pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-08 12:32:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix: parsing excel with chartsheet & Clamp begin to a minimum of 0 to prevent negative indexing (#10819)

Browse Source 
### What problem does this PR solve?

Fix: parsing excel with chartsheet #10815

Fix: Clamp begin to a minimum of 0 to prevent negative indexing #10804
### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
This commit is contained in:
Billy Bao
2025-10-28 09:40:37 +08:00
committed by GitHub
parent 850e119a81
commit e59458c36b
3 changed files with 27 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
deepdoc/parser/excel_parser.py
View File

@ -123,7 +123,12 @@ class RAGFlowExcelParser:
for sheetname in wb.sheetnames:
ws = wb[sheetname]
rows = list(ws.rows)
try:
rows = list(ws.rows)
except Exception as e:
logging.warning(f"Skip sheet '{sheetname}' due to rows access error: {e}")
continue
if not rows:
continue
@ -170,7 +175,11 @@ class RAGFlowExcelParser:
res = []
for sheetname in wb.sheetnames:
ws = wb[sheetname]
rows = list(ws.rows)
try:
rows = list(ws.rows)
except Exception as e:
logging.warning(f"Skip sheet '{sheetname}' due to rows access error: {e}")
continue
if not rows:
continue
ti = list(rows[0])
@ -193,9 +202,14 @@ class RAGFlowExcelParser:
if fnm.split(".")[-1].lower().find("xls") >= 0:
wb = RAGFlowExcelParser._load_excel_to_workbook(BytesIO(binary))
total = 0
for sheetname in wb.sheetnames:
ws = wb[sheetname]
total += len(list(ws.rows))
try:
ws = wb[sheetname]
total += len(list(ws.rows))
except Exception as e:
logging.warning(f"Skip sheet '{sheetname}' due to rows access error: {e}")
continue
return total
if fnm.split(".")[-1].lower() in ["csv", "txt"]: