This is an automated email from the ASF dual-hosted git repository.
fokko pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/iceberg-python.git
The following commit(s) were added to refs/heads/main by this push:
new f6d56e98 fix invalidation logic (#911)
f6d56e98 is described below
commit f6d56e9865b4e7e59eb8da539a11014faeb4085b
Author: Sung Yun <[email protected]>
AuthorDate: Fri Jul 12 05:31:06 2024 -0400
fix invalidation logic (#911)
---
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 56f22425..91745a58 100644
--- a/pyiceberg/io/pyarrow.py
+++ b/pyiceberg/io/pyarrow.py
@@ -1876,6 +1876,7 @@ 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
@@ -1891,8 +1892,6 @@ 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]
