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.

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

Dashboard As Code for Reconcile #768

Merged
merged 13 commits into from
Oct 2, 2024
Original file line number Diff line number Diff line change
@@ -0,0 +1,31 @@
select
main.recon_id,
main.source_type,
main.report_type,
main.source_table.`catalog` as source_catalog,
main.source_table.`schema` as source_schema,
main.source_table.table_name as source_table_name,
CASE
WHEN COALESCE(MAIN.SOURCE_TABLE.CATALOG, '') <> '' THEN CONCAT(MAIN.SOURCE_TABLE.CATALOG, '.', MAIN.SOURCE_TABLE.SCHEMA, '.', MAIN.SOURCE_TABLE.TABLE_NAME)
ELSE CONCAT(MAIN.SOURCE_TABLE.SCHEMA, '.', MAIN.SOURCE_TABLE.TABLE_NAME)
END AS source_table,
main.target_table.`catalog` as target_catalog,
main.target_table.`schema` as target_schema,
main.target_table.table_name as target_table_name,
CONCAT(MAIN.TARGET_TABLE.CATALOG, '.', MAIN.TARGET_TABLE.SCHEMA, '.', MAIN.TARGET_TABLE.TABLE_NAME) AS target_table,
sundarshankar89 marked this conversation as resolved.
Show resolved Hide resolved
metrics.run_metrics.status as status,
metrics.run_metrics.exception_message as exception,
metrics.recon_metrics.row_comparison.missing_in_source as missing_in_source,
metrics.recon_metrics.row_comparison.missing_in_target as missing_in_target,
metrics.recon_metrics.column_comparison.absolute_mismatch as absolute_mismatch,
metrics.recon_metrics.column_comparison.threshold_mismatch as threshold_mismatch,
metrics.recon_metrics.column_comparison.mismatch_columns as mismatch_columns,
metrics.recon_metrics.schema_comparison as schema_comparison,
metrics.run_metrics.run_by_user as executed_by,
main.start_ts as start_ts,
main.end_ts as end_ts
from IDENTIFIER(:catalog || '.' || :schema || '.main' ) main
inner join
IDENTIFIER(:catalog || '.' || :schema || '.metrics' ) metrics
on main.recon_table_id = metrics.recon_table_id
order by metrics.inserted_ts desc, main.recon_id, main.target_table.table_name
Original file line number Diff line number Diff line change
@@ -0,0 +1,31 @@
with tmp as (select
recon_table_id,
inserted_ts,
explode(data) as schema_data
from IDENTIFIER(:catalog || '.' || :schema || '.details' )
where recon_type='schema'
)
select
main.recon_id,
main.source_table.`catalog` as source_catalog,
main.source_table.`schema` as source_schema,
main.source_table.table_name as source_table_name,
CASE
WHEN COALESCE(MAIN.SOURCE_TABLE.CATALOG, '') <> '' THEN CONCAT(MAIN.SOURCE_TABLE.CATALOG, '.', MAIN.SOURCE_TABLE.SCHEMA, '.', MAIN.SOURCE_TABLE.TABLE_NAME)
ELSE CONCAT(MAIN.SOURCE_TABLE.SCHEMA, '.', MAIN.SOURCE_TABLE.TABLE_NAME)
END AS source_table,
main.target_table.`catalog` as target_catalog,
main.target_table.`schema` as target_schema,
main.target_table.table_name as target_table_name,
CONCAT(MAIN.TARGET_TABLE.CATALOG, '.', MAIN.TARGET_TABLE.SCHEMA, '.', MAIN.TARGET_TABLE.TABLE_NAME) AS target_table,
schema_data['source_column'] as source_column,
schema_data['source_datatype'] as source_datatype,
schema_data['databricks_column'] as databricks_column,
schema_data['databricks_datatype'] as databricks_datatype,
schema_data['is_valid'] as is_valid
from
IDENTIFIER(:catalog || '.' || :schema || '.main' ) main
inner join
tmp
on main.recon_table_id = tmp.recon_table_id
order by tmp.inserted_ts desc, main.recon_id, main.target_table
Original file line number Diff line number Diff line change
@@ -0,0 +1,22 @@
with tmp as (select recon_table_id, inserted_ts ,recon_type, explode(data) as data,
row_number() over(partition by recon_table_id,recon_type order by recon_table_id) as rn
from IDENTIFIER(:catalog || '.' || :schema || '.details' )
where recon_type != 'schema')
select main.recon_id,
main.source_table.`catalog` as source_catalog,
main.source_table.`schema` as source_schema,
main.source_table.table_name as source_table_name,
CASE
WHEN COALESCE(MAIN.SOURCE_TABLE.CATALOG, '') <> '' THEN CONCAT(MAIN.SOURCE_TABLE.CATALOG, '.', MAIN.SOURCE_TABLE.SCHEMA, '.', MAIN.SOURCE_TABLE.TABLE_NAME)
ELSE CONCAT(MAIN.SOURCE_TABLE.SCHEMA, '.', MAIN.SOURCE_TABLE.TABLE_NAME)
END AS source_table,
main.target_table.`catalog` as target_catalog,
main.target_table.`schema` as target_schema,
main.target_table.table_name as target_table_name,
CONCAT(MAIN.TARGET_TABLE.CATALOG, '.', MAIN.TARGET_TABLE.SCHEMA, '.', MAIN.TARGET_TABLE.TABLE_NAME) AS target_table,
recon_type, key, value, rn
from tmp
inner join
IDENTIFIER(:catalog || '.' || :schema || '.main' ) main
on main.recon_table_id = tmp.recon_table_id
lateral view explode(data) exploded_data AS key, value
Original file line number Diff line number Diff line change
@@ -0,0 +1,26 @@
select
main.recon_id,
main.source_type,
main.report_type,
main.source_table.`catalog` as source_catalog,
main.source_table.`schema` as source_schema,
main.source_table.table_name as source_table_name,
CASE
WHEN COALESCE(MAIN.SOURCE_TABLE.CATALOG, '') <> '' THEN CONCAT(MAIN.SOURCE_TABLE.CATALOG, '.', MAIN.SOURCE_TABLE.SCHEMA, '.', MAIN.SOURCE_TABLE.TABLE_NAME)
ELSE CONCAT(MAIN.SOURCE_TABLE.SCHEMA, '.', MAIN.SOURCE_TABLE.TABLE_NAME)
END AS source_table,
main.target_table.`catalog` as target_catalog,
main.target_table.`schema` as target_schema,
main.target_table.table_name as target_table_name,
CONCAT(MAIN.TARGET_TABLE.CATALOG, '.', MAIN.TARGET_TABLE.SCHEMA, '.', MAIN.TARGET_TABLE.TABLE_NAME) AS target_table,
metrics.run_metrics.status as status,
metrics.run_metrics.run_by_user as executed_by,
main.start_ts as start_ts,
main.end_ts as end_ts,
date(main.start_ts) as start_date
from IDENTIFIER(:catalog || '.' || :schema || '.main' ) main
inner join
IDENTIFIER(:catalog || '.' || :schema || '.metrics' ) metrics
on main.recon_table_id = metrics.recon_table_id
where metrics.run_metrics.status = false
order by metrics.inserted_ts desc, main.recon_id, main.target_table.table_name
Original file line number Diff line number Diff line change
@@ -0,0 +1,20 @@
select
main.recon_id,
main.source_type,
main.report_type,
CASE
WHEN COALESCE(MAIN.SOURCE_TABLE.CATALOG, '') <> '' THEN CONCAT(MAIN.SOURCE_TABLE.CATALOG, '.', MAIN.SOURCE_TABLE.SCHEMA, '.', MAIN.SOURCE_TABLE.TABLE_NAME)
ELSE CONCAT(MAIN.SOURCE_TABLE.SCHEMA, '.', MAIN.SOURCE_TABLE.TABLE_NAME)
END AS source_table,
CONCAT(MAIN.TARGET_TABLE.CATALOG, '.', MAIN.TARGET_TABLE.SCHEMA, '.', MAIN.TARGET_TABLE.TABLE_NAME) AS target_table,
metrics.run_metrics.status as status,
metrics.run_metrics.run_by_user as executed_by,
main.start_ts as start_ts,
main.end_ts as end_ts,
date(main.start_ts) as start_date
from IDENTIFIER(:catalog || '.' || :schema || '.main' ) main
inner join
IDENTIFIER(:catalog || '.' || :schema || '.metrics' ) metrics
on main.recon_table_id = metrics.recon_table_id
where metrics.run_metrics.status = true
order by metrics.inserted_ts desc, main.recon_id, main.target_table.table_name

Large diffs are not rendered by default.

sundarshankar89 marked this conversation as resolved.
Show resolved Hide resolved
Empty file.
Loading