Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add archive update task #53

Merged
merged 1 commit into from
Nov 15, 2024
Merged

Add archive update task #53

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 13 additions & 6 deletions linkage_dag.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,6 +41,7 @@
get_post_success,
)
from dataloader.airflow_utils.utils import clear_gcs_dir
from dataloader.scripts.clean_backups import clean_backups
from dataloader.scripts.populate_documentation import update_table_descriptions

production_dataset = "literature"
Expand Down Expand Up @@ -629,18 +630,23 @@

# We're done! Checks passed, so copy to production and post success to slack
start_production_cp = DummyOperator(task_id="start_production_cp")
update_archive = PythonOperator(
task_id="update_archive",
op_kwargs={"dataset": backup_dataset, "backup_prefix": production_dataset},
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",
)

curr_date = datetime.now().strftime("%Y%m%d")
with open(
f"{os.environ.get('DAGS_FOLDER')}/schemas/{gcs_folder}/table_descriptions.json"
) as f:
table_desc = json.loads(f.read())

trigger_org_fixes = TriggerDagRunOperator(
task_id="trigger_org_fixes",
trigger_dag_id="org_fixes",
)

for table in production_tables:
push_to_production = BigQueryToBigQueryOperator(
task_id="copy_" + table.lower(),
Expand Down Expand Up @@ -670,6 +676,7 @@
>> push_to_production
>> snapshot
>> pop_descriptions
>> update_archive
>> success_alert
>> trigger_org_fixes
)
Expand All @@ -691,7 +698,7 @@
create_disposition="CREATE_IF_NEEDED",
write_disposition="WRITE_TRUNCATE",
)
start_production_cp >> copy_cld2 >> snapshot_cld2 >> success_alert
start_production_cp >> copy_cld2 >> snapshot_cld2 >> update_archive

# task structure
clear_tmp_dir >> metadata_sequences_start
Expand Down
Loading