You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@iceberg.apache.org by su...@apache.org on 2024/08/09 14:17:23 UTC
(iceberg-python) 10/11: Allow setting `write.parquet.page-row-limit` (#1017)
This is an automated email from the ASF dual-hosted git repository.
sungwy pushed a commit to branch pyiceberg-0.7.x
in repository https://gitbox.apache.org/repos/asf/iceberg-python.git
commit f1076b1a03f105d97381d96eb902dc0024848551
Author: Fokko Driesprong <fo...@apache.org>
AuthorDate: Fri Aug 9 10:34:03 2024 +0200
Allow setting `write.parquet.page-row-limit` (#1017)
* Allow setting `write.parquet.page-row-limit`
It is being passed down to PyArrow here:
https://github.com/apache/iceberg-python/blob/8aeab4951080fa196c0d29c72cba1cbba824ffc4/pyiceberg/io/pyarrow.py#L2374-L2377
* Update test
---
pyiceberg/io/pyarrow.py | 1 -
tests/integration/test_writes/test_writes.py | 1 -
2 files changed, 2 deletions(-)
diff --git a/pyiceberg/io/pyarrow.py b/pyiceberg/io/pyarrow.py
index 6c5db515..52188459 100644
--- a/pyiceberg/io/pyarrow.py
+++ b/pyiceberg/io/pyarrow.py
@@ -2285,7 +2285,6 @@ def _get_parquet_writer_kwargs(table_properties: Properties) -> Dict[str, Any]:
for key_pattern in [
TableProperties.PARQUET_ROW_GROUP_SIZE_BYTES,
- TableProperties.PARQUET_PAGE_ROW_LIMIT,
TableProperties.PARQUET_BLOOM_FILTER_MAX_BYTES,
f"{TableProperties.PARQUET_BLOOM_FILTER_COLUMN_ENABLED_PREFIX}.*",
]:
diff --git a/tests/integration/test_writes/test_writes.py b/tests/integration/test_writes/test_writes.py
index f9ff7d10..07168628 100644
--- a/tests/integration/test_writes/test_writes.py
+++ b/tests/integration/test_writes/test_writes.py
@@ -528,7 +528,6 @@ def test_write_parquet_other_properties(
"properties",
[
{"write.parquet.row-group-size-bytes": "42"},
- {"write.parquet.page-row-limit": "42"},
{"write.parquet.bloom-filter-enabled.column.bool": "42"},
{"write.parquet.bloom-filter-max-bytes": "42"},
],