From 9db7d2e43662d350c967a073c8b3db1f370c2bf1 Mon Sep 17 00:00:00 2001
From: Will Deng <william.deng14@gmail.com>
Date: Tue, 30 Jul 2024 14:29:16 -0400
Subject: [PATCH] added description to validation task

---
 .../validation/data_warehouse_model_validator.py   | 14 ++++++++++++--
 .../validation/test_data_warehouse_tasks.py        |  8 ++++++--
 2 files changed, 18 insertions(+), 4 deletions(-)

diff --git a/metricflow/validation/data_warehouse_model_validator.py b/metricflow/validation/data_warehouse_model_validator.py
index 8ed5360353..ffc0e89190 100644
--- a/metricflow/validation/data_warehouse_model_validator.py
+++ b/metricflow/validation/data_warehouse_model_validator.py
@@ -87,6 +87,7 @@ class DataWarehouseValidationTask:
 
     query_and_params_callable: Callable[[], Tuple[str, SqlBindParameters]]
     error_message: str
+    description: str
     context: Optional[ValidationContext] = None
     on_fail_subtasks: List[DataWarehouseValidationTask] = field(default_factory=lambda: [])
 
@@ -155,6 +156,7 @@ def gen_semantic_model_tasks(
                         semantic_model=SemanticModelReference(semantic_model_name=semantic_model.name),
                     ),
                     error_message=f"Unable to access semantic model `{semantic_model.name}` in data warehouse",
+                    description=f"Validating semantic_model {semantic_model.name}",
                 )
             )
 
@@ -236,6 +238,7 @@ def gen_dimension_tasks(
                             element_type=SemanticModelElementType.DIMENSION,
                         ),
                         error_message=f"Unable to query dimension `{spec.qualified_name}` on semantic model `{semantic_model.name}` in data warehouse",
+                        description=f"Validating dimension `{spec.qualified_name}` in semantic_model `{semantic_model.name}`",
                     )
                 )
 
@@ -261,6 +264,7 @@ def gen_dimension_tasks(
                     ),
                     error_message=f"Failed to query dimensions in data warehouse for semantic model `{semantic_model.name}`",
                     on_fail_subtasks=semantic_model_sub_tasks,
+                    description=f"Validating all dimensions in semantic_model `{semantic_model.name}`",
                 )
             )
         return tasks
@@ -317,6 +321,7 @@ def gen_entity_tasks(
                             element_type=SemanticModelElementType.ENTITY,
                         ),
                         error_message=f"Unable to query entity `{spec.element_name}` on semantic model `{semantic_model.name}` in data warehouse",
+                        description=f"Validating entity `{spec.element_name}` in semantic_model `{semantic_model.name}`",
                     )
                 )
 
@@ -341,6 +346,7 @@ def gen_entity_tasks(
                     ),
                     error_message=f"Failed to query entities in data warehouse for semantic model `{semantic_model.name}`",
                     on_fail_subtasks=semantic_model_sub_tasks,
+                    description=f"Validating all entities in semantic_model `{semantic_model.name}`",
                 )
             )
         return tasks
@@ -413,6 +419,7 @@ def gen_measure_tasks(
                             element_type=SemanticModelElementType.MEASURE,
                         ),
                         error_message=f"Unable to query measure `{spec.element_name}` on semantic model `{semantic_model.name}` in data warehouse",
+                        description=f"Validating measure `{spec.element_name}` in semantic_model `{semantic_model.name}`",
                     )
                 )
 
@@ -435,6 +442,7 @@ def gen_measure_tasks(
                         ),
                         error_message=f"Failed to query measures in data warehouse for semantic model `{semantic_model.name}`",
                         on_fail_subtasks=source_node_to_sub_task[source_node],
+                        description=f"Validating all measures in semantic_model `{semantic_model.name}`",
                     )
                 )
         return tasks
@@ -478,7 +486,8 @@ def gen_metric_tasks(
                         file_context=FileContext.from_metadata(metadata=metric.metadata),
                         metric=MetricModelReference(metric_name=metric.name),
                     ),
-                    error_message=f"Unable to query metric `{metric.name}`.",
+                    error_message=f"Unable to query metric `{metric.name}`",
+                    description=f"Validating metric `{metric.name}`",
                 )
             )
         return tasks
@@ -513,7 +522,8 @@ def gen_saved_query_tasks(
                         element_type=SavedQueryElementType.METRIC,
                         element_value=saved_query.name,
                     ),
-                    error_message=f"Unable to query saved query `{saved_query.name}`.",
+                    error_message=f"Unable to query saved query `{saved_query.name}`",
+                    description=f"Validating saved_query `{saved_query.name}`",
                 )
             )
         return tasks
diff --git a/tests_metricflow/validation/test_data_warehouse_tasks.py b/tests_metricflow/validation/test_data_warehouse_tasks.py
index b79ae1df56..7047d26126 100644
--- a/tests_metricflow/validation/test_data_warehouse_tasks.py
+++ b/tests_metricflow/validation/test_data_warehouse_tasks.py
@@ -63,7 +63,9 @@ def good_query() -> Tuple[str, SqlBindParameters]:
         return ("SELECT 'foo' AS foo", SqlBindParameters())
 
     tasks = [
-        DataWarehouseValidationTask(query_and_params_callable=good_query, error_message="Could not select foo"),
+        DataWarehouseValidationTask(
+            query_and_params_callable=good_query, description="Validating foo", error_message="Could not select foo"
+        ),
     ]
 
     issues = dw_validator.run_tasks(tasks=tasks)
@@ -73,7 +75,9 @@ def bad_query() -> Tuple[str, SqlBindParameters]:
         return ("SELECT (true) AS col1 FROM doesnt_exist", SqlBindParameters())
 
     err_msg_bad = "Could not access table 'doesnt_exist' in data warehouse"
-    bad_task = DataWarehouseValidationTask(query_and_params_callable=bad_query, error_message=err_msg_bad)
+    bad_task = DataWarehouseValidationTask(
+        query_and_params_callable=bad_query, description="Validating foo", error_message=err_msg_bad
+    )
 
     tasks.append(bad_task)
     issues = dw_validator.run_tasks(tasks=tasks)