From 8a86c5ce7fc913afd71ef33d1bab7c52a6746e99 Mon Sep 17 00:00:00 2001 From: James Dunham Date: Wed, 28 May 2025 16:22:05 -0400 Subject: [PATCH] Trigger affiliations DAG The new author affiliations pipeline will run after article linkage. We'll no longer use the org-fixes DAG. --- README.md | 2 +- linkage_dag.py | 8 ++++---- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/README.md b/README.md index 04fb8d4..50ea6e7 100644 --- a/README.md +++ b/README.md @@ -59,7 +59,7 @@ always reflect outputs on current metadata for a given merged article regardless We automate article linkage using Apache Airflow. `linkage_dag.py` contains our current implementation. * This dag is triggered from the [Semantic Scholar ETL dag](https://github.com/georgetown-cset/semantic-scholar-etl-pipeline/blob/main/s2_dag.py) which runs once a month. -* This dag triggers the [Org Fixes dag](https://github.com/georgetown-cset/org-fixes/blob/main/org_fixes_dag.py). +* This dag triggers the [affiliations dag](https://github.com/georgetown-cset/author-affiliations/blob/main/pipeline/affiliations_dag.py). The DAG generates two tables of analytic significance: diff --git a/linkage_dag.py b/linkage_dag.py index fc90eb3..6aa7898 100644 --- a/linkage_dag.py +++ b/linkage_dag.py @@ -636,9 +636,9 @@ python_callable=clean_backups, ) success_alert = get_post_success("Article linkage update succeeded!", dag) - trigger_org_fixes = TriggerDagRunOperator( - task_id="trigger_org_fixes", - trigger_dag_id="org_fixes", + trigger_affiliations = TriggerDagRunOperator( + task_id="trigger_affiliations", + trigger_dag_id="affiliations", ) curr_date = datetime.now().strftime("%Y%m%d") @@ -678,7 +678,7 @@ >> pop_descriptions >> update_archive >> success_alert - >> trigger_org_fixes + >> trigger_affiliations ) # We don't show the "all metadata" table in the production dataset, but we do need to