key1
+return $x
+

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-equi-join_01.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-equi-join_01.aql
new file mode 100644
index 0000000..6950747
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-equi-join_01.aql

@@ -0,0 +1,29 @@
+/*
+ * Description  : Notice the query hint to use an indexed nested-loops join plan.
+ *              : We expect a plan that hash-exchanges internal dataset DsTwo, then probes internal dataset DsOne’s primary index.
+ * Expected Res : Success
+ * Date         : 29th November 2012
+ */
+
+drop dataverse test1 if exists;
+create dataverse test1;
+
+create type test1.TestType as open {
+          key1: int32,
+          key2: int32,
+          fname : string,
+          lname : string
+}
+
+create dataset test1.DsOne(TestType) primary key key1;
+create dataset test1.DsTwo(TestType) primary key key1;
+
+// Please note content enclosed in the comment in the predicate is a HINT to the optimizer
+
+write output to nc1:"rttest/btree-index-join_primary-equi-join_01.adm";
+
+for $x in dataset('test1.DsOne')
+for $y in dataset('test1.DsTwo')
+where $x.key1 /*+ indexnl */ = $y.key2
+return $x
+

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-equi-join_02.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-equi-join_02.aql
new file mode 100644
index 0000000..b7832fd
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-equi-join_02.aql

@@ -0,0 +1,29 @@
+/*
+ * Description  : Notice the query hint to use an indexed nested-loops join plan. 
+ *              : We expect a plan that hash-exchanges internal dataset DsTwo, then probes internal dataset DsOne’s primary index. 
+ * Expected Res : Success
+ * Date         : 29th November 2012
+ */
+
+drop dataverse test1 if exists;
+create dataverse test1;
+
+create type test1.TestType as open {
+          key1: int32,
+          key2: int32,
+          fname : string,
+          lname : string
+}
+
+create dataset test1.DsOne(TestType) primary key key1;
+create dataset test1.DsTwo(TestType) primary key key1;
+
+// Please note content enclosed in the comment in the predicate is a HINT to the optimizer
+
+write output to nc1:"rttest/btree-index-join_primary-equi-join_02.adm";
+
+for $x in dataset('test1.DsOne')
+for $y in dataset('test1.DsTwo')
+where $x.key2 /*+ indexnl */ = $y.key1
+return $x
+

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-equi-join_03.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-equi-join_03.aql
new file mode 100644
index 0000000..9268c2c
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-equi-join_03.aql

@@ -0,0 +1,46 @@
+/*
+ * Description    : Equi joins two datasets, Customers and Orders, based on the customer id.
+ *                  Given the 'indexnl' hint we expect the join to be transformed
+ *                  into an indexed nested-loop join using Customers' primary index.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  lastorder: {
+    oid: int32,
+    total: float
+  }
+}
+
+create type OrderType as closed {
+  oid: int32,
+  cid: int32,
+  orderstatus: string,
+  orderpriority: string,
+  clerk: string,
+  total: float
+}
+
+create dataset Customers(CustomerType) primary key cid;
+create dataset Orders(OrderType) primary key oid;
+
+write output to nc1:"rttest/btree-index-join_primary-equi-join_04.adm";
+
+for $c in dataset('Customers')
+for $o in dataset('Orders')
+where $c.cid /*+ indexnl */ = $o.cid
+return {"customer":$c, "order": $o} 

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-equi-join_04.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-equi-join_04.aql
new file mode 100644
index 0000000..3c07154
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-equi-join_04.aql

@@ -0,0 +1,46 @@
+/*
+ * Description    : Equi joins two datasets, Customers and Orders, based on the customer id.
+ *                  Given the 'indexnl' hint we expect the join to be transformed
+ *                  into an indexed nested-loop join using Customers' primary index.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  lastorder: {
+    oid: int32,
+    total: float
+  }
+}
+
+create type OrderType as closed {
+  oid: int32,
+  cid: int32,
+  orderstatus: string,
+  orderpriority: string,
+  clerk: string,
+  total: float
+}
+
+create dataset Customers(CustomerType) primary key cid;
+create dataset Orders(OrderType) primary key oid;
+
+write output to nc1:"rttest/btree-index-join_primary-equi-join_05.adm";
+
+for $o in dataset('Orders')
+for $c in dataset('Customers')
+where $o.cid /*+ indexnl */ = $c.cid 
+return {"customer":$c, "order": $o} 

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-equi-join_05.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-equi-join_05.aql
new file mode 100644
index 0000000..7da6b0c
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-equi-join_05.aql

@@ -0,0 +1,36 @@
+/*
+ * Description    : Self-equi joins a dataset, Customers, based on the customer id.
+ *                  Given the 'indexnl' hint we expect the join to be transformed
+ *                  into an indexed nested-loop join using Customers' primary index.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  lastorder: {
+    oid: int32,
+    total: float
+  }
+}
+
+create dataset Customers(CustomerType) primary key cid;
+
+write output to nc1:"rttest/btree-index-join_primary-equi-join_06.adm";
+
+for $c1 in dataset('Customers')
+for $c2 in dataset('Customers')
+where $c1.cid /*+ indexnl */ = $c2.cid 
+return {"customer1":$c1, "customer2":$c2} 

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-ge-join_01.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-ge-join_01.aql
new file mode 100644
index 0000000..8bc306c
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-ge-join_01.aql

@@ -0,0 +1,29 @@
+/*
+ * Description  : Notice the query hint to use an indexed nested-loops join plan. 
+ *              : We expect a plan that broadcasts internal dataset DsTwo, then probes internal dataset DsOne’s primary index. 
+ * Expected Res : Success
+ * Date         : 29th November 2012
+ */
+
+drop dataverse test1 if exists;
+create dataverse test1;
+
+create type test1.TestType as open {
+          key1: int32,
+          key2: int32,
+          fname : string,
+          lname : string
+}
+
+create dataset test1.DsOne(TestType) primary key key1;
+create dataset test1.DsTwo(TestType) primary key key1;
+
+// Please note content enclosed in the comment in the predicate is the HINT to the optimizer
+
+write output to nc1:"rttest/btree-index-join_primary-ge-join_01.adm";
+
+for $x in dataset('test1.DsOne')
+for $y in dataset('test1.DsTwo')
+where $x.key1 /*+ indexnl */ >= $y.key2
+return $x
+

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-ge-join_02.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-ge-join_02.aql
new file mode 100644
index 0000000..06be0e9
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-ge-join_02.aql

@@ -0,0 +1,29 @@
+/*
+ * Description  : Notice the query hint to use an indexed nested-loops join plan. 
+ *              : We expect a plan that broadcasts internal dataset DsTwo, then probes internal dataset DsOne’s primary index. 
+ * Expected Res : Success
+ * Date         : 29th November 2012
+ */
+
+drop dataverse test1 if exists;
+create dataverse test1;
+
+create type test1.TestType as open {
+          key1: int32,
+          key2: int32,
+          fname : string,
+          lname : string
+}
+
+create dataset test1.DsOne(TestType) primary key key1;
+create dataset test1.DsTwo(TestType) primary key key1;
+
+// Please note content enclosed in the comment in the predicate is the HINT to the optimizer
+
+write output to nc1:"rttest/btree-index-join_primary-ge-join_02.adm";
+
+for $x in dataset('test1.DsOne')
+for $y in dataset('test1.DsTwo')
+where $x.key2 /*+ indexnl */ <= $y.key1
+return $x
+

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-gt-join_01.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-gt-join_01.aql
new file mode 100644
index 0000000..67d75a1
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-gt-join_01.aql

@@ -0,0 +1,29 @@
+/*
+ * Description  : Notice the query hint to use an indexed nested-loops join plan. 
+ *              : We expect a plan that broadcasts internal dataset DsTwo, then probes internal dataset DsOne’s primary index. 
+ * Expected Res : Success
+ * Date         : 29th November 2012
+ */
+
+drop dataverse test1 if exists;
+create dataverse test1;
+
+create type test1.TestType as open {
+          key1: int32,
+          key2: int32,
+          fname : string,
+          lname : string
+}
+
+create dataset test1.DsOne(TestType) primary key key1;
+create dataset test1.DsTwo(TestType) primary key key1;
+
+// Please note content enclosed in the comment in the predicate is the HINT to the optimizer
+
+write output to nc1:"rttest/btree-index-join_primary-gt-join_01.adm";
+
+for $x in dataset('test1.DsOne')
+for $y in dataset('test1.DsTwo')
+where $x.key1 /*+ indexnl */ > $y.key2
+return $x
+

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-gt-join_02.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-gt-join_02.aql
new file mode 100644
index 0000000..a7be083
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-gt-join_02.aql

@@ -0,0 +1,29 @@
+/*
+ * Description  : Notice the query hint to use an indexed nested-loops join plan. 
+ *              : We expect a plan that broadcasts internal dataset DsTwo, then probes internal dataset DsOne’s primary index. 
+ * Expected Res : Success
+ * Date         : 29th November 2012
+ */
+
+drop dataverse test1 if exists;
+create dataverse test1;
+
+create type test1.TestType as open {
+          key1: int32,
+          key2: int32,
+          fname : string,
+          lname : string
+}
+
+create dataset test1.DsOne(TestType) primary key key1;
+create dataset test1.DsTwo(TestType) primary key key1;
+
+// Please note content enclosed in the comment in the predicate is the HINT to the optimizer
+
+write output to nc1:"rttest/btree-index-join_primary-gt-join_02.adm";
+
+for $x in dataset('test1.DsOne')
+for $y in dataset('test1.DsTwo')
+where $x.key2 /*+ indexnl */ < $y.key1
+return $x
+

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-le-join_01.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-le-join_01.aql
new file mode 100644
index 0000000..66f2ace
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-le-join_01.aql

@@ -0,0 +1,29 @@
+/*
+ * Description  : Notice the query hint to use an indexed nested-loops join plan. 
+ *              : We expect a plan that broadcasts internal dataset DsTwo, then probes internal dataset DsOne’s primary index. 
+ * Expected Res : Success
+ * Date         : 29th November 2012
+ */
+
+drop dataverse test1 if exists;
+create dataverse test1;
+
+create type test1.TestType as open {
+          key1: int32,
+          key2: int32,
+          fname : string,
+          lname : string
+}
+
+create dataset test1.DsOne(TestType) primary key key1;
+create dataset test1.DsTwo(TestType) primary key key1;
+
+// Please note content enclosed in the comment in the predicate is the HINT to the optimizer
+
+write output to nc1:"rttest/btree-index-join_primary-le-join_01.adm";
+
+for $x in dataset('test1.DsOne')
+for $y in dataset('test1.DsTwo')
+where $x.key1 /*+ indexnl */ <= $y.key2
+return $x
+

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-le-join_02.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-le-join_02.aql
new file mode 100644
index 0000000..39c1d51
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-le-join_02.aql

@@ -0,0 +1,29 @@
+/*
+ * Description  : Notice the query hint to use an indexed nested-loops join plan. 
+ *              : We expect a plan that broadcasts internal dataset DsTwo, then probes internal dataset DsOne’s primary index. 
+ * Expected Res : Success
+ * Date         : 29th November 2012
+ */
+
+drop dataverse test1 if exists;
+create dataverse test1;
+
+create type test1.TestType as open {
+          key1: int32,
+          key2: int32,
+          fname : string,
+          lname : string
+}
+
+create dataset test1.DsOne(TestType) primary key key1;
+create dataset test1.DsTwo(TestType) primary key key1;
+
+// Please note content enclosed in the comment in the predicate is the HINT to the optimizer
+
+write output to nc1:"rttest/btree-index-join_primary-le-join_02.adm";
+
+for $x in dataset('test1.DsOne')
+for $y in dataset('test1.DsTwo')
+where $x.key2 /*+ indexnl */ >= $y.key1
+return $x
+

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-lt-join_01.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-lt-join_01.aql
new file mode 100644
index 0000000..ef6a616
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-lt-join_01.aql

@@ -0,0 +1,29 @@
+/*
+ * Description  : Notice the query hint to use an indexed nested-loops join plan. 
+ *              : We expect a plan that broadcasts internal dataset DsTwo, then probes internal dataset DsOne’s primary index. 
+ * Expected Res : Success
+ * Date         : 29th November 2012
+ */
+
+drop dataverse test1 if exists;
+create dataverse test1;
+
+create type test1.TestType as open {
+          key1: int32,
+          key2: int32,
+          fname : string,
+          lname : string
+}
+
+create dataset test1.DsOne(TestType) primary key key1;
+create dataset test1.DsTwo(TestType) primary key key1;
+
+// Please note content enclosed in the comment in the predicate is the HINT to the optimizer
+
+write output to nc1:"rttest/btree-index-join_primary-lt-join_01.adm";
+
+for $x in dataset('test1.DsOne')
+for $y in dataset('test1.DsTwo')
+where $x.key1 /*+ indexnl */ < $y.key2
+return $x
+

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-lt-join_02.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-lt-join_02.aql
new file mode 100644
index 0000000..4924514
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/primary-lt-join_02.aql

@@ -0,0 +1,29 @@
+/*
+ * Description  : Notice the query hint to use an indexed nested-loops join plan. 
+ *              : We expect a plan that broadcasts internal dataset DsTwo, then probes internal dataset DsOne’s primary index. 
+ * Expected Res : Success
+ * Date         : 29th November 2012
+ */
+
+drop dataverse test1 if exists;
+create dataverse test1;
+
+create type test1.TestType as open {
+          key1: int32,
+          key2: int32,
+          fname : string,
+          lname : string
+}
+
+create dataset test1.DsOne(TestType) primary key key1;
+create dataset test1.DsTwo(TestType) primary key key1;
+
+// Please note content enclosed in the comment in the predicate is the HINT to the optimizer
+
+write output to nc1:"rttest/btree-index-join_primary-lt-join_02.adm";
+
+for $x in dataset('test1.DsOne')
+for $y in dataset('test1.DsTwo')
+where $x.key2 /*+ indexnl */ > $y.key1
+return $x
+

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/secondary-equi-join-multiindex.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/secondary-equi-join-multiindex.aql
new file mode 100644
index 0000000..c596984
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/secondary-equi-join-multiindex.aql

@@ -0,0 +1,60 @@
+/*
+ * Description    : Equi joins two datasets, FacebookUsers and FacebookMessages, based on their user's id.
+ *                  We first expect FacebookUsers' primary index to be used 
+ *                  to satisfy the range condition on it's primary key. 
+ *                  FacebookMessages has a secondary btree index on author-id-copy, and given the 'indexnl' hint 
+ *                  we expect the join to be transformed into an indexed nested-loop join.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type EmploymentType as closed { 
+  organization-name: string,
+  start-date: date,
+  end-date: date?
+} 
+
+create type FacebookUserType as closed { 
+  id: int32,
+  id-copy: int32,
+  alias: string,
+  name: string,
+  user-since: datetime,
+  user-since-copy: datetime,
+  friend-ids: {{ int32 }},
+  employment: [EmploymentType]
+} 
+
+create type FacebookMessageType as closed { 
+  message-id: int32,
+  message-id-copy: int32,
+  author-id: int32,
+  author-id-copy: int32,
+  in-response-to: int32?,
+  sender-location: point?,
+  message: string
+} 
+
+create dataset FacebookUsers(FacebookUserType)
+primary key id;
+
+create dataset FacebookMessages(FacebookMessageType)
+primary key message-id;
+
+create index fbmIdxAutId if not exists on FacebookMessages(author-id-copy);
+
+write output to nc1:"rttest/btree-index-join_title-secondary-equi-join-multiindex.adm";
+
+for $user in dataset('FacebookUsers')
+for $message in dataset('FacebookMessages')
+where $user.id /*+ indexnl */ = $message.author-id-copy
+and $user.id >= 11000 and $user.id <= 12000
+return {
+  "fbu-ID": $user.id,
+  "fbm-auth-ID": $message.author-id,
+  "uname": $user.name,
+  "message": $message.message
+}

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/secondary-equi-join-multipred.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/secondary-equi-join-multipred.aql
new file mode 100644
index 0000000..bb803b0
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/secondary-equi-join-multipred.aql

@@ -0,0 +1,41 @@
+/*
+ * Description    : Equi joins two datasets, DBLP and CSX, based on their title.
+ *                  DBLP has a secondary btree index on title, and given the 'indexnl' hint 
+ *                  we expect the join to be transformed into an indexed nested-loop join.
+ *                  We expect the additional predicates to be put into a select above the 
+ *                  primary index search.
+ * 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) primary key id;
+
+create dataset CSX(CSXType) primary key id;
+
+create index title_index on DBLP(title);
+
+write output to nc1:"rttest/btree-index-join_title-secondary-equi-join-multipred.adm";
+
+for $a in dataset('DBLP')
+for $b in dataset('CSX')
+where $a.title /*+ indexnl */ = $b.title and $a.authors < $b.authors and $a.misc > $b.misc
+return {"arec": $a, "brec": $b}

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/secondary-equi-join_01.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/secondary-equi-join_01.aql
new file mode 100644
index 0000000..8a4f056
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/secondary-equi-join_01.aql

@@ -0,0 +1,39 @@
+/*
+ * Description    : Equi joins two datasets, DBLP and CSX, based on their title.
+ *                  DBLP has a secondary btree index on title, and given the 'indexnl' hint 
+ *                  we expect the join to be transformed into an indexed nested-loop join.
+ * 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) primary key id;
+
+create dataset CSX(CSXType) primary key id;
+
+create index title_index on DBLP(title);
+
+write output to nc1:"rttest/btree-index-join_title-secondary-equi-join_01.adm";
+
+for $a in dataset('DBLP')
+for $b in dataset('CSX')
+where $a.title /*+ indexnl */ = $b.title
+return {"arec": $a, "brec": $b}

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/secondary-equi-join_02.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/secondary-equi-join_02.aql
new file mode 100644
index 0000000..fa68cd2
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/secondary-equi-join_02.aql

@@ -0,0 +1,39 @@
+/*
+ * Description    : Equi joins two datasets, DBLP and CSX, based on their title.
+ *                  CSX has a secondary btree index on title, and given the 'indexnl' hint 
+ *                  we expect the join to be transformed into an indexed nested-loop join.
+ * 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) primary key id;
+
+create dataset CSX(CSXType) primary key id;
+
+create index title_index on CSX(title);
+
+write output to nc1:"rttest/btree-index-join_title-secondary-equi-join_02.adm";
+
+for $a in dataset('DBLP')
+for $b in dataset('CSX')
+where $a.title /*+ indexnl */ = $b.title
+return {"arec": $a, "brec": $b}

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/secondary-equi-join_03.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/secondary-equi-join_03.aql
new file mode 100644
index 0000000..3eedafd
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index-join/secondary-equi-join_03.aql

@@ -0,0 +1,29 @@
+/*
+ * Description    : Equi self-joins a dataset, DBLP, based on its title.
+ *                  DBLP has a secondary btree index on title, and given the 'indexnl' hint 
+ *                  we expect the join to be transformed into an indexed nested-loop join.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+create index title_index on DBLP(title);
+
+write output to nc1:"rttest/btree-index-join_title-secondary-equi-join_03.adm";
+
+for $a in dataset('DBLP')
+for $b in dataset('DBLP')
+where $a.title /*+ indexnl */ = $b.title
+return {"arec": $a, "brec": $b}

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-01.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-01.aql
new file mode 100644
index 0000000..0d096a7
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-01.aql

@@ -0,0 +1,26 @@
+/*
+ *  Description     : This test is intended to verify that the primary BTree index is NOT used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+// Please note this is a Negative test and the BTree index should NOT be used in the plan.
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-primary-01.adm";
+
+create type TestType as open {
+    fname : string,
+    lname : string
+}
+
+// create internal dataset with primary index (composite key) defined on fname,lname fields
+create dataset testdst(TestType) primary key fname,lname;
+
+for $emp in dataset('testdst') 
+where $emp.fname > "Roger"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-02.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-02.aql
new file mode 100644
index 0000000..fbcdd50
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-02.aql

@@ -0,0 +1,26 @@
+/*
+ *  Description     : This test is intended to verify that the primary BTree index is NOT used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+// This is a Negative test - prefix search, BTree index should not be used in the plan.
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-primary-02.adm";
+
+create type TestType as open {
+    fname : string,
+    lname : string
+}
+
+// create internal dataset with primary index defined on fname,lname fields
+create dataset testdst(TestType) primary key fname,lname;
+
+for $emp in dataset('testdst') 
+where $emp.fname >= "Susan"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-03.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-03.aql
new file mode 100644
index 0000000..2047b62
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-03.aql

@@ -0,0 +1,26 @@
+/*
+ *  Description     : This test is intended to verify that the primary BTree index is NOT used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+// Negative test - prefix search, BTree index should not be used.
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-primary-03.adm";
+
+create type TestType as open {
+    fname : string,
+    lname : string
+}
+
+// create internal dataset with primary index defined on fname,lname fields
+create dataset testdst(TestType) primary key fname,lname;
+
+for $emp in dataset('testdst') 
+where $emp.fname < "Isa"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-04.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-04.aql
new file mode 100644
index 0000000..84147ae
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-04.aql

@@ -0,0 +1,26 @@
+/*
+ *  Description     : This test is intended to verify that the primary BTree index is NOT used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+// Negative test - prefix search, BTree index should not be used in query plan
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-primary-04.adm";
+
+create type TestType as open {
+    fname : string,
+    lname : string
+}
+
+// create internal dataset with primary index defined on fname,lname fields
+create dataset testdst(TestType) primary key fname,lname;
+
+for $emp in dataset('testdst') 
+where $emp.fname <= "Vanpatten"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-05.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-05.aql
new file mode 100644
index 0000000..0fbf179
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-05.aql

@@ -0,0 +1,26 @@
+/*
+ *  Description     : This test is intended to verify that the primary BTree index is NOT used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+// Negative test - BTree index should NOT be used in query plan
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-primary-05.adm";
+
+create type TestType as open {
+    fname : string,
+    lname : string
+}
+
+// create internal dataset with primary index defined on fname,lname fields
+create dataset testdst(TestType) primary key fname,lname;
+
+for $emp in dataset('testdst') 
+where $emp.fname != "Max"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-06.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-06.aql
new file mode 100644
index 0000000..08164fd
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-06.aql

@@ -0,0 +1,26 @@
+/*
+ *  Description     : This test is intended to verify that the primary BTree index is used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+// Negative test - prefix search, BTree index should NOT be used in the query plan.
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-primary-06.adm";
+
+create type TestType as open {
+    fname : string,
+    lname : string
+}
+
+// create internal dataset with primary index defined on fname,lname fields
+create dataset testdst(TestType) primary key fname,lname;
+
+for $emp in dataset('testdst') 
+where $emp.fname = "Julio"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-07.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-07.aql
new file mode 100644
index 0000000..2b635a5
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-07.aql

@@ -0,0 +1,27 @@
+/*
+ *  Description     : This test is intended to verify that the primary BTree index is NOT used 
+ *                  : in the optimized query plan. 
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+// THE BTREE INDEX IN THIS CASE SHOULD NOT BE PICKED UP!!!!
+// Verify that the optimized query plan does not have the BTree search
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-primary-07.adm";
+
+create type TestType as open {
+    fname : string,
+    lname : string
+}
+
+// create internal dataset with primary index defined on fname,lname fields
+create dataset testdst(TestType) primary key fname,lname;
+
+for $emp in dataset('testdst') 
+where $emp.lname = "Kim"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-08.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-08.aql
new file mode 100644
index 0000000..337072e
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-08.aql

@@ -0,0 +1,22 @@
+/*
+ *  Description     : This test is intended to verify that the primary BTree index is used in the optimized query plan 
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-primary-08.adm";
+
+create type TestType as open {
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key fname,lname;
+
+for $emp in dataset('testdst') 
+where $emp.fname = "Young Seok" and $emp.lname = "Kim"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-09.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-09.aql
new file mode 100644
index 0000000..cc52d2a
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-09.aql

@@ -0,0 +1,26 @@
+/*
+ *  Description     : BTree Index verification test
+ *                  : This test is intended to verify that the primary BTree index is NOT used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+// Negative test
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-primary-09.adm";
+
+create type TestType as open {
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key fname,lname;
+
+for $emp in dataset('testdst') 
+where $emp.fname = "Julio" or $emp.lname = "Malaika"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-10.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-10.aql
new file mode 100644
index 0000000..4d0f85e
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-10.aql

@@ -0,0 +1,24 @@
+/*
+ *  Description     : BTree Index verification (usage) test
+ *                  : This test is intended to verify that the primary BTree index is used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-primary-10.adm";
+
+create type TestType as open {
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key fname,lname;
+
+for $emp in dataset('testdst') 
+where $emp.fname > "Alex" and $emp.lname < "Zach"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-11.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-11.aql
new file mode 100644
index 0000000..164e49a
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-11.aql

@@ -0,0 +1,24 @@
+/*
+ *  Description     : BTree Index verification test
+ *                  : This test is intended to verify that the primary BTree index is NOT used 
+ *                  : in the optimized query plan for predicates.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-primary-11.adm";
+
+create type TestType as open {
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key fname,lname;
+
+for $emp in dataset('testdst') 
+where $emp.fname > "Allan" and $emp.lname < "Zubi"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-12.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-12.aql
new file mode 100644
index 0000000..659d1ff
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-12.aql

@@ -0,0 +1,26 @@
+/*
+ *  Description     : BTree Index verification (usage) test
+ *                  : This test is intended to verify that the primary BTree index is NOT used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+// Negative test - prefix search
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-primary-12.adm";
+
+create type TestType as open {
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key fname,lname;
+
+for $emp in dataset('testdst') 
+where $emp.fname > "Allan" and $emp.lname = "Xu"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-13.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-13.aql
new file mode 100644
index 0000000..3c49200
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-13.aql

@@ -0,0 +1,26 @@
+/*
+ *  Description     : BTree Index verification test
+ *                  : This test is intended to verify that the primary BTree index is NOT used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+// Negative test - prefix search
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-primary-13.adm";
+
+create type TestType as open {
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key fname,lname;
+
+for $emp in dataset('testdst') 
+where $emp.fname = "Julio" and $emp.lname < "Xu"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-14.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-14.aql
new file mode 100644
index 0000000..e93061f
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-14.aql

@@ -0,0 +1,24 @@
+/*
+ *  Description     : BTree Index verification test
+ *                  : This test is intended to verify that the primary BTree index is NOT used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-primary-14.adm";
+
+create type TestType as open {
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key fname,lname;
+
+for $emp in dataset('testdst') 
+where $emp.fname >= "Michael" and $emp.lname <= "Xu"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-15.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-15.aql
new file mode 100644
index 0000000..97a486a
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-15.aql

@@ -0,0 +1,24 @@
+/*
+ *  Description     : BTree Index verification test
+ *                  : This test is intended to verify that the primary BTree index is used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-primary-15.adm";
+
+create type TestType as open {
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key fname,lname;
+
+for $emp in dataset('testdst') 
+where $emp.fname > "Craig" and $emp.lname > "Kevin" and $emp.fname < "Mary" and $emp.lname < "Tomes"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-16.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-16.aql
new file mode 100644
index 0000000..cf80ed2
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-16.aql

@@ -0,0 +1,24 @@
+/*
+ *  Description     : BTree Index verification test
+ *                  : This test is intended to verify that the primary BTree index is used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-primary-16.adm";
+
+create type TestType as open {
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key fname,lname;
+
+for $emp in dataset('testdst') 
+where $emp.fname >= "Craig" and $emp.lname >= "Kevin" and $emp.fname <= "Mary" and $emp.lname <= "Tomes"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-17.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-17.aql
new file mode 100644
index 0000000..db9c994
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-17.aql

@@ -0,0 +1,24 @@
+/*
+ *  Description     : BTree Index verification test
+ *                  : This test is intended to verify that the primary BTree index is NOT used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-primary-17.adm";
+
+create type TestType as open {
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key fname,lname;
+
+for $emp in dataset('testdst') 
+where $emp.fname <= "Craig" and $emp.lname > "Kevin"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-18.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-18.aql
new file mode 100644
index 0000000..9787005
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-18.aql

@@ -0,0 +1,24 @@
+/*
+ *  Description     : BTree Index verification test
+ *                  : This test is intended to verify that the primary BTree index is NOT used 
+ *                  : in the optimized query plan 
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-primary-18.adm";
+
+create type TestType as open {
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key fname,lname;
+
+for $emp in dataset('testdst') 
+where $emp.fname != "Michael" and $emp.lname != "Carey"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-19.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-19.aql
new file mode 100644
index 0000000..0dff6af
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-19.aql

@@ -0,0 +1,24 @@
+/*
+ *  Description     : BTree Index verification test
+ *                  : This test is intended to verify that the primary BTree index is used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-primary-19.adm";
+
+create type TestType as open {
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key fname,lname;
+
+for $emp in dataset('testdst') 
+where $emp.fname > "Craig" and $emp.lname > "Kevin" and $emp.fname <= "Mary" and $emp.lname <= "Tomes"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-20.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-20.aql
new file mode 100644
index 0000000..ac9e374
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-20.aql

@@ -0,0 +1,24 @@
+/*
+ *  Description     : BTree Index verification test
+ *                  : This test is intended to verify that the primary BTree index is used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-primary-20.adm";
+
+create type TestType as open {
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key fname,lname;
+
+for $emp in dataset('testdst') 
+where $emp.fname >= "Craig" and $emp.lname >= "Kevin" and $emp.fname < "Mary" and $emp.lname < "Tomes"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-21.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-21.aql
new file mode 100644
index 0000000..afa241f
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-21.aql

@@ -0,0 +1,24 @@
+/*
+ *  Description     : BTree Index verification test
+ *                  : This test is intended to verify that the primary BTree index is used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-primary-21.adm";
+
+create type TestType as open {
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key fname;
+
+for $emp in dataset('testdst') 
+where $emp.fname > "Max" 
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-22.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-22.aql
new file mode 100644
index 0000000..4af86a0
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-22.aql

@@ -0,0 +1,24 @@
+/*
+ *  Description     : BTree Index verification test
+ *                  : This test is intended to verify that the primary BTree index is used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-primary-22.adm";
+
+create type TestType as open {
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key fname;
+
+for $emp in dataset('testdst') 
+where $emp.fname >= "Sofia" 
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-23.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-23.aql
new file mode 100644
index 0000000..f73bd1f
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-23.aql

@@ -0,0 +1,24 @@
+/*
+ *  Description     : BTree Index verification test
+ *                  : This test is intended to verify that the primary BTree index is used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-primary-23.adm";
+
+create type TestType as open {
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key fname;
+
+for $emp in dataset('testdst') 
+where $emp.fname < "Chen" 
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-24.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-24.aql
new file mode 100644
index 0000000..1faa37e
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-24.aql

@@ -0,0 +1,24 @@
+/*
+ *  Description     : BTree Index verification test
+ *                  : This test is intended to verify that the primary BTree index is used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-primary-24.adm";
+
+create type TestType as open {
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key fname;
+
+for $emp in dataset('testdst') 
+where $emp.fname <= "Julio" 
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-25.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-25.aql
new file mode 100644
index 0000000..6b24b7c
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-25.aql

@@ -0,0 +1,24 @@
+/*
+ *  Description     : BTree Index verification test
+ *                  : This test is intended to verify that the primary BTree index is used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-primary-25.adm";
+
+create type TestType as open {
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key fname;
+
+for $emp in dataset('testdst') 
+where $emp.fname > "Neil" and $emp.fname < "Roger" 
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-26.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-26.aql
new file mode 100644
index 0000000..05a69d2
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-26.aql

@@ -0,0 +1,24 @@
+/*
+ *  Description     : BTree Index verification test
+ *                  : This test is intended to verify that the primary BTree index is used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-primary-26.adm";
+
+create type TestType as open {
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key fname;
+
+for $emp in dataset('testdst') 
+where $emp.fname >= "Max" and $emp.fname <= "Roger" 
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-27.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-27.aql
new file mode 100644
index 0000000..e9ccb87
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-27.aql

@@ -0,0 +1,24 @@
+/*
+ *  Description     : BTree Index verification test
+ *                  : This test is intended to verify that the primary BTree index is used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 5th Feb 2013
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-primary-27.adm";
+
+create type TestType as open {
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key fname,lname;
+
+for $emp in dataset('testdst') 
+where $emp.fname > "Craig" and $emp.lname > "Kevin" and $emp.fname <= "Mary" and $emp.lname < "Tomes"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-28.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-28.aql
new file mode 100644
index 0000000..5e7b4e3
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-28.aql

@@ -0,0 +1,24 @@
+/*
+ *  Description     : BTree Index verification test
+ *                  : This test is intended to verify that the primary BTree index is used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 5th Feb 2013
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-primary-28.adm";
+
+create type TestType as open {
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType)  primary key fname,lname;
+
+for $emp in dataset('testdst') 
+where $emp.fname > "Craig" and $emp.lname > "Kevin" and $emp.fname < "Mary" and $emp.lname <= "Tomes"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-29.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-29.aql
new file mode 100644
index 0000000..c7d4753
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-29.aql

@@ -0,0 +1,24 @@
+/*
+ *  Description     : BTree Index verification test
+ *                  : This test is intended to verify that the primary BTree index is used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 5th Feb 2013
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-primary-29.adm";
+
+create type TestType as open {
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType)  primary key fname,lname;
+
+for $emp in dataset('testdst') 
+where $emp.fname > "Craig" and $emp.lname >= "Kevin" and $emp.fname < "Mary" and $emp.lname < "Tomes"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-30.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-30.aql
new file mode 100644
index 0000000..a9a2573
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-primary-30.aql

@@ -0,0 +1,24 @@
+/*
+ *  Description     : BTree Index verification test
+ *                  : This test is intended to verify that the primary BTree index is used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 5th Feb 2013
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-primary-30.adm";
+
+create type TestType as open {
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType)  primary key fname,lname;
+
+for $emp in dataset('testdst') 
+where $emp.fname >= "Craig" and $emp.lname > "Kevin" and $emp.fname < "Mary" and $emp.lname < "Tomes"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-31.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-31.aql
new file mode 100644
index 0000000..c2e6257
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-31.aql

@@ -0,0 +1,29 @@
+/*
+ *  Description     : BTree Index verification test
+ *                  : This test is intended to verify that the secondary BTree index is NOT used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+// Please note this is a Negative test and the BTree index should NOT be used in the plan.
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-primary-31.adm";
+
+create type TestType as open {
+    id : int32,
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key id;
+
+create index sec_Idx on testdst(fname,lname);
+
+for $emp in dataset('testdst') 
+where $emp.fname > "Roger"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-32.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-32.aql
new file mode 100644
index 0000000..d009e2e
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-32.aql

@@ -0,0 +1,29 @@
+/*
+ *  Description     : BTree Index verification test
+ *                  : This test is intended to verify that the secondary BTree index is NOT used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+// This is a Negative test - prefix search, BTree index should not be used in the plan.
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-secondary-32.adm";
+
+create type TestType as open {
+    id : int32,
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key id;
+
+create index sec_Idx on testdst(fname,lname);
+
+for $emp in dataset('testdst') 
+where $emp.fname >= "Susan"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-33.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-33.aql
new file mode 100644
index 0000000..2b364e4
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-33.aql

@@ -0,0 +1,29 @@
+/*
+ *  Description     : BTree Index verification (usage) test
+ *                  : This test is intended to verify that the secondary BTree index is used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+// Negative test - prefix search, BTree index should not be used.
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-secondary-33.adm";
+
+create type TestType as open {
+    id : int32,
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key id;
+
+create index sec_Idx on testdst(fname,lname);
+
+for $emp in dataset('testdst') 
+where $emp.fname < "Isa"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-34.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-34.aql
new file mode 100644
index 0000000..f20b5a9
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-34.aql

@@ -0,0 +1,29 @@
+/*
+ *  Description     : BTree Index verification test
+ *                  : This test is intended to verify that the secondary BTree index is NOT used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+// Negative test - prefix search, BTree index should not be used in query plan
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-secondary-34.adm";
+
+create type TestType as open {
+    id : int32,
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key id;
+
+create index sec_Idx on testdst(fname,lname);
+
+for $emp in dataset('testdst') 
+where $emp.fname <= "Vanpatten"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-35.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-35.aql
new file mode 100644
index 0000000..dfc5017
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-35.aql

@@ -0,0 +1,29 @@
+/*
+ *  Description     : BTree Index verification test
+ *                  : This test is intended to verify that the secondary BTree index is NOT used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+// Negative test - BTree index should NOT be used in query plan
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-secondary-35.adm";
+
+create type TestType as open {
+    id : int32,
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key id;
+
+create index sec_Idx on testdst(fname,lname);
+
+for $emp in dataset('testdst') 
+where $emp.fname != "Max"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-36.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-36.aql
new file mode 100644
index 0000000..7d72623
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-36.aql

@@ -0,0 +1,29 @@
+/*
+ *  Description     : BTree Index verification test
+ *                  : This test is intended to verify that the secondary BTree index is used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+// Negative test - prefix search, BTree index should NOT be used in the query plan.
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-secondary-36.adm";
+
+create type TestType as open {
+    id : int32,
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key id;
+
+create index sec_Idx on testdst(fname,lname);
+
+for $emp in dataset('testdst') 
+where $emp.fname = "Julio"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-37.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-37.aql
new file mode 100644
index 0000000..7c155ce
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-37.aql

@@ -0,0 +1,29 @@
+/*
+ *  Description     : BTree Index verification test
+ *                  : This test is intended to verify that the secondary BTree index is NOT used in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+// THE BTREE INDEX IN THIS CASE SHOULD NOT BE PICKED UP!!!!
+// Verify that the optimized query plan does not have the BTree search
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-secondary-37.adm";
+
+create type TestType as open {
+    id : int32,
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key id;
+
+create index sec_Idx on testdst(fname,lname);
+
+for $emp in dataset('testdst') 
+where $emp.lname = "Kim"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-38.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-38.aql
new file mode 100644
index 0000000..dc63f05
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-38.aql

@@ -0,0 +1,26 @@
+/*
+ *  Description     : BTree Index verification test
+ *                  : This test is intended to verify that the secondary BTree index is used in the optimized query plan 
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-secondary-38.adm";
+
+create type TestType as open {
+    id : int32,
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key id;
+
+create index sec_Idx on testdst(fname,lname);
+
+for $emp in dataset('testdst') 
+where $emp.fname = "Young Seok" and $emp.lname = "Kim"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-39.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-39.aql
new file mode 100644
index 0000000..a9d32c3
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-39.aql

@@ -0,0 +1,29 @@
+/*
+ *  Description     : BTree Index verification test
+ *                  : This test is intended to verify that the secondary BTree index is NOT used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+// Negative test
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-secondary-39.adm";
+
+create type TestType as open {
+    id : int32,
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key id;
+
+create index sec_Idx on testdst(fname,lname);
+
+for $emp in dataset('testdst') 
+where $emp.fname = "Julio" or $emp.lname = "Malaika"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-40.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-40.aql
new file mode 100644
index 0000000..25c6dec
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-40.aql

@@ -0,0 +1,27 @@
+/*
+ *  Description     : BTree Index verification test
+ *                  : This test is intended to verify that the secondary BTree index is used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-secondary-40.adm";
+
+create type TestType as open {
+    id : int32,
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key id;
+
+create index sec_Idx on testdst(fname,lname);
+
+for $emp in dataset('testdst') 
+where $emp.fname > "Alex" and $emp.lname < "Zach"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-41.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-41.aql
new file mode 100644
index 0000000..bc65009
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-41.aql

@@ -0,0 +1,27 @@
+/*
+ *  Description     : BTree Index verification test
+ *                  : This test is intended to verify that the secondary BTree index is NOT used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-secondary-41.adm";
+
+create type TestType as open {
+    id : int32,
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key id;
+
+create index sec_Idx on testdst(fname,lname);
+
+for $emp in dataset('testdst') 
+where $emp.fname > "Allan" and $emp.lname < "Zubi"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-42.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-42.aql
new file mode 100644
index 0000000..289d1b4
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-42.aql

@@ -0,0 +1,29 @@
+/*
+ *  Description     : BTree Index verification test
+ *                  : This test is intended to verify that the secondary BTree index is NOT used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+// Negative test - prefix search
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-secondary-42.adm";
+
+create type TestType as open {
+    id : int32,
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key id;
+
+create index sec_Idx on testdst(fname,lname);
+
+for $emp in dataset('testdst') 
+where $emp.fname > "Allan" and $emp.lname = "Xu"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-43.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-43.aql
new file mode 100644
index 0000000..86e5d67
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-43.aql

@@ -0,0 +1,29 @@
+/*
+ *  Description     : BTree Index verification test
+ *                  : This test is intended to verify that the secondary BTree index is NOT used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+// Negative test - prefix search
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-secondary-43.adm";
+
+create type TestType as open {
+    id : int32,
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key id;
+
+create index sec_Idx on testdst(fname,lname);
+
+for $emp in dataset('testdst') 
+where $emp.fname = "Julio" and $emp.lname < "Xu"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-44.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-44.aql
new file mode 100644
index 0000000..54e149e
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-44.aql

@@ -0,0 +1,27 @@
+/*
+ *  Description     : BTree Index verification test
+ *                  : This test is intended to verify that the secondary BTree index is NOT used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-secondary-44.adm";
+
+create type TestType as open {
+    id : int32,
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key id;
+
+create index sec_Idx on testdst(fname,lname);
+
+for $emp in dataset('testdst') 
+where $emp.fname >= "Michael" and $emp.lname <= "Xu"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-45.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-45.aql
new file mode 100644
index 0000000..cc33e5a
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-45.aql

@@ -0,0 +1,27 @@
+/*
+ *  Description     : BTree Index verification test
+ *                  : This test is intended to verify that the secondary BTree index is used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-secondary-45.adm";
+
+create type TestType as open {
+    id : int32,
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key id;
+
+create index sec_Idx on testdst(fname,lname);
+
+for $emp in dataset('testdst') 
+where $emp.fname > "Craig" and $emp.lname > "Kevin" and $emp.fname < "Mary" and $emp.lname < "Tomes"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-46.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-46.aql
new file mode 100644
index 0000000..f486e44
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-46.aql

@@ -0,0 +1,27 @@
+/*
+ *  Description     : BTree Index verification test
+ *                  : This test is intended to verify that the secondary BTree index is used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-secondary-46.adm";
+
+create type TestType as open {
+    id : int32,
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key id;
+
+create index sec_Idx on testdst(fname,lname);
+
+for $emp in dataset('testdst') 
+where $emp.fname >= "Craig" and $emp.lname >= "Kevin" and $emp.fname <= "Mary" and $emp.lname <= "Tomes"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-47.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-47.aql
new file mode 100644
index 0000000..5d06a51
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-47.aql

@@ -0,0 +1,27 @@
+/*
+ *  Description     : BTree Index verification test
+ *                  : This test is intended to verify that the secondary BTree index is NOT used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-secondary-47.adm";
+
+create type TestType as open {
+    id : int32,
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key id;
+
+create index sec_Idx on testdst(fname,lname);
+
+for $emp in dataset('testdst') 
+where $emp.fname <= "Craig" and $emp.lname > "Kevin"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-48.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-48.aql
new file mode 100644
index 0000000..2dc1ab4
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-48.aql

@@ -0,0 +1,27 @@
+/*
+ *  Description     : BTree Index verification test
+ *                  : This test is intended to verify that the secondary BTree index is NOT used 
+ *                  : in the optimized query plan 
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-secondary-48.adm";
+
+create type TestType as open {
+    id : int32,
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key id;
+
+create index sec_Idx on testdst(fname,lname);
+
+for $emp in dataset('testdst') 
+where $emp.fname != "Michael" and $emp.lname != "Carey"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-49.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-49.aql
new file mode 100644
index 0000000..6175ba6
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-49.aql

@@ -0,0 +1,28 @@
+/*
+ *  Description     : BTree Index verification test
+ *                  : This test is intended to verify that the secondary BTree index is used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-secondary-49.adm";
+
+create type TestType as open {
+    id : int32,
+    fname : string,
+    lname : string
+}
+
+// create internal dataset
+create dataset testdst(TestType) primary key id;
+
+create index sec_Idx on testdst(fname,lname);
+
+for $emp in dataset('testdst') 
+where $emp.fname > "Craig" and $emp.lname > "Kevin" and $emp.fname <= "Mary" and $emp.lname <= "Tomes"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-50.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-50.aql
new file mode 100644
index 0000000..04aefc3
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-50.aql

@@ -0,0 +1,27 @@
+/*
+ *  Description     : BTree Index verification test
+ *                  : This test is intended to verify that the secondary BTree index is used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-secondary-50.adm";
+
+create type TestType as open {
+    id : int32,
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key id;
+
+create index sec_Idx on testdst(fname,lname);
+
+for $emp in dataset('testdst') 
+where $emp.fname >= "Craig" and $emp.lname >= "Kevin" and $emp.fname < "Mary" and $emp.lname < "Tomes"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-51.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-51.aql
new file mode 100644
index 0000000..5ae63a9
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-51.aql

@@ -0,0 +1,27 @@
+/*
+ *  Description     : BTree Index verification test
+ *                  : This test is intended to verify that the secondary BTree index is used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-secondary-51.adm";
+
+create type TestType as open {
+    id : int32,
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key id;
+
+create index sec_Idx on testdst(fname,lname);
+
+for $emp in dataset('testdst')
+where $emp.fname >= "Craig" and $emp.lname <= "Kevin" and $emp.fname <= "Mary" and $emp.lname >= "Tomes"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-52.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-52.aql
new file mode 100644
index 0000000..e720742
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-52.aql

@@ -0,0 +1,26 @@
+/*
+ *  Description     : This test is intended to verify that the secondary BTree index is used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-secondary-52.adm";
+
+create type TestType as open {
+    id : int32,
+    fname : string,
+    lname : string
+}
+ 
+create dataset testdst(TestType) primary key id;
+
+create index sec_Idx on testdst(fname);
+
+for $emp in dataset('testdst') 
+where $emp.fname > "Max" 
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-53.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-53.aql
new file mode 100644
index 0000000..65a9b6d
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-53.aql

@@ -0,0 +1,26 @@
+/*
+ *  Description     : This test is intended to verify that the secondary BTree index is used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-secondary-53.adm";
+
+create type TestType as open {
+    id : int32,
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key id;
+
+create index sec_Idx on testdst(fname);
+
+for $emp in dataset('testdst') 
+where $emp.fname >= "Sofia" 
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-54.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-54.aql
new file mode 100644
index 0000000..a18975a
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-54.aql

@@ -0,0 +1,26 @@
+/*
+ *  Description     : This test is intended to verify that the secondary BTree index is used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-secondary-54.adm";
+
+create type TestType as open {
+    id : int32,
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key id;
+
+create index sec_Idx on testdst(fname);
+
+for $emp in dataset('testdst') 
+where $emp.fname < "Chen" 
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-55.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-55.aql
new file mode 100644
index 0000000..94c1463
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-55.aql

@@ -0,0 +1,26 @@
+/*
+ *  Description     : This test is intended to verify that the secondary BTree index is used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-secondary-55.adm";
+
+create type TestType as open {
+    id : int32,
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key id;
+
+create index sec_Idx on testdst(fname);
+
+for $emp in dataset('testdst') 
+where $emp.fname <= "Julio" 
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-56.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-56.aql
new file mode 100644
index 0000000..53f8ca4
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-56.aql

@@ -0,0 +1,26 @@
+/*
+ *  Description     : This test is intended to verify that the primary BTree index is used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-primary-56.adm";
+
+create type TestType as open {
+    id : int32,
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key id;
+
+create index sec_Idx on testdst(fname);
+
+for $emp in dataset('testdst') 
+where $emp.fname > "Neil" and $emp.fname < "Roger" 
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-57.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-57.aql
new file mode 100644
index 0000000..43cf54d
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-57.aql

@@ -0,0 +1,26 @@
+/*
+ *  Description     : This test is intended to verify that the secondary BTree index is used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-secondary-57.adm";
+
+create type TestType as open {
+    id : int32,
+    fname : string,
+    lname : string
+}
+
+create dataset testdst(TestType) primary key id;
+
+create index sec_Idx on testdst(fname);
+
+for $emp in dataset('testdst') 
+where $emp.fname >= "Max" and $emp.fname <= "Roger" 
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-58.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-58.aql
new file mode 100644
index 0000000..aa18136
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-58.aql

@@ -0,0 +1,26 @@
+/*
+ *  Description     : This test is intended to verify that the secondary BTree index is used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-secondary-58.adm";
+
+create type TestType as open {
+    id : int32,
+    fname : string,
+    lname : string
+}
+ 
+create dataset testdst(TestType) primary key id;
+
+create index sec_Idx on testdst(fname);
+
+for $emp in dataset('testdst') 
+where $emp.fname = "Max" 
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-59.aql b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-59.aql
new file mode 100644
index 0000000..2b0a300
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/btree-index/btree-secondary-59.aql

@@ -0,0 +1,28 @@
+/*
+ *  Description     : BTree Index verification test
+ *                  : This test is intended to verify that the secondary BTree index is used 
+ *                  : in the optimized query plan.
+ *  Expected Result : Success
+ *  Date            : 13th Aug 2012
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/btree-index_btree-secondary-49.adm";
+
+create type TestType as open {
+    id : int32,
+    fname : string,
+    lname : string
+}
+
+// create internal dataset
+create dataset testdst(TestType)  primary key id;
+
+create index sec_Idx on testdst(fname,lname);
+
+for $emp in dataset('testdst') 
+where $emp.fname > "Craig" and $emp.lname > "Kevin" and $emp.fname <= "Mary" and $emp.lname < "Tomes"
+return $emp

diff --git a/asterix-app/src/test/resources/optimizerts/queries/cell-aggregation-with-filtering.aql b/asterix-app/src/test/resources/optimizerts/queries/cell-aggregation-with-filtering.aql
deleted file mode 100644
index a328a1b..0000000
--- a/asterix-app/src/test/resources/optimizerts/queries/cell-aggregation-with-filtering.aql
+++ /dev/null

@@ -1,37 +0,0 @@
-drop dataverse twitter if exists;
-create dataverse twitter;
-use dataverse twitter;
-
-create type Tweet as closed {
-	id: int32,
-	tweetid: int64,
-	loc: point,
-	time: datetime,
-	text: string
-}
-
-create nodegroup group1 if exists on nc1, nc2;
-
-create dataset TwitterData(Tweet)
-  partitioned by key id on group1;
-
-
-load dataset TwitterData 
-using "edu.uci.ics.asterix.external.dataset.adapter.NCFileSystemAdapter"
-(("path"="nc1://data/twitter/extrasmalltweets.txt"),("format"="adm")) pre-sorted;
-
-create index rtree_index_point on TwitterData(loc) type rtree;
-
-write output to nc1:"rttest/spatial_cell-aggregation-with-filtering.adm";
-
-for $t in dataset('TwitterData')
-let $region := polygon("
-	33.80503407287759,-126.41235263538363 
-	44.9090773200516,-126.41235263538363 
-	44.9090773200516,-87.65258701038363 
-	33.80503407287759,-87.65258701038363")
-
-where spatial-intersect($t.loc, $region)
-group by $c := spatial-cell($t.loc, create-point(24.5,-125.5), 3.0, 3.0) with $t
-order by count($t)
-return { "cell": $c, "count": count($t) }

diff --git a/asterix-app/src/test/resources/optimizerts/queries/consolidate-selects-complex.aql b/asterix-app/src/test/resources/optimizerts/queries/consolidate-selects-complex.aql
new file mode 100644
index 0000000..7dfe817
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/consolidate-selects-complex.aql

@@ -0,0 +1,31 @@
+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 nodegroup group1 if not exists on nc1, nc2;
+
+create dataset DBLP(DBLPType) 
+  primary key id on group1;
+
+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;
+
+write output to nc1:"rttest/consolidate-complex-selects.aql";
+
+for $paper in dataset('DBLP')
+let $paper_tokens := word-tokens($paper.title)
+let $query_tokens := word-tokens("Transactions for Cooperative Environments")
+let $jacca := similarity-jaccard-check($paper_tokens, $query_tokens, 0.8f)
+let $jaccb := similarity-jaccard-check($paper_tokens, $query_tokens, 0.5f)
+let $jaccc := similarity-jaccard-check($paper_tokens, $query_tokens, 0.3f)
+where $jacca[0] and $jaccb[0] and $paper.authors = "testauth" and $jaccc
+return {"Paper": $paper_tokens, "Query": $query_tokens }
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/consolidate-selects-simple.aql b/asterix-app/src/test/resources/optimizerts/queries/consolidate-selects-simple.aql
new file mode 100644
index 0000000..d21fa6e
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/consolidate-selects-simple.aql

@@ -0,0 +1,28 @@
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type CustomerType as closed {
+  c_custkey: int32, 
+  c_name: string, 
+  c_address: string, 
+  c_nationkey: int32, 
+  c_phone: string, 
+  c_acctbal: double, 
+  c_mktsegment: string,
+  c_comment: string
+}
+
+create nodegroup group1 if not exists on nc1, nc2;
+
+create dataset Customers(CustomerType) 
+  primary key c_custkey on group1;
+
+write output to nc1:"rttest/consolidate-selects-simple.aql";
+
+for $c in dataset('Customers')
+where $c.c_name = "testname" 
+  and $c.c_address = "testaddr"
+  and $c.c_nationkey = 1
+  and $c.c_phone = "123456789"
+return $c
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/count-tweets.aql b/asterix-app/src/test/resources/optimizerts/queries/count-tweets.aql
index 5e4cde1..651cf88 100644
--- a/asterix-app/src/test/resources/optimizerts/queries/count-tweets.aql
+++ b/asterix-app/src/test/resources/optimizerts/queries/count-tweets.aql

@@ -6,7 +6,7 @@
   id: int32,
   tweetid: int64,
   loc: point,
-  time: string,
+  time: datetime,
   text: string
 }
 

diff --git a/asterix-app/src/test/resources/optimizerts/queries/cust_group_no_agg.aql b/asterix-app/src/test/resources/optimizerts/queries/cust_group_no_agg.aql
index 6fdae88..6a86b8a 100644
--- a/asterix-app/src/test/resources/optimizerts/queries/cust_group_no_agg.aql
+++ b/asterix-app/src/test/resources/optimizerts/queries/cust_group_no_agg.aql

@@ -18,7 +18,7 @@
 create nodegroup group1 if not exists on nc1, nc2;
 
 create dataset Customers(CustomerType) 
-  partitioned by key c_custkey on group1;
+  primary key c_custkey on group1;
 
 write output to nc1:"/tmp/.adm";
 

diff --git a/asterix-app/src/test/resources/optimizerts/queries/denorm-cust-order.aql b/asterix-app/src/test/resources/optimizerts/queries/denorm-cust-order.aql
index acad4a1..389dad5 100644
--- a/asterix-app/src/test/resources/optimizerts/queries/denorm-cust-order.aql
+++ b/asterix-app/src/test/resources/optimizerts/queries/denorm-cust-order.aql

@@ -36,9 +36,9 @@
 create nodegroup group1 if not exists on nc1, nc2;
 
 create dataset Customers(CustomerType) 
-  partitioned by key cid on group1;
+  primary key cid on group1;
 create dataset Orders(OrderType)
-  partitioned by key oid on group1;
+  primary key oid on group1;
 
 write output to nc1:"/tmp/custorder.adm";
 

diff --git a/asterix-app/src/test/resources/optimizerts/queries/distinct_aggregate.aql b/asterix-app/src/test/resources/optimizerts/queries/distinct_aggregate.aql
index a4784c1..6fc1dac 100644
--- a/asterix-app/src/test/resources/optimizerts/queries/distinct_aggregate.aql
+++ b/asterix-app/src/test/resources/optimizerts/queries/distinct_aggregate.aql

@@ -24,7 +24,7 @@
 create nodegroup group1 if not exists on nc1, nc2;
 
 create dataset LineItems_q1(LineItemType)
-  partitioned by key l_orderkey, l_linenumber on group1;
+  primary key l_orderkey, l_linenumber on group1;
 
 write output to nc1:"rttest/tpch_q1_pricing_summary_report_nt.adm";
  

diff --git a/asterix-app/src/test/resources/optimizerts/queries/fj-dblp-csx.aql b/asterix-app/src/test/resources/optimizerts/queries/fj-dblp-csx.aql
index 2898058..f748eae 100644
--- a/asterix-app/src/test/resources/optimizerts/queries/fj-dblp-csx.aql
+++ b/asterix-app/src/test/resources/optimizerts/queries/fj-dblp-csx.aql

@@ -22,8 +22,8 @@
 
 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;
+create dataset DBLP(DBLPType) primary key id on group1;
+create dataset CSX(CSXType) primary key id on group1;
 
 write output to nc1:'rttest/fj-dblp-csx.adm';
 

diff --git a/asterix-app/src/test/resources/optimizerts/queries/fj-phase1.aql b/asterix-app/src/test/resources/optimizerts/queries/fj-phase1.aql
index 778232a..19ceda0 100644
--- a/asterix-app/src/test/resources/optimizerts/queries/fj-phase1.aql
+++ b/asterix-app/src/test/resources/optimizerts/queries/fj-phase1.aql

@@ -19,10 +19,10 @@
 create nodegroup group1 if not exists on nc1, nc2;
 
 create dataset Users(UserType) 
-  partitioned by key uid on group1;
+  primary key uid on group1;
 
 create dataset Visitors(VisitorType) 
-  partitioned by key vid on group1;
+  primary key vid on group1;
 
 
 // set simfunction "jaccard";

diff --git a/asterix-app/src/test/resources/optimizerts/queries/fj-phase2-with-hints.aql b/asterix-app/src/test/resources/optimizerts/queries/fj-phase2-with-hints.aql
index 866c027..a0973f4 100644
--- a/asterix-app/src/test/resources/optimizerts/queries/fj-phase2-with-hints.aql
+++ b/asterix-app/src/test/resources/optimizerts/queries/fj-phase2-with-hints.aql

@@ -15,7 +15,7 @@
 create nodegroup group1 if not exists on nc1, nc2;
 
 create dataset DBLP_fuzzyjoin_078(DBLPType) 
-  partitioned by key id on group1;
+  primary key id on group1;
 
 write output to nc1:'rttest/fuzzyjoin_078.adm';
 

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inlined_q18_large_volume_customer.aql b/asterix-app/src/test/resources/optimizerts/queries/inlined_q18_large_volume_customer.aql
index 49c4157..0db7a51 100644
--- a/asterix-app/src/test/resources/optimizerts/queries/inlined_q18_large_volume_customer.aql
+++ b/asterix-app/src/test/resources/optimizerts/queries/inlined_q18_large_volume_customer.aql

@@ -49,11 +49,11 @@
 create nodegroup group1 if not exists on nc1, nc2;
 
 create dataset LineItems(LineItemType)
-  partitioned by key l_orderkey, l_linenumber on group1;
+  primary key l_orderkey, l_linenumber on group1;
 create dataset Orders(OrderType)
-  partitioned by key o_orderkey on group1;
+  primary key o_orderkey on group1;
 create dataset Customers(CustomerType) 
-  partitioned by key c_custkey on group1;
+  primary key c_custkey on group1;
 
 write output to nc1:"/tmp/inlined_q18_large_volume_customer.adm";
 

diff --git a/asterix-app/src/test/resources/optimizerts/queries/introhashpartitionmerge.aql b/asterix-app/src/test/resources/optimizerts/queries/introhashpartitionmerge.aql
index 9427ab5..cd1d78c 100644
--- a/asterix-app/src/test/resources/optimizerts/queries/introhashpartitionmerge.aql
+++ b/asterix-app/src/test/resources/optimizerts/queries/introhashpartitionmerge.aql

@@ -9,7 +9,7 @@
 
 create nodegroup group1 if not exists on nc1, nc2;
 
-create dataset TOKENSRANKEDADM(TOKENSRANKEDADMType) partitioned by key rank on group1;
+create dataset TOKENSRANKEDADM(TOKENSRANKEDADMType) primary key rank on group1;
 
 write output to nc1:'rttest/introhashpartitionmerge.adm';
 

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/ngram-contains-panic.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/ngram-contains-panic.aql
new file mode 100644
index 0000000..d193238
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/ngram-contains-panic.aql

@@ -0,0 +1,29 @@
+/*
+ * Description    : Tests whether an ngram_index is applied to optimize a selection query using the contains function.
+ *                  The index should *not* be applied (see below).
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+create index ngram_index on DBLP(title) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-basic_ngram-contains-panic.adm";
+
+// Cannot optimize this query because the string constant is shorter than the gram length.
+for $o in dataset('DBLP')
+where contains($o.title, "Mu")
+order by $o.id
+return $o
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/ngram-contains.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/ngram-contains.aql
new file mode 100644
index 0000000..137b1c7
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/ngram-contains.aql

@@ -0,0 +1,28 @@
+/*
+ * Description    : Tests whether an ngram_index is applied to optimize a selection query using the contains function.
+ *                  The index should be applied.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+create index ngram_index on DBLP(title) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-basic_ngram-contains.adm";
+
+for $o in dataset('DBLP')
+where contains($o.title, "Multimedia")
+order by $o.id
+return $o
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/ngram-edit-distance-check-panic.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/ngram-edit-distance-check-panic.aql
new file mode 100644
index 0000000..6f7f38c
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/ngram-edit-distance-check-panic.aql

@@ -0,0 +1,29 @@
+/*
+ * Description    : Tests whether an ngram_index is applied to optimize a selection query using the edit-distance-check function on strings.
+ *                  The index should *not* be applied (see below).
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+create index ngram_index on DBLP(authors) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-basic_ngram-edit-distance-check-panic.adm";
+
+// This query cannot be optimized with an index, based on the high edit distance.
+for $o in dataset('DBLP')
+let $ed := edit-distance-check($o.authors, "Amihay Motro", 5)
+where $ed[0]
+return $o
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/ngram-edit-distance-check.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/ngram-edit-distance-check.aql
new file mode 100644
index 0000000..0d9db19
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/ngram-edit-distance-check.aql

@@ -0,0 +1,27 @@
+/*
+ * Description    : Tests whether an ngram_index is applied to optimize a selection query using the edit-distance-check function on strings.
+ *                  The index should be applied.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+create index ngram_index on DBLP(authors) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-basic_ngram-edit-distance-check.adm";
+
+for $o in dataset('DBLP')
+where edit-distance-check($o.authors, "Amihay Motro", 1)[0]
+return $o
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/ngram-edit-distance-panic.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/ngram-edit-distance-panic.aql
new file mode 100644
index 0000000..7decdb5
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/ngram-edit-distance-panic.aql

@@ -0,0 +1,28 @@
+/*
+ * Description    : Tests whether an ngram_index is applied to optimize a selection query using the edit-distance function on strings.
+ *                  The index should *not* be applied (see below).
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+create index ngram_index on DBLP(authors) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-basic_ngram-edit-distance-panic.adm";
+
+// This query cannot be optimized with an index, based on the high edit distance.
+for $o in dataset('DBLP')
+where edit-distance($o.authors, "Amihay Motro") <= 5
+return $o
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/ngram-edit-distance.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/ngram-edit-distance.aql
new file mode 100644
index 0000000..c7a9ba4
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/ngram-edit-distance.aql

@@ -0,0 +1,27 @@
+/*
+ * Description    : Tests whether an ngram_index is applied to optimize a selection query using the edit-distance function on strings.
+ *                  The index should be applied.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+create index ngram_index on DBLP(authors) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-basic_ngram-edit-distance.adm";
+
+for $o in dataset('DBLP')
+where edit-distance($o.authors, "Amihay Motro") <= 1
+return $o
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/ngram-fuzzyeq-edit-distance.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/ngram-fuzzyeq-edit-distance.aql
new file mode 100644
index 0000000..3a3d7bb
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/ngram-fuzzyeq-edit-distance.aql

@@ -0,0 +1,30 @@
+/*
+ * Description    : Tests whether an ngram_index is applied to optimize a selection query with ~= using edit-distance on strings.
+ *                  The index should be applied.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+create index ngram_index on DBLP(authors) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-basic_ngram-fuzzyeq-edit-distance.adm";
+
+set simfunction 'edit-distance';
+set simthreshold '1';
+
+for $o in dataset('DBLP')
+where $o.authors ~= "Amihay Motro"
+return $o
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/ngram-fuzzyeq-jaccard.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/ngram-fuzzyeq-jaccard.aql
new file mode 100644
index 0000000..5e9ac0e
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/ngram-fuzzyeq-jaccard.aql

@@ -0,0 +1,30 @@
+/*
+ * Description    : Tests whether an ngram_index is applied to optimize a selection query with ~= using Jaccard on 3-gram tokens.
+ *                  The index should be applied.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+create index ngram_index on DBLP(title) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-basic_ngram-fuzzyeq-jaccard.adm";
+
+set simfunction 'jaccard';
+set simthreshold '0.8f';
+
+for $o in dataset('DBLP')
+where gram-tokens($o.title, 3, false) ~= gram-tokens("Transactions for Cooperative Environments", 3, false)
+return $o

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/ngram-jaccard-check.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/ngram-jaccard-check.aql
new file mode 100644
index 0000000..dbb9c71
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/ngram-jaccard-check.aql

@@ -0,0 +1,27 @@
+/*
+ * Description    : Tests whether an ngram_index is applied to optimize a selection query using the similarity-jaccard-check function on 3-gram tokens.
+ *                  The index should be applied.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+create index ngram_index on DBLP(title) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-basic_ngram-jaccard-check.adm";
+
+for $o in dataset('DBLP')
+where similarity-jaccard-check(gram-tokens($o.title, 3, false), gram-tokens("Transactions for Cooperative Environments", 3, false), 0.5f)[0]
+return $o
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/ngram-jaccard.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/ngram-jaccard.aql
new file mode 100644
index 0000000..f25fb8b
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/ngram-jaccard.aql

@@ -0,0 +1,27 @@
+/*
+ * Description    : Tests whether an ngram_index is applied to optimize a selection query using the similarity-jaccard function on 3-gram tokens.
+ *                  The index should be applied.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+create index ngram_index on DBLP(title) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-basic_ngram-jaccard.adm";
+
+for $o in dataset('DBLP')
+where similarity-jaccard(gram-tokens($o.title, 3, false), gram-tokens("Transactions for Cooperative Environments", 3, false)) >= 0.5f
+return $o

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/olist-edit-distance-check-panic.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/olist-edit-distance-check-panic.aql
new file mode 100644
index 0000000..c105eab
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/olist-edit-distance-check-panic.aql

@@ -0,0 +1,36 @@
+/*
+ * Description    : Tests whether a keyword index is applied to optimize a selection query using the edit-distance-check function on lists.
+ *                  The index should *not* be applied (see below).
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: [string],
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-basic_olist-edit-distance-check-panic.adm";
+
+// Index should not be applied because all list elements can be modified by 3 edit operations.
+for $c in dataset('Customers')
+where edit-distance-check($c.interests, ["computers", "wine", "walking"], 3)[0]
+order by $c.cid
+return $c

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/olist-edit-distance-check.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/olist-edit-distance-check.aql
new file mode 100644
index 0000000..b12037d1
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/olist-edit-distance-check.aql

@@ -0,0 +1,35 @@
+/*
+ * Description    : Tests whether a keyword index is applied to optimize a selection query using the edit-distance-check function on lists.
+ *                  The index should be applied.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: [string],
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-basic_olist-edit-distance-check.adm";
+
+for $c in dataset('Customers')
+where edit-distance-check($c.interests, ["computers", "wine", "walking"], 1)[0]
+order by $c.cid
+return $c

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/olist-edit-distance-panic.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/olist-edit-distance-panic.aql
new file mode 100644
index 0000000..84bcbb9
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/olist-edit-distance-panic.aql

@@ -0,0 +1,36 @@
+/*
+ * Description    : Tests whether a keyword index is applied to optimize a selection query using the edit-distance function on lists.
+ *                  The index should *not* be applied (see below).
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: [string],
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-basic_olist-edit-distance-panic.adm";
+
+// Index should not be applied because all list elements can be modified by 3 edit operations.
+for $c in dataset('Customers')
+where edit-distance($c.interests, ["computers", "wine", "walking"]) <= 3
+order by $c.cid
+return $c

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/olist-edit-distance.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/olist-edit-distance.aql
new file mode 100644
index 0000000..afafa37
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/olist-edit-distance.aql

@@ -0,0 +1,35 @@
+/*
+ * Description    : Tests whether a keyword index is applied to optimize a selection query using the edit-distance function on lists.
+ *                  The index should be applied.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: [string],
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-basic_olist-edit-distance.adm";
+
+for $c in dataset('Customers')
+where edit-distance($c.interests, ["computers", "wine", "walking"]) <= 1
+order by $c.cid
+return $c

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/olist-fuzzyeq-edit-distance.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/olist-fuzzyeq-edit-distance.aql
new file mode 100644
index 0000000..86b6474
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/olist-fuzzyeq-edit-distance.aql

@@ -0,0 +1,38 @@
+/*
+ * Description    : Tests whether a keyword index is applied to optimize a selection query with ~= using edit-distance on lists.
+ *                  The index should be applied.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: [string],
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-basic_olist-fuzzyeq-edit-distance.adm";
+
+set simfunction 'edit-distance';
+set simthreshold '1';
+
+for $c in dataset('Customers')
+where $c.interests ~= ["computers", "wine", "walking"]
+order by $c.cid
+return $c

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/olist-fuzzyeq-jaccard.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/olist-fuzzyeq-jaccard.aql
new file mode 100644
index 0000000..64812db
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/olist-fuzzyeq-jaccard.aql

@@ -0,0 +1,37 @@
+/*
+ * Description    : Tests whether a keyword is applied to optimize a selection query with ~= using Jaccard on lists.
+ *                  The index should be applied.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: [string],
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-basic_olist-fuzzyeq-jaccard.adm";
+
+set simfunction 'jaccard';
+set simthreshold '0.8f';
+
+for $c in dataset('Customers')
+where $c.interests ~= ["databases", "computers", "wine"]
+return $c

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/olist-jaccard-check.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/olist-jaccard-check.aql
new file mode 100644
index 0000000..4f8b8fe
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/olist-jaccard-check.aql

@@ -0,0 +1,34 @@
+/*
+ * Description    : Tests whether a keyword index is applied to optimize a selection query using the similarity-jaccard-check function on lists.
+ *                  The index should be applied.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: [string],
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-basic_olist-jaccard-check.adm";
+
+for $c in dataset('Customers')
+where similarity-jaccard-check($c.interests, ["databases", "computers", "wine"], 0.7f)[0]
+return $c

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/olist-jaccard.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/olist-jaccard.aql
new file mode 100644
index 0000000..62d6806
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/olist-jaccard.aql

@@ -0,0 +1,34 @@
+/*
+ * Description    : Tests whether a keyword index is applied to optimize a selection query using the similarity-jaccard function on lists.
+ *                  The index should be applied.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: [string],
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-basic_olist-jaccard.adm";
+
+for $c in dataset('Customers')
+where similarity-jaccard($c.interests, ["databases", "computers", "wine"]) >= 0.7f
+return $c

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/ulist-fuzzyeq-jaccard.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/ulist-fuzzyeq-jaccard.aql
new file mode 100644
index 0000000..4ac02c8
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/ulist-fuzzyeq-jaccard.aql

@@ -0,0 +1,37 @@
+/*
+ * Description    : Tests whether a keyword is applied to optimize a selection query with ~= using Jaccard on sets.
+ *                  The index should be applied.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: {{string}},
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-basic_ulist-fuzzyeq-jaccard.adm";
+
+set simfunction 'jaccard';
+set simthreshold '0.8f';
+
+for $c in dataset('Customers')
+where $c.interests ~= ["databases", "computers", "wine"]
+return $c

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/ulist-jaccard-check.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/ulist-jaccard-check.aql
new file mode 100644
index 0000000..80e8aef
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/ulist-jaccard-check.aql

@@ -0,0 +1,34 @@
+/*
+ * Description    : Tests whether a keyword index is applied to optimize a selection query using the similarity-jaccard-check function on sets.
+ *                  The index should be applied.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: {{string}},
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-basic_ulist-jaccard.adm";
+
+for $c in dataset('Customers')
+where similarity-jaccard-check($c.interests, ["databases", "computers", "wine"], 0.7f)[0]
+return $c

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/ulist-jaccard.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/ulist-jaccard.aql
new file mode 100644
index 0000000..588ca14
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/ulist-jaccard.aql

@@ -0,0 +1,34 @@
+/*
+ * Description    : Tests whether a keyword index is applied to optimize a selection query using the similarity-jaccard function on sets.
+ *                  The index should be applied.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: {{string}},
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-basic_ulist-jaccard.adm";
+
+for $c in dataset('Customers')
+where similarity-jaccard($c.interests, ["databases", "computers", "wine"]) >= 0.7f
+return $c

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/word-contains.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/word-contains.aql
new file mode 100644
index 0000000..8d9cb02
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/word-contains.aql

@@ -0,0 +1,29 @@
+/*
+ * Description    : Tests whether a keyword index is applied to optimize a selection query using the contains function.
+ *                  The index should *not* be applied (see below).
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+create index keyword_index on DBLP(title) type keyword;
+
+write output to nc1:"rttest/inverted-index-basic_word-contains.adm";
+
+// Contains cannot be answered with a word inverted index.
+for $o in dataset('DBLP')
+where contains($o.title, "Multimedia")
+order by $o.id
+return $o

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/word-fuzzyeq-jaccard.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/word-fuzzyeq-jaccard.aql
new file mode 100644
index 0000000..006398e
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/word-fuzzyeq-jaccard.aql

@@ -0,0 +1,30 @@
+/*
+ * Description    : Tests whether a keyword is applied to optimize a selection query with ~= using Jaccard on word tokens.
+ *                  The index should be applied.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+create index keyword_index on DBLP(title) type keyword;
+
+write output to nc1:"rttest/inverted-index-basic_word-fuzzyeq-jaccard.adm";
+
+set simfunction 'jaccard';
+set simthreshold '0.5f';
+
+for $o in dataset('DBLP')
+where word-tokens($o.title) ~= word-tokens("Transactions for Cooperative Environments")
+return $o

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/word-jaccard-check.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/word-jaccard-check.aql
new file mode 100644
index 0000000..4c814e4
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/word-jaccard-check.aql

@@ -0,0 +1,28 @@
+/*
+ * Description    : Tests whether a keyword index is applied to optimize a selection query using the similarity-jaccard-check function on word tokens.
+ *                  The index should be applied.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+create index keyword_index on DBLP(title) type keyword;
+
+write output to nc1:"rttest/inverted-index-basic_word-jaccard-check.adm";
+
+for $o in dataset('DBLP')
+where similarity-jaccard-check(word-tokens($o.title), word-tokens("Transactions for Cooperative Environments"), 0.5f)[0]
+return $o
+

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/word-jaccard.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/word-jaccard.aql
new file mode 100644
index 0000000..53a5bbb
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/word-jaccard.aql

@@ -0,0 +1,28 @@
+/*
+ * Description    : Tests whether a keyword index is applied to optimize a selection query using the similarity-jaccard function on word tokens.
+ *                  The index should be applied.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+create index keyword_index on DBLP(title) type keyword;
+
+write output to nc1:"rttest/inverted-index-basic_word-jaccard.adm";
+
+for $o in dataset('DBLP')
+where similarity-jaccard(word-tokens($o.title), word-tokens("Transactions for Cooperative Environments")) >= 0.5f
+return $o
+

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-complex/ngram-edit-distance-check-let-panic-nopanic_01.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-complex/ngram-edit-distance-check-let-panic-nopanic_01.aql
new file mode 100644
index 0000000..1c96adc
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-complex/ngram-edit-distance-check-let-panic-nopanic_01.aql

@@ -0,0 +1,32 @@
+/*
+ * Description    : Tests whether an ngram_index is applied to optimize a selection query using 
+ *                  two edit-distance-check function of which only the first can be optimized with an index. 
+ *                  Tests that the optimizer rule correctly drills through the let clauses.
+ *                  The index should be applied.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+create index ngram_index on DBLP(authors) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-complex_ngram-edit-distance-check-let-panic-nopanic_01.adm";
+
+// Only the first edit-distance-check can be optimized with an index.
+for $o in dataset('DBLP')
+let $eda := edit-distance-check($o.authors, "Amihay Motro", 3)
+let $edb := edit-distance-check($o.authors, "Amihay Motro", 5)
+where $eda[0] and $edb[0] 
+return $o
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-complex/ngram-edit-distance-check-let-panic-nopanic_02.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-complex/ngram-edit-distance-check-let-panic-nopanic_02.aql
new file mode 100644
index 0000000..e80443e
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-complex/ngram-edit-distance-check-let-panic-nopanic_02.aql

@@ -0,0 +1,32 @@
+/*
+ * Description    : Tests whether an ngram_index is applied to optimize a selection query using 
+ *                  two edit-distance-check function of which only the second can be optimized with an index.
+ *                  Tests that the optimizer rule correctly drills through the let clauses.
+ *                  The index should be applied.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+create index ngram_index on DBLP(authors) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-complex_ngram-edit-distance-check-let-panic-nopanic_01.adm";
+
+// Only the second edit-distance-check can be optimized with an index.
+for $o in dataset('DBLP')
+let $edb := edit-distance-check($o.authors, "Amihay Motro", 5)
+let $eda := edit-distance-check($o.authors, "Amihay Motro", 3)
+where $edb[0] and $eda[0] 
+return $o
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-complex/ngram-edit-distance-check-let-panic.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-complex/ngram-edit-distance-check-let-panic.aql
new file mode 100644
index 0000000..d0d3035
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-complex/ngram-edit-distance-check-let-panic.aql

@@ -0,0 +1,30 @@
+/*
+ * Description    : Tests whether an ngram_index is applied to optimize a selection query using the edit-distance-check function on strings.
+ *                  Tests that the optimizer rule correctly drills through the let clauses.
+ *                  The index should *not* be applied (see below).
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+create index ngram_index on DBLP(authors) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-complex_ngram-edit-distance-check-let-panic.adm";
+
+// This query cannot be optimized with an index, based on the high edit distance.
+for $o in dataset('DBLP')
+let $ed := edit-distance-check($o.authors, "Amihay Motro", 5)
+where $ed[0]
+return $o
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-complex/ngram-edit-distance-check-let.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-complex/ngram-edit-distance-check-let.aql
new file mode 100644
index 0000000..2d2f34f
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-complex/ngram-edit-distance-check-let.aql

@@ -0,0 +1,29 @@
+/*
+ * Description    : Tests whether an ngram_index is applied to optimize a selection query using the edit-distance-check function on strings.
+ *                  Tests that the optimizer rule correctly drills through the let clauses.
+ *                  The index should be applied.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+create index ngram_index on DBLP(authors) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-complex_ngram-edit-distance-check-let.adm";
+
+for $o in dataset('DBLP')
+let $ed := edit-distance-check($o.authors, "Amihay Motro", 1)
+where $ed[0]
+return $o
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-complex/ngram-jaccard-check-let.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-complex/ngram-jaccard-check-let.aql
new file mode 100644
index 0000000..fb59040
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-complex/ngram-jaccard-check-let.aql

@@ -0,0 +1,29 @@
+/*
+ * Description    : Tests whether an ngram_index is applied to optimize a selection query using the similarity-jaccard-check function on 3-gram tokens.
+ *                  Tests that the optimizer rule correctly drills through the let clauses.
+ *                  The index should be applied.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+create index ngram_index on DBLP(title) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-complex_ngram-jaccard-check-let.adm";
+
+for $o in dataset('DBLP')
+let $jacc := similarity-jaccard-check(gram-tokens($o.title, 3, false), gram-tokens("Transactions for Cooperative Environments", 3, false), 0.5f)
+where $jacc[0]
+return $o
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-complex/ngram-jaccard-check-multi-let.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-complex/ngram-jaccard-check-multi-let.aql
new file mode 100644
index 0000000..b86c6b2
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-complex/ngram-jaccard-check-multi-let.aql

@@ -0,0 +1,32 @@
+/*
+ * Description    : Tests whether an ngram_index is applied to optimize a selection query using the similarity-jaccard-check function on 3-gram tokens.
+ *                  Tests that the optimizer rule correctly drills through the let clauses.
+ *                  The index should be applied.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+create index ngram_index on DBLP(title) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-complex_ngram-jaccard-check-multi-let.adm";
+
+// This test is complex because we have three assigns to drill into.
+for $paper in dataset('DBLP')
+let $paper_tokens := gram-tokens($paper.title, 3, false)
+let $query_tokens := gram-tokens("Transactions for Cooperative Environments", 3, false)
+let $jacc := similarity-jaccard-check($paper_tokens, $query_tokens, 0.5f)
+where $jacc[0]
+return {"Paper": $paper_tokens, "Query": $query_tokens }
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-complex/olist-edit-distance-check-let-panic.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-complex/olist-edit-distance-check-let-panic.aql
new file mode 100644
index 0000000..aa9bc59
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-complex/olist-edit-distance-check-let-panic.aql

@@ -0,0 +1,37 @@
+/*
+ * Description    : Tests whether an ngram_index is applied to optimize a selection query using the edit-distance-check function on lists.
+ *                  Tests that the optimizer rule correctly drills through the let clauses.
+ *                  The index should *not* be applied (see below).
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: [string],
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-complex_olist-edit-distance-check-let-panic.adm";
+
+for $c in dataset('Customers')
+let $ed := edit-distance-check($c.interests, ["computers", "wine", "walking"], 3)
+where $ed[0]
+order by $c.cid
+return $c

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-complex/olist-edit-distance-check-let.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-complex/olist-edit-distance-check-let.aql
new file mode 100644
index 0000000..8a78450
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-complex/olist-edit-distance-check-let.aql

@@ -0,0 +1,37 @@
+/*
+ * Description    : Tests whether an ngram_index is applied to optimize a selection query using the edit-distance-check function on lists.
+ *                  Tests that the optimizer rule correctly drills through the let clauses.
+ *                  The index should be applied.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: [string],
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-complex_olist-edit-distance-check-let.adm";
+
+for $c in dataset('Customers')
+let $ed := edit-distance-check($c.interests, ["computers", "wine", "walking"], 1)
+where $ed[0]
+order by $c.cid
+return $c

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-complex/olist-jaccard-check-let.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-complex/olist-jaccard-check-let.aql
new file mode 100644
index 0000000..48ec727
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-complex/olist-jaccard-check-let.aql

@@ -0,0 +1,36 @@
+/*
+ * Description    : Tests whether a keyword index is applied to optimize a selection query using the similarity-jaccard-check function on lists.
+ *                  Tests that the optimizer rule correctly drills through the let clauses.
+ *                  The index should be applied.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: [string],
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-complex_olist-jaccard-check-let.adm";
+
+for $c in dataset('Customers')
+let $jacc := similarity-jaccard-check($c.interests, ["databases", "computers", "wine"], 0.7f)
+where $jacc[0]
+return $c

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-complex/ulist-jaccard-check-let.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-complex/ulist-jaccard-check-let.aql
new file mode 100644
index 0000000..0757d41
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-complex/ulist-jaccard-check-let.aql

@@ -0,0 +1,36 @@
+/*
+ * Description    : Tests whether a keyword index is applied to optimize a selection query using the similarity-jaccard-check function on lists.
+ *                  Tests that the optimizer rule correctly drills through the let clauses.
+ *                  The index should be applied.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: {{string}},
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-complex_ulist-jaccard-check-let.adm";
+
+for $c in dataset('Customers')
+let $jacc := similarity-jaccard-check($c.interests, ["databases", "computers", "wine"], 0.7f)
+where $jacc[0]
+return $c

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-complex/word-jaccard-check-let.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-complex/word-jaccard-check-let.aql
new file mode 100644
index 0000000..ec97668
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-complex/word-jaccard-check-let.aql

@@ -0,0 +1,30 @@
+/*
+ * Description    : Tests whether a keyword index is applied to optimize a selection query using the similarity-jaccard-check function on word tokens.
+ *                  Tests that the optimizer rule correctly drills through the let clauses.
+ *                  The index should be applied.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+create index keyword_index on DBLP(title) type keyword;
+
+write output to nc1:"rttest/inverted-index-complex_word-jaccard-check-let.adm";
+
+for $o in dataset('DBLP')
+let $jacc := similarity-jaccard-check(word-tokens($o.title), word-tokens("Transactions for Cooperative Environments"), 0.5f)
+where $jacc[0]
+return $o
+

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-complex/word-jaccard-check-multi-let.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-complex/word-jaccard-check-multi-let.aql
new file mode 100644
index 0000000..bf1821e
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-complex/word-jaccard-check-multi-let.aql

@@ -0,0 +1,32 @@
+/*
+ * Description    : Tests whether a keyword index is applied to optimize a selection query using the similarity-jaccard-check function on word tokens.
+ *                  Tests that the optimizer rule correctly drills through the let clauses.
+ *                  The index should be applied.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+create index keyword_index on DBLP(title) type keyword;
+
+write output to nc1:"rttest/inverted-index-complex_word-jaccard-check-multi-let.adm";
+
+// This test is complex because we have three assigns to drill into.
+for $paper in dataset('DBLP')
+let $paper_tokens := word-tokens($paper.title)
+let $query_tokens := word-tokens("Transactions for Cooperative Environments")
+let $jacc := similarity-jaccard-check($paper_tokens, $query_tokens, 0.8f)
+where $jacc[0]
+return {"Paper": $paper_tokens, "Query": $query_tokens }
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/ngram-edit-distance-inline.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/ngram-edit-distance-inline.aql
new file mode 100644
index 0000000..ee768d7
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/ngram-edit-distance-inline.aql

@@ -0,0 +1,31 @@
+/*
+ * Description    : Fuzzy self joins a dataset, DBLP, based on the edit-distance function of its authors.
+ *                  DBLP has a 3-gram index on authors, 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.
+ *                  We expect the top-level equi join introduced because of surrogate optimization to be removed, since it is not necessary.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+create index ngram_index on DBLP(authors) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-join-noeqjoin_ngram-edit-distance-inline.adm";
+
+for $a in dataset('DBLP')
+for $b in dataset('DBLP')
+let $ed := edit-distance($a.authors, $b.authors)
+where $ed < 3 and $a.id < $b.id
+return {"aauthors": $a.authors, "bauthors": $b.authors, "ed": $ed}
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/ngram-edit-distance.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/ngram-edit-distance.aql
new file mode 100644
index 0000000..ca2827d
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/ngram-edit-distance.aql

@@ -0,0 +1,39 @@
+/*
+ * Description    : Fuzzy joins two datasets, DBLP and CSX, based on the edit-distance function of their authors.
+ *                  DBLP has a 3-gram index on authors, and we expect the join to be transformed into an indexed nested-loop join.
+ *                  We expect the top-level equi join introduced because of surrogate optimization to be removed, since it is not necessary. 
+ * 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) primary key id;
+
+create dataset CSX(CSXType) primary key id;
+
+create index ngram_index on DBLP(authors) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-join-noeqjoin_ngram-edit-distance.adm";
+
+for $a in dataset('DBLP')
+for $b in dataset('CSX')
+where edit-distance($a.authors, $b.authors) < 3 and $a.id < $b.id
+return {"aauthors": $a.authors, "bauthors": $b.authors}
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/ngram-fuzzyeq-edit-distance.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/ngram-fuzzyeq-edit-distance.aql
new file mode 100644
index 0000000..0e15708
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/ngram-fuzzyeq-edit-distance.aql

@@ -0,0 +1,42 @@
+/*
+ * Description    : Fuzzy joins two datasets, DBLP and CSX, based on ~= using edit distance of their authors.
+ *                  DBLP has a 3-gram index on authors, and we expect the join to be transformed into an indexed nested-loop join.
+ *                  We expect the top-level equi join introduced because of surrogate optimization to be removed, since it is not necessary. 
+ * 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) primary key id;
+
+create dataset CSX(CSXType) primary key id;
+
+create index ngram_index on CSX(authors) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-join-noeqjoin_ngram-fuzzyeq-edit-distance.adm";
+
+set simfunction 'edit-distance';
+set simthreshold '3';
+
+for $a in dataset('DBLP')
+for $b in dataset('CSX')
+where $a.authors ~= $b.authors and $a.id < $b.id
+return {"aauthors": $a.authors, "bauthors": $b.authors}
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/ngram-fuzzyeq-jaccard.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/ngram-fuzzyeq-jaccard.aql
new file mode 100644
index 0000000..1a97936
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/ngram-fuzzyeq-jaccard.aql

@@ -0,0 +1,42 @@
+/*
+ * Description    : Fuzzy joins two datasets, DBLP and CSX, based on ~= using Jaccard 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 expect the top-level equi join introduced because of surrogate optimization to be removed, since it is not necessary.
+ * 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) primary key id;
+
+create dataset CSX(CSXType) primary key id;
+
+create index ngram_index on DBLP(title) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-join-noeqjoin_ngram-fuzzyeq-jaccard.adm";
+
+set simfunction 'jaccard';
+set simthreshold '0.5f';
+
+for $a in dataset('DBLP')
+for $b in dataset('CSX')
+where gram-tokens($a.title, 3, false) ~= gram-tokens($b.title, 3, false) and $a.id < $b.id
+return {"atitle": $a.title, "btitle": $b.title}
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/ngram-jaccard-inline.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/ngram-jaccard-inline.aql
new file mode 100644
index 0000000..bf6bb82
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/ngram-jaccard-inline.aql

@@ -0,0 +1,31 @@
+/*
+ * Description    : Fuzzy self joins a dataset, DBLP, based on the similarity-jaccard function of its 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.
+ *                  We expect the top-level equi join introduced because of surrogate optimization to be removed, since it is not necessary.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+create index ngram_index on DBLP(title) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-join-noeqjoin_ngram-jaccard-inline.adm";
+
+for $a in dataset('DBLP')
+for $b in dataset('DBLP')
+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
+return {"atitle": $a.title, "btitle": $b.title, "jacc": $jacc}
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/ngram-jaccard.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/ngram-jaccard.aql
new file mode 100644
index 0000000..dae2a78
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/ngram-jaccard.aql

@@ -0,0 +1,40 @@
+/*
+ * 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 expect the top-level equi join introduced because of surrogate optimization to be removed, since it is not necessary.
+ * 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) primary key id;
+
+create dataset CSX(CSXType) primary key id;
+
+create index ngram_index on DBLP(title) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-join-noeqjoin_ngram-jaccard.adm";
+
+for $a in dataset('DBLP')
+for $b in dataset('CSX')
+where similarity-jaccard(gram-tokens($a.title, 3, false), gram-tokens($b.title, 3, false)) >= 0.5f
+      and $a.id < $b.id
+return {"atitle": $a.title, "btitle": $b.title}
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/olist-edit-distance-inline.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/olist-edit-distance-inline.aql
new file mode 100644
index 0000000..21114fc
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/olist-edit-distance-inline.aql

@@ -0,0 +1,38 @@
+/*
+ * Description    : Fuzzy self joins a dataset, Customers, based on the edit-distance function of its interest lists.
+ *                  Customers has a keyword index on interests, 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.
+ *                  We expect the top-level equi join introduced because of surrogate optimization to be removed, since it is not necessary.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: [string],
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+  
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-join-noeqjoin_olist-edit-distance-inline.adm";
+
+for $a in dataset('Customers')
+for $b in dataset('Customers')
+let $ed := edit-distance($a.interests, $b.interests)
+where $ed <= 2 and $a.cid < $b.cid
+return {"ainterests": $a.interests, "binterests": $b.interests, "ed": $ed}

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/olist-edit-distance.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/olist-edit-distance.aql
new file mode 100644
index 0000000..b90b4f7
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/olist-edit-distance.aql

@@ -0,0 +1,38 @@
+/*
+ * Description    : Fuzzy joins two datasets, Customer and Customer2, based on the edit-distance function of their interest lists.
+ *                  Customers has a keyword index on interests, and we expect the join to be transformed into an indexed nested-loop join.
+ *                  We expect the top-level equi join introduced because of surrogate optimization to be removed, since it is not necessary.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: [string],
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+  
+create dataset Customers2(CustomerType) primary key cid;
+
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-join-noeqjoin_olist-edit-distance.adm";
+
+for $a in dataset('Customers')
+for $b in dataset('Customers2')
+where edit-distance($a.interests, $b.interests) <= 2 and $a.cid < $b.cid
+return {"ainterests": $a.interests, "binterests": $b.interests}

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/olist-fuzzyeq-edit-distance.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/olist-fuzzyeq-edit-distance.aql
new file mode 100644
index 0000000..c78f65c
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/olist-fuzzyeq-edit-distance.aql

@@ -0,0 +1,41 @@
+/*
+ * Description    : Fuzzy joins two datasets, Customer and Customer2, based on ~= using edit distance of their interest lists.
+ *                  Customers has a keyword index on interests, and we expect the join to be transformed into an indexed nested-loop join.
+ *                  We expect the top-level equi join introduced because of surrogate optimization to be removed, since it is not necessary.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: [string],
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+  
+create dataset Customers2(CustomerType) primary key cid;
+
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-join-noeqjoin_olist-fuzzyeq-edit-distance.adm";
+
+set simfunction 'edit-distance';
+set simthreshold '3';
+
+for $a in dataset('Customers')
+for $b in dataset('Customers2')
+where $a.interests ~= $b.interests and $a.cid < $b.cid
+return {"ainterests": $a.interests, "binterests": $b.interests}

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/olist-fuzzyeq-jaccard.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/olist-fuzzyeq-jaccard.aql
new file mode 100644
index 0000000..3bbcc28
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/olist-fuzzyeq-jaccard.aql

@@ -0,0 +1,41 @@
+/*
+ * Description    : Fuzzy joins two datasets, Customer and Customer2, based on ~= using Jaccard of their interest lists.
+ *                  Customers has a keyword index on interests, and we expect the join to be transformed into an indexed nested-loop join.
+ *                  We expect the top-level equi join introduced because of surrogate optimization to be removed, since it is not necessary.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: [string],
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+  
+create dataset Customers2(CustomerType) primary key cid;
+
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-join-noeqjoin_olist-fuzzyeq-jaccard.adm";
+
+set simfunction 'jaccard';
+set simthreshold '0.7f';
+
+for $a in dataset('Customers')
+for $b in dataset('Customers2')
+where $a.interests /*+ indexnl */ ~= $b.interests and $a.cid < $b.cid
+return {"ainterests": $a.interests, "binterests": $b.interests}

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/olist-jaccard-inline.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/olist-jaccard-inline.aql
new file mode 100644
index 0000000..7dca72a
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/olist-jaccard-inline.aql

@@ -0,0 +1,38 @@
+/*
+ * Description    : Fuzzy self joins a dataset, Customers, based on the similarity-jaccard function of its interest lists.
+ *                  Customers has a keyword index on interests, 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.
+ *                  We expect the top-level equi join introduced because of surrogate optimization to be removed, since it is not necessary.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: [string],
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+  
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-join-noeqjoin_olist-jaccard-inline.adm";
+
+for $a in dataset('Customers')
+for $b in dataset('Customers')
+let $jacc := /*+ indexnl */ similarity-jaccard($a.interests, $b.interests)
+where $jacc >= 0.7f and $a.cid < $b.cid
+return {"ainterests": $a.interests, "binterests": $b.interests, "jacc": $jacc }

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/olist-jaccard.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/olist-jaccard.aql
new file mode 100644
index 0000000..79d8baf
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/olist-jaccard.aql

@@ -0,0 +1,38 @@
+/*
+ * Description    : Fuzzy joins two datasets, Customer and Customer2, based on the similarity-jaccard function of their interest lists.
+ *                  Customers has a keyword index on interests, and we expect the join to be transformed into an indexed nested-loop join.
+ *                  We expect the top-level equi join introduced because of surrogate optimization to be removed, since it is not necessary.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: [string],
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+  
+create dataset Customers2(CustomerType) primary key cid;
+
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-join-noeqjoin_olist-jaccard.adm";
+
+for $a in dataset('Customers')
+for $b in dataset('Customers2')
+where /*+ indexnl */ similarity-jaccard($a.interests, $b.interests) >= 0.7f and $a.cid < $b.cid
+return {"ainterests": $a.interests, "binterests": $b.interests}

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/ulist-fuzzyeq-jaccard.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/ulist-fuzzyeq-jaccard.aql
new file mode 100644
index 0000000..0efb32d
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/ulist-fuzzyeq-jaccard.aql

@@ -0,0 +1,41 @@
+/*
+ * Description    : Fuzzy joins two datasets, Customer and Customer2, based on ~= using Jaccard of their interest sets.
+ *                  Customers has a keyword index on interests, and we expect the join to be transformed into an indexed nested-loop join.
+ *                  We expect the top-level equi join introduced because of surrogate optimization to be removed, since it is not necessary.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: {{string}},
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+  
+create dataset Customers2(CustomerType) primary key cid;
+
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-join-noeqjoin_ulist-fuzzyeq-jaccard.adm";
+
+set simfunction 'jaccard';
+set simthreshold '0.7f';
+
+for $a in dataset('Customers')
+for $b in dataset('Customers2')
+where $a.interests /*+ indexnl */ ~= $b.interests and $a.cid < $b.cid
+return {"ainterests": $a.interests, "binterests": $b.interests}

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/ulist-jaccard-inline.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/ulist-jaccard-inline.aql
new file mode 100644
index 0000000..2bca24d
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/ulist-jaccard-inline.aql

@@ -0,0 +1,38 @@
+/*
+ * Description    : Fuzzy self joins a dataset, Customers, based on the similarity-jaccard function of its interest sets.
+ *                  Customers has a keyword index on interests, 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.
+ *                  We expect the top-level equi join introduced because of surrogate optimization to be removed, since it is not necessary.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: {{string}},
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+  
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-join-noeqjoin_ulist-jaccard-inline.adm";
+
+for $a in dataset('Customers')
+for $b in dataset('Customers')
+let $jacc := /*+ indexnl */ similarity-jaccard($a.interests, $b.interests)
+where $jacc >= 0.7f and $a.cid < $b.cid
+return {"ainterests": $a.interests, "binterests": $b.interests, "jacc": $jacc}

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/ulist-jaccard.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/ulist-jaccard.aql
new file mode 100644
index 0000000..8805542
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/ulist-jaccard.aql

@@ -0,0 +1,38 @@
+/*
+ * Description    : Fuzzy joins two datasets, Customer and Customer2, based on the similarity-jaccard function of their interest sets.
+ *                  Customers has a keyword index on interests, and we expect the join to be transformed into an indexed nested-loop join.
+ *                  We expect the top-level equi join introduced because of surrogate optimization to be removed, since it is not necessary.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: {{string}},
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+  
+create dataset Customers2(CustomerType) primary key cid;
+
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-join-noeqjoin_ulist-jaccard.adm";
+
+for $a in dataset('Customers')
+for $b in dataset('Customers2')
+where /*+ indexnl */ similarity-jaccard($a.interests, $b.interests) >= 0.7f and $a.cid < $b.cid
+return {"ainterests": $a.interests, "binterests": $b.interests}

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/word-fuzzyeq-jaccard.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/word-fuzzyeq-jaccard.aql
new file mode 100644
index 0000000..2d2e0cc
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/word-fuzzyeq-jaccard.aql

@@ -0,0 +1,42 @@
+/*
+ * Description    : Fuzzy joins two datasets, DBLP and CSX, based on ~= using Jaccard of their titles' word tokens.
+ *                  DBLP has a keyword index on title, and we expect the join to be transformed into an indexed nested-loop join.
+ *                  We expect the top-level equi join introduced because of surrogate optimization to be removed, since it is not necessary.
+ * 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) primary key id;
+
+create dataset CSX(CSXType) primary key id;
+
+create index keyword_index on DBLP(title) type keyword;
+
+write output to nc1:"rttest/inverted-index-join-noeqjoin_word-fuzzyeq-jaccard.adm";
+
+set simfunction 'jaccard';
+set simthreshold '0.5f';
+
+for $a in dataset('DBLP')
+for $b in dataset('CSX')
+where word-tokens($a.title) ~= word-tokens($b.title) and $a.id < $b.id
+return {"atitle": $a.title, "btitle": $b.title}

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/word-jaccard-inline.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/word-jaccard-inline.aql
new file mode 100644
index 0000000..0d5bf9c
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/word-jaccard-inline.aql

@@ -0,0 +1,31 @@
+/*
+ * Description    : Fuzzy self joins a dataset, DBLP, based on the similarity-jaccard function of its titles' word tokens.
+ *                  DBLP has a keyword 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.
+ *                  We expect the top-level equi join introduced because of surrogate optimization to be removed, since it is not necessary.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+create index keyword_index on DBLP(title) type keyword;
+
+write output to nc1:"rttest/inverted-index-join-noeqjoin_word-jaccard-inline.adm";
+
+for $a in dataset('DBLP')
+for $b in dataset('DBLP')
+let $jacc := similarity-jaccard(word-tokens($a.title), word-tokens($b.title))
+where $jacc >= 0.5f and $a.id < $b.id
+return {"atitle": $a.title, "btitle": $b.title, "jacc": $jacc}

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/word-jaccard.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/word-jaccard.aql
new file mode 100644
index 0000000..5ffa92e
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/word-jaccard.aql

@@ -0,0 +1,41 @@
+/*
+ * Description    : Fuzzy joins two datasets, DBLP and CSX, based on the similarity-jaccard function of their titles' word tokens.
+ *                  DBLP has a keyword index on title, and we expect the join to be transformed into an indexed nested-loop join.
+ *                  We expect the top-level equi join introduced because of surrogate optimization to be removed, since it is not necessary.
+ * 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) primary key id;
+
+create dataset CSX(CSXType) primary key id;
+
+create index keyword_index on DBLP(title) type keyword;
+
+write output to nc1:"rttest/inverted-index-join-noeqjoin_word-jaccard.adm";
+
+for $a in dataset('DBLP')
+for $b in dataset('CSX')
+where similarity-jaccard(word-tokens($a.title), word-tokens($b.title)) >= 0.5f
+      and $a.id < $b.id
+return {"atitle": $a.title, "btitle": $b.title}
+

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-edit-distance-check_01.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-edit-distance-check_01.aql
new file mode 100644
index 0000000..d24ee17
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-edit-distance-check_01.aql

@@ -0,0 +1,38 @@
+/*
+ * Description    : Fuzzy joins two datasets, DBLP and CSX, based on the edit-distance-check function of their authors.
+ *                  DBLP has a 3-gram index on authors, and we expect the join to be transformed into an indexed nested-loop join.
+ * 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) primary key id;
+
+create dataset CSX(CSXType) primary key id;
+
+create index ngram_index on DBLP(authors) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-join_ngram-edit-distance-check_01.adm";
+
+for $a in dataset('DBLP')
+for $b in dataset('CSX')
+where edit-distance-check($a.authors, $b.authors, 3)[0] and $a.id < $b.id
+return {"arec": $a, "brec": $b }
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-edit-distance-check_02.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-edit-distance-check_02.aql
new file mode 100644
index 0000000..ec553a0
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-edit-distance-check_02.aql

@@ -0,0 +1,38 @@
+/*
+ * Description    : Fuzzy joins two datasets, DBLP and CSX, based on the edit-distance-check function of their authors.
+ *                  CSX has a 3-gram index on authors, and we expect the join to be transformed into an indexed nested-loop join.
+ * 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) primary key id;
+
+create dataset CSX(CSXType) primary key id;
+
+create index ngram_index on CSX(authors) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-join_ngram-edit-distance-check_02.adm";
+
+for $a in dataset('DBLP')
+for $b in dataset('CSX')
+where edit-distance-check($a.authors, $b.authors, 3)[0] and $a.id < $b.id
+return {"arec": $a, "brec": $b }
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-edit-distance-check_03.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-edit-distance-check_03.aql
new file mode 100644
index 0000000..4de1680
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-edit-distance-check_03.aql

@@ -0,0 +1,28 @@
+/*
+ * Description    : Fuzzy self joins a dataset, DBLP, based on the edit-distance-check function of its authors.
+ *                  DBLP has a 3-gram index on authors, and we expect the join to be transformed into an indexed nested-loop join.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+create index ngram_index on DBLP(authors) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-join_ngram-edit-distance-check_03.adm";
+
+for $a in dataset('DBLP')
+for $b in dataset('DBLP')
+where edit-distance-check($a.authors, $b.authors, 3)[0] and $a.id < $b.id
+return {"arec": $a, "brec": $b }
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-edit-distance-check_04.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-edit-distance-check_04.aql
new file mode 100644
index 0000000..091676f
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-edit-distance-check_04.aql

@@ -0,0 +1,30 @@
+/*
+ * Description    : Fuzzy self joins a dataset, DBLP, based on the edit-distance-check function of its authors.
+ *                  DBLP has a 3-gram index on authors, 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 dataset DBLP(DBLPType) primary key id;
+
+create index ngram_index on DBLP(authors) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-join_ngram-edit-distance-check_04.adm";
+
+for $a in dataset('DBLP')
+for $b in dataset('DBLP')
+let $ed := edit-distance-check($a.authors, $b.authors, 3)
+where $ed[0] and $a.id < $b.id
+return {"arec": $a, "brec": $b, "ed": $ed[1] }
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-edit-distance_01.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-edit-distance_01.aql
new file mode 100644
index 0000000..8a0282c
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-edit-distance_01.aql

@@ -0,0 +1,38 @@
+/*
+ * Description    : Fuzzy joins two datasets, DBLP and CSX, based on the edit-distance function of their authors.
+ *                  DBLP has a 3-gram index on authors, and we expect the join to be transformed into an indexed nested-loop join.
+ * 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) primary key id;
+
+create dataset CSX(CSXType) primary key id;
+
+create index ngram_index on DBLP(authors) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-join_ngram-edit-distance_01.adm";
+
+for $a in dataset('DBLP')
+for $b in dataset('CSX')
+where edit-distance($a.authors, $b.authors) < 3 and $a.id < $b.id
+return {"arec": $a, "brec": $b }
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-edit-distance_02.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-edit-distance_02.aql
new file mode 100644
index 0000000..5d026db
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-edit-distance_02.aql

@@ -0,0 +1,38 @@
+/*
+ * Description    : Fuzzy joins two datasets, DBLP and CSX, based on the edit-distance function of their authors.
+ *                  CSX has a 3-gram index on authors, and we expect the join to be transformed into an indexed nested-loop join.
+ * 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) primary key id;
+
+create dataset CSX(CSXType) primary key id;
+
+create index ngram_index on CSX(authors) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-join_ngram-edit-distance_02.adm";
+
+for $a in dataset('DBLP')
+for $b in dataset('CSX')
+where edit-distance($a.authors, $b.authors) < 3 and $a.id < $b.id
+return {"arec": $a, "brec": $b }
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-edit-distance_03.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-edit-distance_03.aql
new file mode 100644
index 0000000..11b39c5
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-edit-distance_03.aql

@@ -0,0 +1,28 @@
+/*
+ * Description    : Fuzzy self joins a dataset, DBLP, based on the edit-distance function of its authors.
+ *                  DBLP has a 3-gram index on authors, and we expect the join to be transformed into an indexed nested-loop join.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+create index ngram_index on DBLP(authors) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-join_ngram-edit-distance_03.adm";
+
+for $a in dataset('DBLP')
+for $b in dataset('DBLP')
+where edit-distance($a.authors, $b.authors) < 3 and $a.id < $b.id
+return {"arec": $a, "brec": $b }
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-edit-distance_04.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-edit-distance_04.aql
new file mode 100644
index 0000000..b8952e9
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-edit-distance_04.aql

@@ -0,0 +1,30 @@
+/*
+ * Description    : Fuzzy self joins a dataset, DBLP, based on the edit-distance function of its authors.
+ *                  DBLP has a 3-gram index on authors, 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 dataset DBLP(DBLPType) primary key id;
+
+create index ngram_index on DBLP(authors) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-join_ngram-edit-distance_03.adm";
+
+for $a in dataset('DBLP')
+for $b in dataset('DBLP')
+let $ed := edit-distance($a.authors, $b.authors)
+where $ed < 3 and $a.id < $b.id
+return {"arec": $a, "brec": $b, "ed": $ed}
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-fuzzyeq-edit-distance_01.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-fuzzyeq-edit-distance_01.aql
new file mode 100644
index 0000000..4704213
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-fuzzyeq-edit-distance_01.aql

@@ -0,0 +1,41 @@
+/*
+ * Description    : Fuzzy joins two datasets, DBLP and CSX, based on ~= using edit distance of their authors.
+ *                  DBLP has a 3-gram index on authors, and we expect the join to be transformed into an indexed nested-loop join.
+ * 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) primary key id;
+
+create dataset CSX(CSXType) primary key id;
+
+create index ngram_index on CSX(authors) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-join_ngram-fuzzyeq-edit-distance_01.adm";
+
+set simfunction 'edit-distance';
+set simthreshold '3';
+
+for $a in dataset('DBLP')
+for $b in dataset('CSX')
+where $a.authors ~= $b.authors and $a.id < $b.id
+return {"arec": $a, "brec": $b }
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-fuzzyeq-edit-distance_02.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-fuzzyeq-edit-distance_02.aql
new file mode 100644
index 0000000..8454be9
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-fuzzyeq-edit-distance_02.aql

@@ -0,0 +1,41 @@
+/*
+ * Description    : Fuzzy joins two datasets, DBLP and CSX, based on ~= using edit distance of their authors.
+ *                  CSX has a 3-gram index on authors, and we expect the join to be transformed into an indexed nested-loop join.
+ * 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) primary key id;
+
+create dataset CSX(CSXType) primary key id;
+
+create index ngram_index on DBLP(authors) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-join_ngram-fuzzyeq-edit-distance_01.adm";
+
+set simfunction 'edit-distance';
+set simthreshold '3';
+
+for $a in dataset('DBLP')
+for $b in dataset('CSX')
+where $a.authors ~= $b.authors and $a.id < $b.id
+return {"arec": $a, "brec": $b }
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-fuzzyeq-edit-distance_03.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-fuzzyeq-edit-distance_03.aql
new file mode 100644
index 0000000..4187d8f
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-fuzzyeq-edit-distance_03.aql

@@ -0,0 +1,30 @@
+/*
+ * Description    : Fuzzy self joins a dataset, DBLP, based on ~= using edit distance of its authors.
+ *                  DBLP has a 3-gram index on authors, and we expect the join to be transformed into an indexed nested-loop join.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+create index ngram_index on DBLP(authors) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-join_ngram-fuzzyeq-edit-distance_03.adm";
+
+set simfunction 'edit-distance';
+set simthreshold '3';
+
+for $a in dataset('DBLP')
+for $b in dataset('DBLP')
+where $a.authors ~= $b.authors and $a.id < $b.id
+return {"arec": $a, "brec": $b }
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-fuzzyeq-jaccard_01.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-fuzzyeq-jaccard_01.aql
new file mode 100644
index 0000000..84fb8f3
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-fuzzyeq-jaccard_01.aql

@@ -0,0 +1,41 @@
+/*
+ * Description    : Fuzzy joins two datasets, DBLP and CSX, based on ~= using Jaccard 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.
+ * 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) primary key id;
+
+create dataset CSX(CSXType) primary key id;
+
+create index ngram_index on DBLP(title) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-join_ngram-fuzzyeq-jaccard_01.adm";
+
+set simfunction 'jaccard';
+set simthreshold '0.5f';
+
+for $a in dataset('DBLP')
+for $b in dataset('CSX')
+where gram-tokens($a.title, 3, false) ~= gram-tokens($b.title, 3, false) and $a.id < $b.id
+return {"arec": $a, "brec": $b }
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-fuzzyeq-jaccard_02.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-fuzzyeq-jaccard_02.aql
new file mode 100644
index 0000000..d0c3c6f
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-fuzzyeq-jaccard_02.aql

@@ -0,0 +1,41 @@
+/*
+ * Description    : Fuzzy joins two datasets, DBLP and CSX, based on ~= using Jaccard their titles' 3-gram tokens.
+ *                  CSX has a 3-gram index on title, and we expect the join to be transformed into an indexed nested-loop join.
+ * 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) primary key id;
+
+create dataset CSX(CSXType) primary key id;
+
+create index ngram_index on CSX(title) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-join_ngram-fuzzyeq-jaccard_02.adm";
+
+set simfunction 'jaccard';
+set simthreshold '0.5f';
+
+for $a in dataset('DBLP')
+for $b in dataset('CSX')
+where gram-tokens($a.title, 3, false) ~= gram-tokens($b.title, 3, false) and $a.id < $b.id
+return {"arec": $a, "brec": $b }
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-fuzzyeq-jaccard_03.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-fuzzyeq-jaccard_03.aql
new file mode 100644
index 0000000..a725edc
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-fuzzyeq-jaccard_03.aql

@@ -0,0 +1,31 @@
+/*
+ * Description    : Fuzzy self joins a dataset, DBLP, based on ~= using Jaccard of its 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.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+create index ngram_index on DBLP(title) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-join_ngram-fuzzyeq-jaccard_03.adm";
+
+set simfunction 'jaccard';
+set simthreshold '0.5f';
+
+for $a in dataset('DBLP')
+for $b in dataset('DBLP')
+where gram-tokens($a.title, 3, false) ~= gram-tokens($b.title, 3, false) and $a.id < $b.id
+return {"arec": $a, "brec": $b }
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-jaccard-check_01.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-jaccard-check_01.aql
new file mode 100644
index 0000000..c25e2e3
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-jaccard-check_01.aql

@@ -0,0 +1,39 @@
+/*
+ * Description    : Fuzzy joins two datasets, DBLP and CSX, based on the similarity-jaccard-check 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.
+ * 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) primary key id;
+
+create dataset CSX(CSXType) primary key id;
+
+create index ngram_index on DBLP(title) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-join_ngram-jaccard-check_01.adm";
+
+for $a in dataset('DBLP')
+for $b in dataset('CSX')
+where similarity-jaccard-check(gram-tokens($a.title, 3, false), gram-tokens($b.title, 3, false), 0.5f)[0]
+      and $a.id < $b.id
+return {"arec": $a, "brec": $b }
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-jaccard-check_02.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-jaccard-check_02.aql
new file mode 100644
index 0000000..0e9f4d5
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-jaccard-check_02.aql

@@ -0,0 +1,39 @@
+/*
+ * Description    : Fuzzy joins two datasets, DBLP and CSX, based the similarity-jaccard-check function of their titles' 3-gram tokens.
+ *                  CSX has a 3-gram index on title, and we expect the join to be transformed into an indexed nested-loop join.
+ * 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) primary key id;
+
+create dataset CSX(CSXType) primary key id;
+
+create index ngram_index on CSX(title) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-join_ngram-jaccard-check_02.adm";
+
+for $a in dataset('DBLP')
+for $b in dataset('CSX')
+where similarity-jaccard-check(gram-tokens($a.title, 3, false), gram-tokens($b.title, 3, false), 0.5f)[0]
+      and $a.id < $b.id
+return {"arec": $a, "brec": $b }
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-jaccard-check_03.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-jaccard-check_03.aql
new file mode 100644
index 0000000..bbd0f51
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-jaccard-check_03.aql

@@ -0,0 +1,29 @@
+/*
+ * Description    : Fuzzy self joins a dataset, DBLP, based on the similarity-jaccard-check function of its 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.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+create index ngram_index on DBLP(title) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-join_ngram-jaccard-check_03.adm";
+
+for $a in dataset('DBLP')
+for $b in dataset('DBLP')
+where similarity-jaccard-check(gram-tokens($a.title, 3, false), gram-tokens($b.title, 3, false), 0.5f)[0]
+      and $a.id < $b.id
+return {"arec": $a, "brec": $b }
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-jaccard-check_04.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-jaccard-check_04.aql
new file mode 100644
index 0000000..956f712
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-jaccard-check_04.aql

@@ -0,0 +1,30 @@
+/*
+ * Description    : Fuzzy self joins a dataset, DBLP, based on the similarity-jaccard-check function of its 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 dataset DBLP(DBLPType) primary key id;
+
+create index ngram_index on DBLP(title) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-join_ngram-jaccard-check_04.adm";
+
+for $a in dataset('DBLP')
+for $b in dataset('DBLP')
+let $jacc := similarity-jaccard-check(gram-tokens($a.title, 3, false), gram-tokens($b.title, 3, false), 0.5f)
+where $jacc[0] and $a.id < $b.id
+return {"arec": $a, "brec": $b, "jacc": $jacc[1] }
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-jaccard_01.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-jaccard_01.aql
new file mode 100644
index 0000000..742cb69
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-jaccard_01.aql

@@ -0,0 +1,39 @@
+/*
+ * 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.
+ * 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) primary key id;
+
+create dataset CSX(CSXType) primary key id;
+
+create index ngram_index on DBLP(title) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-join_ngram-jaccard_01.adm";
+
+for $a in dataset('DBLP')
+for $b in dataset('CSX')
+where similarity-jaccard(gram-tokens($a.title, 3, false), gram-tokens($b.title, 3, false)) >= 0.5f
+      and $a.id < $b.id
+return {"arec": $a, "brec": $b }
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-jaccard_02.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-jaccard_02.aql
new file mode 100644
index 0000000..a620399
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-jaccard_02.aql

@@ -0,0 +1,39 @@
+/*
+ * Description    : Fuzzy joins two datasets, DBLP and CSX, based the similarity-jaccard function of their titles' 3-gram tokens.
+ *                  CSX has a 3-gram index on title, and we expect the join to be transformed into an indexed nested-loop join.
+ * 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) primary key id;
+
+create dataset CSX(CSXType) primary key id;
+
+create index ngram_index on CSX(title) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-join_ngram-jaccard_02.adm";
+
+for $a in dataset('DBLP')
+for $b in dataset('CSX')
+where similarity-jaccard(gram-tokens($a.title, 3, false), gram-tokens($b.title, 3, false)) >= 0.5f
+      and $a.id < $b.id
+return {"arec": $a, "brec": $b }
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-jaccard_03.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-jaccard_03.aql
new file mode 100644
index 0000000..d12bf98
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-jaccard_03.aql

@@ -0,0 +1,29 @@
+/*
+ * Description    : Fuzzy self joins a dataset, DBLP, based on the similarity-jaccard function of its 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.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+create index ngram_index on DBLP(title) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-join_ngram-jaccard_03.adm";
+
+for $a in dataset('DBLP')
+for $b in dataset('DBLP')
+where similarity-jaccard(gram-tokens($a.title, 3, false), gram-tokens($b.title, 3, false)) >= 0.5f
+      and $a.id < $b.id
+return {"arec": $a, "brec": $b }
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-jaccard_04.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-jaccard_04.aql
new file mode 100644
index 0000000..6b308c8
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ngram-jaccard_04.aql

@@ -0,0 +1,30 @@
+/*
+ * Description    : Fuzzy self joins a dataset, DBLP, based on the similarity-jaccard function of its 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 dataset DBLP(DBLPType) primary key id;
+
+create index ngram_index on DBLP(title) type ngram(3);
+
+write output to nc1:"rttest/inverted-index-join_ngram-jaccard_04.adm";
+
+for $a in dataset('DBLP')
+for $b in dataset('DBLP')
+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
+return {"arec": $a, "brec": $b, "jacc": $jacc }
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-edit-distance-check_01.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-edit-distance-check_01.aql
new file mode 100644
index 0000000..1afe025
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-edit-distance-check_01.aql

@@ -0,0 +1,37 @@
+/*
+ * Description    : Fuzzy joins two datasets, Customer and Customer2, based on the edit-distance-check function of their interest lists.
+ *                  Customers has a keyword index on interests, and we expect the join to be transformed into an indexed nested-loop join.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: [string],
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+  
+create dataset Customers2(CustomerType) primary key cid;
+
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-join_olist-edit-distance-check_01.adm";
+
+for $a in dataset('Customers')
+for $b in dataset('Customers2')
+where edit-distance-check($a.interests, $b.interests, 3)[0] and $a.cid < $b.cid
+return {"arec": $a, "brec": $b }

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-edit-distance-check_02.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-edit-distance-check_02.aql
new file mode 100644
index 0000000..aec4c85
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-edit-distance-check_02.aql

@@ -0,0 +1,37 @@
+/*
+ * Description    : Fuzzy joins two datasets, Customer and Customer2, based on the edit-distance-check function of their interest lists.
+ *                  Customers2 has a keyword index on interests, and we expect the join to be transformed into an indexed nested-loop join.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: [string],
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+  
+create dataset Customers2(CustomerType) primary key cid;
+
+create index interests_index on Customers2(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-join_olist-edit-distance-check_02.adm";
+
+for $a in dataset('Customers')
+for $b in dataset('Customers2')
+where edit-distance-check($a.interests, $b.interests, 3)[0] and $a.cid < $b.cid
+return {"arec": $a, "brec": $b }

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-edit-distance-check_03.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-edit-distance-check_03.aql
new file mode 100644
index 0000000..47cea17
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-edit-distance-check_03.aql

@@ -0,0 +1,35 @@
+/*
+ * Description    : Fuzzy self joins a dataset, Customers, based on the edit-distance-check function of its interest lists.
+ *                  Customers has a keyword index on interests, and we expect the join to be transformed into an indexed nested-loop join.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: [string],
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+  
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-join_olist-edit-distance-check_03.adm";
+
+for $a in dataset('Customers')
+for $b in dataset('Customers')
+where edit-distance-check($a.interests, $b.interests, 3)[0] and $a.cid < $b.cid
+return {"arec": $a, "brec": $b }

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-edit-distance-check_04.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-edit-distance-check_04.aql
new file mode 100644
index 0000000..9abc4e8
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-edit-distance-check_04.aql

@@ -0,0 +1,37 @@
+/*
+ * Description    : Fuzzy self joins a dataset, Customers, based on the edit-distance-check function of its interest lists.
+ *                  Customers has a keyword index on interests, 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 AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: [string],
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+  
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-join_olist-edit-distance-check_04.adm";
+
+for $a in dataset('Customers')
+for $b in dataset('Customers')
+let $ed := edit-distance-check($a.interests, $b.interests, 3)
+where $ed[0] and $a.cid < $b.cid
+return {"arec": $a, "brec": $b, "ed": $ed[1] }

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-edit-distance_01.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-edit-distance_01.aql
new file mode 100644
index 0000000..b8f6144
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-edit-distance_01.aql

@@ -0,0 +1,37 @@
+/*
+ * Description    : Fuzzy joins two datasets, Customer and Customer2, based on the edit-distance function of their interest lists.
+ *                  Customers has a keyword index on interests, and we expect the join to be transformed into an indexed nested-loop join.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: [string],
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+  
+create dataset Customers2(CustomerType) primary key cid;
+
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-join_olist-edit-distance_01.adm";
+
+for $a in dataset('Customers')
+for $b in dataset('Customers2')
+where edit-distance($a.interests, $b.interests) <= 2 and $a.cid < $b.cid
+return {"arec": $a, "brec": $b }

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-edit-distance_02.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-edit-distance_02.aql
new file mode 100644
index 0000000..7b17749
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-edit-distance_02.aql

@@ -0,0 +1,37 @@
+/*
+ * Description    : Fuzzy joins two datasets, Customer and Customer2, based on the edit-distance function of their interest lists.
+ *                  Customers2 has a keyword index on interests, and we expect the join to be transformed into an indexed nested-loop join.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: [string],
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+  
+create dataset Customers2(CustomerType) primary key cid;
+
+create index interests_index on Customers2(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-join_olist-edit-distance_02.adm";
+
+for $a in dataset('Customers')
+for $b in dataset('Customers2')
+where edit-distance($a.interests, $b.interests) <= 2 and $a.cid < $b.cid
+return {"arec": $a, "brec": $b }

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-edit-distance_03.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-edit-distance_03.aql
new file mode 100644
index 0000000..7132950
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-edit-distance_03.aql

@@ -0,0 +1,35 @@
+/*
+ * Description    : Fuzzy self joins a dataset, Customers, based on the edit-distance function of its interest lists.
+ *                  Customers has a keyword index on interests, and we expect the join to be transformed into an indexed nested-loop join.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: [string],
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+  
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-join_olist-edit-distance_03.adm";
+
+for $a in dataset('Customers')
+for $b in dataset('Customers')
+where edit-distance($a.interests, $b.interests) <= 2 and $a.cid < $b.cid
+return {"arec": $a, "brec": $b }

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-edit-distance_04.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-edit-distance_04.aql
new file mode 100644
index 0000000..84c7d5b
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-edit-distance_04.aql

@@ -0,0 +1,37 @@
+/*
+ * Description    : Fuzzy self joins a dataset, Customers, based on the edit-distance function of its interest lists.
+ *                  Customers has a keyword index on interests, 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 AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: [string],
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+  
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-join_olist-edit-distance_04.adm";
+
+for $a in dataset('Customers')
+for $b in dataset('Customers')
+let $ed := edit-distance($a.interests, $b.interests)
+where $ed <= 2 and $a.cid < $b.cid
+return {"arec": $a, "brec": $b, "ed": $ed }

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-fuzzyeq-edit-distance_01.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-fuzzyeq-edit-distance_01.aql
new file mode 100644
index 0000000..c84bd28
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-fuzzyeq-edit-distance_01.aql

@@ -0,0 +1,40 @@
+/*
+ * Description    : Fuzzy joins two datasets, Customer and Customer2, based on ~= using edit distance of their interest lists.
+ *                  Customers has a keyword index on interests, and we expect the join to be transformed into an indexed nested-loop join.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: [string],
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+  
+create dataset Customers2(CustomerType) primary key cid;
+
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-join_olist-fuzzyeq-jaccard_01.adm";
+
+set simfunction 'edit-distance';
+set simthreshold '3';
+
+for $a in dataset('Customers')
+for $b in dataset('Customers2')
+where $a.interests ~= $b.interests and $a.cid < $b.cid
+return {"arec": $a, "brec": $b }

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-fuzzyeq-edit-distance_02.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-fuzzyeq-edit-distance_02.aql
new file mode 100644
index 0000000..c6b9d9c
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-fuzzyeq-edit-distance_02.aql

@@ -0,0 +1,40 @@
+/*
+ * Description    : Fuzzy joins two datasets, Customer and Customer2, based on ~= using edit distance of their interest lists.
+ *                  Customers2 has a keyword index on interests, and we expect the join to be transformed into an indexed nested-loop join.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: [string],
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+  
+create dataset Customers2(CustomerType) primary key cid;
+
+create index interests_index on Customers2(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-join_olist-fuzzyeq-jaccard_02.adm";
+
+set simfunction 'edit-distance';
+set simthreshold '3';
+
+for $a in dataset('Customers')
+for $b in dataset('Customers2')
+where $a.interests ~= $b.interests and $a.cid < $b.cid
+return {"arec": $a, "brec": $b }

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-fuzzyeq-edit-distance_03.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-fuzzyeq-edit-distance_03.aql
new file mode 100644
index 0000000..962f05c
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-fuzzyeq-edit-distance_03.aql

@@ -0,0 +1,38 @@
+/*
+ * Description    : Fuzzy self joins a dataset, Customers, based on ~= using edit distance of its interest lists.
+ *                  Customers has a keyword index on interests, and we expect the join to be transformed into an indexed nested-loop join.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: [string],
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+  
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-join_olist-fuzzyeq-jaccard_03.adm";
+
+set simfunction 'edit-distance';
+set simthreshold '3';
+
+for $a in dataset('Customers')
+for $b in dataset('Customers')
+where $a.interests ~= $b.interests and $a.cid < $b.cid
+return {"arec": $a, "brec": $b }

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-fuzzyeq-jaccard_01.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-fuzzyeq-jaccard_01.aql
new file mode 100644
index 0000000..4b3793a
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-fuzzyeq-jaccard_01.aql

@@ -0,0 +1,40 @@
+/*
+ * Description    : Fuzzy joins two datasets, Customer and Customer2, based on ~= using Jaccard of their interest lists.
+ *                  Customers has a keyword index on interests, and we expect the join to be transformed into an indexed nested-loop join.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: [string],
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+  
+create dataset Customers2(CustomerType) primary key cid;
+
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-join_olist-fuzzyeq-jaccard_01.adm";
+
+set simfunction 'jaccard';
+set simthreshold '0.7f';
+
+for $a in dataset('Customers')
+for $b in dataset('Customers2')
+where $a.interests /*+ indexnl */ ~= $b.interests and $a.cid < $b.cid
+return {"arec": $a, "brec": $b }

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-fuzzyeq-jaccard_02.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-fuzzyeq-jaccard_02.aql
new file mode 100644
index 0000000..60cdb07
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-fuzzyeq-jaccard_02.aql

@@ -0,0 +1,40 @@
+/*
+ * Description    : Fuzzy joins two datasets, Customer and Customer2, based on ~= using Jaccard of their interest lists.
+ *                  Customers2 has a keyword index on interests, and we expect the join to be transformed into an indexed nested-loop join.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: [string],
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+  
+create dataset Customers2(CustomerType) primary key cid;
+
+create index interests_index on Customers2(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-join_olist-fuzzyeq-jaccard_02.adm";
+
+set simfunction 'jaccard';
+set simthreshold '0.7f';
+
+for $a in dataset('Customers')
+for $b in dataset('Customers2')
+where $a.interests /*+ indexnl */ ~= $b.interests and $a.cid < $b.cid
+return {"arec": $a, "brec": $b }

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-fuzzyeq-jaccard_03.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-fuzzyeq-jaccard_03.aql
new file mode 100644
index 0000000..2df41b5
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-fuzzyeq-jaccard_03.aql

@@ -0,0 +1,38 @@
+/*
+ * Description    : Fuzzy self joins a dataset, Customers, based on ~= using Jaccard of its interest lists.
+ *                  Customers has a keyword index on interests, and we expect the join to be transformed into an indexed nested-loop join.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: [string],
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+  
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-join_olist-fuzzyeq-jaccard_03.adm";
+
+set simfunction 'jaccard';
+set simthreshold '0.7f';
+
+for $a in dataset('Customers')
+for $b in dataset('Customers')
+where $a.interests /*+ indexnl */ ~= $b.interests and $a.cid < $b.cid
+return {"arec": $a, "brec": $b }

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-jaccard-check_01.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-jaccard-check_01.aql
new file mode 100644
index 0000000..8968ec6
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-jaccard-check_01.aql

@@ -0,0 +1,37 @@
+/*
+ * Description    : Fuzzy joins two datasets, Customer and Customer2, based on the similarity-jaccard-check function of their interest lists.
+ *                  Customers has a keyword index on interests, and we expect the join to be transformed into an indexed nested-loop join.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: [string],
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+  
+create dataset Customers2(CustomerType) primary key cid;
+
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-join_olist-jaccard-check_01.adm";
+
+for $a in dataset('Customers')
+for $b in dataset('Customers2')
+where /*+ indexnl */ similarity-jaccard-check($a.interests, $b.interests, 0.7f)[0] and $a.cid < $b.cid
+return {"arec": $a, "brec": $b }

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-jaccard-check_02.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-jaccard-check_02.aql
new file mode 100644
index 0000000..96b8622
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-jaccard-check_02.aql

@@ -0,0 +1,37 @@
+/*
+ * Description    : Fuzzy joins two datasets, Customer and Customer2, based on the similarity-jaccard-check function of their interest lists.
+ *                  Customers2 has a keyword index on interests, and we expect the join to be transformed into an indexed nested-loop join.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: [string],
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+  
+create dataset Customers2(CustomerType) primary key cid;
+
+create index interests_index on Customers2(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-join_olist-jaccard-check_02.adm";
+
+for $a in dataset('Customers')
+for $b in dataset('Customers2')
+where /*+ indexnl */ similarity-jaccard-check($a.interests, $b.interests, 0.7f)[0] and $a.cid < $b.cid
+return {"arec": $a, "brec": $b }

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-jaccard-check_03.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-jaccard-check_03.aql
new file mode 100644
index 0000000..e8763b4
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-jaccard-check_03.aql

@@ -0,0 +1,35 @@
+/*
+ * Description    : Fuzzy self joins a dataset, Customers, based on the similarity-jaccard-check function of its interest lists.
+ *                  Customers has a keyword index on interests, and we expect the join to be transformed into an indexed nested-loop join.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: [string],
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+  
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-join_olist-jaccard-check_03.adm";
+
+for $a in dataset('Customers')
+for $b in dataset('Customers')
+where /*+ indexnl */ similarity-jaccard-check($a.interests, $b.interests, 0.7f)[0] and $a.cid < $b.cid
+return {"arec": $a, "brec": $b }

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-jaccard-check_04.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-jaccard-check_04.aql
new file mode 100644
index 0000000..3194e47
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-jaccard-check_04.aql

@@ -0,0 +1,37 @@
+/*
+ * Description    : Fuzzy self joins a dataset, Customers, based on the similarity-jaccard-check function of its interest lists.
+ *                  Customers has a keyword index on interests, 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 AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: [string],
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+  
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-join_olist-jaccard-check_04.adm";
+
+for $a in dataset('Customers')
+for $b in dataset('Customers')
+let $jacc := /*+ indexnl */ similarity-jaccard-check($a.interests, $b.interests, 0.7f)
+where $jacc[0] and $a.cid < $b.cid
+return {"arec": $a, "brec": $b, "jacc": $jacc[1] }

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-jaccard_01.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-jaccard_01.aql
new file mode 100644
index 0000000..1c4c7c2
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-jaccard_01.aql

@@ -0,0 +1,37 @@
+/*
+ * Description    : Fuzzy joins two datasets, Customer and Customer2, based on the similarity-jaccard function of their interest lists.
+ *                  Customers has a keyword index on interests, and we expect the join to be transformed into an indexed nested-loop join.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: [string],
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+  
+create dataset Customers2(CustomerType) primary key cid;
+
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-join_olist-jaccard_01.adm";
+
+for $a in dataset('Customers')
+for $b in dataset('Customers2')
+where /*+ indexnl */ similarity-jaccard($a.interests, $b.interests) >= 0.7f and $a.cid < $b.cid
+return {"arec": $a, "brec": $b }

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-jaccard_02.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-jaccard_02.aql
new file mode 100644
index 0000000..212b64b
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-jaccard_02.aql

@@ -0,0 +1,37 @@
+/*
+ * Description    : Fuzzy joins two datasets, Customer and Customer2, based on the similarity-jaccard function of their interest lists.
+ *                  Customers2 has a keyword index on interests, and we expect the join to be transformed into an indexed nested-loop join.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: [string],
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+  
+create dataset Customers2(CustomerType) primary key cid;
+
+create index interests_index on Customers2(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-join_olist-jaccard_02.adm";
+
+for $a in dataset('Customers')
+for $b in dataset('Customers2')
+where /*+ indexnl */ similarity-jaccard($a.interests, $b.interests) >= 0.7f and $a.cid < $b.cid
+return {"arec": $a, "brec": $b }

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-jaccard_03.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-jaccard_03.aql
new file mode 100644
index 0000000..22b4108
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-jaccard_03.aql

@@ -0,0 +1,35 @@
+/*
+ * Description    : Fuzzy self joins a dataset, Customers, based on the similarity-jaccard function of its interest lists.
+ *                  Customers has a keyword index on interests, and we expect the join to be transformed into an indexed nested-loop join.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: [string],
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+  
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-join_olist-jaccard_03.adm";
+
+for $a in dataset('Customers')
+for $b in dataset('Customers')
+where /*+ indexnl */ similarity-jaccard($a.interests, $b.interests) >= 0.7f and $a.cid < $b.cid
+return {"arec": $a, "brec": $b }

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-jaccard_04.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-jaccard_04.aql
new file mode 100644
index 0000000..32e8a6c
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/olist-jaccard_04.aql

@@ -0,0 +1,37 @@
+/*
+ * Description    : Fuzzy self joins a dataset, Customers, based on the similarity-jaccard function of its interest lists.
+ *                  Customers has a keyword index on interests, 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 AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: [string],
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+  
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-join_olist-jaccard_04.adm";
+
+for $a in dataset('Customers')
+for $b in dataset('Customers')
+let $jacc := /*+ indexnl */ similarity-jaccard($a.interests, $b.interests)
+where $jacc >= 0.7f and $a.cid < $b.cid
+return {"arec": $a, "brec": $b, "jacc": $jacc }

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ulist-fuzzyeq-jaccard_01.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ulist-fuzzyeq-jaccard_01.aql
new file mode 100644
index 0000000..cd391a4
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ulist-fuzzyeq-jaccard_01.aql

@@ -0,0 +1,40 @@
+/*
+ * Description    : Fuzzy joins two datasets, Customer and Customer2, based on ~= using Jaccard of their interest sets.
+ *                  Customers has a keyword index on interests, and we expect the join to be transformed into an indexed nested-loop join.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: {{string}},
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+  
+create dataset Customers2(CustomerType) primary key cid;
+
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-join_ulist-fuzzyeq-jaccard_01.adm";
+
+set simfunction 'jaccard';
+set simthreshold '0.7f';
+
+for $a in dataset('Customers')
+for $b in dataset('Customers2')
+where $a.interests /*+ indexnl */ ~= $b.interests and $a.cid < $b.cid
+return {"arec": $a, "brec": $b }

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ulist-fuzzyeq-jaccard_02.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ulist-fuzzyeq-jaccard_02.aql
new file mode 100644
index 0000000..a7d7118
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ulist-fuzzyeq-jaccard_02.aql

@@ -0,0 +1,40 @@
+/*
+ * Description    : Fuzzy joins two datasets, Customer and Customer2, based on ~= using Jaccard of their interest sets.
+ *                  Customers2 has a keyword index on interests, and we expect the join to be transformed into an indexed nested-loop join.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: {{string}},
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+  
+create dataset Customers2(CustomerType) primary key cid;
+
+create index interests_index on Customers2(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-join_ulist-fuzzyeq-jaccard_02.adm";
+
+set simfunction 'jaccard';
+set simthreshold '0.7f';
+
+for $a in dataset('Customers')
+for $b in dataset('Customers2')
+where $a.interests /*+ indexnl */ ~= $b.interests and $a.cid < $b.cid
+return {"arec": $a, "brec": $b }

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ulist-fuzzyeq-jaccard_03.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ulist-fuzzyeq-jaccard_03.aql
new file mode 100644
index 0000000..a5ec440
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ulist-fuzzyeq-jaccard_03.aql

@@ -0,0 +1,38 @@
+/*
+ * Description    : Fuzzy self joins a dataset, Customers, based on ~= using Jaccard of its interest sets.
+ *                  Customers has a keyword index on interests, and we expect the join to be transformed into an indexed nested-loop join.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: {{string}},
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+  
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-join_ulist-fuzzyeq-jaccard_03.adm";
+
+set simfunction 'jaccard';
+set simthreshold '0.7f';
+
+for $a in dataset('Customers')
+for $b in dataset('Customers')
+where $a.interests /*+ indexnl */ ~= $b.interests and $a.cid < $b.cid
+return {"arec": $a, "brec": $b }

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ulist-jaccard-check_01.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ulist-jaccard-check_01.aql
new file mode 100644
index 0000000..dead8cc
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ulist-jaccard-check_01.aql

@@ -0,0 +1,37 @@
+/*
+ * Description    : Fuzzy joins two datasets, Customer and Customer2, based on the similarity-jaccard-check function of their interest sets.
+ *                  Customers has a keyword index on interests, and we expect the join to be transformed into an indexed nested-loop join.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: {{string}},
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+  
+create dataset Customers2(CustomerType) primary key cid;
+
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-join_ulist-jaccard-check_01.adm";
+
+for $a in dataset('Customers')
+for $b in dataset('Customers2')
+where /*+ indexnl */ similarity-jaccard-check($a.interests, $b.interests, 0.7f)[0] and $a.cid < $b.cid
+return {"arec": $a, "brec": $b }

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ulist-jaccard-check_02.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ulist-jaccard-check_02.aql
new file mode 100644
index 0000000..b18abf8
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ulist-jaccard-check_02.aql

@@ -0,0 +1,37 @@
+/*
+ * Description    : Fuzzy joins two datasets, Customer and Customer2, based on the similarity-jaccard-check function of their interest sets.
+ *                  Customers2 has a keyword index on interests, and we expect the join to be transformed into an indexed nested-loop join.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: {{string}},
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+  
+create dataset Customers2(CustomerType) primary key cid;
+
+create index interests_index on Customers2(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-join_ulist-jaccard-check_02.adm";
+
+for $a in dataset('Customers')
+for $b in dataset('Customers2')
+where /*+ indexnl */ similarity-jaccard-check($a.interests, $b.interests, 0.7f)[0] and $a.cid < $b.cid
+return {"arec": $a, "brec": $b }

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ulist-jaccard-check_03.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ulist-jaccard-check_03.aql
new file mode 100644
index 0000000..5afd428
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ulist-jaccard-check_03.aql

@@ -0,0 +1,35 @@
+/*
+ * Description    : Fuzzy self joins a dataset, Customers, based on the similarity-jaccard-check function of its interest sets.
+ *                  Customers has a keyword index on interests, and we expect the join to be transformed into an indexed nested-loop join.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: {{string}},
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+  
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-join_ulist-jaccard-check_03.adm";
+
+for $a in dataset('Customers')
+for $b in dataset('Customers')
+where /*+ indexnl */ similarity-jaccard-check($a.interests, $b.interests, 0.7f)[0] and $a.cid < $b.cid
+return {"arec": $a, "brec": $b }

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ulist-jaccard-check_04.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ulist-jaccard-check_04.aql
new file mode 100644
index 0000000..3c8bdd7
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ulist-jaccard-check_04.aql

@@ -0,0 +1,37 @@
+/*
+ * Description    : Fuzzy self joins a dataset, Customers, based on the similarity-jaccard-check function of its interest sets.
+ *                  Customers has a keyword index on interests, 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 AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: {{string}},
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+  
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-join_ulist-jaccard-check_04.adm";
+
+for $a in dataset('Customers')
+for $b in dataset('Customers')
+let $jacc := /*+ indexnl */ similarity-jaccard-check($a.interests, $b.interests, 0.7f)
+where $jacc[0] and $a.cid < $b.cid
+return {"arec": $a, "brec": $b, "jacc": $jacc[1] }

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ulist-jaccard_01.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ulist-jaccard_01.aql
new file mode 100644
index 0000000..2001a2a
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ulist-jaccard_01.aql

@@ -0,0 +1,37 @@
+/*
+ * Description    : Fuzzy joins two datasets, Customer and Customer2, based on the similarity-jaccard function of their interest sets.
+ *                  Customers has a keyword index on interests, and we expect the join to be transformed into an indexed nested-loop join.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: {{string}},
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+  
+create dataset Customers2(CustomerType) primary key cid;
+
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-join_ulist-jaccard_01.adm";
+
+for $a in dataset('Customers')
+for $b in dataset('Customers2')
+where /*+ indexnl */ similarity-jaccard($a.interests, $b.interests) >= 0.7f and $a.cid < $b.cid
+return {"arec": $a, "brec": $b }

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ulist-jaccard_02.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ulist-jaccard_02.aql
new file mode 100644
index 0000000..95ce2ad
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ulist-jaccard_02.aql

@@ -0,0 +1,37 @@
+/*
+ * Description    : Fuzzy joins two datasets, Customer and Customer2, based on the similarity-jaccard function of their interest sets.
+ *                  Customers2 has a keyword index on interests, and we expect the join to be transformed into an indexed nested-loop join.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: {{string}},
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+  
+create dataset Customers2(CustomerType) primary key cid;
+
+create index interests_index on Customers2(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-join_ulist-jaccard_02.adm";
+
+for $a in dataset('Customers')
+for $b in dataset('Customers2')
+where /*+ indexnl */ similarity-jaccard($a.interests, $b.interests) >= 0.7f and $a.cid < $b.cid
+return {"arec": $a, "brec": $b }

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ulist-jaccard_03.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ulist-jaccard_03.aql
new file mode 100644
index 0000000..e4fc27f
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ulist-jaccard_03.aql

@@ -0,0 +1,35 @@
+/*
+ * Description    : Fuzzy self joins a dataset, Customers, based on the similarity-jaccard function of its interest sets.
+ *                  Customers has a keyword index on interests, and we expect the join to be transformed into an indexed nested-loop join.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: {{string}},
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+  
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-join_ulist-jaccard_03.adm";
+
+for $a in dataset('Customers')
+for $b in dataset('Customers')
+where /*+ indexnl */ similarity-jaccard($a.interests, $b.interests) >= 0.7f and $a.cid < $b.cid
+return {"arec": $a, "brec": $b }

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ulist-jaccard_04.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ulist-jaccard_04.aql
new file mode 100644
index 0000000..6356f79
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/ulist-jaccard_04.aql

@@ -0,0 +1,37 @@
+/*
+ * Description    : Fuzzy self joins a dataset, Customers, based on the similarity-jaccard function of its interest sets.
+ *                  Customers has a keyword index on interests, 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 AddressType as closed {
+  number: int32, 
+  street: string,
+  city: string
+}
+
+create type CustomerType as closed {
+  cid: int32, 
+  name: string,
+  age: int32?,
+  address: AddressType?,
+  interests: {{string}},
+  children: [ { name: string, age: int32? } ]
+}
+
+create dataset Customers(CustomerType) primary key cid;
+  
+create index interests_index on Customers(interests) type keyword;
+
+write output to nc1:"rttest/inverted-index-join_ulist-jaccard_04.adm";
+
+for $a in dataset('Customers')
+for $b in dataset('Customers')
+let $jacc := /*+ indexnl */ similarity-jaccard($a.interests, $b.interests)
+where $jacc >= 0.7f and $a.cid < $b.cid
+return {"arec": $a, "brec": $b, "jacc": $jacc }

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/word-fuzzyeq-jaccard_01.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/word-fuzzyeq-jaccard_01.aql
new file mode 100644
index 0000000..ff39969
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/word-fuzzyeq-jaccard_01.aql

@@ -0,0 +1,41 @@
+/*
+ * Description    : Fuzzy joins two datasets, DBLP and CSX, based on ~= using Jaccard of their titles' word tokens.
+ *                  DBLP has a keyword index on title, and we expect the join to be transformed into an indexed nested-loop join.
+ * 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) primary key id;
+
+create dataset CSX(CSXType) primary key id;
+
+create index keyword_index on DBLP(title) type keyword;
+
+write output to nc1:"rttest/inverted-index-join_word-fuzzyeq-jaccard_01.adm";
+
+set simfunction 'jaccard';
+set simthreshold '0.5f';
+
+for $a in dataset('DBLP')
+for $b in dataset('CSX')
+where word-tokens($a.title) ~= word-tokens($b.title) and $a.id < $b.id
+return {"arec": $a, "brec": $b }

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/word-fuzzyeq-jaccard_02.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/word-fuzzyeq-jaccard_02.aql
new file mode 100644
index 0000000..f693855
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/word-fuzzyeq-jaccard_02.aql

@@ -0,0 +1,41 @@
+/*
+ * Description    : Fuzzy joins two datasets, DBLP and CSX, based on ~= using Jaccard of their titles' word tokens.
+ *                  CSX has a keyword index on title, and we expect the join to be transformed into an indexed nested-loop join.
+ * 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) primary key id;
+
+create dataset CSX(CSXType) primary key id;
+
+create index keyword_index on CSX(title) type keyword;
+
+write output to nc1:"rttest/inverted-index-join_word-fuzzyeq-jaccard_02.adm";
+
+set simfunction 'jaccard';
+set simthreshold '0.5f';
+
+for $a in dataset('DBLP')
+for $b in dataset('CSX')
+where word-tokens($a.title) ~= word-tokens($b.title) and $a.id < $b.id
+return {"arec": $a, "brec": $b }

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/word-fuzzyeq-jaccard_03.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/word-fuzzyeq-jaccard_03.aql
new file mode 100644
index 0000000..72f9bdc
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/word-fuzzyeq-jaccard_03.aql

@@ -0,0 +1,31 @@
+/*
+ * Description    : Fuzzy self joins a dataset, DBLP, based on ~= using Jaccard of its titles' word tokens.
+ *                  DBLP has a keyword index on title, and we expect the join to be transformed into an indexed nested-loop join.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+create index keyword_index on DBLP(title) type keyword;
+
+write output to nc1:"rttest/inverted-index-join_word-fuzzyeq-jaccard_03.adm";
+
+set simfunction 'jaccard';
+set simthreshold '0.5f';
+
+for $a in dataset('DBLP')
+for $b in dataset('DBLP')
+where word-tokens($a.title) ~= word-tokens($b.title) and $a.id < $b.id
+return {"arec": $a, "brec": $b }

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/word-jaccard-check_01.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/word-jaccard-check_01.aql
new file mode 100644
index 0000000..2a076bc
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/word-jaccard-check_01.aql

@@ -0,0 +1,39 @@
+/*
+ * Description    : Fuzzy joins two datasets, DBLP and CSX, based on the similarity-jaccard-check function of their titles' word tokens.
+ *                  DBLP has a keyword index on title, and we expect the join to be transformed into an indexed nested-loop join.
+ * 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) primary key id;
+
+create dataset CSX(CSXType) primary key id;
+
+create index keyword_index on DBLP(title) type keyword;
+
+write output to nc1:"rttest/inverted-index-join_word-jaccard-check_01.adm";
+
+for $a in dataset('DBLP')
+for $b in dataset('CSX')
+where similarity-jaccard-check(word-tokens($a.title), word-tokens($b.title), 0.5f)[0]
+      and $a.id < $b.id
+return {"arec": $a, "brec": $b }

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/word-jaccard-check_02.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/word-jaccard-check_02.aql
new file mode 100644
index 0000000..98b3972
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/word-jaccard-check_02.aql

@@ -0,0 +1,39 @@
+/*
+ * Description    : Fuzzy joins two datasets, DBLP and CSX, based on the similarity-jaccard-check function of their titles' word tokens.
+ *                  CSX has a keyword index on title, and we expect the join to be transformed into an indexed nested-loop join.
+ * 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) primary key id;
+
+create dataset CSX(CSXType) primary key id;
+
+create index keyword_index on CSX(title) type keyword;
+
+write output to nc1:"rttest/inverted-index-join_word-jaccard-check_02.adm";
+
+for $a in dataset('DBLP')
+for $b in dataset('CSX')
+where similarity-jaccard-check(word-tokens($a.title), word-tokens($b.title), 0.5f)[0]
+      and $a.id < $b.id
+return {"arec": $a, "brec": $b }

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/word-jaccard-check_03.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/word-jaccard-check_03.aql
new file mode 100644
index 0000000..dace174
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/word-jaccard-check_03.aql

@@ -0,0 +1,29 @@
+/*
+ * Description    : Fuzzy self joins a dataset, DBLP, based on the similarity-jaccard-check function of its titles' word tokens.
+ *                  DBLP has a keyword index on title, and we expect the join to be transformed into an indexed nested-loop join.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+create index keyword_index on DBLP(title) type keyword;
+
+write output to nc1:"rttest/inverted-index-join_word-jaccard-check_03.adm";
+
+for $a in dataset('DBLP')
+for $b in dataset('DBLP')
+where similarity-jaccard-check(word-tokens($a.title), word-tokens($b.title), 0.5f)[0]
+      and $a.id < $b.id
+return {"arec": $a, "brec": $b }

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/word-jaccard-check_04.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/word-jaccard-check_04.aql
new file mode 100644
index 0000000..fa68be2
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/word-jaccard-check_04.aql

@@ -0,0 +1,30 @@
+/*
+ * Description    : Fuzzy self joins a dataset, DBLP, based on the similarity-jaccard-check function of its titles' word tokens.
+ *                  DBLP has a keyword 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 dataset DBLP(DBLPType) primary key id;
+
+create index keyword_index on DBLP(title) type keyword;
+
+write output to nc1:"rttest/inverted-index-join_word-jaccard-check_04.adm";
+
+for $a in dataset('DBLP')
+for $b in dataset('DBLP')
+let $jacc := similarity-jaccard-check(word-tokens($a.title), word-tokens($b.title), 0.5f)
+where $jacc[0] and $a.id < $b.id
+return {"arec": $a, "brec": $b, "jacc": $jacc[1] }

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/word-jaccard_01.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/word-jaccard_01.aql
new file mode 100644
index 0000000..df0b75e
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/word-jaccard_01.aql

@@ -0,0 +1,40 @@
+/*
+ * Description    : Fuzzy joins two datasets, DBLP and CSX, based on the similarity-jaccard function of their titles' word tokens.
+ *                  DBLP has a keyword index on title, and we expect the join to be transformed into an indexed nested-loop join.
+ * 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) primary key id;
+
+create dataset CSX(CSXType) primary key id;
+
+create index keyword_index on DBLP(title) type keyword;
+
+write output to nc1:"rttest/inverted-index-join_word-jaccard_01.adm";
+
+for $a in dataset('DBLP')
+for $b in dataset('CSX')
+where similarity-jaccard(word-tokens($a.title), word-tokens($b.title)) >= 0.5f
+      and $a.id < $b.id
+return {"arec": $a, "brec": $b }
+

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/word-jaccard_02.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/word-jaccard_02.aql
new file mode 100644
index 0000000..1f227c8
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/word-jaccard_02.aql

@@ -0,0 +1,40 @@
+/*
+ * Description    : Fuzzy joins two datasets, DBLP and CSX, based on the similarity-jaccard function of their titles' word tokens.
+ *                  CSX has a keyword index on title, and we expect the join to be transformed into an indexed nested-loop join.
+ * 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) primary key id;
+
+create dataset CSX(CSXType) primary key id;
+
+create index keyword_index on CSX(title) type keyword;
+
+write output to nc1:"rttest/inverted-index-join_word-jaccard_02.adm";
+
+for $a in dataset('DBLP')
+for $b in dataset('CSX')
+where similarity-jaccard(word-tokens($a.title), word-tokens($b.title)) >= 0.5f
+      and $a.id < $b.id
+return {"arec": $a, "brec": $b }
+

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/word-jaccard_03.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/word-jaccard_03.aql
new file mode 100644
index 0000000..7a719ff
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/word-jaccard_03.aql

@@ -0,0 +1,29 @@
+/*
+ * Description    : Fuzzy self joins a dataset, DBLP, based on the similarity-jaccard function of its titles' word tokens.
+ *                  DBLP has a keyword index on title, and we expect the join to be transformed into an indexed nested-loop join.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+create index keyword_index on DBLP(title) type keyword;
+
+write output to nc1:"rttest/inverted-index-join_word-jaccard_03.adm";
+
+for $a in dataset('DBLP')
+for $b in dataset('DBLP')
+where similarity-jaccard(word-tokens($a.title), word-tokens($b.title)) >= 0.5f
+      and $a.id < $b.id
+return {"arec": $a, "brec": $b }

diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/word-jaccard_04.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/word-jaccard_04.aql
new file mode 100644
index 0000000..077803b
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join/word-jaccard_04.aql

@@ -0,0 +1,30 @@
+/*
+ * Description    : Fuzzy self joins a dataset, DBLP, based on the similarity-jaccard function of its titles' word tokens.
+ *                  DBLP has a keyword 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 dataset DBLP(DBLPType) primary key id;
+
+create index keyword_index on DBLP(title) type keyword;
+
+write output to nc1:"rttest/inverted-index-join_word-jaccard_04.adm";
+
+for $a in dataset('DBLP')
+for $b in dataset('DBLP')
+let $jacc := similarity-jaccard(word-tokens($a.title), word-tokens($b.title))
+where $jacc >= 0.5f and $a.id < $b.id
+return {"arec": $a, "brec": $b, "jacc": $jacc }

diff --git a/asterix-app/src/test/resources/optimizerts/queries/join-super-key_01.aql b/asterix-app/src/test/resources/optimizerts/queries/join-super-key_01.aql
index f0251ad..52b35b8 100644
--- a/asterix-app/src/test/resources/optimizerts/queries/join-super-key_01.aql
+++ b/asterix-app/src/test/resources/optimizerts/queries/join-super-key_01.aql

@@ -66,9 +66,9 @@
 write output to nc1:"/tmp/join-super-key_01.adm";
 
 create dataset LineItems(LineItemType)
-  partitioned by key l_partkey, l_linenumber on group1;
+  primary key l_partkey, l_linenumber on group1;
 create dataset PartSupp(PartSuppType)
-  partitioned by key ps_partkey, ps_suppkey on group1;  
+  primary key ps_partkey, ps_suppkey on group1;  
 
 
 for $li in dataset('LineItems')

diff --git a/asterix-app/src/test/resources/optimizerts/queries/join-super-key_02.aql b/asterix-app/src/test/resources/optimizerts/queries/join-super-key_02.aql
index 0904f37..98f7e9e 100644
--- a/asterix-app/src/test/resources/optimizerts/queries/join-super-key_02.aql
+++ b/asterix-app/src/test/resources/optimizerts/queries/join-super-key_02.aql

@@ -66,9 +66,9 @@
 write output to nc1:"/tmp/join-super-key_01.adm";
 
 create dataset LineItems(LineItemType)
-  partitioned by key l_partkey, l_linenumber on group1;
+  primary key l_partkey, l_linenumber on group1;
 create dataset PartSupp(PartSuppType)
-  partitioned by key ps_partkey, ps_suppkey on group1;  
+  primary key ps_partkey, ps_suppkey on group1;  
 
 
 for $ps in dataset('PartSupp')

diff --git a/asterix-app/src/test/resources/optimizerts/queries/loj-super-key_01.aql b/asterix-app/src/test/resources/optimizerts/queries/loj-super-key_01.aql
index 1f43f73..4855576 100644
--- a/asterix-app/src/test/resources/optimizerts/queries/loj-super-key_01.aql
+++ b/asterix-app/src/test/resources/optimizerts/queries/loj-super-key_01.aql

@@ -66,9 +66,9 @@
 write output to nc1:"/tmp/loj-super-key_01.adm";
 
 create dataset LineItems(LineItemType)
-  partitioned by key l_partkey, l_linenumber on group1;
+  primary key l_partkey, l_linenumber on group1;
 create dataset PartSupp(PartSuppType)
-  partitioned by key ps_partkey, ps_suppkey on group1;  
+  primary key ps_partkey, ps_suppkey on group1;  
 
 
 for $li in dataset('LineItems')

diff --git a/asterix-app/src/test/resources/optimizerts/queries/loj-super-key_02.aql b/asterix-app/src/test/resources/optimizerts/queries/loj-super-key_02.aql
index ceab193..ce937c5 100644
--- a/asterix-app/src/test/resources/optimizerts/queries/loj-super-key_02.aql
+++ b/asterix-app/src/test/resources/optimizerts/queries/loj-super-key_02.aql

@@ -66,9 +66,9 @@
 write output to nc1:"/tmp/loj-super-key_01.adm";
 
 create dataset LineItems(LineItemType)
-  partitioned by key l_partkey, l_linenumber on group1;
+  primary key l_partkey, l_linenumber on group1;
 create dataset PartSupp(PartSuppType)
-  partitioned by key ps_partkey, ps_suppkey on group1;  
+  primary key ps_partkey, ps_suppkey on group1;  
 
 
 for $ps in dataset('PartSupp')

diff --git a/asterix-app/src/test/resources/optimizerts/queries/nested_loj2.aql b/asterix-app/src/test/resources/optimizerts/queries/nested_loj2.aql
index 0b77f55..d235b09 100644
--- a/asterix-app/src/test/resources/optimizerts/queries/nested_loj2.aql
+++ b/asterix-app/src/test/resources/optimizerts/queries/nested_loj2.aql

@@ -47,11 +47,11 @@
 create nodegroup group1 if not exists on nc1, nc2;
 
 create dataset LineItems(LineItemType)
-  partitioned by key l_orderkey, l_linenumber on group1;
+  primary key l_orderkey, l_linenumber on group1;
 create dataset Orders(OrderType)
-  partitioned by key o_orderkey on group1;
+  primary key o_orderkey on group1;
 create dataset Customers(CustomerType) 
-  partitioned by key c_custkey on group1;
+  primary key c_custkey on group1;
 
 write output to nc1:"/tmp/nested_loj.adm";
 

diff --git a/asterix-app/src/test/resources/optimizerts/queries/nested_loj3.aql b/asterix-app/src/test/resources/optimizerts/queries/nested_loj3.aql
index 3a1ef04..1616a67 100644
--- a/asterix-app/src/test/resources/optimizerts/queries/nested_loj3.aql
+++ b/asterix-app/src/test/resources/optimizerts/queries/nested_loj3.aql

@@ -57,13 +57,13 @@
 create nodegroup group1 if not exists on nc1, nc2;
 
 create dataset LineItems(LineItemType)
-  partitioned by key l_orderkey, l_linenumber on group1;
+  primary key l_orderkey, l_linenumber on group1;
 create dataset Orders(OrderType)
-  partitioned by key o_orderkey on group1;
+  primary key o_orderkey on group1;
 create dataset Customers(CustomerType) 
-  partitioned by key c_custkey on group1;
+  primary key c_custkey on group1;
 create dataset PartSupp(PartSuppType)
-  partitioned by key ps_partkey, ps_suppkey on group1;  
+  primary key ps_partkey, ps_suppkey on group1;  
 
 write output to nc1:"/tmp/nested_loj.adm";
 

diff --git a/asterix-app/src/test/resources/optimizerts/queries/noncollocated.aql b/asterix-app/src/test/resources/optimizerts/queries/noncollocated.aql
index 3aa1855..26b5ab0 100644
--- a/asterix-app/src/test/resources/optimizerts/queries/noncollocated.aql
+++ b/asterix-app/src/test/resources/optimizerts/queries/noncollocated.aql

@@ -21,10 +21,10 @@
 create nodegroup group2 if not exists on nc2;
 
 create dataset Users(UserType) 
-  partitioned by key uid on group1;
+  primary key uid on group1;
 
 create dataset Visitors(VisitorType) 
-  partitioned by key vid on group2;
+  primary key vid on group2;
 
 
 write output to nc1:"/tmp/fuzzy1.adm";

diff --git a/asterix-app/src/test/resources/optimizerts/queries/orderby-desc-using-gby.aql b/asterix-app/src/test/resources/optimizerts/queries/orderby-desc-using-gby.aql
index 682800c..8cef009 100644
--- a/asterix-app/src/test/resources/optimizerts/queries/orderby-desc-using-gby.aql
+++ b/asterix-app/src/test/resources/optimizerts/queries/orderby-desc-using-gby.aql

@@ -24,7 +24,7 @@
 create nodegroup group1 if not exists on nc1, nc2;
 
 create dataset Customers(CustomerType) 
-  partitioned by key cid on group1;
+  primary key cid on group1;
   
 write output to nc1:"rttest/gby-using-orderby-desc.adm";
 

diff --git a/asterix-app/src/test/resources/optimizerts/queries/orders-aggreg.aql b/asterix-app/src/test/resources/optimizerts/queries/orders-aggreg.aql
index c2f96f6..960a8e6 100644
--- a/asterix-app/src/test/resources/optimizerts/queries/orders-aggreg.aql
+++ b/asterix-app/src/test/resources/optimizerts/queries/orders-aggreg.aql

@@ -16,7 +16,7 @@
 create nodegroup group1 if not exists on nc1, nc2;
 
 create dataset Orders(OrderType)
-  partitioned by key oid on group1;
+  primary key oid on group1;
 
 write output to nc1:"/tmp/orders-aggreg.adm";
 

diff --git a/asterix-app/src/test/resources/optimizerts/queries/orders-composite-index-search.aql b/asterix-app/src/test/resources/optimizerts/queries/orders-composite-index-search.aql
new file mode 100644
index 0000000..73ec062
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/orders-composite-index-search.aql

@@ -0,0 +1,30 @@
+drop dataverse index_search if exists;
+create dataverse index_search;
+use dataverse index_search;
+
+create type OrderType as closed {
+  o_orderkey: int32, 
+  o_custkey: int32, 
+  o_orderstatus: string, 
+  o_totalprice: double, 
+  o_orderdate: string, 
+  o_orderpriority: string,
+  o_clerk: string, 
+  o_shippriority: int32, 
+  o_comment: string
+}
+
+create dataset Orders(OrderType) primary key o_orderkey;
+
+create index idx_Custkey_Orderstatus on Orders(o_custkey, o_orderstatus);
+
+write output to nc1:"/tmp/index_search.adm";
+
+for $o in dataset('Orders')
+where
+  $o.o_custkey = 40 and $o.o_orderstatus = "P"
+return {  
+  "o_orderkey": $o.o_orderkey,
+  "o_custkey": $o.o_custkey,
+  "o_orderstatus": $o.o_orderstatus
+}

diff --git a/asterix-app/src/test/resources/optimizerts/queries/orders-index-search-conjunctive-open_01.aql b/asterix-app/src/test/resources/optimizerts/queries/orders-index-search-conjunctive-open_01.aql
new file mode 100644
index 0000000..b5aa50d
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/orders-index-search-conjunctive-open_01.aql

@@ -0,0 +1,40 @@
+drop dataverse tpch if exists;
+create dataverse tpch;
+use dataverse tpch;
+
+
+create type OrderType as open {
+  o_orderkey: int32, 
+  o_custkey: int32, 
+  o_orderstatus: string, 
+  o_totalprice: double, 
+  o_orderdate: string, 
+  o_orderpriority: string,
+  o_clerk: string, 
+  o_shippriority: int32, 
+  o_comment: string
+}
+
+
+create nodegroup group1 if not exists on nc1, nc2;
+
+create dataset Orders(OrderType)
+  primary key o_orderkey on group1;
+
+load dataset Orders 
+using "edu.uci.ics.asterix.external.dataset.adapter.NCFileSystemAdapter"
+(("path"="nc1://data/tpch0.001/orders.tbl"),("format"="delimited-text"),("delimiter"="|")) pre-sorted;
+
+create index idx_Orders_Custkey on Orders(o_custkey);
+
+write output to nc1:"/tmp/index_search-conjunctive.adm";
+
+
+for $o in dataset('Orders')
+where
+  $o.o_custkey = 40 and $o.o_totalprice > 150000.0
+order by $o.o_orderkey
+return {  
+  "o_orderkey": $o.o_orderkey,
+  "o_custkey": $o.o_custkey
+}

diff --git a/asterix-app/src/test/resources/optimizerts/queries/orders-index-search-conjunctive-open_02.aql b/asterix-app/src/test/resources/optimizerts/queries/orders-index-search-conjunctive-open_02.aql
new file mode 100644
index 0000000..daef719
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/orders-index-search-conjunctive-open_02.aql

@@ -0,0 +1,41 @@
+drop dataverse tpch if exists;
+create dataverse tpch;
+use dataverse tpch;
+
+
+create type OrderType as open {
+  o_orderkey: int32, 
+  o_custkey: int32, 
+  o_orderstatus: string, 
+  o_totalprice: double, 
+  o_orderdate: string, 
+  o_orderpriority: string,
+  o_clerk: string, 
+  o_shippriority: int32, 
+  o_comment: string
+}
+
+
+create nodegroup group1 if not exists on nc1, nc2;
+
+create dataset Orders(OrderType)
+  primary key o_orderkey on group1;
+
+load dataset Orders 
+using "edu.uci.ics.asterix.external.dataset.adapter.NCFileSystemAdapter"
+(("path"="nc1://data/tpch0.001/orders.tbl"),("format"="delimited-text"),("delimiter"="|")) pre-sorted;
+
+create index idx_Orders_Custkey on Orders(o_custkey);
+
+write output to nc1:"/tmp/index_search-conjunctive.adm";
+
+
+for $o in dataset('Orders')
+where
+  $o.o_custkey = 40 and $o.o_totalprice > 150000.0
+order by $o.o_orderkey
+return {  
+  "o_orderkey": $o.o_orderkey,
+  "o_custkey": $o.o_custkey,
+  "o_totalprice": $o.o_totalprice
+}

diff --git a/asterix-app/src/test/resources/optimizerts/queries/orders-index-search-conjunctive_01.aql b/asterix-app/src/test/resources/optimizerts/queries/orders-index-search-conjunctive_01.aql
index f5b5067..21a7f5a 100644
--- a/asterix-app/src/test/resources/optimizerts/queries/orders-index-search-conjunctive_01.aql
+++ b/asterix-app/src/test/resources/optimizerts/queries/orders-index-search-conjunctive_01.aql

@@ -19,11 +19,11 @@
 create nodegroup group1 if not exists on nc1, nc2;
 
 create dataset Orders(OrderType)
-  partitioned by key o_orderkey on group1;
+  primary key o_orderkey on group1;
 
 load dataset Orders 
 using "edu.uci.ics.asterix.external.dataset.adapter.NCFileSystemAdapter"
-(("path"="nc1:///data/tpch0.001/orders.tbl"),("format"="delimited-text"),("delimiter"="|")) pre-sorted;
+(("path"="nc1://data/tpch0.001/orders.tbl"),("format"="delimited-text"),("delimiter"="|")) pre-sorted;
 
 create index idx_Orders_Custkey on Orders(o_custkey);
 

diff --git a/asterix-app/src/test/resources/optimizerts/queries/orders-index-search-conjunctive_02.aql b/asterix-app/src/test/resources/optimizerts/queries/orders-index-search-conjunctive_02.aql
index fed390c..25a6d3f 100644
--- a/asterix-app/src/test/resources/optimizerts/queries/orders-index-search-conjunctive_02.aql
+++ b/asterix-app/src/test/resources/optimizerts/queries/orders-index-search-conjunctive_02.aql

@@ -19,7 +19,7 @@
 create nodegroup group1 if not exists on nc1, nc2;
 
 create dataset Orders(OrderType)
-  partitioned by key o_orderkey on group1;
+  primary key o_orderkey on group1;
 
 load dataset Orders 
 using "edu.uci.ics.asterix.external.dataset.adapter.NCFileSystemAdapter"

diff --git a/asterix-app/src/test/resources/optimizerts/queries/orders-index-search-open.aql b/asterix-app/src/test/resources/optimizerts/queries/orders-index-search-open.aql
new file mode 100644
index 0000000..31d41b6
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/orders-index-search-open.aql

@@ -0,0 +1,35 @@
+drop dataverse index_search if exists;
+
+create dataverse index_search;
+
+use dataverse index_search;
+
+create type OrderType as open {
+  o_orderkey: int32, 
+  o_custkey: int32, 
+  o_orderstatus: string, 
+  o_totalprice: double, 
+  o_orderdate: string, 
+  o_orderpriority: string,
+  o_clerk: string, 
+  o_shippriority: int32, 
+  o_comment: string
+}
+
+
+create nodegroup group1 if not exists on nc1, nc2;
+
+create dataset Orders(OrderType)
+  primary key o_orderkey on group1;
+
+create index idx_Orders_Custkey on Orders(o_custkey);
+
+write output to nc1:"/tmp/index_search.adm";
+
+for $o in dataset('Orders')
+where
+  $o.o_custkey = 40
+return {  
+  "o_orderkey": $o.o_orderkey,
+  "o_custkey": $o.o_custkey 
+}

diff --git a/asterix-app/src/test/resources/optimizerts/queries/orders-index-search.aql b/asterix-app/src/test/resources/optimizerts/queries/orders-index-search.aql
index 75be90b..4e01059 100644
--- a/asterix-app/src/test/resources/optimizerts/queries/orders-index-search.aql
+++ b/asterix-app/src/test/resources/optimizerts/queries/orders-index-search.aql

@@ -20,7 +20,7 @@
 create nodegroup group1 if not exists on nc1, nc2;
 
 create dataset Orders(OrderType)
-  partitioned by key o_orderkey on group1;
+  primary key o_orderkey on group1;
 
 create index idx_Orders_Custkey on Orders(o_custkey);
 

diff --git a/asterix-app/src/test/resources/optimizerts/queries/prim-idx-search-open.aql b/asterix-app/src/test/resources/optimizerts/queries/prim-idx-search-open.aql
new file mode 100644
index 0000000..1f6f887
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/prim-idx-search-open.aql

@@ -0,0 +1,36 @@
+drop dataverse prim_index_search if exists;
+
+create dataverse prim_index_search;
+
+use dataverse prim_index_search;
+
+
+create type OrderType as open {
+  o_orderkey: int32, 
+  o_custkey: int32, 
+  o_orderstatus: string, 
+  o_totalprice: double, 
+  o_orderdate: string, 
+  o_orderpriority: string,
+  o_clerk: string, 
+  o_shippriority: int32, 
+  o_comment: string
+}
+
+
+create nodegroup group1 if not exists on nc1, nc2;
+
+create dataset Orders(OrderType)
+  primary key o_orderkey on group1;
+
+
+write output to nc1:"/tmp/prim_index_search.adm";
+
+
+for $o in dataset('Orders')
+where
+  $o.o_orderkey = 34
+return {  
+  "o_orderkey": $o.o_orderkey,
+  "o_custkey": $o.o_custkey 
+}

diff --git a/asterix-app/src/test/resources/optimizerts/queries/prim-idx-search.aql b/asterix-app/src/test/resources/optimizerts/queries/prim-idx-search.aql
index 7a22597..7939fed 100644
--- a/asterix-app/src/test/resources/optimizerts/queries/prim-idx-search.aql
+++ b/asterix-app/src/test/resources/optimizerts/queries/prim-idx-search.aql

@@ -21,7 +21,7 @@
 create nodegroup group1 if not exists on nc1, nc2;
 
 create dataset Orders(OrderType)
-  partitioned by key o_orderkey on group1;
+  primary key o_orderkey on group1;
 
 
 write output to nc1:"/tmp/prim_index_search.adm";

diff --git a/asterix-app/src/test/resources/optimizerts/queries/pull_select_above_eq_join.aql b/asterix-app/src/test/resources/optimizerts/queries/pull_select_above_eq_join.aql
index dfc05ff..ee998cf 100644
--- a/asterix-app/src/test/resources/optimizerts/queries/pull_select_above_eq_join.aql
+++ b/asterix-app/src/test/resources/optimizerts/queries/pull_select_above_eq_join.aql

@@ -21,10 +21,10 @@
 create nodegroup group1 if not exists on nc1, nc2;
 
 create dataset Users(UserType) 
-  partitioned by key uid on group1;
+  primary key uid on group1;
 
 create dataset Visitors(VisitorType) 
-  partitioned by key vid on group1;
+  primary key vid on group1;
 
 
 write output to nc1:"/tmp/pull-select-above-eq-join.adm";

diff --git a/asterix-app/src/test/resources/optimizerts/queries/push-project-through-group.aql b/asterix-app/src/test/resources/optimizerts/queries/push-project-through-group.aql
index 5dd229b..3c0235c 100644
--- a/asterix-app/src/test/resources/optimizerts/queries/push-project-through-group.aql
+++ b/asterix-app/src/test/resources/optimizerts/queries/push-project-through-group.aql

@@ -15,7 +15,7 @@
 create nodegroup group1 if not exists on nc1, nc2;
 
 create dataset DBLP(DBLPType) 
-  partitioned by key id on group1;
+  primary key id on group1;
 
 
 write output to nc1:'rttest/fuzzyjoin_080.adm';

diff --git a/asterix-app/src/test/resources/optimizerts/queries/push_limit.aql b/asterix-app/src/test/resources/optimizerts/queries/push_limit.aql
index a9c4fe7..0ffe2b0 100644
--- a/asterix-app/src/test/resources/optimizerts/queries/push_limit.aql
+++ b/asterix-app/src/test/resources/optimizerts/queries/push_limit.aql

@@ -16,7 +16,7 @@
 
 create nodegroup group1 if not exists on nc1, nc2;
 create dataset Orders(OrderType)
-  partitioned by key o_orderkey on group1;
+  primary key o_orderkey on group1;
 
 write output to nc1:"/tmp/push_limit.adm";
 

diff --git a/asterix-app/src/test/resources/optimizerts/queries/q1.aql b/asterix-app/src/test/resources/optimizerts/queries/q1.aql
index 8f62292..ced342d 100644
--- a/asterix-app/src/test/resources/optimizerts/queries/q1.aql
+++ b/asterix-app/src/test/resources/optimizerts/queries/q1.aql

@@ -27,7 +27,7 @@
 
 create nodegroup group1 if not exists on nc1, nc2;
 
-create dataset User(UserType) partitioned by key name on group1;
+create dataset User(UserType) primary key name on group1;
 
 write output to nc1:"/tmp/q1.adm";
 

diff --git a/asterix-app/src/test/resources/optimizerts/queries/q1_pricing_summary_report_nt.aql b/asterix-app/src/test/resources/optimizerts/queries/q1_pricing_summary_report_nt.aql
new file mode 100644
index 0000000..b6de1fa
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/q1_pricing_summary_report_nt.aql

@@ -0,0 +1,50 @@
+drop dataverse tpch if exists;
+create dataverse tpch;
+use dataverse tpch;
+
+create type LineItemType as closed {
+  l_orderkey: int32, 
+  l_partkey: int32, 
+  l_suppkey: int32, 
+  l_linenumber: int32, 
+  l_quantity: double, 
+  l_extendedprice: double,
+  l_discount: double, 
+  l_tax: double,
+  l_returnflag: string, 
+  l_linestatus: string, 
+  l_shipdate: string,
+  l_commitdate: string, 
+  l_receiptdate: string, 
+  l_shipinstruct: string, 
+  l_shipmode: string, 
+  l_comment: string
+}
+
+create dataset LineItem(LineItemType)
+  primary key l_orderkey, l_linenumber;
+
+load dataset LineItem 
+using "edu.uci.ics.asterix.external.dataset.adapter.NCFileSystemAdapter"
+(("path"="nc1://data/tpch0.001/lineitem.tbl"),("format"="delimited-text"),("delimiter"="|")) pre-sorted;
+
+write output to nc1:"rttest/tpch_q1_pricing_summary_report_nt.adm";
+ 
+for $l in dataset('LineItem')
+where $l.l_shipdate <= '1998-09-02'
+/*+ hash*/
+group by $l_returnflag := $l.l_returnflag, $l_linestatus := $l.l_linestatus  
+  with $l
+order by $l_returnflag, $l_linestatus
+return {
+  "l_returnflag": $l_returnflag,
+  "l_linestatus": $l_linestatus,
+  "sum_qty": sum(for $i in $l return $i.l_quantity),
+  "sum_base_price": sum(for $i in $l return $i.l_extendedprice),
+  "sum_disc_price": sum(for $i in $l return $i.l_extendedprice * (1 - $i.l_discount)),
+  "sum_charge": sum(for $i in $l return $i.l_extendedprice * (1 - $i.l_discount) * (1 + $i.l_tax)),
+  "ave_qty": avg(for $i in $l return $i.l_quantity),  
+  "ave_price": avg(for $i in $l return $i.l_extendedprice),
+  "ave_disc": avg(for $i in $l return $i.l_discount),
+  "count_order": count($l)
+}   

diff --git a/asterix-app/src/test/resources/optimizerts/queries/q2.aql b/asterix-app/src/test/resources/optimizerts/queries/q2.aql
index 17b1f86..5fba695 100644
--- a/asterix-app/src/test/resources/optimizerts/queries/q2.aql
+++ b/asterix-app/src/test/resources/optimizerts/queries/q2.aql

@@ -34,7 +34,7 @@
 
 create nodegroup group1 if not exists on nc1, nc2;
 
-create dataset Event(EventType) partitioned by key name on group1;
+create dataset Event(EventType) primary key name on group1;
 
 write output to nc1:"/tmp/q2.adm";
 

diff --git a/asterix-app/src/test/resources/optimizerts/queries/q3_shipping_priority.aql b/asterix-app/src/test/resources/optimizerts/queries/q3_shipping_priority.aql
index 89c6fd9..8e6bf6e6 100644
--- a/asterix-app/src/test/resources/optimizerts/queries/q3_shipping_priority.aql
+++ b/asterix-app/src/test/resources/optimizerts/queries/q3_shipping_priority.aql

@@ -49,11 +49,11 @@
 create nodegroup group1 if not exists on nc1, nc2;
 
 create dataset LineItems(LineItemType)
-  partitioned by key l_orderkey, l_linenumber on group1;
+  primary key l_orderkey, l_linenumber on group1;
 create dataset Orders(OrderType)
-  partitioned by key o_orderkey on group1;
+  primary key o_orderkey on group1;
 create dataset Customers(CustomerType) 
-  partitioned by key c_custkey on group1;
+  primary key c_custkey on group1;
 
 write output to nc1:"/tmp/q3_shipping_priority.adm";
 

diff --git a/asterix-app/src/test/resources/optimizerts/queries/q5_local_supplier_volume.aql b/asterix-app/src/test/resources/optimizerts/queries/q5_local_supplier_volume.aql
index 6b5ccfa..670a392 100644
--- a/asterix-app/src/test/resources/optimizerts/queries/q5_local_supplier_volume.aql
+++ b/asterix-app/src/test/resources/optimizerts/queries/q5_local_supplier_volume.aql

@@ -72,17 +72,17 @@
 create nodegroup group1 if not exists on nc1, nc2;
 
 create dataset LineItems(LineItemType)
-  partitioned by key l_orderkey, l_linenumber on group1;
+  primary key l_orderkey, l_linenumber on group1;
 create dataset Orders(OrderType)
-  partitioned by key o_orderkey on group1;
+  primary key o_orderkey on group1;
 create dataset Customers(CustomerType) 
-  partitioned by key c_custkey on group1;
+  primary key c_custkey on group1;
 create dataset Suppliers(SupplierType)
-  partitioned by key s_suppkey on group1;
+  primary key s_suppkey on group1;
 create dataset Nations(NationType) 
-  partitioned by key n_nationkey on group1;
+  primary key n_nationkey on group1;
 create dataset Regions(RegionType)
-  partitioned by key r_regionkey on group1;
+  primary key r_regionkey on group1;
   
 write output to nc1:"/tmp/q5_local_supplier.adm";
 

diff --git a/asterix-app/src/test/resources/optimizerts/queries/rtree-index-join/spatial-intersect-point_01.aql b/asterix-app/src/test/resources/optimizerts/queries/rtree-index-join/spatial-intersect-point_01.aql
new file mode 100644
index 0000000..e95be99
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/rtree-index-join/spatial-intersect-point_01.aql

@@ -0,0 +1,33 @@
+/*
+ * Description    : Joins two datasets on the intersection of their point attributes.
+ *                  The dataset 'MyData1' has an RTree index, and we expect the 
+ *                  join to be transformed into an indexed nested-loop join.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type MyRecord as closed {
+  id: int32,
+  point: point,
+  kwds: string,
+  line1: line,
+  line2: line,
+  poly1: polygon,
+  poly2: polygon,
+  rec: rectangle
+}
+
+create dataset MyData1(MyRecord) primary key id;
+create dataset MyData2(MyRecord) primary key id;
+
+create index rtree_index on MyData1(point) type rtree;
+
+write output to nc1:"rttest/index-join_rtree-spatial-intersect-point.adm";
+
+for $a in dataset('MyData1')
+for $b in dataset('MyData2')
+where spatial-intersect($a.point, $b.point)
+return {"a": $a, "b": $b}

diff --git a/asterix-app/src/test/resources/optimizerts/queries/rtree-index-join/spatial-intersect-point_02.aql b/asterix-app/src/test/resources/optimizerts/queries/rtree-index-join/spatial-intersect-point_02.aql
new file mode 100644
index 0000000..c0a8634
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/rtree-index-join/spatial-intersect-point_02.aql

@@ -0,0 +1,33 @@
+/*
+ * Description    : Joins two datasets on the intersection of their point attributes.
+ *                  The dataset 'MyData2' has an RTree index, and we expect the 
+ *                  join to be transformed into an indexed nested-loop join.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type MyRecord as closed {
+  id: int32,
+  point: point,
+  kwds: string,
+  line1: line,
+  line2: line,
+  poly1: polygon,
+  poly2: polygon,
+  rec: rectangle
+}
+
+create dataset MyData1(MyRecord) primary key id;
+create dataset MyData2(MyRecord) primary key id;
+
+create index rtree_index on MyData2(point) type rtree;
+
+write output to nc1:"rttest/rtree-index-join_spatial-intersect-point_02.adm";
+
+for $a in dataset('MyData1')
+for $b in dataset('MyData2')
+where spatial-intersect($a.point, $b.point)
+return {"a": $a, "b": $b}

diff --git a/asterix-app/src/test/resources/optimizerts/queries/rtree-index-join/spatial-intersect-point_03.aql b/asterix-app/src/test/resources/optimizerts/queries/rtree-index-join/spatial-intersect-point_03.aql
new file mode 100644
index 0000000..6fb79f3
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/rtree-index-join/spatial-intersect-point_03.aql

@@ -0,0 +1,32 @@
+/*
+ * Description    : Self-joins a dataset on the intersection of its point attribute.
+ *                  The dataset has an RTree index, and we expect the 
+ *                  join to be transformed into an indexed nested-loop join.
+ * Success        : Yes
+ */
+
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type MyRecord as closed {
+  id: int32,
+  point: point,
+  kwds: string,
+  line1: line,
+  line2: line,
+  poly1: polygon,
+  poly2: polygon,
+  rec: rectangle
+}
+
+create dataset MyData(MyRecord) primary key id;
+
+create index rtree_index on MyData(point) type rtree;
+
+write output to nc1:"rttest/rtree-index-join_spatial-intersect-point_03.adm";
+
+for $a in dataset('MyData')
+for $b in dataset('MyData')
+where spatial-intersect($a.point, $b.point)
+return {"a": $a, "b": $b}

diff --git a/asterix-app/src/test/resources/optimizerts/queries/rtree-secondary-index-open.aql b/asterix-app/src/test/resources/optimizerts/queries/rtree-secondary-index-open.aql
new file mode 100644
index 0000000..b4a5796
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/rtree-secondary-index-open.aql

@@ -0,0 +1,33 @@
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+create type MyRecord as closed {
+  id: int32,
+  point: point,
+  kwds: string,
+  line1: line,
+  line2: line,
+  poly1: polygon,
+  poly2: polygon,
+  rec: rectangle,
+  circle: circle
+}
+
+create nodegroup group1  if not exists on nc1, nc2;
+
+create dataset MyData(MyRecord)
+  primary key id on group1;
+
+load dataset MyData 
+using "edu.uci.ics.asterix.external.dataset.adapter.NCFileSystemAdapter"
+(("path"="nc1://data/spatial/spatialData.json"),("format"="adm")) pre-sorted;
+
+create index rtree_index_point on MyData(point) type rtree;
+
+
+write output to nc1:"rttest/index_rtree-secondary-index-open.adm";
+
+for $o in dataset('MyData')
+where spatial-intersect($o.point, create-polygon(create-point(4.0,1.0), create-point(4.0,4.0), create-point(12.0,4.0), create-point(12.0,1.0)))
+return {"id":$o.id}

diff --git a/asterix-app/src/test/resources/optimizerts/queries/rtree-secondary-index.aql b/asterix-app/src/test/resources/optimizerts/queries/rtree-secondary-index.aql
index d525458..41a5a91 100644
--- a/asterix-app/src/test/resources/optimizerts/queries/rtree-secondary-index.aql
+++ b/asterix-app/src/test/resources/optimizerts/queries/rtree-secondary-index.aql

@@ -10,13 +10,14 @@
   line2: line,
   poly1: polygon,
   poly2: polygon,
-  rec: rectangle
+  rec: rectangle,
+  circle: circle
 }
 
 create nodegroup group1  if not exists on nc1, nc2;
 
 create dataset MyData(MyRecord)
-  partitioned by key id on group1;
+  primary key id on group1;
 
 load dataset MyData 
 using "edu.uci.ics.asterix.external.dataset.adapter.NCFileSystemAdapter"

diff --git a/asterix-app/src/test/resources/optimizerts/queries/scan-delete-all.aql b/asterix-app/src/test/resources/optimizerts/queries/scan-delete-all.aql
index d30b7f8..7b8215f 100644
--- a/asterix-app/src/test/resources/optimizerts/queries/scan-delete-all.aql
+++ b/asterix-app/src/test/resources/optimizerts/queries/scan-delete-all.aql

@@ -30,9 +30,9 @@
 create nodegroup group1 if not exists on nc1, nc2;
 
 create dataset LineItems_q1(LineItemType)
-  partitioned by key l_orderkey on group1;
+  primary key l_orderkey on group1;
 
 create dataset LineID(LineIDType)
-  partitioned by key l_orderkey on group1;
+  primary key l_orderkey on group1;
 
 delete $l from dataset LineItems_q1;

diff --git a/asterix-app/src/test/resources/optimizerts/queries/scan-delete-rtree-secondary-index.aql b/asterix-app/src/test/resources/optimizerts/queries/scan-delete-rtree-secondary-index.aql
index 5f1e8d3..a307a1d 100644
--- a/asterix-app/src/test/resources/optimizerts/queries/scan-delete-rtree-secondary-index.aql
+++ b/asterix-app/src/test/resources/optimizerts/queries/scan-delete-rtree-secondary-index.aql

@@ -10,13 +10,14 @@
   line2: line,
   poly1: polygon,
   poly2: polygon,
-  rec: rectangle
+  rec: rectangle,
+  circle: circle
 }
 
 create nodegroup group1  if not exists on nc1, nc2;
 
 create dataset MyData(MyRecord)
-  partitioned by key id on group1;
+  primary key id on group1;
 
 load dataset MyData 
 using "edu.uci.ics.asterix.external.dataset.adapter.NCFileSystemAdapter"

diff --git a/asterix-app/src/test/resources/optimizerts/queries/scan-delete.aql b/asterix-app/src/test/resources/optimizerts/queries/scan-delete.aql
index 9bf6a4c..57e1bd3 100644
--- a/asterix-app/src/test/resources/optimizerts/queries/scan-delete.aql
+++ b/asterix-app/src/test/resources/optimizerts/queries/scan-delete.aql

@@ -31,9 +31,9 @@
 create nodegroup group1 if not exists on nc1, nc2;
 
 create dataset LineItems_q1(LineItemType)
-  partitioned by key l_orderkey on group1;
+  primary key l_orderkey on group1;
 
 create dataset LineID(LineIDType)
-  partitioned by key l_orderkey on group1;
+  primary key l_orderkey on group1;
 
 delete $l from dataset LineItems_q1 where $l.l_shipdate <= '1998-09-02';

diff --git a/asterix-app/src/test/resources/optimizerts/queries/scan-insert-secondary-index.aql b/asterix-app/src/test/resources/optimizerts/queries/scan-insert-secondary-index.aql
index afecc04..97bc8df 100644
--- a/asterix-app/src/test/resources/optimizerts/queries/scan-insert-secondary-index.aql
+++ b/asterix-app/src/test/resources/optimizerts/queries/scan-insert-secondary-index.aql

@@ -30,10 +30,10 @@
 create nodegroup group1 if not exists on nc1, nc2;
 
 create dataset LineItems_q1(LineItemType)
-  partitioned by key l_orderkey on group1;
+  primary key l_orderkey on group1;
 
 create dataset LineID(LineIDType)
-  partitioned by key l_orderkey on group1;
+  primary key l_orderkey on group1;
   
 create index idx_LineID_partkey on LineID(l_partkey);
 create index idx_LineID_suppkey on LineID(l_suppkey);

diff --git a/asterix-app/src/test/resources/optimizerts/queries/scan-insert.aql b/asterix-app/src/test/resources/optimizerts/queries/scan-insert.aql
index beb73a7..1c26a46 100644
--- a/asterix-app/src/test/resources/optimizerts/queries/scan-insert.aql
+++ b/asterix-app/src/test/resources/optimizerts/queries/scan-insert.aql

@@ -30,10 +30,10 @@
 create nodegroup group1 if not exists on nc1, nc2;
 
 create dataset LineItems_q1(LineItemType)
-  partitioned by key l_orderkey on group1;
+  primary key l_orderkey on group1;
 
 create dataset LineID(LineIDType)
-  partitioned by key l_orderkey on group1;
+  primary key l_orderkey on group1;
 
 insert into dataset LineID (
 for $l in dataset('LineItems_q1')

diff --git a/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-let-to-edit-distance-check_01.aql b/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-let-to-edit-distance-check_01.aql
new file mode 100644
index 0000000..4d63c15
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-let-to-edit-distance-check_01.aql

@@ -0,0 +1,28 @@
+/*
+ * Description    : Tests that the SimilarityCheckRule rewrites the edit-distance function with a threshold 
+ *                  into edit-distance-check if possible.
+ *                  Tests that the optimizer drills through the let clause.
+ *                  Replacement should happen because of a "<=" condition on the edit distance.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+write output to nc1:"rttest/similarity_edit-distance-let-to-edit-distance-check_01.adm";
+
+for $o in dataset('DBLP')
+let $ed := edit-distance($o.authors, "Michael J. Carey")
+where $ed <= 2
+return $ed
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-let-to-edit-distance-check_02.aql b/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-let-to-edit-distance-check_02.aql
new file mode 100644
index 0000000..762b41c
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-let-to-edit-distance-check_02.aql

@@ -0,0 +1,28 @@
+/*
+ * Description    : Tests that the SimilarityCheckRule rewrites the edit-distance function with a threshold 
+ *                  into edit-distance-check if possible.
+ *                  Tests that the optimizer drills through the let clause. 
+ *                  Replacement should happen because of a reverse "<=" condition on the edit distance.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+write output to nc1:"rttest/similarity_edit-distance-let-to-edit-distance-check_02.adm";
+
+for $o in dataset('DBLP')
+let $ed := edit-distance($o.authors, "Michael J. Carey")
+where 2 >= $ed
+return $ed
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-let-to-edit-distance-check_03.aql b/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-let-to-edit-distance-check_03.aql
new file mode 100644
index 0000000..e14f329
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-let-to-edit-distance-check_03.aql

@@ -0,0 +1,28 @@
+/*
+ * Description    : Tests that the SimilarityCheckRule rewrites the edit-distance function with a threshold 
+ *                  into edit-distance-check if possible.
+ *                  Tests that the optimizer drills through the let clause.
+ *                  Replacement should happen because of a "<" condition on the edit distance.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+write output to nc1:"rttest/similarity_edit-distance-let-to-edit-distance-check_03.adm";
+
+for $o in dataset('DBLP')
+let $ed := edit-distance($o.authors, "Michael J. Carey")
+where $ed < 3
+return $ed
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-let-to-edit-distance-check_04.aql b/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-let-to-edit-distance-check_04.aql
new file mode 100644
index 0000000..f539938
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-let-to-edit-distance-check_04.aql

@@ -0,0 +1,28 @@
+/*
+ * Description    : Tests that the SimilarityCheckRule rewrites the edit-distance function with a threshold 
+ *                  into edit-distance-check if possible.
+ *                  Tests that the optimizer drills through the let clause.
+ *                  Replacement should happen because of a reverse "<" condition on the edit distance.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+write output to nc1:"rttest/similarity_edit-distance-let-to-edit-distance-check_04.adm";
+
+for $o in dataset('DBLP')
+let $ed := edit-distance($o.authors, "Michael J. Carey")
+where 3 > $ed
+return $ed
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-let-to-edit-distance-check_05.aql b/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-let-to-edit-distance-check_05.aql
new file mode 100644
index 0000000..b126f67
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-let-to-edit-distance-check_05.aql

@@ -0,0 +1,28 @@
+/*
+ * Description    : Tests that the SimilarityCheckRule rewrites the edit-distance function with a threshold 
+ *                  into edit-distance-check if possible.
+ *                  Tests that the optimizer drills through the let clause.
+ *                  Replacement should *not* happen because of a ">=" condition on the edit distance.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+write output to nc1:"rttest/similarity_edit-distance-let-to-edit-distance-check_05.adm";
+
+for $o in dataset('DBLP')
+let $ed := edit-distance($o.authors, "Michael J. Carey")
+where $ed >= 2
+return $ed
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-let-to-edit-distance-check_06.aql b/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-let-to-edit-distance-check_06.aql
new file mode 100644
index 0000000..f32285e
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-let-to-edit-distance-check_06.aql

@@ -0,0 +1,28 @@
+/*
+ * Description    : Tests that the SimilarityCheckRule rewrites the edit-distance function with a threshold 
+ *                  into edit-distance-check if possible.
+ *                  Tests that the optimizer drills through the let clause.
+ *                   Replacement should *not* happen because of a reverse ">=" condition on the edit distance.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+write output to nc1:"rttest/similarity_edit-distance-let-to-edit-distance-check_06.adm";
+
+for $o in dataset('DBLP')
+let $ed := edit-distance($o.authors, "Michael J. Carey")
+where 2 <= $ed
+return $ed
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-let-to-edit-distance-check_07.aql b/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-let-to-edit-distance-check_07.aql
new file mode 100644
index 0000000..2dff7e5
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-let-to-edit-distance-check_07.aql

@@ -0,0 +1,28 @@
+/*
+ * Description    : Tests that the SimilarityCheckRule rewrites the edit-distance function with a threshold 
+ *                  into edit-distance-check if possible.
+ *                  Tests that the optimizer drills through the let clause.
+ *                  Replacement should *not* happen because of a ">" condition on the edit distance.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+write output to nc1:"rttest/similarity_edit-distance-let-to-edit-distance-check_07.adm";
+
+for $o in dataset('DBLP')
+let $ed := edit-distance($o.authors, "Michael J. Carey")
+where $ed > 2
+return $ed
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-let-to-edit-distance-check_08.aql b/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-let-to-edit-distance-check_08.aql
new file mode 100644
index 0000000..9bc10e6
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-let-to-edit-distance-check_08.aql

@@ -0,0 +1,28 @@
+/*
+ * Description    : Tests that the SimilarityCheckRule rewrites the edit-distance function with a threshold 
+ *                  into edit-distance-check if possible.
+ *                  Tests that the optimizer drills through the let clause.
+ *                  Replacement should *not* happen because of a reverse ">" condition on the edit distance.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+write output to nc1:"rttest/similarity_edit-distance-let-to-edit-distance-check_08.adm";
+
+for $o in dataset('DBLP')
+let $ed := edit-distance($o.authors, "Michael J. Carey")
+where 2 < $ed
+return $ed
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-to-edit-distance-check_01.aql b/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-to-edit-distance-check_01.aql
new file mode 100644
index 0000000..09e962c
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-to-edit-distance-check_01.aql

@@ -0,0 +1,26 @@
+/*
+ * Description    : Tests that the SimilarityCheckRule rewrites the edit-distance function with a threshold 
+ *                  into edit-distance-check if possible.
+ *                  Replacement should happen because of a "<=" condition on the edit distance.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+write output to nc1:"rttest/similarity_edit-distance-to-edit-distance-check_01.adm";
+
+for $o in dataset('DBLP')
+where edit-distance($o.authors, "Michael J. Carey") <= 2
+return $o

diff --git a/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-to-edit-distance-check_02.aql b/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-to-edit-distance-check_02.aql
new file mode 100644
index 0000000..35e28fc
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-to-edit-distance-check_02.aql

@@ -0,0 +1,26 @@
+/*
+ * Description    : Tests that the SimilarityCheckRule rewrites the edit-distance function with a threshold 
+ *                  into edit-distance-check if possible.
+ *                  Replacement should happen because of a reverse "<=" condition on the edit distance.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+write output to nc1:"rttest/similarity_edit-distance-to-edit-distance-check_02.adm";
+
+for $o in dataset('DBLP')
+where 2 >= edit-distance($o.authors, "Michael J. Carey")
+return $o
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-to-edit-distance-check_03.aql b/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-to-edit-distance-check_03.aql
new file mode 100644
index 0000000..e05f85a
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-to-edit-distance-check_03.aql

@@ -0,0 +1,26 @@
+/*
+ * Description    : Tests that the SimilarityCheckRule rewrites the edit-distance function with a threshold 
+ *                  into edit-distance-check if possible.
+ *                  Replacement should happen because of a "<" condition on the edit distance.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+write output to nc1:"rttest/similarity_edit-distance-to-edit-distance-check_03.adm";
+
+for $o in dataset('DBLP')
+where edit-distance($o.authors, "Michael J. Carey") < 3
+return $o
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-to-edit-distance-check_04.aql b/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-to-edit-distance-check_04.aql
new file mode 100644
index 0000000..b890967
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-to-edit-distance-check_04.aql

@@ -0,0 +1,26 @@
+/*
+ * Description    : Tests that the SimilarityCheckRule rewrites the edit-distance function with a threshold 
+ *                  into edit-distance-check if possible.
+ *                  Replacement should happen because of a reverse "<" condition on the edit distance.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+write output to nc1:"rttest/similarity_edit-distance-to-edit-distance-check_04.adm";
+
+for $o in dataset('DBLP')
+where 3 > edit-distance($o.authors, "Michael J. Carey")
+return $o
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-to-edit-distance-check_05.aql b/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-to-edit-distance-check_05.aql
new file mode 100644
index 0000000..bc66061
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-to-edit-distance-check_05.aql

@@ -0,0 +1,27 @@
+/*
+ * Description    : Tests that the SimilarityCheckRule rewrites the edit-distance function with a threshold 
+ *                  into edit-distance-check if possible.
+ *                  Replacement should *not* happen because of a ">=" condition on the edit distance.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+write output to nc1:"rttest/similarity_edit-distance-to-edit-distance-check_05.adm";
+
+// We cannot introduce edit-distance-check because the condition is >=
+for $o in dataset('DBLP')
+where edit-distance($o.authors, "Michael J. Carey") >= 2
+return $o
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-to-edit-distance-check_06.aql b/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-to-edit-distance-check_06.aql
new file mode 100644
index 0000000..018d6d1
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-to-edit-distance-check_06.aql

@@ -0,0 +1,27 @@
+/*
+ * Description    : Tests that the SimilarityCheckRule rewrites the edit-distance function with a threshold 
+ *                  into edit-distance-check if possible.
+ *                  Replacement should *not* happen because of a reverse ">=" condition on the edit distance.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+write output to nc1:"rttest/similarity_edit-distance-to-edit-distance-check_06.adm";
+
+// We cannot introduce edit-distance-check because the condition is <=
+for $o in dataset('DBLP')
+where 2 <= edit-distance($o.authors, "Michael J. Carey")
+return $o
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-to-edit-distance-check_07.aql b/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-to-edit-distance-check_07.aql
new file mode 100644
index 0000000..cdaefa9
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-to-edit-distance-check_07.aql

@@ -0,0 +1,27 @@
+/*
+ * Description    : Tests that the SimilarityCheckRule rewrites the edit-distance function with a threshold 
+ *                  into edit-distance-check if possible.
+ *                  Replacement should *not* happen because of a ">" condition on the edit distance.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+write output to nc1:"rttest/similarity_edit-distance-to-edit-distance-check_07.adm";
+
+// We cannot introduce edit-distance-check because the condition is >
+for $o in dataset('DBLP')
+where edit-distance($o.authors, "Michael J. Carey") > 2
+return $o
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-to-edit-distance-check_08.aql b/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-to-edit-distance-check_08.aql
new file mode 100644
index 0000000..745044f
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/similarity/edit-distance-to-edit-distance-check_08.aql

@@ -0,0 +1,27 @@
+/*
+ * Description    : Tests that the SimilarityCheckRule rewrites the edit-distance function with a threshold 
+ *                  into edit-distance-check if possible.
+ *                  Replacement should *not* happen because of a reverse ">" condition on the edit distance.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+write output to nc1:"rttest/similarity_edit-distance-to-edit-distance-check_08.adm";
+
+// We cannot introduce edit-distance-check because the condition is <
+for $o in dataset('DBLP')
+where 2 < edit-distance($o.authors, "Michael J. Carey")
+return $o
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/similarity/fuzzyeq-to-edit-distance-check.aql b/asterix-app/src/test/resources/optimizerts/queries/similarity/fuzzyeq-to-edit-distance-check.aql
new file mode 100644
index 0000000..f6e9d52
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/similarity/fuzzyeq-to-edit-distance-check.aql

@@ -0,0 +1,29 @@
+/*
+ * Description    : Tests that the FuzzyEqRule rewrites ~= using edit distance 
+ *                  into edit-distance-check.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+write output to nc1:"rttest/similarity_fuzzyeq-to-edit-distance-check.adm";
+
+set simfunction 'edit-distance';
+set simthreshold '1';
+
+// Tests two rules: FuzzyEqRule and SimilarityCheckRule
+for $o in dataset('DBLP')
+where $o.authors ~= "Michael J. Carey"
+return $o
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/similarity/fuzzyeq-to-jaccard-check.aql b/asterix-app/src/test/resources/optimizerts/queries/similarity/fuzzyeq-to-jaccard-check.aql
new file mode 100644
index 0000000..5f57a3e
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/similarity/fuzzyeq-to-jaccard-check.aql

@@ -0,0 +1,29 @@
+/*
+ * Description    : Tests that the FuzzyEqRule rewrites ~= using Jaccard 
+ *                  into edit-distance-check.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+write output to nc1:"rttest/similarity_fuzzyeq-to-jaccard-check.adm";
+
+set simfunction 'jaccard';
+set simthreshold '0.8f';
+
+// Tests two rules: FuzzyEqRule and SimilarityCheckRule
+for $paper in dataset('DBLP')
+where word-tokens($paper.title) ~= word-tokens("Transactions for Cooperative Environments")
+return $paper
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-let-to-jaccard-check_01.aql b/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-let-to-jaccard-check_01.aql
new file mode 100644
index 0000000..733c6d9
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-let-to-jaccard-check_01.aql

@@ -0,0 +1,28 @@
+/*
+ * Description    : Tests that the SimilarityCheckRule rewrites the similarity-jaccard function with a threshold 
+ *                  into similarity-jaccard-check-check if possible.
+ *                  Tests that the optimizer drills through the let clause.
+ *                  Replacement should happen because of a ">=" condition on the similarity.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+write output to nc1:"rttest/similarity_jaccard-let-to-jaccard-check_01.adm";
+
+for $paper in dataset('DBLP')
+let $jacc := similarity-jaccard(word-tokens($paper.title), word-tokens("Transactions for Cooperative Environments"))
+where $jacc >= 0.8f
+return $jacc

diff --git a/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-let-to-jaccard-check_02.aql b/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-let-to-jaccard-check_02.aql
new file mode 100644
index 0000000..a360ef1
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-let-to-jaccard-check_02.aql

@@ -0,0 +1,28 @@
+/*
+ * Description    : Tests that the SimilarityCheckRule rewrites the similarity-jaccard function with a threshold 
+ *                  into similarity-jaccard-check-check if possible.
+ *                  Tests that the optimizer drills through the let clause.
+ *                  Replacement should happen because of a reverse ">=" condition on the similarity.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+write output to nc1:"rttest/similarity_jaccard-let-to-jaccard-check_01.adm";
+
+for $paper in dataset('DBLP')
+let $jacc := similarity-jaccard(word-tokens($paper.title), word-tokens("Transactions for Cooperative Environments"))
+where 0.8f <= $jacc 
+return $jacc

diff --git a/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-let-to-jaccard-check_03.aql b/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-let-to-jaccard-check_03.aql
new file mode 100644
index 0000000..ad8abca
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-let-to-jaccard-check_03.aql

@@ -0,0 +1,28 @@
+/*
+ * Description    : Tests that the SimilarityCheckRule rewrites the similarity-jaccard function with a threshold 
+ *                  into similarity-jaccard-check-check if possible.
+ *                  Tests that the optimizer drills through the let clause.
+ *                  Replacement should happen because of a ">" condition on the similarity.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+write output to nc1:"rttest/similarity_jaccard-let-to-jaccard-check_01.adm";
+
+for $paper in dataset('DBLP')
+let $jacc := similarity-jaccard(word-tokens($paper.title), word-tokens("Transactions for Cooperative Environments"))
+where $jacc > 0.8f
+return $jacc

diff --git a/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-let-to-jaccard-check_04.aql b/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-let-to-jaccard-check_04.aql
new file mode 100644
index 0000000..fd236de
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-let-to-jaccard-check_04.aql

@@ -0,0 +1,28 @@
+/*
+ * Description    : Tests that the SimilarityCheckRule rewrites the similarity-jaccard function with a threshold 
+ *                  into similarity-jaccard-check-check if possible.
+ *                  Tests that the optimizer drills through the let clause.
+ *                  Replacement should happen because of a reverse ">" condition on the similarity.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+write output to nc1:"rttest/similarity_jaccard-let-to-jaccard-check_01.adm";
+
+for $paper in dataset('DBLP')
+let $jacc := similarity-jaccard(word-tokens($paper.title), word-tokens("Transactions for Cooperative Environments"))
+where 0.8f < $jacc 
+return $jacc

diff --git a/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-let-to-jaccard-check_05.aql b/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-let-to-jaccard-check_05.aql
new file mode 100644
index 0000000..b750a5d
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-let-to-jaccard-check_05.aql

@@ -0,0 +1,28 @@
+/*
+ * Description    : Tests that the SimilarityCheckRule rewrites the similarity-jaccard function with a threshold 
+ *                  into similarity-jaccard-check-check if possible.
+ *                  Tests that the optimizer drills through the let clause.
+ *                  Replacement should *not* happen because of a "<=" condition on the similarity.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+write output to nc1:"rttest/similarity_jaccard-let-to-jaccard-check_01.adm";
+
+for $paper in dataset('DBLP')
+let $jacc := similarity-jaccard(word-tokens($paper.title), word-tokens("Transactions for Cooperative Environments"))
+where $jacc <= 0.8f
+return $jacc

diff --git a/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-let-to-jaccard-check_06.aql b/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-let-to-jaccard-check_06.aql
new file mode 100644
index 0000000..56b1471
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-let-to-jaccard-check_06.aql

@@ -0,0 +1,28 @@
+/*
+ * Description    : Tests that the SimilarityCheckRule rewrites the similarity-jaccard function with a threshold 
+ *                  into similarity-jaccard-check-check if possible.
+ *                  Tests that the optimizer drills through the let clause.
+ *                  Replacement should *not* happen because of a reverse "<=" condition on the similarity.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+write output to nc1:"rttest/similarity_jaccard-let-to-jaccard-check_01.adm";
+
+for $paper in dataset('DBLP')
+let $jacc := similarity-jaccard(word-tokens($paper.title), word-tokens("Transactions for Cooperative Environments"))
+where 0.8f >= $jacc 
+return $jacc

diff --git a/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-let-to-jaccard-check_07.aql b/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-let-to-jaccard-check_07.aql
new file mode 100644
index 0000000..6ae0444
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-let-to-jaccard-check_07.aql

@@ -0,0 +1,28 @@
+/*
+ * Description    : Tests that the SimilarityCheckRule rewrites the similarity-jaccard function with a threshold 
+ *                  into similarity-jaccard-check-check if possible.
+ *                  Tests that the optimizer drills through the let clause.
+ *                  Replacement should *not* happen because of a "<" condition on the similarity.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+write output to nc1:"rttest/similarity_jaccard-let-to-jaccard-check_01.adm";
+
+for $paper in dataset('DBLP')
+let $jacc := similarity-jaccard(word-tokens($paper.title), word-tokens("Transactions for Cooperative Environments"))
+where $jacc < 0.8f
+return $jacc

diff --git a/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-let-to-jaccard-check_08.aql b/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-let-to-jaccard-check_08.aql
new file mode 100644
index 0000000..5d04402
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-let-to-jaccard-check_08.aql

@@ -0,0 +1,28 @@
+/*
+ * Description    : Tests that the SimilarityCheckRule rewrites the similarity-jaccard function with a threshold 
+ *                  into similarity-jaccard-check-check if possible.
+ *                  Tests that the optimizer drills through the let clause.
+ *                  Replacement should *not* happen because of a reverse "<" condition on the similarity.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+write output to nc1:"rttest/similarity_jaccard-let-to-jaccard-check_01.adm";
+
+for $paper in dataset('DBLP')
+let $jacc := similarity-jaccard(word-tokens($paper.title), word-tokens("Transactions for Cooperative Environments"))
+where 0.8f > $jacc 
+return $jacc

diff --git a/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-to-jaccard-check_01.aql b/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-to-jaccard-check_01.aql
new file mode 100644
index 0000000..33eb133
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-to-jaccard-check_01.aql

@@ -0,0 +1,26 @@
+/*
+ * Description    : Tests that the SimilarityCheckRule rewrites the similarity-jaccard function with a threshold 
+ *                  into similarity-jaccard-check-check if possible.
+ *                  Replacement should happen because of a ">=" condition on the similarity.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+write output to nc1:"rttest/similarity_jaccard-to-jaccard-check_01.adm";
+
+for $paper in dataset('DBLP')
+where similarity-jaccard(word-tokens($paper.title), word-tokens("Transactions for Cooperative Environments")) >= 0.8f
+return $paper
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-to-jaccard-check_02.aql b/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-to-jaccard-check_02.aql
new file mode 100644
index 0000000..3bdf01f
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-to-jaccard-check_02.aql

@@ -0,0 +1,26 @@
+/*
+ * Description    : Tests that the SimilarityCheckRule rewrites the similarity-jaccard function with a threshold 
+ *                  into similarity-jaccard-check-check if possible.
+ *                  Replacement should happen because of a reverse ">=" condition on the similarity.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+write output to nc1:"rttest/similarity_jaccard-to-jaccard-check_02.adm";
+
+for $paper in dataset('DBLP')
+where 0.8f <= similarity-jaccard(word-tokens($paper.title), word-tokens("Transactions for Cooperative Environments"))
+return $paper
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-to-jaccard-check_03.aql b/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-to-jaccard-check_03.aql
new file mode 100644
index 0000000..3a22a16
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-to-jaccard-check_03.aql

@@ -0,0 +1,26 @@
+/*
+ * Description    : Tests that the SimilarityCheckRule rewrites the similarity-jaccard function with a threshold 
+ *                  into similarity-jaccard-check-check if possible.
+ *                  Replacement should happen because of a ">" condition on the similarity.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+write output to nc1:"rttest/similarity_jaccard-to-jaccard-check_02.adm";
+
+for $paper in dataset('DBLP')
+where similarity-jaccard(word-tokens($paper.title), word-tokens("Transactions for Cooperative Environments")) > 0.8f
+return $paper
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-to-jaccard-check_04.aql b/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-to-jaccard-check_04.aql
new file mode 100644
index 0000000..bdce095
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-to-jaccard-check_04.aql

@@ -0,0 +1,26 @@
+/*
+ * Description    : Tests that the SimilarityCheckRule rewrites the similarity-jaccard function with a threshold 
+ *                  into similarity-jaccard-check-check if possible.
+ *                  Replacement should happen because of a reverse ">" condition on the similarity.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+write output to nc1:"rttest/similarity_jaccard-to-jaccard-check_03.adm";
+
+for $paper in dataset('DBLP')
+where 0.8f < similarity-jaccard(word-tokens($paper.title), word-tokens("Transactions for Cooperative Environments"))
+return $paper
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-to-jaccard-check_05.aql b/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-to-jaccard-check_05.aql
new file mode 100644
index 0000000..977f22a
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-to-jaccard-check_05.aql

@@ -0,0 +1,27 @@
+/*
+ * Description    : Tests that the SimilarityCheckRule rewrites the similarity-jaccard function with a threshold 
+ *                  into similarity-jaccard-check-check if possible.
+ *                  Replacement should *not* happen because of a "<=" condition on the similarity.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+write output to nc1:"rttest/similarity_jaccard-to-jaccard-check_05.adm";
+
+// We cannot introduce jaccard-check because the condition is <=
+for $paper in dataset('DBLP')
+where similarity-jaccard(word-tokens($paper.title), word-tokens("Transactions for Cooperative Environments")) <= 0.8f
+return $paper
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-to-jaccard-check_06.aql b/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-to-jaccard-check_06.aql
new file mode 100644
index 0000000..eb3f3ef
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-to-jaccard-check_06.aql

@@ -0,0 +1,27 @@
+/*
+ * Description    : Tests that the SimilarityCheckRule rewrites the similarity-jaccard function with a threshold 
+ *                  into similarity-jaccard-check-check if possible.
+ *                  Replacement should *not* happen because of a reverse "<=" condition on the similarity.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+write output to nc1:"rttest/similarity_jaccard-to-jaccard-check_06.adm";
+
+// We cannot introduce jaccard-check because the condition is >=
+for $paper in dataset('DBLP')
+where 0.8f >= similarity-jaccard(word-tokens($paper.title), word-tokens("Transactions for Cooperative Environments"))
+return $paper
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-to-jaccard-check_07.aql b/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-to-jaccard-check_07.aql
new file mode 100644
index 0000000..753ce3c
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-to-jaccard-check_07.aql

@@ -0,0 +1,27 @@
+/*
+ * Description    : Tests that the SimilarityCheckRule rewrites the similarity-jaccard function with a threshold 
+ *                  into similarity-jaccard-check-check if possible.
+ *                  Replacement should *not* happen because of a "<" condition on the similarity.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+write output to nc1:"rttest/similarity_jaccard-to-jaccard-check_07.adm";
+
+// We cannot introduce jaccard-check because the condition is <
+for $paper in dataset('DBLP')
+where similarity-jaccard(word-tokens($paper.title), word-tokens("Transactions for Cooperative Environments")) < 0.8f
+return $paper
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-to-jaccard-check_08.aql b/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-to-jaccard-check_08.aql
new file mode 100644
index 0000000..2d1bd93
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/similarity/jaccard-to-jaccard-check_08.aql

@@ -0,0 +1,27 @@
+/*
+ * Description    : Tests that the SimilarityCheckRule rewrites the similarity-jaccard function with a threshold 
+ *                  into similarity-jaccard-check-check if possible.
+ *                  Replacement should *not* happen because of a reverse "<" condition on the similarity.
+ * 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 dataset DBLP(DBLPType) primary key id;
+
+write output to nc1:"rttest/similarity_jaccard-to-jaccard-check_08.adm";
+
+// We cannot introduce jaccard-check because the condition is >
+for $paper in dataset('DBLP')
+where 0.8f > similarity-jaccard(word-tokens($paper.title), word-tokens("Transactions for Cooperative Environments"))
+return $paper
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/sort-cust.aql b/asterix-app/src/test/resources/optimizerts/queries/sort-cust.aql
index ec4f6f1..9605b37 100644
--- a/asterix-app/src/test/resources/optimizerts/queries/sort-cust.aql
+++ b/asterix-app/src/test/resources/optimizerts/queries/sort-cust.aql

@@ -27,7 +27,7 @@
 create nodegroup group1 if not exists on nc1, nc2;
 
 create dataset Customers(CustomerType)
-  partitioned by key cid on group1;
+  primary key cid on group1;
 
 write output to nc1:"/tmp/custlimit.adm";
 

diff --git a/asterix-app/src/test/resources/optimizerts/queries/unnest-to-join_01.aql b/asterix-app/src/test/resources/optimizerts/queries/unnest-to-join_01.aql
new file mode 100644
index 0000000..85ee87a
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/unnest-to-join_01.aql

@@ -0,0 +1,15 @@
+/*
+ * Description    : Tests that non-datascan unnests are rewritten into joins.
+ * Success        : Yes
+ */
+ 
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/unnest-to-join_01.adm";
+
+for $x in [1,2,3,4,5,6]
+for $y in [4,5,6,7,8,9]
+where $x = $y
+return $y
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/unnest-to-join_02.aql b/asterix-app/src/test/resources/optimizerts/queries/unnest-to-join_02.aql
new file mode 100644
index 0000000..2402eb0
--- /dev/null
+++ b/asterix-app/src/test/resources/optimizerts/queries/unnest-to-join_02.aql

@@ -0,0 +1,12 @@
+/*
+ * Description    : Tests that non-datascan unnests in a subplan are rewritten into joins.
+ * Success        : Yes
+ */
+ 
+drop dataverse test if exists;
+create dataverse test;
+use dataverse test;
+
+write output to nc1:"rttest/unnest-to-join_02.adm";
+
+some $x in [1,2,3,4,5,6], $y in [4,5,6,7,8,9] satisfies $x = $y
\ No newline at end of file

diff --git a/asterix-app/src/test/resources/optimizerts/queries/unnest_list_in_subplan.aql b/asterix-app/src/test/resources/optimizerts/queries/unnest_list_in_subplan.aql
index 5a943f1..3f34242 100644
--- a/asterix-app/src/test/resources/optimizerts/queries/unnest_list_in_subplan.aql
+++ b/asterix-app/src/test/resources/optimizerts/queries/unnest_list_in_subplan.aql

@@ -17,8 +17,8 @@
 
 create nodegroup group1 if not exists on nc1, nc2;
 
-create dataset DBLP(DBLPType) partitioned by key id on group1;
-create dataset TOKENSRANKEDADM(TOKENSRANKEDADMType) partitioned by key rank on group1;
+create dataset DBLP(DBLPType) primary key id on group1;
+create dataset TOKENSRANKEDADM(TOKENSRANKEDADMType) primary key rank on group1;
 
 write output to nc1:'rttest/unnest_list_in_subplan.adm';
commit	5ee049d45ea3aa9e6317cd59063e2e0b4f2d4d4c	[log] [tgz]
author	vinayakb <vinayakb@eaa15691-b419-025a-1212-ee371bd00084>	Sat Apr 06 21:21:29 2013 +0000
committer	vinayakb <vinayakb@eaa15691-b419-025a-1212-ee371bd00084>	Sat Apr 06 21:21:29 2013 +0000
tree	8f8ff948c7f4786d5950fdbc75c56fa5027f2e97
parent	a13f242d1b42dd3e21079c5ace934ae20ecae218 [diff]