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 7d25bade Allow setting `write.parquet.page-row-limit` (#1017)
7d25bade is described below
commit 7d25bade00f144dd26937e134cbcea26f381a5c3
Author: Fokko Driesprong <[email protected]>
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 1ff3f4ef..b99c3b17 100644
--- a/pyiceberg/io/pyarrow.py
+++ b/pyiceberg/io/pyarrow.py
@@ -2345,7 +2345,6 @@ 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 540e9bb3..631f5e36 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"},
],
