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: unexpected truncated Excel files (#9500)

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

Handle unexpected truncated Excel files.

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
This commit is contained in:
Yongteng Lei
2025-08-15 17:00:34 +08:00
committed by GitHub
parent 5a4dfecfbe
commit eef43fa25c
2 changed files with 11 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
deepdoc/parser/excel_parser.py
View File

@ -90,9 +90,17 @@ class RAGFlowExcelParser:
return wb
def html(self, fnm, chunk_rows=256):
from html import escape
file_like_object = BytesIO(fnm) if not isinstance(fnm, str) else fnm
wb = RAGFlowExcelParser._load_excel_to_workbook(file_like_object)
tb_chunks = []
def _fmt(v):
if v is None:
return ""
return str(v).strip()
for sheetname in wb.sheetnames:
ws = wb[sheetname]
rows = list(ws.rows)
@ -101,7 +109,7 @@ class RAGFlowExcelParser:
tb_rows_0 = "<tr>"
for t in list(rows[0]):
tb_rows_0 += f"<th>{t.value}</th>"
tb_rows_0 += f"<th>{escape(_fmt(t.value))}</th>"
tb_rows_0 += "</tr>"
for chunk_i in range((len(rows) - 1) // chunk_rows + 1):
@ -109,7 +117,7 @@ class RAGFlowExcelParser:
tb += f"<table><caption>{sheetname}</caption>"
tb += tb_rows_0
for r in list(
rows[1 + chunk_i * chunk_rows: 1 + (chunk_i + 1) * chunk_rows]
rows[1 + chunk_i * chunk_rows: min(1 + (chunk_i + 1) * chunk_rows, len(rows))]
):
tb += "<tr>"
for i, c in enumerate(r):