ENH: Treat array entries without items property

src/caosadvancedtools/models/parser.py

@@ -154,7 +154,12 @@ def parse_model_from_string(string):
     return parser.parse_model_from_string(string)
 
 
-def parse_model_from_json_schema(filename: str, top_level_recordtype: bool = True):
+def parse_model_from_json_schema(
+        filename: str,
+        top_level_recordtype: bool = True,
+        types_for_missing_array_items: dict = {},
+        ignore_unspecified_array_items: bool = False
+):
     """Return a datamodel parsed from a json schema definition.
 
     Parameters
@@ -164,7 +169,14 @@ def parse_model_from_json_schema(filename: str, top_level_recordtype: bool = Tru
     top_level_recordtype : bool, optional
         Whether there is a record type defined at the top level of the
         schema. Default is true.
-
+    types_for_missing_array_items : dict, optional
+        dictionary containing fall-back types for json entries with `type:
+        array` but without `items` specification. Default is an empty dict.
+    ignore_unspecified_array_items : bool, optional
+        Whether to ignore `type: array` entries the type of which is not
+        specified by their `items` property or given in
+        `types_for_missing_array_items`. An error is raised if they are not
+        ignored. Default is False.
 
     Returns
     -------
@@ -181,7 +193,7 @@ def parse_model_from_json_schema(filename: str, top_level_recordtype: bool = Tru
     # @author Florian Spreckelsen
     # @date 2022-02-17
     # @review Daniel Hornung 2022-02-18
-    parser = JsonSchemaParser()
+    parser = JsonSchemaParser(types_for_missing_array_items, ignore_unspecified_array_items)
 
     return parser.parse_model_from_json_schema(filename, top_level_recordtype)
 
@@ -629,6 +641,11 @@ class JsonSchemaParser(Parser):
     # @date 2022-02-17
     # @review Timm Fitschen 2022-02-30
 
+    def __init__(self, types_for_missing_array_items={}, ignore_unspecified_array_items=False):
+        super().__init__()
+        self.types_for_missing_array_items = types_for_missing_array_items
+        self.ignore_unspecified_array_items = ignore_unspecified_array_items
+
     def parse_model_from_json_schema(self, filename: str, top_level_recordtype: bool = True):
         """Return a datamodel created from the definition in the json schema in
         `filename`.
@@ -755,7 +772,7 @@ class JsonSchemaParser(Parser):
         if name == "name":
             # This is identified with the CaosDB name property as long as the
             # type is correct.
-            if not elt["type"] == "string":
+            if not elt["type"] == "string" and "string" not in elt["type"]:
                 raise JsonSchemaDefinitionError(
                     "The 'name' property must be string-typed, otherwise it cannot "
                     "be identified with CaosDB's name property."
@@ -786,7 +803,8 @@ class JsonSchemaParser(Parser):
             # treat_something function
             ent.description = elt["description"]
 
-        self.model[name] = ent
+        if ent is not None:
+            self.model[name] = ent
         return ent, force_list
 
     def _treat_record_type(self, elt: dict, name: str):
@@ -846,26 +864,33 @@ class JsonSchemaParser(Parser):
     def _treat_list(self, elt: dict, name: str):
         # @review Timm Fitschen 2022-02-30
 
-        if "items" not in elt:
+        if "items" not in elt and name not in self.types_for_missing_array_items:
+            if self.ignore_unspecified_array_items:
+                return None, False
             raise JsonSchemaDefinitionError(
                 f"The definition of the list items is missing in {elt}.")
-        items = elt["items"]
-        if "enum" in items:
-            return self._treat_enum(items, name), True
-        if items["type"] in JSON_SCHEMA_ATOMIC_TYPES:
-            datatype = db.LIST(self._get_atomic_datatype(items))
+        if "items" in elt:
+            items = elt["items"]
+            if "enum" in items:
+                return self._treat_enum(items, name), True
+            if items["type"] in JSON_SCHEMA_ATOMIC_TYPES:
+                datatype = db.LIST(self._get_atomic_datatype(items))
+                return db.Property(name=name, datatype=datatype), False
+            if items["type"] == "object":
+                if "title" not in items or self._stringify(items["title"]) == name:
+                    # Property is RecordType
+                    return self._treat_record_type(items, name), True
+                else:
+                    # List property will be an entity of its own with a name
+                    # different from the referenced RT
+                    ref_rt = self._treat_record_type(
+                        items, self._stringify(items["title"]))
+                    self.model[ref_rt.name] = ref_rt
+                    return db.Property(name=name, datatype=db.LIST(ref_rt)), False
+        else:
+            # Use predefined type:
+            datatype = db.LIST(self.types_for_missing_array_items[name])
             return db.Property(name=name, datatype=datatype), False
-        if items["type"] == "object":
-            if "title" not in items or self._stringify(items["title"]) == name:
-                # Property is RecordType
-                return self._treat_record_type(items, name), True
-            else:
-                # List property will be an entity of its own with a name
-                # different from the referenced RT
-                ref_rt = self._treat_record_type(
-                    items, self._stringify(items["title"]))
-                self.model[ref_rt.name] = ref_rt
-                return db.Property(name=name, datatype=db.LIST(ref_rt)), False
 
     def _get_pattern_prop(self):
         if "__pattern_property_pattern_property" in self.model:

unittests/test_json_schema_model_parser.py

@@ -414,3 +414,30 @@ def test_no_toplevel_entity():
     assert pattern_object_rt.get_importance(pp.name) == db.OBLIGATORY
     date_id_prop = pattern_object_rt.get_property("date_id")
     assert date_id_prop.datatype == db.TEXT
+
+
+def test_missing_array_items():
+
+    # strict behavior
+    with pytest.raises(JsonSchemaDefinitionError) as err:
+        parse_model_from_json_schema(os.path.join(
+            FILEPATH, "datamodel_missing_array_items.schema.json"))
+
+    assert "{'type': 'array'}" in str(err)
+
+    # ignore all problems, so a RT is created that does not have the property
+    model = parse_model_from_json_schema(os.path.join(
+        FILEPATH, "datamodel_missing_array_items.schema.json"), ignore_unspecified_array_items=True)
+    assert "something_with_missing_array_items" in model
+    rt = model["something_with_missing_array_items"]
+    assert isinstance(rt, db.RecordType)
+    assert rt.get_property("missing") is None
+
+    # specify the type:
+    type_dict = {"missing": db.FILE}
+    model = parse_model_from_json_schema(os.path.join(
+        FILEPATH, "datamodel_missing_array_items.schema.json"), types_for_missing_array_items=type_dict)
+    assert "something_with_missing_array_items" in model
+    rt = model["something_with_missing_array_items"]
+    assert rt.get_property("missing") is not None
+    assert rt.get_property("missing").datatype == db.LIST(db.FILE)