Update workflow execution search tests

Author: naglepuff

nmdc_server/fakes.py

@@ -203,7 +203,7 @@ class PipelineStepBase(SQLAlchemyModelFactory):
     started_at_time: datetime = Faker("date_time")
     ended_at_time: datetime = Faker("date_time")
     execution_resource: str = Faker("word")
-    omics_processing: models.OmicsProcessing = SubFactory(OmicsProcessingFactory)
+    was_informed_by: List[models.OmicsProcessing] = []
 
 
 class ReadsQCFactory(PipelineStepBase):

nmdc_server/filters.py

@@ -35,6 +35,7 @@
     MetaPGeneFunction,
     MetaTGeneFunction,
     Table,
+    _table_model_map,
     workflow_execution_tables,
 )
 
@@ -107,7 +108,15 @@ def join(self, target_table: Table, query: Query) -> Query:
         raise NotImplementedError()
 
     def _join_omics_processing_related_tables(self, target_table: Table, query: Query) -> Query:
-        if target_table != Table.omics_processing:
+        if target_table in workflow_execution_tables:
+            association_table = models.workflow_activity_to_data_generation_map[target_table.value]
+            query = query.join(
+                association_table
+            ).join(
+                models.OmicsProcessing,
+                models.OmicsProcessing.id == association_table.c.data_generation_id,
+            )
+        elif target_table != Table.omics_processing:
             query = query.join(models.OmicsProcessing)
 
         return self.join_omics_processing(query)
@@ -252,10 +261,27 @@ def join_study(self, query: Query) -> Query:
         )
 
 
-workflow_filter_classes: List[Type[OmicsProcessingFilter]] = []
+class WorkflowExecutionFilter(OmicsProcessingFilter):
+    table = Table.reads_qc
+
+    def join_omics_processing(self, query: Query) -> Query:
+        association_table = models.workflow_activity_to_data_generation_map[self.table.value]
+        model = _table_model_map[self.table]
+        q = query.join(
+            association_table,
+            association_table.c.data_generation_id == models.OmicsProcessing.id,
+        ).join(
+            model,
+            model.id == association_table.c[f"{self.table.value}_id"]  # type: ignore
+        )
+        print(q)
+        return q
+
+
+workflow_filter_classes: List[Type[WorkflowExecutionFilter]] = []
 for table in workflow_execution_tables:
     workflow_filter_classes.append(
-        type(f"{table.value}_filter", (OmicsProcessingFilter,), {"table": table})
+        type(f"{table.value}_filter", (WorkflowExecutionFilter,), {"table": table})
     )
 
 
@@ -404,7 +430,14 @@ class MetaproteomicAnalysisFilter(OmicsProcessingFilter):
     table = Table.metaproteomic_analysis
 
     def join_omics_processing(self, query: Query) -> Query:
-        return query.join(self.table.model)
+        association_table = models.metaproteomic_analysis_data_generation_association
+        return query.join(
+            association_table,
+            association_table.c.data_generation_id == models.OmicsProcessing.id,
+        ).join(
+            models.MetaproteomicAnalysis,
+            models.MetaproteomicAnalysis.id == association_table.c.metaproteomic_analysis_id,
+        )
 
     def join_biosample(self, query: Query) -> Query:
         return (

tests/test_download.py

@@ -18,7 +18,7 @@ def test_bulk_download_query(db: Session):
     )
     op1.outputs.append(raw1)
 
-    metag = fakes.MetagenomeAnnotationFactory(omics_processing=op1)
+    metag = fakes.MetagenomeAnnotationFactory(was_informed_by=[op1])
     metag_output = fakes.DataObjectFactory(
         url="https://data.microbiomedata.org/data/metag",
         omics_processing=op1,
@@ -64,7 +64,7 @@ def test_generate_bulk_download(db: Session, client: TestClient, logged_in_user)
     )
     op1.outputs.append(raw1)
 
-    metag = fakes.MetagenomeAnnotationFactory(omics_processing=op1)
+    metag = fakes.MetagenomeAnnotationFactory(was_informed_by=[op1])
     metag_output = fakes.DataObjectFactory(
         url="https://data.microbiomedata.org/data/metag",
         omics_processing=op1,
@@ -97,7 +97,7 @@ def test_generate_bulk_download_filtered(
     )
     op1.outputs.append(raw1)
 
-    metag = fakes.MetagenomeAnnotationFactory(omics_processing=op1)
+    metag = fakes.MetagenomeAnnotationFactory(was_informed_by=[op1])
     metag_output = fakes.DataObjectFactory(
         url="https://data.microbiomedata.org/data/metag",
         omics_processing=op1,

tests/test_query.py

@@ -367,37 +367,37 @@ def test_pipeline_query(db: Session, table):
     omics_processing1 = fakes.OmicsProcessingFactory(name="omics_processing1")
     omics_processing2 = fakes.OmicsProcessingFactory(name="omics_processing2")
 
-    fakes.ReadsQCFactory(omics_processing=omics_processing1, name="reads_qc1")
-    fakes.ReadsQCFactory(omics_processing=omics_processing1, name="reads_qc2")
-    fakes.ReadsQCFactory(omics_processing=omics_processing2, name="reads_qc3")
+    fakes.ReadsQCFactory(was_informed_by=[omics_processing1], name="reads_qc1")
+    fakes.ReadsQCFactory(was_informed_by=[omics_processing1], name="reads_qc2")
+    fakes.ReadsQCFactory(was_informed_by=[omics_processing2], name="reads_qc3")
 
-    fakes.MetagenomeAssemblyFactory(omics_processing=omics_processing1, name="assembly1")
-    fakes.MetagenomeAssemblyFactory(omics_processing=omics_processing1, name="assembly2")
-    fakes.MetagenomeAssemblyFactory(omics_processing=omics_processing2, name="assembly3")
+    fakes.MetagenomeAssemblyFactory(was_informed_by=[omics_processing1], name="assembly1")
+    fakes.MetagenomeAssemblyFactory(was_informed_by=[omics_processing1], name="assembly2")
+    fakes.MetagenomeAssemblyFactory(was_informed_by=[omics_processing2], name="assembly3")
 
-    fakes.MetagenomeAnnotationFactory(omics_processing=omics_processing1, name="annotation1")
-    fakes.MetagenomeAnnotationFactory(omics_processing=omics_processing1, name="annotation2")
-    fakes.MetagenomeAnnotationFactory(omics_processing=omics_processing2, name="annotation3")
+    fakes.MetagenomeAnnotationFactory(was_informed_by=[omics_processing1], name="annotation1")
+    fakes.MetagenomeAnnotationFactory(was_informed_by=[omics_processing1], name="annotation2")
+    fakes.MetagenomeAnnotationFactory(was_informed_by=[omics_processing2], name="annotation3")
 
-    fakes.MetaproteomicAnalysisFactory(omics_processing=omics_processing1, name="analysis1")
-    fakes.MetaproteomicAnalysisFactory(omics_processing=omics_processing1, name="analysis2")
-    fakes.MetaproteomicAnalysisFactory(omics_processing=omics_processing2, name="analysis3")
+    fakes.MetaproteomicAnalysisFactory(was_informed_by=[omics_processing1], name="analysis1")
+    fakes.MetaproteomicAnalysisFactory(was_informed_by=[omics_processing1], name="analysis2")
+    fakes.MetaproteomicAnalysisFactory(was_informed_by=[omics_processing2], name="analysis3")
 
-    fakes.MAGsAnalysisFactory(omics_processing=omics_processing1, name="mags1")
-    fakes.MAGsAnalysisFactory(omics_processing=omics_processing1, name="mags2")
-    fakes.MAGsAnalysisFactory(omics_processing=omics_processing2, name="mags3")
+    fakes.MAGsAnalysisFactory(was_informed_by=[omics_processing1], name="mags1")
+    fakes.MAGsAnalysisFactory(was_informed_by=[omics_processing1], name="mags2")
+    fakes.MAGsAnalysisFactory(was_informed_by=[omics_processing2], name="mags3")
 
-    fakes.ReadBasedAnalysisFactory(omics_processing=omics_processing1, name="reads1")
-    fakes.ReadBasedAnalysisFactory(omics_processing=omics_processing1, name="reads2")
-    fakes.ReadBasedAnalysisFactory(omics_processing=omics_processing2, name="reads3")
+    fakes.ReadBasedAnalysisFactory(was_informed_by=[omics_processing1], name="reads1")
+    fakes.ReadBasedAnalysisFactory(was_informed_by=[omics_processing1], name="reads2")
+    fakes.ReadBasedAnalysisFactory(was_informed_by=[omics_processing2], name="reads3")
 
-    fakes.NOMAnalysisFactory(omics_processing=omics_processing1, name="nom1")
-    fakes.NOMAnalysisFactory(omics_processing=omics_processing1, name="nom2")
-    fakes.NOMAnalysisFactory(omics_processing=omics_processing2, name="nom3")
+    fakes.NOMAnalysisFactory(was_informed_by=[omics_processing1], name="nom1")
+    fakes.NOMAnalysisFactory(was_informed_by=[omics_processing1], name="nom2")
+    fakes.NOMAnalysisFactory(was_informed_by=[omics_processing2], name="nom3")
 
-    fakes.MetabolomicsAnalysisFactory(omics_processing=omics_processing1, name="metab1")
-    fakes.MetabolomicsAnalysisFactory(omics_processing=omics_processing1, name="metab2")
-    fakes.MetabolomicsAnalysisFactory(omics_processing=omics_processing2, name="metab3")
+    fakes.MetabolomicsAnalysisFactory(was_informed_by=[omics_processing1], name="metab1")
+    fakes.MetabolomicsAnalysisFactory(was_informed_by=[omics_processing1], name="metab2")
+    fakes.MetabolomicsAnalysisFactory(was_informed_by=[omics_processing2], name="metab3")
     db.commit()
 
     # test omics_processing not associated with biosamples