From d6a941ebf57a1a0a422d4b2c4a402db1098f3586 Mon Sep 17 00:00:00 2001
From: HaiyangP <46739135+HaiyangPeng@users.noreply.github.com>
Date: Tue, 24 Jun 2025 18:18:30 +0800
Subject: [PATCH] Fix the bug of long type value overflow (#8313)

### What problem does this PR solve?

This PR will fix the #8271 by extending int type to float type when
there is any value out of long type range in a column.
### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
---
 rag/app/table.py | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/rag/app/table.py b/rag/app/table.py
index 450cd6280..90b4c2849 100644
--- a/rag/app/table.py
+++ b/rag/app/table.py
@@ -92,11 +92,15 @@ def column_data_type(arr):
     arr = list(arr)
     counts = {"int": 0, "float": 0, "text": 0, "datetime": 0, "bool": 0}
     trans = {t: f for f, t in [(int, "int"), (float, "float"), (trans_datatime, "datetime"), (trans_bool, "bool"), (str, "text")]}
+    float_flag = False
     for a in arr:
         if a is None:
             continue
-        if re.match(r"[+-]?[0-9]{,19}(\.0+)?$", str(a).replace("%%", "")):
+        if re.match(r"[+-]?[0-9]+$", str(a).replace("%%", "")):
             counts["int"] += 1
+            if int(str(a)) > 2**63 - 1:
+                float_flag = True
+                break
         elif re.match(r"[+-]?[0-9.]{,19}$", str(a).replace("%%", "")):
             counts["float"] += 1
         elif re.match(r"(true|yes|是|\*|✓|✔|☑|✅|√|false|no|否|⍻|×)$", str(a), flags=re.IGNORECASE):
@@ -105,8 +109,11 @@ def column_data_type(arr):
             counts["datetime"] += 1
         else:
             counts["text"] += 1
-    counts = sorted(counts.items(), key=lambda x: x[1] * -1)
-    ty = counts[0][0]
+    if float_flag:
+        ty = "float"
+    else:
+        counts = sorted(counts.items(), key=lambda x: x[1] * -1)
+        ty = counts[0][0]
     for i in range(len(arr)):
         if arr[i] is None:
             continue