academic_observatory_workflows.doi_workflow.tasks

Functions

make_sensors(*, sensor_dag_ids)

create_datasets(*, output_project_id, ...)

create_repo_institution_to_ror_table(*, release, ...)

create_ror_hierarchy_table(*, release, ...)

create_intermediate_table(*, release, sql_query, ...)

create_aggregate_table(*, release, aggregation, ...)

update_table_descriptions(*, release, aggregations, ...)

add_dataset_release(*, release, api_bq_project_id, ...)

Module Contents

academic_observatory_workflows.doi_workflow.tasks.make_sensors(*, sensor_dag_ids: list[str])[source]
academic_observatory_workflows.doi_workflow.tasks.create_datasets(*, output_project_id: str, bq_data_location: str, bq_intermediate_dataset_id: str, bq_dashboards_dataset_id: str, bq_observatory_dataset_id: str)[source]
academic_observatory_workflows.doi_workflow.tasks.create_repo_institution_to_ror_table(*, release: academic_observatory_workflows.doi_workflow.release.DOIRelease, input_project_id: str, output_project_id: str, bq_unpaywall_dataset_id: str, bq_intermediate_dataset_id: str, max_fetch_threads: int)[source]
academic_observatory_workflows.doi_workflow.tasks.create_ror_hierarchy_table(*, release: academic_observatory_workflows.doi_workflow.release.DOIRelease, input_project_id: str, output_project_id: str, bq_ror_dataset_id: str, bq_intermediate_dataset_id: str)[source]
academic_observatory_workflows.doi_workflow.tasks.create_intermediate_table(*, release: academic_observatory_workflows.doi_workflow.release.DOIRelease, sql_query: academic_observatory_workflows.doi_workflow.queries.SQLQuery, output_project_id: str, ti: airflow.models.taskinstance.TaskInstance)[source]
academic_observatory_workflows.doi_workflow.tasks.create_aggregate_table(*, release: academic_observatory_workflows.doi_workflow.release.DOIRelease, aggregation: academic_observatory_workflows.doi_workflow.queries.Aggregation, output_project_id: str, bq_observatory_dataset_id: str)[source]
academic_observatory_workflows.doi_workflow.tasks.update_table_descriptions(*, release: academic_observatory_workflows.doi_workflow.release.DOIRelease, aggregations: list[academic_observatory_workflows.doi_workflow.queries.Aggregation], input_table_task_ids: list[str], output_project_id: str, bq_observatory_dataset_id: str, ti: airflow.models.taskinstance.TaskInstance)[source]
academic_observatory_workflows.doi_workflow.tasks.add_dataset_release(*, release: academic_observatory_workflows.doi_workflow.release.DOIRelease, api_bq_project_id: str, api_bq_dataset_id: str)[source]