Method handle_table

docling/backend/html_backend.py:307–378

Handles table tags.

(self, element: Tag, idx: int, doc: DoclingDocument)

            _log.warn("list-item has no text: ", element)

    def handle_table(self, element: Tag, idx: int, doc: DoclingDocument):
        """Handles table tags."""

        nested_tables = element.find("table")
        if nested_tables is not None:
            _log.warn("detected nested tables: skipping for now")
            return

        # Count the number of rows (number of <tr> elements)
        num_rows = len(element.find_all("tr"))

        # Find the number of columns (taking into account colspan)
        num_cols = 0
        for row in element.find_all("tr"):
            col_count = 0
            for cell in row.find_all(["td", "th"]):
                colspan = int(cell.get("colspan", 1))
                col_count += colspan
            num_cols = max(num_cols, col_count)

        grid = [[None for _ in range(num_cols)] for _ in range(num_rows)]

        data = TableData(num_rows=num_rows, num_cols=num_cols, table_cells=[])

        # Iterate over the rows in the table
        for row_idx, row in enumerate(element.find_all("tr")):

            # For each row, find all the column cells (both <td> and <th>)
            cells = row.find_all(["td", "th"])

            # Check if each cell in the row is a header -> means it is a column header
            col_header = True
            for j, html_cell in enumerate(cells):
                if html_cell.name == "td":
                    col_header = False

            col_idx = 0
            # Extract and print the text content of each cell
            for _, html_cell in enumerate(cells):

                text = html_cell.text
                try:
                    text = self.extract_table_cell_text(html_cell)
                except Exception as exc:
                    _log.warn("exception: ", exc)
                    exit(-1)

                # label = html_cell.name

                col_span = int(html_cell.get("colspan", 1))
                row_span = int(html_cell.get("rowspan", 1))

                while grid[row_idx][col_idx] is not None:
                    col_idx += 1
                for r in range(row_span):
                    for c in range(col_span):
                        grid[row_idx + r][col_idx + c] = text