fix(document_extractor): xlsx file column int type error (#21408)

This commit is contained in:
quicksand 2025-06-24 13:42:13 +08:00 • committed by GitHub
commit 45146edb31
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 24 additions and 1 deletions

View file

@ -451,7 +451,7 @@ def _extract_text_from_excel(file_content: bytes) -> str:
df = df.applymap(lambda x: " ".join(str(x).splitlines()) if isinstance(x, str) else x) # type: ignore
# Combine multi-line text in column names into a single line
df.columns = pd.Index([" ".join(col.splitlines()) for col in df.columns])
df.columns = pd.Index([" ".join(str(col).splitlines()) for col in df.columns])
# Manually construct the Markdown table
markdown_table += _construct_markdown_table(df) + "\n\n"