|
| 1 | +# Copyright 2020 Google LLC |
| 2 | +# |
| 3 | +# Licensed under the Apache License, Version 2.0 (the "License"); |
| 4 | +# you may not use this file except in compliance with the License. |
| 5 | +# You may obtain a copy of the License at |
| 6 | +# |
| 7 | +# http://www.apache.org/licenses/LICENSE-2.0 |
| 8 | +# |
| 9 | +# Unless required by applicable law or agreed to in writing, software |
| 10 | +# distributed under the License is distributed on an "AS IS" BASIS, |
| 11 | +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
| 12 | +# See the License for the specific language governing permissions and |
| 13 | +# limitations under the License. |
| 14 | + |
| 15 | +# This sample walks a user through creating a workflow |
| 16 | +# for Cloud Dataproc using the Python client library. |
| 17 | + |
| 18 | +import sys |
| 19 | +# [START dataproc_inline_workflow] |
| 20 | +from google.cloud import dataproc_v1 as dataproc |
| 21 | + |
| 22 | + |
| 23 | +def instantiate_inline_workflow(project_id, region): |
| 24 | + """This sample walks a user through submitting a workflow |
| 25 | + for a Cloud Dataproc using the Python client library. |
| 26 | +
|
| 27 | + Args: |
| 28 | + project_id (string): Project to use for running the workflow. |
| 29 | + region (string): Region where the workflow resources should live. |
| 30 | + """ |
| 31 | + |
| 32 | + # Create a client with the endpoint set to the desired region. |
| 33 | + workflow_client = dataproc.WorkflowTemplateServiceClient( |
| 34 | + client_options={ |
| 35 | + 'api_endpoint': '{}-dataproc.googleapis.com:443'.format(region)} |
| 36 | + ) |
| 37 | + |
| 38 | + parent = workflow_client.region_path(project_id, region) |
| 39 | + |
| 40 | + template = { |
| 41 | + 'jobs': [ |
| 42 | + { |
| 43 | + 'hadoop_job': { |
| 44 | + 'main_jar_file_uri': 'file:///usr/lib/hadoop-mapreduce/' |
| 45 | + 'hadoop-mapreduce-examples.jar', |
| 46 | + 'args': [ |
| 47 | + 'teragen', |
| 48 | + '1000', |
| 49 | + 'hdfs:///gen/' |
| 50 | + ] |
| 51 | + }, |
| 52 | + 'step_id': 'teragen' |
| 53 | + }, |
| 54 | + { |
| 55 | + 'hadoop_job': { |
| 56 | + 'main_jar_file_uri': 'file:///usr/lib/hadoop-mapreduce/' |
| 57 | + 'hadoop-mapreduce-examples.jar', |
| 58 | + 'args': [ |
| 59 | + 'terasort', |
| 60 | + 'hdfs:///gen/', |
| 61 | + 'hdfs:///sort/' |
| 62 | + ] |
| 63 | + }, |
| 64 | + 'step_id': 'terasort', |
| 65 | + 'prerequisite_step_ids': [ |
| 66 | + 'teragen' |
| 67 | + ] |
| 68 | + }], |
| 69 | + 'placement': { |
| 70 | + 'managed_cluster': { |
| 71 | + 'cluster_name': 'my-managed-cluster', |
| 72 | + 'config': { |
| 73 | + 'gce_cluster_config': { |
| 74 | + # Leave 'zone_uri' empty for 'autozone' |
| 75 | + # 'zone_uri': '' |
| 76 | + 'zone_uri': 'us-central1-a' |
| 77 | + } |
| 78 | + } |
| 79 | + } |
| 80 | + } |
| 81 | + } |
| 82 | + |
| 83 | + # Submit the request to instantiate the workflow from an inline template. |
| 84 | + operation = workflow_client.instantiate_inline_workflow_template( |
| 85 | + parent, template) |
| 86 | + operation.result() |
| 87 | + |
| 88 | + # Output a success message. |
| 89 | + print('Workflow ran successfully.') |
| 90 | +# [END dataproc_inline_workflow] |
| 91 | + |
| 92 | + |
| 93 | +if __name__ == "__main__": |
| 94 | + instantiate_inline_workflow(sys.argv[1], sys.argv[2]) |
0 commit comments