diff --git a/rag/app/naive.py b/rag/app/naive.py index 06d0f3369..1a6c0b92b 100644 --- a/rag/app/naive.py +++ b/rag/app/naive.py @@ -226,17 +226,20 @@ class Docx(DocxParser): for r in tb.rows: html += "" i = 0 - while i < len(r.cells): - span = 1 - c = r.cells[i] - for j in range(i + 1, len(r.cells)): - if c.text == r.cells[j].text: - span += 1 - i = j - else: - break - i += 1 - html += f"{c.text}" if span == 1 else f"{c.text}" + try: + while i < len(r.cells): + span = 1 + c = r.cells[i] + for j in range(i + 1, len(r.cells)): + if c.text == r.cells[j].text: + span += 1 + i = j + else: + break + i += 1 + html += f"{c.text}" if span == 1 else f"{c.text}" + except Exception as e: + logging.warning(f"Error parsing table, ignore: {e}") html += "" html += "" tbls.append(((None, html), ""))