fix: big xls file error (#4859)

### What problem does this PR solve?

if *.xls file is too large, .eg >50M, I get error.

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

deepdoc/parser/excel_parser.py

@@ -1,6 +1,3 @@
-#
-#  Copyright 2025 The InfiniFlow Authors. All Rights Reserved.
-#
 #  Licensed under the Apache License, Version 2.0 (the "License");
 #  you may not use this file except in compliance with the License.
 #  You may obtain a copy of the License at
@@ -14,19 +11,51 @@
 #  limitations under the License.
 #
 
-from openpyxl import load_workbook
+from openpyxl import load_workbook, Workbook
 import sys
 from io import BytesIO
 
 from rag.nlp import find_codec
 
+import pandas as pd
+
 
 class RAGFlowExcelParser:
     def html(self, fnm, chunk_rows=256):
-        if isinstance(fnm, str):
-            wb = load_workbook(fnm)
+
+        # if isinstance(fnm, str):
+        #     wb = load_workbook(fnm)
+        # else:
+        #     wb = load_workbook(BytesIO(fnm))++
+
+        s_fnm = fnm
+        if not isinstance(fnm, str):
+            s_fnm = BytesIO(fnm)
         else:
-            wb = load_workbook(BytesIO(fnm))
+            pass
+
+        try:
+            wb = load_workbook(s_fnm)
+        except Exception as e:
+            print(f'****wxy: file parser error: {e}, s_fnm={s_fnm}, trying convert files')
+            df = pd.read_excel(s_fnm)
+            wb = Workbook()
+            # if len(wb.worksheets) > 0:
+            #   del wb.worksheets[0]
+            # else: pass
+            ws = wb.active
+            ws.title = "Data"
+            for col_num, column_name in enumerate(df.columns, 1):
+                ws.cell(row=1, column=col_num, value=column_name)
+            else:
+                pass
+            for row_num, row in enumerate(df.values, 2):
+                for col_num, value in enumerate(row, 1):
+                    ws.cell(row=row_num, column=col_num, value=value)
+                else:
+                    pass
+            else:
+                pass
 
         tb_chunks = []
         for sheetname in wb.sheetnames:
@@ -45,7 +74,7 @@ def html(self, fnm, chunk_rows=256):
                 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: 1 + (chunk_i + 1) * chunk_rows]
                 ):
                     tb += "<tr>"
                     for i, c in enumerate(r):
@@ -60,10 +89,41 @@ def html(self, fnm, chunk_rows=256):
         return tb_chunks
 
     def __call__(self, fnm):
-        if isinstance(fnm, str):
-            wb = load_workbook(fnm)
+        # if isinstance(fnm, str):
+        #   wb = load_workbook(fnm)
+        # else:
+        #   wb = load_workbook(BytesIO(fnm))
+
+        s_fnm = fnm
+        if not isinstance(fnm, str):
+            s_fnm = BytesIO(fnm)
         else:
-            wb = load_workbook(BytesIO(fnm))
+            pass
+
+        try:
+            wb = load_workbook(s_fnm)
+        except Exception as e:
+            print(f'****wxy: file parser error: {e}, s_fnm={s_fnm}, trying convert files')
+            df = pd.read_excel(s_fnm)
+            wb = Workbook()
+            if len(wb.worksheets) > 0:
+                del wb.worksheets[0]
+            else:
+                pass
+            ws = wb.active
+            ws.title = "Data"
+            for col_num, column_name in enumerate(df.columns, 1):
+                ws.cell(row=1, column=col_num, value=column_name)
+            else:
+                pass
+            for row_num, row in enumerate(df.values, 2):
+                for col_num, value in enumerate(row, 1):
+                    ws.cell(row=row_num, column=col_num, value=value)
+                else:
+                    pass
+            else:
+                pass
+
         res = []
         for sheetname in wb.sheetnames:
             ws = wb[sheetname]
@@ -104,3 +164,4 @@ def row_number(fnm, binary):
 if __name__ == "__main__":
     psr = RAGFlowExcelParser()
     psr(sys.argv[1])
+