1
0
Files
hudi/docker/demo/config/test-suite/spark-sql-partitioned-managed-cow.yaml
Y Ethan Guo 5d60491f5b [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>
2021-09-13 11:53:13 -04:00

65 lines
2.1 KiB
YAML

# 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