Minor TODO fixes

hed/schema/schema_attribute_validator_hed_id.py

@@ -1,5 +1,4 @@
 from hed.schema.hed_cache import get_library_data
-from hed.schema.schema_io.df_util import remove_prefix
 from semantic_version import Version
 from hed.schema.hed_schema_io import load_schema_version
 from hed.schema.hed_cache import get_hed_versions
@@ -87,13 +86,13 @@ def verify_tag_id(self, hed_schema, tag_entry, attribute_name):
 
         if old_id:
             try:
-                old_id = int(remove_prefix(old_id, "HED_"))
+                old_id = int(old_id.removeprefix("HED_"))
             except ValueError:
                 # Just silently ignore invalid old_id values(this shouldn't happen)
                 pass
         if new_id:
             try:
-                new_id = int(remove_prefix(new_id, "HED_"))
+                new_id = int(new_id.removeprefix("HED_"))
             except ValueError:
                 return ErrorHandler.format_error(SchemaAttributeErrors.SCHEMA_HED_ID_INVALID, tag_entry.name, new_id)
         # Nothing to verify

hed/schema/schema_io/df_util.py

@@ -233,13 +233,6 @@ def get_library_name_and_id(schema):
     return name.capitalize(), starting_id
 
 
-# todo: Replace this once we no longer support < python 3.10
-def remove_prefix(text, prefix):
-    if text and text.startswith(prefix):
-        return text[len(prefix) :]
-    return text
-
-
 def calculate_attribute_type(attribute_entry):
     """Returns the type of this attribute(annotation, object, data)
 

hed/schema/schema_io/hed_id_util.py

@@ -9,7 +9,6 @@
 from hed.schema.schema_io import schema_util
 from hed.errors.exceptions import HedFileError
 from hed.schema.hed_schema_constants import HedKey
-from hed.schema.schema_io.df_util import remove_prefix
 from hed.schema.hed_cache import get_library_data
 from hed.schema.schema_io import df_constants as constants
 
@@ -67,7 +66,7 @@ def get_all_ids(df):
         Union[Set, None]: None if this has no HED column, otherwise all unique numbers as a set.
     """
     if constants.hed_id in df.columns:
-        modified_df = df[constants.hed_id].apply(lambda x: remove_prefix(x, "HED_"))
+        modified_df = df[constants.hed_id].apply(lambda x: x.removeprefix("HED_") if isinstance(x, str) else x)
         modified_df = pd.to_numeric(modified_df, errors="coerce").dropna().astype(int)
         return set(modified_df.unique())
     return None
@@ -171,7 +170,7 @@ def _verify_hedid_matches(section, df, unused_tag_ids):
                     row_number, row, f"'{label}' has an improperly formatted hedID in dataframe."
                 )
                 continue
-            id_value = remove_prefix(df_id, "HED_")
+            id_value = df_id.removeprefix("HED_")
             try:
                 id_int = int(id_value)
                 if id_int not in unused_tag_ids:

hed/schema/schema_io/schema2df.py

@@ -4,7 +4,6 @@
 from hed.schema.schema_io.df_util import (
     create_empty_dataframes,
     get_library_name_and_id,
-    remove_prefix,
     calculate_attribute_type,
 )
 from hed.schema.schema_io.schema2base import Schema2Base
@@ -49,7 +48,7 @@ def _get_object_name_and_id(self, object_name, include_prefix=False):
             - The full formatted hed_id.
         """
         prefix, obj_id = get_library_name_and_id(self._schema)
-        name = f"{prefix}{remove_prefix(object_name, 'Hed')}"
+        name = f"{prefix}{object_name.removeprefix('Hed')}"
         full_hed_id = self._get_object_id(object_name, obj_id, include_prefix)
         return name, full_hed_id
 

tests/schema/test_hed_id_util.py

@@ -111,6 +111,32 @@ def test_get_all_ids_mixed_invalid(self):
         result = get_all_ids(df)
         self.assertEqual(result, {1, 3})  # Should ignore non-numeric and malformed IDs
 
+    def test_get_all_ids_with_nan(self):
+        # Test when hedId column contains NaN values (pandas null)
+        df = pd.DataFrame({"hedId": ["HED_0000001", pd.NA, "HED_0000003", None]})
+        result = get_all_ids(df)
+        self.assertEqual(result, {1, 3})  # Should handle NaN/None gracefully
+
+    def test_get_all_ids_with_numeric_types(self):
+        # Test when hedId column contains numeric types (edge case)
+        # pd.to_numeric will convert these numeric values as-is
+        df = pd.DataFrame({"hedId": ["HED_0000001", 123, "HED_0000003", 456]})
+        result = get_all_ids(df)
+        # Should extract from valid string entries with HED_ prefix AND numeric values
+        self.assertEqual(result, {1, 3, 123, 456})
+
+    def test_get_all_ids_empty_strings(self):
+        # Test when hedId column contains empty strings
+        df = pd.DataFrame({"hedId": ["HED_0000001", "", "HED_0000003", ""]})
+        result = get_all_ids(df)
+        self.assertEqual(result, {1, 3})
+
+    def test_get_all_ids_with_none(self):
+        # Test when hedId column contains None values
+        df = pd.DataFrame({"hedId": ["HED_0000001", None, "HED_0000003", None]})
+        result = get_all_ids(df)
+        self.assertEqual(result, {1, 3})
+
     def test_assign_hed_ids_section(self):
         df = pd.DataFrame(
             {