academic_observatory_workflows.doi_workflow.workflow

Attributes

`SENSOR_DAG_IDS`
`AGGREGATIONS`

Classes

DagParams

Functions

create_dag(→ airflow.DAG)

Module Contents

academic_observatory_workflows.doi_workflow.workflow.SENSOR_DAG_IDS = ['crossref_fundref', 'crossref_metadata', 'openalex', 'ror', 'unpaywall', 'pubmed', 'orcid'][source]

academic_observatory_workflows.doi_workflow.workflow.AGGREGATIONS[source]

class academic_observatory_workflows.doi_workflow.workflow.DagParams(dag_id: str, cloud_workspace: observatory_platform.airflow.workflow.CloudWorkspace, bq_intermediate_dataset_id: str = 'observatory_intermediate', bq_dashboards_dataset_id: str = 'coki_dashboards', bq_observatory_dataset_id: str = 'observatory', bq_unpaywall_dataset_id: str = 'unpaywall', bq_ror_dataset_id: str = 'ror', api_bq_dataset_id: str = 'dataset_api', sql_queries: List[List[academic_observatory_workflows.doi_workflow.queries.SQLQuery]] = None, max_fetch_threads: int = 4, start_date: pendulum.DateTime | None = pendulum.datetime(2020, 8, 30), schedule: str | None = '@weekly', sensor_dag_ids: List[str] = None, max_active_runs: int = 1, retries: int = 3, **kwargs)[source]

dag_id[source]

cloud_workspace[source]

bq_intermediate_dataset_id = 'observatory_intermediate'[source]

bq_dashboards_dataset_id = 'coki_dashboards'[source]

bq_observatory_dataset_id = 'observatory'[source]

bq_unpaywall_dataset_id = 'unpaywall'[source]

bq_ror_dataset_id = 'ror'[source]

api_bq_dataset_id = 'dataset_api'[source]

sql_queries = None[source]

max_fetch_threads = 4[source]

start_date[source]

schedule = '@weekly'[source]

sensor_dag_ids = None[source]

max_active_runs = 1[source]

retries = 3[source]

input_table_task_ids = [][source]

academic_observatory_workflows.doi_workflow.workflow.create_dag(dag_params: DagParams) → airflow.DAG[source]