From 93e39fc833d17aa8cbcbee54937ab48e32937aeb Mon Sep 17 00:00:00 2001
From: Sung Yun <107272191+syun64@users.noreply.github.com>
Date: Wed, 10 Jul 2024 22:05:31 +0000
Subject: [PATCH] fix invalidation logic

---
 pyiceberg/io/pyarrow.py | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/pyiceberg/io/pyarrow.py b/pyiceberg/io/pyarrow.py
index ae7799cfde..da1f650eaf 100644
--- a/pyiceberg/io/pyarrow.py
+++ b/pyiceberg/io/pyarrow.py
@@ -1860,6 +1860,7 @@ def data_file_statistics_from_parquet_metadata(
 
     col_aggs = {}
 
+    invalidate_col: Set[int] = set()
     for r in range(parquet_metadata.num_row_groups):
         # References:
         # https://github.com/apache/iceberg/blob/fc381a81a1fdb8f51a0637ca27cd30673bd7aad3/parquet/src/main/java/org/apache/iceberg/parquet/ParquetUtil.java#L232
@@ -1875,8 +1876,6 @@ def data_file_statistics_from_parquet_metadata(
         else:
             split_offsets.append(data_offset)
 
-        invalidate_col: Set[int] = set()
-
         for pos in range(parquet_metadata.num_columns):
             column = row_group.column(pos)
             field_id = parquet_column_mapping[column.path_in_schema]