WIP: XLSX reader

src/caosadvancedtools/table_json_conversion/convert.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 Henrik tom Wörden <h.tomwoerden@indiscale.com>
+# Copyright (C) 2024 Daniel Hornung <d.hornung@indiscale.com>
+#
+# 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/>.
+
+from fill_xlsx import read_or_dict
+
+
+class XLSXConverter:
+    def __init__(self, schema: Union[dict, str, TextIO]):
+        """
+
+Parameters
+----------
+schema: Union[dict, str, TextIO]
+  If given, validate the date against this schema first.  This raises an exception if the validation
+  fails.  May be given as dict with the schema, path to a json file as string or as a readable file
+  like object.
+        """
+        self._schema = read_or_dict(schema)

src/caosadvancedtools/table_json_conversion/fill_xlsx.py

@@ -118,7 +118,7 @@ def _next_row_index(sheet: Worksheet) -> int:
     return sheet.max_row
 
 
-def _read_or_dict(data: Union[dict, str, TextIO]) -> dict:
+def read_or_dict(data: Union[dict, str, TextIO]) -> dict:
     """If data is a json file name or input stream, read data from there."""
     if isinstance(data, dict):
         pass
@@ -414,12 +414,12 @@ validation_schema: dict, optional
   fails.  If no validation schema is given, try to ignore more errors in the data when filling the
   XLSX template.
 """
-    data = _read_or_dict(data)
+    data = read_or_dict(data)
     assert isinstance(data, dict)
 
     # Validation
     if validation_schema is not None:
-        validation_schema = _read_or_dict(validation_schema)
+        validation_schema = read_or_dict(validation_schema)
         try:
             validate(data, validation_schema, format_checker=FormatChecker())
         except ValidationError as ve: