Fix merged cells text getting duplicated when linearizing as plaintext

Belval · Belval · commit 61165035bef4 · 2024-05-23T16:11:45.000Z
diff --git a/textractor/entities/table.py b/textractor/entities/table.py
@@ -933,6 +933,7 @@ def get_text_and_words(
                 for cell in sorted(row, key=lambda c: c.col_index):
                     # Siblings includes the current cell
                     if cell.siblings:
+                        children = []
                         first_row, first_col, last_row, last_col = cell._get_merged_cell_range()
                         if (cell.col_index == first_col and cell.row_index == first_row) or config.table_duplicate_text_in_merged_cells:
                             for sib in cell.siblings:
