chore!: harmonize CLI flags, rename CLI entry point and add tests for the CLI (DEV-2525)

pyproject.toml

@@ -55,7 +55,7 @@ types-pyyaml = "^6.0.12.10"
 
 
 [tool.poetry.scripts]
-dsp-tools = "dsp_tools.dsp_tools:main"    # definition of the CLI entry point
+dsp-tools = "dsp_tools.cli_entry_point:main"    # definition of the CLI entry point
 
 
 [tool.poetry-exec-plugin.commands]

src/dsp_tools/dsp_tools.py → src/dsp_tools/cli_entry_point.py

@@ -114,7 +114,7 @@ def _make_parser(
         help="The links in the XML file point to IRIs (on the server) instead of IDs (in the same XML file).",
     )
     parser_upload.add_argument(
-        "-V", "--validate", action="store_true", help="validate the XML file without uploading it"
+        "-V", "--validate-only", action="store_true", help="validate the XML file without uploading it"
     )
     parser_upload.add_argument("-v", "--verbose", action="store_true", help=verbose_text)
     parser_upload.add_argument("-m", "--metrics", action="store_true", help="write metrics into a 'metrics' folder")
@@ -449,7 +449,7 @@ def _call_requested_action(args: argparse.Namespace) -> bool:
             verbose=args.verbose,
         )
     elif args.action == "xmlupload":
-        if args.validate:
+        if args.validate_only:
             success = validate_xml_against_schema(input_file=args.xmlfile)
         else:
             success = xml_upload(

src/dsp_tools/excel2xml.py

@@ -1267,14 +1267,14 @@ def make_text_prop(
     for val in values:
         kwargs = {"permissions": val.permissions}
         if check_notna(val.comment):
-            kwargs["comment"] = val.comment  # type: ignore
+            kwargs["comment"] = str(val.comment)
         if check_notna(val.encoding):
-            kwargs["encoding"] = val.encoding  # type: ignore
+            kwargs["encoding"] = str(val.encoding)
         else:
             kwargs["encoding"] = "utf8"
         value_ = etree.Element(
             "{%s}text" % xml_namespace_map[None],
-            **kwargs,  # type: ignore
+            **kwargs,  # type: ignore[arg-type]
             nsmap=xml_namespace_map,
         )
         if kwargs["encoding"] == "utf8":
@@ -2274,7 +2274,7 @@ def excel2xml(
     It takes a tabular data source in CSV/XLS(X) format that is formatted according to the specifications,
     and transforms it into a DSP-conforming XML file
     that can be uploaded to a DSP server with the xmlupload command.
-    The output file is saved in the same directory as the input file,
+    The output file is saved in the current working directory,
     with the name [default_ontology]-data.xml.
 
     Please note that this method doesn't do any data cleaning or data transformation tasks.

src/dsp_tools/utils/id_to_iri.py

@@ -84,7 +84,7 @@ def id_to_iri(
         out_file = file_name + "_replaced_" + timestamp_str + ".xml"
 
     et = etree.ElementTree(tree.getroot())
-    et.write(out_file, pretty_print=True)
+    et.write(out_file, pretty_print=True, xml_declaration=True, encoding="utf-8")
     print(f"XML with replaced IDs was written to file {out_file}.")
 
     return success

test/e2e/test_00A1_import_scripts.py

@@ -2,6 +2,7 @@
 
 import os
 import re
+import subprocess
 import unittest
 
 import pytest
@@ -27,7 +28,7 @@ def test_import_scripts(self) -> None:
         the DSP server.
         """
         # pull the latest state of the git submodule
-        os.system("git submodule update --init --recursive")
+        subprocess.run("git submodule update --init --recursive", check=True, shell=True)
         from dsp_tools.import_scripts import import_script  # pylint: disable=import-outside-toplevel
 
         # execute the import script in its directory