Raise a helpful error when a datatype cannot be found in a schema

schematic/manifest/generator.py

@@ -82,8 +82,19 @@ def __init__(
 
         # Determine whether current data type is file-based
         is_file_based = False
-        if self.root:
+
+        if self.root:    
+            # Check if the class is in the schema
+            root_in_schema = self.sg.se.is_class_in_schema(self.root)
+
+            # If the class could not be found, give a notification
+            if not root_in_schema:
+                exception_message = f"The DataType entered ({self.root}) could not be found in the data model schema. " + \
+                                    "Please confirm that the datatype is in the data model and that the spelling matches the class label in the .jsonld file."
+                raise LookupError(exception_message) 
+
             is_file_based = "Filename" in self.sg.get_node_dependencies(self.root)
+
         self.is_file_based = is_file_based
 
     def _attribute_to_letter(self, attribute, manifest_fields):

tests/test_manifest.py

@@ -94,6 +94,24 @@ def test_init(self, helpers):
         assert generator.root is None
         assert type(generator.sg) is SchemaGenerator
 
+    def test_missing_root_error(self, helpers):
+        """
+        The ManifestGenerator should raise a LookupError during initialization if a data_type is passed in that can't be found in the schema.
+        """
+        # Choose a data type that is not in the schema
+        data_type = "MissingComponent"
+
+        # A LookupError should be raised and include message when the component cannot be found
+        with pytest.raises(LookupError) as e:
+            generator = ManifestGenerator(
+            path_to_json_ld=helpers.get_data_path("example.model.jsonld"),
+            root=data_type,
+            use_annotations=False,
+            )        
+
+        # Check message contents
+        assert f"({data_type}) could not be found in the data model schema" in str(e)
+
     @pytest.mark.google_credentials_needed
     def test_get_manifest_first_time(self, manifest):
 
@@ -145,7 +163,7 @@ def test_get_manifest_first_time(self, manifest):
         # An annotation merged with an attribute from the data model
         if use_annotations:
             assert output["File Format"].tolist() == ["txt", "csv", "fastq"]
-      
+
     @pytest.mark.parametrize("output_format", [None, "dataframe", "excel", "google_sheet"])
     @pytest.mark.parametrize("sheet_url", [None, True, False])
     @pytest.mark.parametrize("dataset_id", [None, "syn27600056"])
@@ -381,5 +399,3 @@ def test_populate_existing_excel_spreadsheet(self, simple_manifest_generator, si
         # remove file
         os.remove(dummy_output_path)
 
-
-