pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-08 20:42:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix "no tc element at grid_offset" (#9375)

Browse Source 
### 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)
This commit is contained in:
Jay Xu
2025-08-11 17:13:10 +08:00
committed by GitHub
parent ce3dd019c3
commit 7f08ba47d7
1 changed files with 14 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
rag/app/naive.py
View File

@ -226,17 +226,20 @@ class Docx(DocxParser):
for r in tb.rows: for r in tb.rows:
html += "<tr>" html += "<tr>"
i = 0 i = 0
while i < len(r.cells): try:
span = 1 while i < len(r.cells):
c = r.cells[i] span = 1
for j in range(i + 1, len(r.cells)): c = r.cells[i]
if c.text == r.cells[j].text: for j in range(i + 1, len(r.cells)):
span += 1 if c.text == r.cells[j].text:
i = j span += 1
else: i = j
break else:
i += 1 break
html += f"<td>{c.text}</td>" if span == 1 else f"<td colspan='{span}'>{c.text}</td>" 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 += "</tr>"
html += "</table>" html += "</table>"
tbls.append(((None, html), "")) tbls.append(((None, html), ""))