Revert inflect changes as it's fixed

docs/requirements.txt

@@ -1,10 +1,9 @@
 defusedxml>=0.7.1
-inflect==6.0.2
+inflect>=6.0.5
 numpy>=1.21.6
 openpyxl>=3.1.0
 pandas>=1.3.5
 portalocker>=2.7.0
-pydantic<2  # For compatibility with inflect
 semantic_version>=2.10.0
 Sphinx>=5.2.2
 sphinx_rtd_theme>=1.0.0

hed/errors/exceptions.py

@@ -2,6 +2,7 @@
 
 
 class HedExceptions:
+    GENERIC_ERROR = 'GENERIC_ERROR'
     # A list of all exceptions that can be generated by the hedtools.
     FILE_NOT_FOUND = 'fileNotFound'
     BAD_PARAMETERS = 'badParameters'

hed/models/base_input.py

@@ -43,11 +43,7 @@ def __init__(self, file, file_type=None, worksheet_name=None, has_column_names=T
             - An invalid dataframe was passed with size 0
             - An invalid extension was provided
             - A duplicate or empty column name appears
-
-        :raises OSError:
             - Cannot open the indicated file
-
-        :raises KeyError:
             - The specified worksheet name does not exist
          """
         if mapper is None:
@@ -77,14 +73,20 @@ def __init__(self, file, file_type=None, worksheet_name=None, has_column_names=T
         elif not file:
             raise HedFileError(HedExceptions.FILE_NOT_FOUND, "Empty file passed to BaseInput.", file)
         elif input_type in self.TEXT_EXTENSION:
-            self._dataframe = pandas.read_csv(file, delimiter='\t', header=pandas_header,
-                                              dtype=str, keep_default_na=True, na_values=None)
+            try:
+                self._dataframe = pandas.read_csv(file, delimiter='\t', header=pandas_header,
+                                                  dtype=str, keep_default_na=True, na_values=None)
+            except Exception as e:
+                raise HedFileError(HedExceptions.GENERIC_ERROR, str(e), self.name) from e
             # Convert nan values to a known value
             self._dataframe = self._dataframe.fillna("n/a")
         elif input_type in self.EXCEL_EXTENSION:
-            self._loaded_workbook = openpyxl.load_workbook(file)
-            loaded_worksheet = self.get_worksheet(self._worksheet_name)
-            self._dataframe = self._get_dataframe_from_worksheet(loaded_worksheet, has_column_names)
+            try:
+                self._loaded_workbook = openpyxl.load_workbook(file)
+                loaded_worksheet = self.get_worksheet(self._worksheet_name)
+                self._dataframe = self._get_dataframe_from_worksheet(loaded_worksheet, has_column_names)
+            except Exception as e:
+                raise HedFileError(HedExceptions.GENERIC_ERROR, str(e), self.name) from e
         else:
             raise HedFileError(HedExceptions.INVALID_EXTENSION, "", file)
 

hed/models/sidecar.py

@@ -132,10 +132,10 @@ def load_sidecar_file(self, file):
                     if not self.name:
                         self.name = file
                     return self._load_json_file(fp)
-            except FileNotFoundError as e:
-                raise HedFileError(HedExceptions.FILE_NOT_FOUND, e.strerror, file)
+            except OSError as e:
+                raise HedFileError(HedExceptions.FILE_NOT_FOUND, e.strerror, file) from e
             except TypeError as e:
-                raise HedFileError(HedExceptions.FILE_NOT_FOUND, str(e), file)
+                raise HedFileError(HedExceptions.FILE_NOT_FOUND, str(e), file) from e
         else:
             return self._load_json_file(file)
 
@@ -189,12 +189,11 @@ def _load_json_file(self, fp):
 
         :raises HedFileError:
             - If the file cannot be parsed.
-
         """
         try:
             return json.load(fp)
-        except json.decoder.JSONDecodeError as e:
-            raise HedFileError(HedExceptions.CANNOT_PARSE_JSON, str(e), self.name)
+        except (json.decoder.JSONDecodeError, AttributeError) as e:
+            raise HedFileError(HedExceptions.CANNOT_PARSE_JSON, str(e), self.name) from e
 
     def extract_definitions(self, hed_schema=None, error_handler=None):
         """ Gather and validate definitions in metadata.

hed/models/tabular_input.py

@@ -13,8 +13,8 @@ def __init__(self, file=None, sidecar=None, name=None):
         """ Constructor for the TabularInput class.
 
         Parameters:
-            file (str or file like): A tsv file to open.
-            sidecar (str or Sidecar): A Sidecar filename or Sidecar
+            file (str or FileLike): A tsv file to open.
+            sidecar (str or Sidecar or FileLike): A Sidecar or source file/filename.
             name (str): The name to display for this file for error purposes.
 
         :raises HedFileError:

hed/tools/visualization/tag_word_cloud.py

@@ -28,7 +28,7 @@ def create_wordcloud(word_dict, mask_path=None, background_color=None, width=400
     kwargs.setdefault('contour_width', 3)
     kwargs.setdefault('contour_color', 'black')
     kwargs.setdefault('prefer_horizontal', 0.75)
-    kwargs.setdefault('default_color_func', default_color_func)
+    kwargs.setdefault('color_func', default_color_func)
     kwargs.setdefault('relative_scaling', 1)
     kwargs.setdefault('max_font_size', height / 15)
     kwargs.setdefault('min_font_size', 5)

requirements.txt

@@ -1,9 +1,8 @@
 defusedxml>=0.7.1
-inflect==6.0.2
+inflect>=6.0.5
 numpy>=1.21.6
 openpyxl>=3.1.0
 pandas>=1.3.5
 portalocker>=2.7.0
-pydantic<2  # For compatibility with inflect
 semantic_version>=2.10.0
 wordcloud==1.9.2

setup.cfg

@@ -29,7 +29,6 @@ install_requires =
     openpyxl
     pandas
     portalocker
-    pydantic < 2
     python-dateutil
     pytz
     semantic-version

tests/models/test_base_input.py

@@ -7,6 +7,8 @@
 from hed.models.column_mapper import ColumnMapper
 from hed.models import DefinitionDict
 from hed import schema
+from hed import HedFileError
+
 import pandas as pd
 import numpy as np
 
@@ -60,6 +62,19 @@ def test_gathered_defs(self):
         }
         self.assertEqual(defs, expected_defs)
 
+    def test_file_not_found(self):
+        with self.assertRaises(HedFileError):
+            BaseInput('nonexistent_file.tsv')
+
+    def test_invalid_input_type_int(self):
+        with self.assertRaises(HedFileError):
+            BaseInput(123)
+
+    def test_invalid_input_type_dict(self):
+        with self.assertRaises(HedFileError):
+            BaseInput({'key': 'value'})
+
+
 
 class TestInsertColumns(unittest.TestCase):
 

tests/models/test_sidecar.py

@@ -40,6 +40,18 @@ def setUpClass(cls):
     def tearDownClass(cls):
         shutil.rmtree(cls.base_output_folder)
 
+    def test_file_not_found(self):
+        with self.assertRaises(HedFileError):
+            Sidecar('nonexistent_file.json')
+
+    def test_invalid_input_type_int(self):
+        with self.assertRaises(HedFileError):
+            Sidecar(123)
+
+    def test_invalid_input_type_dict(self):
+        with self.assertRaises(HedFileError):
+            Sidecar({'key': 'value'})
+
     def test_invalid_filenames(self):
         # Handle missing or invalid files.
         invalid_json = "invalidxmlfile.json"

tests/models/test_spreadsheet_input.py

@@ -24,6 +24,7 @@ def setUpClass(cls):
         cls.base_output_folder = base_output
         os.makedirs(base_output, exist_ok=True)
 
+
     @classmethod
     def tearDownClass(cls):
         shutil.rmtree(cls.base_output_folder)

tests/models/test_tabular_input.py

@@ -28,6 +28,8 @@ def setUpClass(cls):
         cls.sidecar2 = Sidecar(sidecar2_path, name='face_small_json')
         cls.base_output_folder = base_output_folder
 
+        cls.invalid_inputs = [123, {'key': 'value'}, 'nonexistent_file.tsv']
+
     @classmethod
     def tearDownClass(cls):
         shutil.rmtree(cls.base_output_folder)
@@ -82,6 +84,19 @@ def test_validate_file_warnings(self):
         issues2a = input_file2.validate(hed_schema=self.hed_schema, error_handler=ErrorHandler(False))
         breakHere = 3
 
+    def test_invalid_file(self):
+        for invalid_input in self.invalid_inputs:
+            with self.subTest(input=invalid_input):
+                with self.assertRaises(HedFileError):
+                    TabularInput(file=invalid_input)
+
+    def test_invalid_sidecar(self):
+        for invalid_input in self.invalid_inputs:
+            with self.subTest(input=invalid_input):
+                with self.assertRaises(HedFileError):
+                    # Replace 'valid_path.tsv' with a path to an existing .tsv file
+                    TabularInput(file=self.events_path, sidecar=invalid_input)
+
 
 if __name__ == '__main__':
     unittest.main()