ENH(core): new validator module that is supposed to check created records using a json schema

src/caoscrawler/validator.py

+#!/usr/bin/env python3
+# encoding: utf-8
+#
+# This file is a part of the LinkAhead Project.
+#
+# Copyright (C) 2024 Indiscale GmbH <info@indiscale.com>
+# Copyright (C) 2024 Alexander Schlemmer
+#
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as
+# published by the Free Software Foundation, either version 3 of the
+# License, or (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with this program. If not, see <https://www.gnu.org/licenses/>.
+#
+# ** end header
+#
+
+"""
+This module contains functions to validate the output of a scanner run with a
+json schema.
+"""
+
+
+import json
+
+import jsonschema
+import linkahead as db
+# from caosadvancedtools.models.parser import parse_model_from_string
+from caosadvancedtools.json_schema_exporter import recordtype_to_json_schema
+from caosadvancedtools.models.parser import parse_model_from_yaml
+from linkahead.high_level_api import convert_to_python_object
+
+from caoscrawler import scanner
+
+
+def load_json_schema_from_datamodel_yaml(filename: str) -> list:
+    """
+    Load a data model yaml file (using caosadvancedtools) and convert
+    all record types into a json schema using the json_schema_exporter module.
+
+    Arguments
+    ---------
+    filename: str
+        The filename of the yaml file to load.
+
+    Returns
+    -------
+    A list of json schema objects.
+    """
+
+    model = parse_model_from_yaml(filename)
+
+    # TODO: fix needed (https://gitlab.indiscale.com/caosdb/customers/f-fit/management/-/issues/58)
+
+    rt_schemas = []
+    for el in model:
+        if isinstance(el, db.RecordType):
+            rt_schemas.append(recordtype_to_json_schema(el))
+
+    return rt_schemas