[HUDI-2388] Add DAG nodes for Spark SQL in integration test suite (#3583)

- Fixed validation in integ test suite for both deltastreamer and write client path. 

Co-authored-by: Sivabalan Narayanan <n.siva.b@gmail.com>

docker/demo/config/log4j.properties

@@ -21,12 +21,12 @@ log4j.appender.console=org.apache.log4j.ConsoleAppender
 log4j.appender.console.target=System.err
 log4j.appender.console.layout=org.apache.log4j.PatternLayout
 log4j.appender.console.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss} %p %c{1}: %m%n
-
 # Set the default spark-shell log level to WARN. When running the spark-shell, the
 # log level for this class is used to overwrite the root logger's log level, so that
 # the user can have different defaults for the shell and regular Spark apps.
 log4j.logger.org.apache.spark.repl.Main=WARN
-
+# Set logging of integration testsuite to INFO level
+log4j.logger.org.apache.hudi.integ.testsuite=INFO
 # Settings to quiet third party logs that are too verbose
 log4j.logger.org.spark_project.jetty=WARN
 log4j.logger.org.spark_project.jetty.util.component.AbstractLifeCycle=ERROR
@@ -35,7 +35,6 @@ log4j.logger.org.apache.spark.repl.SparkILoop$SparkILoopInterpreter=INFO
 log4j.logger.org.apache.parquet=ERROR
 log4j.logger.parquet=ERROR
 log4j.logger.org.apache.spark=WARN
-
 # SPARK-9183: Settings to avoid annoying messages when looking up nonexistent UDFs in SparkSQL with Hive support
 log4j.logger.org.apache.hadoop.hive.metastore.RetryingHMSHandler=FATAL
 log4j.logger.org.apache.hadoop.hive.ql.exec.FunctionRegistry=ERROR

docker/demo/config/test-suite/spark-sql-nonpartitioned-external-cow-ctas.yaml

@@ -0,0 +1,45 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+dag_name: spark-sql-nonpartitioned-managed-cow-ctas.yaml
+dag_rounds: 1
+dag_intermittent_delay_mins: 1
+dag_content:
+  create_table:
+    config:
+      table_type: cow
+      is_external: true
+      primary_key: _row_key
+      pre_combine_field: test_suite_source_ordering_field
+      use_ctas: true
+      record_size: 1000
+      num_partitions_insert: 1
+      repeat_count: 1
+      num_records_insert: 1000
+    type: spark.sql.SparkSqlCreateTableNode
+    deps: none
+  insert_records:
+    config:
+      record_size: 1000
+      num_partitions_insert: 1
+      repeat_count: 1
+      num_records_insert: 1000
+    type: spark.sql.SparkSqlInsertNode
+    deps: create_table
+  validate:
+    config:
+      delete_input_data: true
+    type: spark.sql.SparkSqlValidateDatasetNode
+    deps: insert_records

docker/demo/config/test-suite/spark-sql-nonpartitioned-external-mor.yaml

@@ -0,0 +1,44 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+dag_name: sspark-sql-nonpartitioned-external-mor.yaml
+dag_rounds: 1
+dag_intermittent_delay_mins: 1
+dag_content:
+  create_table:
+    config:
+      table_type: mor
+      is_external: true
+      primary_key: _row_key
+      pre_combine_field: test_suite_source_ordering_field
+      record_size: 1000
+      num_partitions_insert: 1
+      repeat_count: 1
+      num_records_insert: 1000
+    type: spark.sql.SparkSqlCreateTableNode
+    deps: none
+  insert_records:
+    config:
+      record_size: 1000
+      num_partitions_insert: 1
+      repeat_count: 1
+      num_records_insert: 1000
+    type: spark.sql.SparkSqlInsertNode
+    deps: create_table
+  validate:
+    config:
+      delete_input_data: true
+    type: spark.sql.SparkSqlValidateDatasetNode
+    deps: insert_records

docker/demo/config/test-suite/spark-sql-nonpartitioned-managed-cow-ctas.yaml

@@ -0,0 +1,44 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+dag_name: spark-sql-nonpartitioned-managed-cow-ctas.yaml
+dag_rounds: 1
+dag_intermittent_delay_mins: 1
+dag_content:
+  create_table:
+    config:
+      table_type: cow
+      primary_key: _row_key
+      pre_combine_field: test_suite_source_ordering_field
+      use_ctas: true
+      record_size: 1000
+      num_partitions_insert: 1
+      repeat_count: 1
+      num_records_insert: 1000
+    type: spark.sql.SparkSqlCreateTableNode
+    deps: none
+  insert_records:
+    config:
+      record_size: 1000
+      num_partitions_insert: 1
+      repeat_count: 1
+      num_records_insert: 1000
+    type: spark.sql.SparkSqlInsertNode
+    deps: create_table
+  validate:
+    config:
+      delete_input_data: true
+    type: spark.sql.SparkSqlValidateDatasetNode
+    deps: insert_records

docker/demo/config/test-suite/spark-sql-nonpartitioned-managed-cow.yaml

@@ -0,0 +1,63 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+dag_name: spark-sql-nonpartitioned-managed-cow.yaml
+dag_rounds: 1
+dag_intermittent_delay_mins: 1
+dag_content:
+  create_table:
+    config:
+      table_type: cow
+      primary_key: _row_key
+      pre_combine_field: test_suite_source_ordering_field
+      record_size: 1000
+      num_partitions_insert: 1
+      repeat_count: 1
+      num_records_insert: 1000
+    type: spark.sql.SparkSqlCreateTableNode
+    deps: none
+  insert_records:
+    config:
+      record_size: 1000
+      num_partitions_insert: 1
+      repeat_count: 1
+      num_records_insert: 1000
+    type: spark.sql.SparkSqlInsertNode
+    deps: create_table
+  #merge_records:
+  #  config:
+  #    merge_condition: target._row_key = source._row_key
+  #    matched_action: update set *
+  #    not_matched_action: insert *
+  #    record_size: 1000
+  #    num_partitions_insert: 10
+  #    repeat_count: 1
+  #    num_records_upsert: 100
+  #    num_records_insert: 1000
+  #  type: spark.sql.SparkSqlMergeNode
+  #  deps: insert_records
+  delete_records:
+    config:
+      condition_column: begin_lat
+      record_size: 1000
+      repeat_count: 1
+      ratio_records_change: 0.2
+    type: spark.sql.SparkSqlDeleteNode
+    deps: insert_records
+  validate:
+    config:
+      delete_input_data: true
+    type: spark.sql.SparkSqlValidateDatasetNode
+    deps: delete_records

docker/demo/config/test-suite/spark-sql-partition-cow-updates.yaml

@@ -0,0 +1,61 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+dag_name: spark-sql-partitioned-managed-cow.yaml
+dag_rounds: 1
+dag_intermittent_delay_mins: 1
+dag_content:
+  create_table:
+    config:
+      table_type: cow
+      primary_key: _row_key
+      pre_combine_field: test_suite_source_ordering_field
+      partition_field: rider
+      record_size: 1000
+      num_partitions_insert: 1
+      repeat_count: 1
+      num_records_insert: 1000
+    type: spark.sql.SparkSqlCreateTableNode
+    deps: none
+  insert_records:
+    config:
+      record_size: 1000
+      num_partitions_insert: 1
+      repeat_count: 1
+      num_records_insert: 1000
+    type: spark.sql.SparkSqlInsertNode
+    deps: create_table
+  first_validate:
+    config:
+      delete_input_data: false
+    type: spark.sql.SparkSqlValidateDatasetNode
+    deps: insert_records
+  update_records:
+    config:
+    type: spark.sql.SparkSqlUpdateNode
+    deps: first_validate
+  delete_records:
+    config:
+      condition_column: begin_lat
+      record_size: 1000
+      repeat_count: 1
+      ratio_records_change: 0.2
+    type: spark.sql.SparkSqlDeleteNode
+    deps: update_records
+  second_validate:
+    config:
+      delete_input_data: true
+    type: spark.sql.SparkSqlValidateDatasetNode
+    deps: delete_records

docker/demo/config/test-suite/spark-sql-partitioned-managed-cow-ctas.yaml

@@ -0,0 +1,45 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+dag_name: spark-sql-partitioned-managed-cow-ctas.yaml
+dag_rounds: 1
+dag_intermittent_delay_mins: 1
+dag_content:
+  create_table:
+    config:
+      table_type: cow
+      primary_key: _row_key
+      pre_combine_field: test_suite_source_ordering_field
+      partition_field: rider
+      use_ctas: true
+      record_size: 1000
+      num_partitions_insert: 1
+      repeat_count: 1
+      num_records_insert: 1000
+    type: spark.sql.SparkSqlCreateTableNode
+    deps: none
+  insert_records:
+    config:
+      record_size: 1000
+      num_partitions_insert: 1
+      repeat_count: 1
+      num_records_insert: 1000
+    type: spark.sql.SparkSqlInsertNode
+    deps: create_table
+  validate:
+    config:
+      delete_input_data: true
+    type: spark.sql.SparkSqlValidateDatasetNode
+    deps: insert_records

docker/demo/config/test-suite/spark-sql-partitioned-managed-cow.yaml

@@ -0,0 +1,64 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+dag_name: spark-sql-partitioned-managed-cow.yaml
+dag_rounds: 1
+dag_intermittent_delay_mins: 1
+dag_content:
+  create_table:
+    config:
+      table_type: cow
+      primary_key: _row_key
+      pre_combine_field: test_suite_source_ordering_field
+      partition_field: rider
+      record_size: 1000
+      num_partitions_insert: 1
+      repeat_count: 1
+      num_records_insert: 1000
+    type: spark.sql.SparkSqlCreateTableNode
+    deps: none
+  insert_records:
+    config:
+      record_size: 1000
+      num_partitions_insert: 1
+      repeat_count: 1
+      num_records_insert: 1000
+    type: spark.sql.SparkSqlInsertNode
+    deps: create_table
+  #merge_records:
+  #  config:
+  #    merge_condition: target._row_key = source._row_key
+  #    matched_action: update set *
+  #    not_matched_action: insert *
+  #    record_size: 1000
+  #    num_partitions_insert: 10
+  #    repeat_count: 1
+  #    num_records_upsert: 100
+  #    num_records_insert: 1000
+  #  type: spark.sql.SparkSqlMergeNode
+  #  deps: insert_records
+  delete_records:
+    config:
+      condition_column: begin_lat
+      record_size: 1000
+      repeat_count: 1
+      ratio_records_change: 0.2
+    type: spark.sql.SparkSqlDeleteNode
+    deps: insert_records
+  validate:
+    config:
+      delete_input_data: true
+    type: spark.sql.SparkSqlValidateDatasetNode
+    deps: delete_records