From eef43fa25cbe380983129d169d9fa27cb9410a13 Mon Sep 17 00:00:00 2001
From: Yongteng Lei <yongtengrey@outlook.com>
Date: Fri, 15 Aug 2025 17:00:34 +0800
Subject: [PATCH] Fix: unexpected truncated Excel files (#9500)

### What problem does this PR solve?

Handle unexpected truncated Excel files.

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
---
 deepdoc/parser/excel_parser.py | 12 ++++++++++--
 rag/app/naive.py               |  1 +
 2 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/deepdoc/parser/excel_parser.py b/deepdoc/parser/excel_parser.py
index e0d642775..d90224f59 100644
--- a/deepdoc/parser/excel_parser.py
+++ b/deepdoc/parser/excel_parser.py
@@ -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):
diff --git a/rag/app/naive.py b/rag/app/naive.py
index 5e946d1c8..173ef0aef 100644
--- a/rag/app/naive.py
+++ b/rag/app/naive.py
@@ -490,6 +490,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
             sections = [(_, "") for _ in excel_parser.html(binary, 12) if _]
         else:
             sections = [(_, "") for _ in excel_parser(binary) if _]
+        parser_config["chunk_token_num"] = 12800
 
     elif re.search(r"\.(txt|py|js|java|c|cpp|h|php|go|ts|sh|cs|kt|sql)$", filename, re.IGNORECASE):
         callback(0.1, "Start to parse.")