Class Table

src/table.py:1523–1929

class Table:
    def __init__(self, page, cells):
        self.page = page
        self.textpage = None
        self.cells = cells
        self.header = self._get_header()  # PyMuPDF extension

    @property
    def bbox(self):
        c = self.cells
        return (
            min(map(itemgetter(0), c)),
            min(map(itemgetter(1), c)),
            max(map(itemgetter(2), c)),
            max(map(itemgetter(3), c)),
        )

    @property
    def rows(self) -> list:
        _sorted = sorted(self.cells, key=itemgetter(1, 0))
        xs = list(sorted(set(map(itemgetter(0), self.cells))))
        rows = []
        for y, row_cells in itertools.groupby(_sorted, itemgetter(1)):
            xdict = {cell[0]: cell for cell in row_cells}
            row = TableRow([xdict.get(x) for x in xs])
            rows.append(row)
        return rows

    @property
    def row_count(self) -> int:  # PyMuPDF extension
        return len(self.rows)

    @property
    def col_count(self) -> int:  # PyMuPDF extension
        return max([len(r.cells) for r in self.rows])

    def extract(self, **kwargs) -> list:
        chars = CHARS
        table_arr = []

        def char_in_bbox(char, bbox) -> bool:
            v_mid = (char["top"] + char["bottom"]) / 2
            h_mid = (char["x0"] + char["x1"]) / 2
            x0, top, x1, bottom = bbox
            return bool(
                (h_mid >= x0) and (h_mid < x1) and (v_mid >= top) and (v_mid < bottom)
            )

        for row in self.rows:
            arr = []
            row_chars = [char for char in chars if char_in_bbox(char, row.bbox)]

            for cell in row.cells:
                if cell is None:
                    cell_text = None
                else:
                    cell_chars = [
                        char for char in row_chars if char_in_bbox(char, cell)