From 7f08ba47d7b0a39a1002d42b8162d4c60a21e664 Mon Sep 17 00:00:00 2001
From: Jay Xu <mustangxu@users.noreply.github.com>
Date: Mon, 11 Aug 2025 17:13:10 +0800
Subject: [PATCH] Fix "no `tc` element at grid_offset" (#9375)

### What problem does this PR solve?

fix "no `tc` element at grid_offset", just log warning and ignore.
stacktrace:
```
Traceback (most recent call last):
  File "/ragflow/rag/svr/task_executor.py", line 620, in handle_task
    await do_handle_task(task)
  File "/ragflow/rag/svr/task_executor.py", line 553, in do_handle_task
    chunks = await build_chunks(task, progress_callback)
  File "/ragflow/rag/svr/task_executor.py", line 257, in build_chunks
    cks = await trio.to_thread.run_sync(lambda: chunker.chunk(task["name"], binary=binary, from_page=task["from_page"],
  File "/ragflow/.venv/lib/python3.10/site-packages/trio/_threads.py", line 447, in to_thread_run_sync
    return msg_from_thread.unwrap()
  File "/ragflow/.venv/lib/python3.10/site-packages/outcome/_impl.py", line 213, in unwrap
    raise captured_error
  File "/ragflow/.venv/lib/python3.10/site-packages/trio/_threads.py", line 373, in do_release_then_return_result
    return result.unwrap()
  File "/ragflow/.venv/lib/python3.10/site-packages/outcome/_impl.py", line 213, in unwrap
    raise captured_error
  File "/ragflow/.venv/lib/python3.10/site-packages/trio/_threads.py", line 392, in worker_fn
    ret = context.run(sync_fn, *args)
  File "/ragflow/rag/svr/task_executor.py", line 257, in <lambda>
    cks = await trio.to_thread.run_sync(lambda: chunker.chunk(task["name"], binary=binary, from_page=task["from_page"],
  File "/ragflow/rag/app/naive.py", line 384, in chunk
    sections, tables = Docx()(filename, binary)
  File "/ragflow/rag/app/naive.py", line 230, in __call__
    while i < len(r.cells):
  File "/ragflow/.venv/lib/python3.10/site-packages/docx/table.py", line 438, in cells
    return tuple(_iter_row_cells())
  File "/ragflow/.venv/lib/python3.10/site-packages/docx/table.py", line 436, in _iter_row_cells
    yield from iter_tc_cells(tc)
  File "/ragflow/.venv/lib/python3.10/site-packages/docx/table.py", line 424, in iter_tc_cells
    yield from iter_tc_cells(tc._tc_above)  # pyright: ignore[reportPrivateUsage]
  File "/ragflow/.venv/lib/python3.10/site-packages/docx/oxml/table.py", line 741, in _tc_above
    return self._tr_above.tc_at_grid_offset(self.grid_offset)
  File "/ragflow/.venv/lib/python3.10/site-packages/docx/oxml/table.py", line 98, in tc_at_grid_offset
    raise ValueError(f"no `tc` element at grid_offset={grid_offset}")
ValueError: no `tc` element at grid_offset=10
```

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
---
 rag/app/naive.py | 25 ++++++++++++++-----------
 1 file changed, 14 insertions(+), 11 deletions(-)

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 += "<tr>"
                 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"<td>{c.text}</td>" if span == 1 else f"<td colspan='{span}'>{c.text}</td>"
+                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"<td>{c.text}</td>" if span == 1 else f"<td colspan='{span}'>{c.text}</td>"
+                except Exception as e:
+                    logging.warning(f"Error parsing table, ignore: {e}")
                 html += "</tr>"
             html += "</table>"
             tbls.append(((None, html), ""))