Skip to content
Merged
13 changes: 10 additions & 3 deletions core/pom.xml
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@
<maven.compiler.source>1.8</maven.compiler.source>
<maven.compiler.target>1.8</maven.compiler.target>
<!-- 5.x starting from 5.0.0 requires JRE 11 -->
<mockito.version>4.11.0</mockito.version>
<mockito.version>5.11.0</mockito.version>
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
<slf4j.version>2.0.9</slf4j.version>
<antlr.version>4.13.1</antlr.version>
Expand Down Expand Up @@ -47,7 +47,7 @@
<dependency>
<groupId>com.databricks</groupId>
<artifactId>databricks-sdk-java</artifactId>
<version>0.21.0</version>
<version>0.24.1</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
Expand Down Expand Up @@ -78,7 +78,7 @@
<dependency>
<groupId>org.scalatest</groupId>
<artifactId>scalatest_${scala.binary.version}</artifactId>
<version>3.3.0-SNAP3</version>
<version>3.3.0-SNAP4</version>
<scope>test</scope>
</dependency>
<dependency>
Expand Down Expand Up @@ -230,4 +230,11 @@
</plugin>
</plugins>
</build>
<repositories>
<repository>
<id>maven_central</id>
<name>Maven Central</name>
<url>https://repo.maven.apache.org/maven2/</url>
</repository>
</repositories>
</project>

Large diffs are not rendered by default.

Empty file.
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 +1,22 @@
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 +1,31 @@
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 +1,31 @@
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
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Please update the CASE..WHEN..END statement to if(cond, exp1, exp2)... to simplify the statement and improve readability.

Suggested change
CASE
IF(ISNULL(MAIN.SOURCE_TABLE.CATALOG)
, CONCAT_WS('.', MAIN.SOURCE_TABLE.SCHEMA, MAIN.SOURCE_TABLE.TABLE_NAME)
, CONCAT_WS('.', MAIN.SOURCE_TABLE.CATALOG, MAIN.SOURCE_TABLE.SCHEMA, MAIN.SOURCE_TABLE.TABLE_NAME)) AS source_table,

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.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 +1,20 @@
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