mozilla / bigquery-etl

Bigquery ETL
https://mozilla.github.io/bigquery-etl
Mozilla Public License 2.0
244 stars 98 forks source link

updating metadata for incremental runs #5717

Closed chelseybeck closed 1 month ago

chelseybeck commented 1 month ago

Checklist for reviewer:

For modifications to schemas in restricted namespaces (see CODEOWNERS):

┆Issue is synchronized with this Jira Task

dataops-ci-bot commented 1 month ago

Integration report for "updating metadata for incremental runs"

sql.diff

Click to expand! ```diff diff -bur --no-dereference --new-file /tmp/workspace/main-generated-sql/dags/bqetl_braze.py /tmp/workspace/generated-sql/dags/bqetl_braze.py --- /tmp/workspace/main-generated-sql/dags/bqetl_braze.py 2024-06-03 19:03:13.000000000 +0000 +++ /tmp/workspace/generated-sql/dags/bqetl_braze.py 2024-06-03 19:04:43.000000000 +0000 @@ -158,9 +158,8 @@ project_id="moz-fx-data-shared-prod", owner="cbeck@mozilla.com", email=["cbeck@mozilla.com", "leli@mozilla.com"], - date_partition_parameter=None, + date_partition_parameter="updated_at", depends_on_past=False, - task_concurrency=1, ) braze_external__changed_products_sync__v1 = bigquery_etl_query( @@ -170,9 +169,8 @@ project_id="moz-fx-data-shared-prod", owner="cbeck@mozilla.com", email=["cbeck@mozilla.com", "leli@mozilla.com"], - date_partition_parameter=None, + date_partition_parameter="updated_at", depends_on_past=False, - task_concurrency=1, ) braze_external__changed_users__v1 = bigquery_etl_query( @@ -194,9 +192,8 @@ project_id="moz-fx-data-shared-prod", owner="cbeck@mozilla.com", email=["cbeck@mozilla.com", "leli@mozilla.com"], - date_partition_parameter=None, + date_partition_parameter="updated_at", depends_on_past=False, - task_concurrency=1, ) braze_external__changed_waitlists_sync__v1 = bigquery_etl_query( @@ -206,9 +203,8 @@ project_id="moz-fx-data-shared-prod", owner="cbeck@mozilla.com", email=["cbeck@mozilla.com", "leli@mozilla.com"], - date_partition_parameter=None, + date_partition_parameter="updated_at", depends_on_past=False, - task_concurrency=1, ) braze_external__delete_users_sync__v1 = bigquery_etl_query( @@ -218,9 +214,8 @@ project_id="moz-fx-data-shared-prod", owner="cbeck@mozilla.com", email=["cbeck@mozilla.com", "leli@mozilla.com"], - date_partition_parameter=None, + date_partition_parameter="updated_at", depends_on_past=False, - task_concurrency=1, ) braze_external__users_previous_day_snapshot__v1 = bigquery_etl_query( @@ -360,7 +355,7 @@ owner="cbeck@mozilla.com", email=["cbeck@mozilla.com", "leli@mozilla.com"], depends_on_past=False, - task_concurrency=1, + parameters=["updated_at:DATE:{{ds}}"], retries=0, ) @@ -373,7 +368,7 @@ owner="cbeck@mozilla.com", email=["cbeck@mozilla.com", "leli@mozilla.com"], depends_on_past=False, - task_concurrency=1, + parameters=["updated_at:DATE:{{ds}}"], retries=0, ) @@ -399,7 +394,7 @@ owner="cbeck@mozilla.com", email=["cbeck@mozilla.com", "leli@mozilla.com"], depends_on_past=False, - task_concurrency=1, + parameters=["updated_at:DATE:{{ds}}"], retries=0, ) @@ -412,7 +407,7 @@ owner="cbeck@mozilla.com", email=["cbeck@mozilla.com", "leli@mozilla.com"], depends_on_past=False, - task_concurrency=1, + parameters=["updated_at:DATE:{{ds}}"], retries=0, ) @@ -425,7 +420,7 @@ owner="cbeck@mozilla.com", email=["cbeck@mozilla.com", "leli@mozilla.com"], depends_on_past=False, - task_concurrency=1, + parameters=["updated_at:DATE:{{ds}}"], retries=0, ) diff -bur --no-dereference --new-file /tmp/workspace/main-generated-sql/sql/moz-fx-data-shared-prod/braze_external/changed_newsletters_sync_v1/metadata.yaml /tmp/workspace/generated-sql/sql/moz-fx-data-shared-prod/braze_external/changed_newsletters_sync_v1/metadata.yaml --- /tmp/workspace/main-generated-sql/sql/moz-fx-data-shared-prod/braze_external/changed_newsletters_sync_v1/metadata.yaml 2024-06-03 19:01:29.000000000 +0000 +++ /tmp/workspace/generated-sql/sql/moz-fx-data-shared-prod/braze_external/changed_newsletters_sync_v1/metadata.yaml 2024-06-03 19:01:50.000000000 +0000 @@ -14,7 +14,7 @@ owner1: cbeck scheduling: dag_name: bqetl_braze - date_partition_parameter: null + date_partition_parameter: updated_at bigquery: time_partitioning: null range_partitioning: null diff -bur --no-dereference --new-file /tmp/workspace/main-generated-sql/sql/moz-fx-data-shared-prod/braze_external/changed_products_sync_v1/metadata.yaml /tmp/workspace/generated-sql/sql/moz-fx-data-shared-prod/braze_external/changed_products_sync_v1/metadata.yaml --- /tmp/workspace/main-generated-sql/sql/moz-fx-data-shared-prod/braze_external/changed_products_sync_v1/metadata.yaml 2024-06-03 19:01:29.000000000 +0000 +++ /tmp/workspace/generated-sql/sql/moz-fx-data-shared-prod/braze_external/changed_products_sync_v1/metadata.yaml 2024-06-03 19:01:50.000000000 +0000 @@ -14,7 +14,7 @@ owner1: cbeck scheduling: dag_name: bqetl_braze - date_partition_parameter: null + date_partition_parameter: updated_at bigquery: time_partitioning: null range_partitioning: null diff -bur --no-dereference --new-file /tmp/workspace/main-generated-sql/sql/moz-fx-data-shared-prod/braze_external/changed_users_sync_v1/metadata.yaml /tmp/workspace/generated-sql/sql/moz-fx-data-shared-prod/braze_external/changed_users_sync_v1/metadata.yaml --- /tmp/workspace/main-generated-sql/sql/moz-fx-data-shared-prod/braze_external/changed_users_sync_v1/metadata.yaml 2024-06-03 19:01:29.000000000 +0000 +++ /tmp/workspace/generated-sql/sql/moz-fx-data-shared-prod/braze_external/changed_users_sync_v1/metadata.yaml 2024-06-03 19:01:50.000000000 +0000 @@ -14,7 +14,7 @@ owner1: cbeck scheduling: dag_name: bqetl_braze - date_partition_parameter: null + date_partition_parameter: updated_at bigquery: time_partitioning: null range_partitioning: null diff -bur --no-dereference --new-file /tmp/workspace/main-generated-sql/sql/moz-fx-data-shared-prod/braze_external/changed_waitlists_sync_v1/metadata.yaml /tmp/workspace/generated-sql/sql/moz-fx-data-shared-prod/braze_external/changed_waitlists_sync_v1/metadata.yaml --- /tmp/workspace/main-generated-sql/sql/moz-fx-data-shared-prod/braze_external/changed_waitlists_sync_v1/metadata.yaml 2024-06-03 19:01:29.000000000 +0000 +++ /tmp/workspace/generated-sql/sql/moz-fx-data-shared-prod/braze_external/changed_waitlists_sync_v1/metadata.yaml 2024-06-03 19:01:50.000000000 +0000 @@ -14,7 +14,7 @@ owner1: cbeck scheduling: dag_name: bqetl_braze - date_partition_parameter: null + date_partition_parameter: updated_at bigquery: time_partitioning: null range_partitioning: null diff -bur --no-dereference --new-file /tmp/workspace/main-generated-sql/sql/moz-fx-data-shared-prod/braze_external/delete_users_sync_v1/metadata.yaml /tmp/workspace/generated-sql/sql/moz-fx-data-shared-prod/braze_external/delete_users_sync_v1/metadata.yaml --- /tmp/workspace/main-generated-sql/sql/moz-fx-data-shared-prod/braze_external/delete_users_sync_v1/metadata.yaml 2024-06-03 19:01:29.000000000 +0000 +++ /tmp/workspace/generated-sql/sql/moz-fx-data-shared-prod/braze_external/delete_users_sync_v1/metadata.yaml 2024-06-03 19:01:50.000000000 +0000 @@ -18,13 +18,12 @@ - cbeck@mozilla.com labels: incremental: true - schedule: daily owner: cbeck dag: bqetl_braze owner1: cbeck scheduling: dag_name: bqetl_braze - date_partition_parameter: null + date_partition_parameter: updated_at bigquery: time_partitioning: null range_partitioning: null ```

Link to full diff

dataops-ci-bot commented 1 month ago

Integration report for "Merge branch 'main' into 3763-fix-incremental"

sql.diff

Click to expand! ```diff diff -bur --no-dereference --new-file /tmp/workspace/main-generated-sql/dags/bqetl_braze.py /tmp/workspace/generated-sql/dags/bqetl_braze.py --- /tmp/workspace/main-generated-sql/dags/bqetl_braze.py 2024-06-03 19:13:13.000000000 +0000 +++ /tmp/workspace/generated-sql/dags/bqetl_braze.py 2024-06-03 19:14:32.000000000 +0000 @@ -146,9 +146,8 @@ project_id="moz-fx-data-shared-prod", owner="cbeck@mozilla.com", email=["cbeck@mozilla.com", "leli@mozilla.com"], - date_partition_parameter=None, + date_partition_parameter="updated_at", depends_on_past=False, - task_concurrency=1, ) braze_external__changed_newsletters_sync__v1 = bigquery_etl_query( @@ -158,9 +157,8 @@ project_id="moz-fx-data-shared-prod", owner="cbeck@mozilla.com", email=["cbeck@mozilla.com", "leli@mozilla.com"], - date_partition_parameter=None, + date_partition_parameter="updated_at", depends_on_past=False, - task_concurrency=1, ) braze_external__changed_products_sync__v1 = bigquery_etl_query( @@ -170,9 +168,8 @@ project_id="moz-fx-data-shared-prod", owner="cbeck@mozilla.com", email=["cbeck@mozilla.com", "leli@mozilla.com"], - date_partition_parameter=None, + date_partition_parameter="updated_at", depends_on_past=False, - task_concurrency=1, ) braze_external__changed_users__v1 = bigquery_etl_query( @@ -194,9 +191,8 @@ project_id="moz-fx-data-shared-prod", owner="cbeck@mozilla.com", email=["cbeck@mozilla.com", "leli@mozilla.com"], - date_partition_parameter=None, + date_partition_parameter="updated_at", depends_on_past=False, - task_concurrency=1, ) braze_external__changed_waitlists_sync__v1 = bigquery_etl_query( @@ -206,9 +202,8 @@ project_id="moz-fx-data-shared-prod", owner="cbeck@mozilla.com", email=["cbeck@mozilla.com", "leli@mozilla.com"], - date_partition_parameter=None, + date_partition_parameter="updated_at", depends_on_past=False, - task_concurrency=1, ) braze_external__delete_users_sync__v1 = bigquery_etl_query( @@ -218,9 +213,8 @@ project_id="moz-fx-data-shared-prod", owner="cbeck@mozilla.com", email=["cbeck@mozilla.com", "leli@mozilla.com"], - date_partition_parameter=None, + date_partition_parameter="updated_at", depends_on_past=False, - task_concurrency=1, ) braze_external__users_previous_day_snapshot__v1 = bigquery_etl_query( @@ -347,7 +341,7 @@ owner="cbeck@mozilla.com", email=["cbeck@mozilla.com", "leli@mozilla.com"], depends_on_past=False, - task_concurrency=1, + parameters=["updated_at:DATE:{{ds}}"], retries=0, ) @@ -360,7 +354,7 @@ owner="cbeck@mozilla.com", email=["cbeck@mozilla.com", "leli@mozilla.com"], depends_on_past=False, - task_concurrency=1, + parameters=["updated_at:DATE:{{ds}}"], retries=0, ) @@ -373,7 +367,7 @@ owner="cbeck@mozilla.com", email=["cbeck@mozilla.com", "leli@mozilla.com"], depends_on_past=False, - task_concurrency=1, + parameters=["updated_at:DATE:{{ds}}"], retries=0, ) @@ -399,7 +393,7 @@ owner="cbeck@mozilla.com", email=["cbeck@mozilla.com", "leli@mozilla.com"], depends_on_past=False, - task_concurrency=1, + parameters=["updated_at:DATE:{{ds}}"], retries=0, ) @@ -412,7 +406,7 @@ owner="cbeck@mozilla.com", email=["cbeck@mozilla.com", "leli@mozilla.com"], depends_on_past=False, - task_concurrency=1, + parameters=["updated_at:DATE:{{ds}}"], retries=0, ) @@ -425,7 +419,7 @@ owner="cbeck@mozilla.com", email=["cbeck@mozilla.com", "leli@mozilla.com"], depends_on_past=False, - task_concurrency=1, + parameters=["updated_at:DATE:{{ds}}"], retries=0, ) diff -bur --no-dereference --new-file /tmp/workspace/main-generated-sql/sql/moz-fx-data-shared-prod/braze_external/changed_firefox_subscriptions_sync_v1/metadata.yaml /tmp/workspace/generated-sql/sql/moz-fx-data-shared-prod/braze_external/changed_firefox_subscriptions_sync_v1/metadata.yaml --- /tmp/workspace/main-generated-sql/sql/moz-fx-data-shared-prod/braze_external/changed_firefox_subscriptions_sync_v1/metadata.yaml 2024-06-03 19:11:26.000000000 +0000 +++ /tmp/workspace/generated-sql/sql/moz-fx-data-shared-prod/braze_external/changed_firefox_subscriptions_sync_v1/metadata.yaml 2024-06-03 19:11:42.000000000 +0000 @@ -15,7 +15,7 @@ owner1: cbeck scheduling: dag_name: bqetl_braze - date_partition_parameter: null + date_partition_parameter: updated_at bigquery: time_partitioning: null range_partitioning: null diff -bur --no-dereference --new-file /tmp/workspace/main-generated-sql/sql/moz-fx-data-shared-prod/braze_external/changed_newsletters_sync_v1/metadata.yaml /tmp/workspace/generated-sql/sql/moz-fx-data-shared-prod/braze_external/changed_newsletters_sync_v1/metadata.yaml --- /tmp/workspace/main-generated-sql/sql/moz-fx-data-shared-prod/braze_external/changed_newsletters_sync_v1/metadata.yaml 2024-06-03 19:11:26.000000000 +0000 +++ /tmp/workspace/generated-sql/sql/moz-fx-data-shared-prod/braze_external/changed_newsletters_sync_v1/metadata.yaml 2024-06-03 19:11:42.000000000 +0000 @@ -14,7 +14,7 @@ owner1: cbeck scheduling: dag_name: bqetl_braze - date_partition_parameter: null + date_partition_parameter: updated_at bigquery: time_partitioning: null range_partitioning: null diff -bur --no-dereference --new-file /tmp/workspace/main-generated-sql/sql/moz-fx-data-shared-prod/braze_external/changed_products_sync_v1/metadata.yaml /tmp/workspace/generated-sql/sql/moz-fx-data-shared-prod/braze_external/changed_products_sync_v1/metadata.yaml --- /tmp/workspace/main-generated-sql/sql/moz-fx-data-shared-prod/braze_external/changed_products_sync_v1/metadata.yaml 2024-06-03 19:11:26.000000000 +0000 +++ /tmp/workspace/generated-sql/sql/moz-fx-data-shared-prod/braze_external/changed_products_sync_v1/metadata.yaml 2024-06-03 19:11:42.000000000 +0000 @@ -14,7 +14,7 @@ owner1: cbeck scheduling: dag_name: bqetl_braze - date_partition_parameter: null + date_partition_parameter: updated_at bigquery: time_partitioning: null range_partitioning: null diff -bur --no-dereference --new-file /tmp/workspace/main-generated-sql/sql/moz-fx-data-shared-prod/braze_external/changed_users_sync_v1/metadata.yaml /tmp/workspace/generated-sql/sql/moz-fx-data-shared-prod/braze_external/changed_users_sync_v1/metadata.yaml --- /tmp/workspace/main-generated-sql/sql/moz-fx-data-shared-prod/braze_external/changed_users_sync_v1/metadata.yaml 2024-06-03 19:11:26.000000000 +0000 +++ /tmp/workspace/generated-sql/sql/moz-fx-data-shared-prod/braze_external/changed_users_sync_v1/metadata.yaml 2024-06-03 19:11:42.000000000 +0000 @@ -14,7 +14,7 @@ owner1: cbeck scheduling: dag_name: bqetl_braze - date_partition_parameter: null + date_partition_parameter: updated_at bigquery: time_partitioning: null range_partitioning: null diff -bur --no-dereference --new-file /tmp/workspace/main-generated-sql/sql/moz-fx-data-shared-prod/braze_external/changed_waitlists_sync_v1/metadata.yaml /tmp/workspace/generated-sql/sql/moz-fx-data-shared-prod/braze_external/changed_waitlists_sync_v1/metadata.yaml --- /tmp/workspace/main-generated-sql/sql/moz-fx-data-shared-prod/braze_external/changed_waitlists_sync_v1/metadata.yaml 2024-06-03 19:11:26.000000000 +0000 +++ /tmp/workspace/generated-sql/sql/moz-fx-data-shared-prod/braze_external/changed_waitlists_sync_v1/metadata.yaml 2024-06-03 19:11:42.000000000 +0000 @@ -14,7 +14,7 @@ owner1: cbeck scheduling: dag_name: bqetl_braze - date_partition_parameter: null + date_partition_parameter: updated_at bigquery: time_partitioning: null range_partitioning: null diff -bur --no-dereference --new-file /tmp/workspace/main-generated-sql/sql/moz-fx-data-shared-prod/braze_external/delete_users_sync_v1/metadata.yaml /tmp/workspace/generated-sql/sql/moz-fx-data-shared-prod/braze_external/delete_users_sync_v1/metadata.yaml --- /tmp/workspace/main-generated-sql/sql/moz-fx-data-shared-prod/braze_external/delete_users_sync_v1/metadata.yaml 2024-06-03 19:11:26.000000000 +0000 +++ /tmp/workspace/generated-sql/sql/moz-fx-data-shared-prod/braze_external/delete_users_sync_v1/metadata.yaml 2024-06-03 19:11:42.000000000 +0000 @@ -18,13 +18,12 @@ - cbeck@mozilla.com labels: incremental: true - schedule: daily owner: cbeck dag: bqetl_braze owner1: cbeck scheduling: dag_name: bqetl_braze - date_partition_parameter: null + date_partition_parameter: updated_at bigquery: time_partitioning: null range_partitioning: null ```

Link to full diff