diff --git a/setup.py b/setup.py index bc892961..cb2a64c9 100644 --- a/setup.py +++ b/setup.py @@ -41,7 +41,7 @@ def _run(self, command): setup( # include data files name="amazon-textract-textractor", - version="1.6.0", + version="1.6.1", license="Apache 2.0", description="A package to use AWS Textract services.", url="https://github.com/aws-samples/amazon-textract-textractor", diff --git a/textractor/entities/table.py b/textractor/entities/table.py index 1ef4f444..0f8a6b33 100644 --- a/textractor/entities/table.py +++ b/textractor/entities/table.py @@ -659,10 +659,7 @@ def get_text_and_words( if config.table_linearization_format == "markdown": df = self.to_pandas( use_columns=True, - checkbox_string=[ - config.selection_element_selected, - config.selection_element_not_selected, - ], + config=config ) has_column = any([isinstance(c, str) for c in df.columns]) if config.table_remove_column_headers: @@ -780,7 +777,6 @@ def _get_new_table_cells(rows, filtered_rows): new_cell_siblings.append(new_cells_dict[(new_row, new_col)]) new_cells_dict[(cell_row, cell_col)].siblings = new_cell_siblings - new_cells_dict[(cell_row, cell_col)].words = cell_words new_cells_dict[(cell_row, cell_col)].add_children(cell_children) for sibling in new_cells_dict[(cell_row, cell_col)].siblings: