[SPARK-22787][TEST][SQL] Add a TPC-H query suite

## What changes were proposed in this pull request?
Add a test suite to ensure all the TPC-H queries can be successfully analyzed, optimized and compiled without hitting the max iteration threshold.

## How was this patch tested?
N/A

Author: gatorsmile <[email protected]>

Closes apache#19982 from gatorsmile/testTPCH.

Author: gatorsmile

sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/text/TextFileFormat.scala

@@ -116,9 +116,10 @@ class TextFileFormat extends TextBasedFileFormat with DataSourceRegister {
     readToUnsafeMem(broadcastedHadoopConf, requiredSchema, textOptions.wholeText)
   }
 
-  private def readToUnsafeMem(conf: Broadcast[SerializableConfiguration],
-      requiredSchema: StructType, wholeTextMode: Boolean):
-  (PartitionedFile) => Iterator[UnsafeRow] = {
+  private def readToUnsafeMem(
+      conf: Broadcast[SerializableConfiguration],
+      requiredSchema: StructType,
+      wholeTextMode: Boolean): (PartitionedFile) => Iterator[UnsafeRow] = {
 
     (file: PartitionedFile) => {
       val confValue = conf.value.value

sql/core/src/test/resources/tpch/q1.sql

@@ -0,0 +1,23 @@
+-- using default substitutions
+
+select
+	l_returnflag,
+	l_linestatus,
+	sum(l_quantity) as sum_qty,
+	sum(l_extendedprice) as sum_base_price,
+	sum(l_extendedprice * (1 - l_discount)) as sum_disc_price,
+	sum(l_extendedprice * (1 - l_discount) * (1 + l_tax)) as sum_charge,
+	avg(l_quantity) as avg_qty,
+	avg(l_extendedprice) as avg_price,
+	avg(l_discount) as avg_disc,
+	count(*) as count_order
+from
+	lineitem
+where
+	l_shipdate <= date '1998-12-01' - interval '90' day
+group by
+	l_returnflag,
+	l_linestatus
+order by
+	l_returnflag,
+	l_linestatus

sql/core/src/test/resources/tpch/q10.sql

@@ -0,0 +1,34 @@
+-- using default substitutions
+
+select
+	c_custkey,
+	c_name,
+	sum(l_extendedprice * (1 - l_discount)) as revenue,
+	c_acctbal,
+	n_name,
+	c_address,
+	c_phone,
+	c_comment
+from
+	customer,
+	orders,
+	lineitem,
+	nation
+where
+	c_custkey = o_custkey
+	and l_orderkey = o_orderkey
+	and o_orderdate >= date '1993-10-01'
+	and o_orderdate < date '1993-10-01' + interval '3' month
+	and l_returnflag = 'R'
+	and c_nationkey = n_nationkey
+group by
+	c_custkey,
+	c_name,
+	c_acctbal,
+	c_phone,
+	n_name,
+	c_address,
+	c_comment
+order by
+	revenue desc
+limit 20

sql/core/src/test/resources/tpch/q11.sql

@@ -0,0 +1,29 @@
+-- using default substitutions
+
+select
+	ps_partkey,
+	sum(ps_supplycost * ps_availqty) as value
+from
+	partsupp,
+	supplier,
+	nation
+where
+	ps_suppkey = s_suppkey
+	and s_nationkey = n_nationkey
+	and n_name = 'GERMANY'
+group by
+	ps_partkey having
+		sum(ps_supplycost * ps_availqty) > (
+			select
+				sum(ps_supplycost * ps_availqty) * 0.0001000000
+			from
+				partsupp,
+				supplier,
+				nation
+			where
+				ps_suppkey = s_suppkey
+				and s_nationkey = n_nationkey
+				and n_name = 'GERMANY'
+		)
+order by
+	value desc

sql/core/src/test/resources/tpch/q12.sql

@@ -0,0 +1,30 @@
+-- using default substitutions
+
+select
+	l_shipmode,
+	sum(case
+		when o_orderpriority = '1-URGENT'
+			or o_orderpriority = '2-HIGH'
+			then 1
+		else 0
+	end) as high_line_count,
+	sum(case
+		when o_orderpriority <> '1-URGENT'
+			and o_orderpriority <> '2-HIGH'
+			then 1
+		else 0
+	end) as low_line_count
+from
+	orders,
+	lineitem
+where
+	o_orderkey = l_orderkey
+	and l_shipmode in ('MAIL', 'SHIP')
+	and l_commitdate < l_receiptdate
+	and l_shipdate < l_commitdate
+	and l_receiptdate >= date '1994-01-01'
+	and l_receiptdate < date '1994-01-01' + interval '1' year
+group by
+	l_shipmode
+order by
+	l_shipmode

sql/core/src/test/resources/tpch/q13.sql

@@ -0,0 +1,22 @@
+-- using default substitutions
+
+select
+	c_count,
+	count(*) as custdist
+from
+	(
+		select
+			c_custkey,
+			count(o_orderkey) as c_count
+		from
+			customer left outer join orders on
+				c_custkey = o_custkey
+				and o_comment not like '%special%requests%'
+		group by
+			c_custkey
+	) as c_orders
+group by
+	c_count
+order by
+	custdist desc,
+	c_count desc

sql/core/src/test/resources/tpch/q14.sql

@@ -0,0 +1,15 @@
+-- using default substitutions
+
+select
+	100.00 * sum(case
+		when p_type like 'PROMO%'
+			then l_extendedprice * (1 - l_discount)
+		else 0
+	end) / sum(l_extendedprice * (1 - l_discount)) as promo_revenue
+from
+	lineitem,
+	part
+where
+	l_partkey = p_partkey
+	and l_shipdate >= date '1995-09-01'
+	and l_shipdate < date '1995-09-01' + interval '1' month

sql/core/src/test/resources/tpch/q15.sql

@@ -0,0 +1,35 @@
+-- using default substitutions
+
+with revenue0 as
+	(select
+		l_suppkey as supplier_no,
+		sum(l_extendedprice * (1 - l_discount)) as total_revenue
+	from
+		lineitem
+	where
+		l_shipdate >= date '1996-01-01'
+		and l_shipdate < date '1996-01-01' + interval '3' month
+	group by
+		l_suppkey)
+
+
+select
+	s_suppkey,
+	s_name,
+	s_address,
+	s_phone,
+	total_revenue
+from
+	supplier,
+	revenue0
+where
+	s_suppkey = supplier_no
+	and total_revenue = (
+		select
+			max(total_revenue)
+		from
+			revenue0
+	)
+order by
+	s_suppkey
+

sql/core/src/test/resources/tpch/q16.sql

@@ -0,0 +1,32 @@
+-- using default substitutions
+
+select
+	p_brand,
+	p_type,
+	p_size,
+	count(distinct ps_suppkey) as supplier_cnt
+from
+	partsupp,
+	part
+where
+	p_partkey = ps_partkey
+	and p_brand <> 'Brand#45'
+	and p_type not like 'MEDIUM POLISHED%'
+	and p_size in (49, 14, 23, 45, 19, 3, 36, 9)
+	and ps_suppkey not in (
+		select
+			s_suppkey
+		from
+			supplier
+		where
+			s_comment like '%Customer%Complaints%'
+	)
+group by
+	p_brand,
+	p_type,
+	p_size
+order by
+	supplier_cnt desc,
+	p_brand,
+	p_type,
+	p_size

sql/core/src/test/resources/tpch/q17.sql

@@ -0,0 +1,19 @@
+-- using default substitutions
+
+select
+	sum(l_extendedprice) / 7.0 as avg_yearly
+from
+	lineitem,
+	part
+where
+	p_partkey = l_partkey
+	and p_brand = 'Brand#23'
+	and p_container = 'MED BOX'
+	and l_quantity < (
+		select
+			0.2 * avg(l_quantity)
+		from
+			lineitem
+		where
+			l_partkey = p_partkey
+	)