# 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: simple-deltastreamer.yaml dag_rounds: 1 dag_intermittent_delay_mins: 1 dag_content: first_insert: config: record_size: 1000 num_partitions_insert: 10 repeat_count: 1 num_records_insert: 10000 type: SparkInsertNode deps: none first_upsert: config: record_size: 1000 num_partitions_insert: 10 num_records_insert: 1000 repeat_count: 1 num_records_upsert: 8000 num_partitions_upsert: 10 type: SparkUpsertNode deps: first_insert second_insert: config: record_size: 1000 num_partitions_insert: 10 repeat_count: 1 num_records_insert: 10000 type: SparkInsertNode deps: first_upsert second_upsert: config: record_size: 1000 num_partitions_insert: 10 num_records_insert: 1000 repeat_count: 1 num_records_upsert: 8000 num_partitions_upsert: 10 type: SparkUpsertNode deps: second_insert first_hive_sync: config: queue_name: "adhoc" engine: "mr" type: HiveSyncNode deps: second_upsert first_insert_overwrite_table: config: record_size: 1000 repeat_count: 10 num_records_insert: 10 type: SparkInsertOverwriteTableNode deps: first_hive_sync delete_all_input_except_last: config: delete_input_data_except_latest: true type: DeleteInputDatasetNode deps: first_insert_overwrite_table third_insert: config: record_size: 1000 num_partitions_insert: 10 repeat_count: 1 num_records_insert: 10000 type: SparkInsertNode deps: delete_all_input_except_last third_upsert: config: record_size: 1000 num_partitions_insert: 10 num_records_insert: 1000 repeat_count: 1 num_records_upsert: 8000 num_partitions_upsert: 10 type: SparkUpsertNode deps: third_insert second_hive_sync: config: queue_name: "adhoc" engine: "mr" type: HiveSyncNode deps: third_upsert second_validate: config: validate_full_data : true validate_hive: false delete_input_data: false type: ValidateDatasetNode deps: second_hive_sync