{"id":22492659,"url":"https://github.com/garystafford/dataproc-workflow-templates","last_synced_at":"2026-03-14T22:05:38.431Z","repository":{"id":74258109,"uuid":"161844466","full_name":"garystafford/dataproc-workflow-templates","owner":"garystafford","description":"Demonstration of Google Cloud Dataproc Workflow Templates","archived":false,"fork":false,"pushed_at":"2018-12-17T03:01:54.000Z","size":15,"stargazers_count":5,"open_issues_count":0,"forks_count":7,"subscribers_count":3,"default_branch":"master","last_synced_at":"2023-08-05T02:22:51.475Z","etag":null,"topics":["dataproc","gcp","google-cloud-platform","hadoop","pyspark","spark"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/garystafford.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2018-12-14T21:54:32.000Z","updated_at":"2021-07-23T19:11:15.000Z","dependencies_parsed_at":null,"dependency_job_id":"82478cce-6147-4dc8-8459-d0a24473e3a7","html_url":"https://github.com/garystafford/dataproc-workflow-templates","commit_stats":null,"previous_names":[],"tags_count":0,"template":null,"template_full_name":null,"purl":"pkg:github/garystafford/dataproc-workflow-templates","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/garystafford%2Fdataproc-workflow-templates","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/garystafford%2Fdataproc-workflow-templates/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/garystafford%2Fdataproc-workflow-templates/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/garystafford%2Fdataproc-workflow-templates/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/garystafford","download_url":"https://codeload.github.com/garystafford/dataproc-workflow-templates/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/garystafford%2Fdataproc-workflow-templates/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30519111,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-14T19:51:21.629Z","status":"ssl_error","status_checked_at":"2026-03-14T19:51:12.959Z","response_time":57,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["dataproc","gcp","google-cloud-platform","hadoop","pyspark","spark"],"created_at":"2024-12-06T18:20:20.188Z","updated_at":"2026-03-14T22:05:38.426Z","avatar_url":"https://github.com/garystafford.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# Google Cloud Dataproc WorkflowTemplates API Demo\n\nCode repository for post, [Using the Google Cloud Dataproc WorkflowTemplates API to Automate Spark and Hadoop Workloads on GCP](https://programmaticponderings.com/).\n\n## Files\n* `template-demo-2.yaml`: Non-parametrized version of workflow template with three jobs, using a managed 3-node Spark cluster\n* `template-demo-3.yaml`: Parametrized version of workflow template with one Python-based PySpark job, using a managed 3-node Spark cluster\n* `template-demo-4.yaml`: Parametrized version of workflow template with one Python-based PySpark job, using an existing 3-node Spark cluster\n* `template-demo-5.yaml`: Parametrized version of workflow template with one Java-based Spark job, using an existing 3-node Spark cluster\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgarystafford%2Fdataproc-workflow-templates","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgarystafford%2Fdataproc-workflow-templates","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgarystafford%2Fdataproc-workflow-templates/lists"}