gmakstutis/LightRAG
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

cherry-pick fa887d81

Browse source
This commit is contained in:
Raphaël MANSUY 2025-12-04 19:15:04 +08:00
parent 7e53eaabee
commit 4501740849
1 changed files with 4 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
lightrag/api/routers/document_routes.py
View file

@ -1005,9 +1005,9 @@ def _extract_docx(file_bytes: bytes) -> str:
in_table = False in_table = False
paragraph = Paragraph(element, doc) paragraph = Paragraph(element, doc)
text = paragraph.text text = paragraph.text.strip()
# Always append to preserve document spacing (including blank paragraphs) if text:
content_parts.append(text) content_parts.append(text)
# Check if element is a table # Check if element is a table
elif element.tag.endswith("tbl"): elif element.tag.endswith("tbl"):
@ -1020,7 +1020,7 @@ def _extract_docx(file_bytes: bytes) -> str:
for row in table.rows: for row in table.rows:
row_text = [] row_text = []
for cell in row.cells: for cell in row.cells:
cell_text = cell.text cell_text = cell.text.strip()
# Always append cell text to preserve column structure # Always append cell text to preserve column structure
row_text.append(cell_text) row_text.append(cell_text)
# Only add row if at least one cell has content # Only add row if at least one cell has content