Add better automated tests for Arrow columnar copy in HostColumnarToG…

…pu (#1665)

* Add Data source v2 test classes

Signed-off-by: Thomas Graves <tgraves@nvidia.com>

* update v2 source testing

* fix batch num rows and logging

* update the numberin batch

* Fix issue with reading booleans from ArrowColumnVectors and add more
tests

* move test file so pytest regex pick it up

* add comments

* fix line length

Signed-off-by: Thomas Graves <tgraves@nvidia.com>

integration_tests/src/main/python/datasourcev2_read_test.py

@@ -0,0 +1,42 @@
+# Copyright (c) 2021, NVIDIA CORPORATION.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import pytest
+
+from asserts import assert_gpu_and_cpu_are_equal_collect
+
+columnarClass = 'com.nvidia.spark.rapids.tests.datasourcev2.parquet.ArrowColumnarDataSourceV2'
+
+def readTable(types, classToUse):
+    return lambda spark: spark.read\
+        .option("arrowTypes", types)\
+        .format(classToUse).load()\
+        .orderBy("col1")
+
+def test_read_int():
+    assert_gpu_and_cpu_are_equal_collect(readTable("int", columnarClass))
+
+def test_read_strings():
+    assert_gpu_and_cpu_are_equal_collect(readTable("string", columnarClass))
+
+def test_read_all_types():
+    assert_gpu_and_cpu_are_equal_collect(
+       readTable("int,bool,byte,short,long,string,float,double,date,timestamp", columnarClass),
+            conf={'spark.rapids.sql.castFloatToString.enabled': 'true'})
+
+def test_read_arrow_off():
+    assert_gpu_and_cpu_are_equal_collect(
+        readTable("int,bool,byte,short,long,string,float,double,date,timestamp", columnarClass),
+            conf={'spark.rapids.arrowCopyOptmizationEnabled': 'false',
+                  'spark.rapids.sql.castFloatToString.enabled': 'true'})