Merge branch 'develop' of https://github.com/hed-standard/hed-python …

…into develop

hed/scripts/convert_and_update_schema.py

@@ -72,7 +72,7 @@ def convert_and_update(filenames, set_ids):
 def main():
     parser = argparse.ArgumentParser(description='Update other schema formats based on the changed one.')
     parser.add_argument('filenames', nargs='*', help='List of files to process')
-    parser.add_argument('--set-ids', action='store_true', help='Set IDs for each file')
+    parser.add_argument('--set-ids', action='store_true', help='Add missing hed ids')
 
     args = parser.parse_args()
 

hed/scripts/create_ontology.py

@@ -0,0 +1,48 @@
+from hed.schema import load_schema_version
+from hed.schema.schema_io.df2schema import load_dataframes
+from hed.schema.schema_io.ontology_util import convert_df_to_omn
+from hed.scripts.script_util import get_prerelease_path, get_schema_filename
+import argparse
+import os
+
+
+def create_ontology(repo_path, schema_name, schema_version, dest):
+    final_source = get_prerelease_path(repo_path, schema_name, schema_version)
+    # print(f"Creating ontology from {final_source}")
+
+    dataframes = load_dataframes(final_source)
+    _, omn_dict = convert_df_to_omn(dataframes)
+
+    base = get_schema_filename(schema_name, schema_version)
+    output_dest = os.path.join(dest, base)
+    os.makedirs(output_dest, exist_ok=True)
+    for suffix, omn_text in omn_dict.items():
+        filename = os.path.join(output_dest, f"{base}_{suffix}.omn")
+        with open(filename, mode='w', encoding='utf-8') as opened_file:
+            opened_file.writelines(omn_text)
+
+    return 0
+
+
+def main():
+    parser = argparse.ArgumentParser(description='Convert a specified schema in the prerelease folder to an ontology.')
+    parser.add_argument('repo_path', help='The location of the hed-schemas directory')
+    parser.add_argument('schema_name', help='The name of the schema to convert("standard" for standard schema)')
+    parser.add_argument('schema_version', help='The location of the hed-schemas directory')
+    parser.add_argument('--dest', default=os.path.join("src", "ontology"), help='The base location to save to')
+
+    args = parser.parse_args()
+
+    repo_path = args.repo_path
+    schema_name = args.schema_name
+    schema_version = args.schema_version
+    dest = args.dest
+
+    # Trigger a local cache hit (this ensures trying to load withStandard schemas will work properly)
+    _ = load_schema_version("8.2.0")
+
+    return create_ontology(repo_path, schema_name, schema_version, dest)
+
+
+if __name__ == "__main__":
+    exit(main())

hed/scripts/script_util.py

@@ -159,3 +159,27 @@ def validate_all_schemas(schema_files):
 
         all_issues += single_schema_issues
     return all_issues
+
+
+
+def get_schema_filename(schema_name, schema_version):
+    schema_name = schema_name.lower()
+    if schema_name == "standard" or schema_name == "":
+        return f"HED{schema_version}"
+    else:
+        return f"HED_{schema_name}_{schema_version}"
+
+
+def get_prerelease_path(repo_path, schema_name, schema_version):
+    """Returns the location of the given pre-release schema in the repo"""
+    schema_name = schema_name.lower()
+    if schema_name == "" or schema_name == "standard":
+        base_path = "standard_schema"
+    else:
+        base_path = os.path.join("library_schemas", schema_name)
+
+    base_path = os.path.join(repo_path, base_path, "prerelease")
+
+    schema_filename = get_schema_filename(schema_name, schema_version)
+
+    return os.path.join(base_path, "hedtsv", schema_filename)

pyproject.toml

@@ -57,6 +57,7 @@ run_remodel_backup = "hed.tools.remodeling.cli.run_remodel_backup:main"
 run_remodel_restore = "hed.tools.remodeling.cli.run_remodel_restore:main"
 hed_validate_schemas = "hed.scripts.validate_schemas:main"
 hed_update_schemas = "hed.scripts.convert_and_update_schema:main"
+hed_create_ontology = "hed.scripts.create_ontology:main"
 
 [tool.versioneer]
 VCS = "git"

tests/schema/test_ontology_util.py

@@ -150,7 +150,7 @@ def test_update_dataframes_from_schema(self):
         try:
             updated_dataframes = update_dataframes_from_schema(schema_dataframes_new, schema)
         except HedFileError as e:
-            self.assertEqual(len(e.issues), 111)
+            self.assertEqual(len(e.issues), 115)
         breakHere = 3
 
 

tests/scripts/test_script_util.py

@@ -15,9 +15,9 @@ def test_regular_extension(self):
     def test_tsv_extension(self):
         """Test that .tsv extensions are handled differently."""
         # Assuming the function correctly handles paths with directories
-        self.assertEqual(add_extension("path/to/filename", ".tsv"), "path/to/hedtsv/filename")
+        self.assertEqual(add_extension(os.path.normpath("path/to/filename"), ".tsv"), os.path.normpath("path/to/hedtsv/filename"))
         # Testing with a basename only
-        self.assertEqual(add_extension("filename", ".tsv"), "hedtsv/filename")
+        self.assertEqual(add_extension("filename", ".tsv"), os.path.normpath("hedtsv/filename"))
 
     def test_empty_extension(self):
         """Test adding an empty extension."""
@@ -33,7 +33,7 @@ class TestSortBaseSchemas(unittest.TestCase):
     def test_mixed_file_types(self):
         filenames = [
             "test_schema.mediawiki",
-            "hedtsv/test_schema/test_schema_Tag.tsv",
+            os.path.normpath("hedtsv/test_schema/test_schema_Tag.tsv"),
             "other_schema.xml"
         ]
         expected = {
@@ -45,9 +45,9 @@ def test_mixed_file_types(self):
 
     def test_tsv_in_correct_subfolder(self):
         filenames = [
-            "hedtsv/test_schema/test_schema_Tag.tsv",
-            "hedtsv/test_schema/test_schema_Tag.tsv",
-            "hedtsv/wrong_folder/wrong_name_Tag.tsv"  # Should be ignored
+            os.path.normpath("hedtsv/test_schema/test_schema_Tag.tsv"),
+            os.path.normpath("hedtsv/test_schema/test_schema_Tag.tsv"),
+            os.path.normpath("hedtsv/wrong_folder/wrong_name_Tag.tsv")  # Should be ignored
         ]
         expected = {
             "test_schema": {".tsv"}
@@ -57,20 +57,20 @@ def test_tsv_in_correct_subfolder(self):
 
     def test_tsv_in_correct_subfolder2(self):
         filenames = [
-            "prerelease/hedtsv/test_schema/test_schema_Tag.tsv",
-            "prerelease/hedtsv/test_schema/test_schema_Tag.tsv",
-            "prerelease/hedtsv/wrong_folder/wrong_name_Tag.tsv"  # Should be ignored
+            os.path.normpath("prerelease/hedtsv/test_schema/test_schema_Tag.tsv"),
+            os.path.normpath("prerelease/hedtsv/test_schema/test_schema_Tag.tsv"),
+            os.path.normpath("prerelease/hedtsv/wrong_folder/wrong_name_Tag.tsv")  # Should be ignored
         ]
         expected = {
-            "prerelease/test_schema": {".tsv"}
+            os.path.normpath("prerelease/test_schema"): {".tsv"}
         }
         result = sort_base_schemas(filenames)
         self.assertEqual(dict(result), expected)
 
     def test_ignored_files(self):
         filenames = [
             "test_schema.mediawiki",
-            "not_hedtsv/test_schema/test_schema_Tag.tsv"  # Should be ignored
+            os.path.normpath("not_hedtsv/test_schema/test_schema_Tag.tsv")  # Should be ignored
         ]
         expected = {
             "test_schema": {".mediawiki"}