fix(logic): strip white space;

- Condition stripping on `str` type.
ckan · May 8, 2024 · 88f96a8 · 88f96a8
1 parent 860ca9e
commit 88f96a8
Show file tree

Hide file tree

Showing 2 changed files with 13 additions and 4 deletions.
diff --git a/ckanext/xloader/loader.py b/ckanext/xloader/loader.py
@@ -171,14 +171,20 @@ def load_csv(csv_filepath, resource_id, mimetype='text/csv', logger=None):
                                        skip_rows=skip_rows) as stream:
                 for row in stream:
                     for _index, _cell in enumerate(row):
-                        row[_index] = str(_cell).strip()  # strip white space around cell values
+                        if isinstance(_cell, str):
+                            # strip white space around cell values
+                            #TODO: condition behind DataDictionary option??
+                            row[_index] = _cell.strip()
                     stream.save(**save_args)  # have to save inside of the tabulator stream iterator
         except (EncodingError, UnicodeDecodeError):
             with Stream(csv_filepath, format=file_format, encoding=SINGLE_BYTE_ENCODING,
                         skip_rows=skip_rows) as stream:
                 for row in stream:
                     for _index, _cell in enumerate(row):
-                        row[_index] = str(_cell).strip()  # strip white space around cell values
+                        if isinstance(_cell, str):
+                            # strip white space around cell values
+                            #TODO: condition behind DataDictionary option??
+                            row[_index] = _cell.strip()
                     stream.save(**save_args)  # have to save inside of the tabulator stream iterator
         csv_filepath = f_write.name
 

diff --git a/ckanext/xloader/parser.py b/ckanext/xloader/parser.py
@@ -31,8 +31,11 @@ def convert_types(self, extended_rows):
             for cell_index, cell_value in enumerate(row):
                 if cell_value is None:
                     row[cell_index] = ''
-                cell_value = str(cell_value).strip()  # strip white space around cell values
-                row[cell_index] = str(cell_value).strip()  # strip white space around cell values
+                if isinstance(cell_value, str):
+                    # strip white space around cell values
+                    #TODO: condition behind DataDictionary option??
+                    cell_value = cell_value.strip()
+                    row[cell_index] = cell_value.strip()
                 if not cell_value:
                     continue
                 cell_type = self.types[cell_index] if self.types else None