Skip to content

fix: map write.parquet.page-row-limit to pyarrow's max_rows_per_page #4127

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
YuangGao wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix: map write.parquet.page-row-limit to pyarrow's max_rows_per_page #4127

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 9 additions & 4 deletions pyiceberg/io/pyarrow.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2986,7 +2986,7 @@ def _get_parquet_writer_kwargs(table_properties: Properties) -> dict[str, Any]:
if compression_codec == ICEBERG_UNCOMPRESSED_CODEC:
compression_codec = PYARROW_UNCOMPRESSED_CODEC

return {
kwargs: dict[str, Any] = {
"compression": compression_codec,
"compression_level": compression_level,
"data_page_size": property_as_int(
Expand All @@ -2999,12 +2999,17 @@ def _get_parquet_writer_kwargs(table_properties: Properties) -> dict[str, Any]:
property_name=TableProperties.PARQUET_DICT_SIZE_BYTES,
default=TableProperties.PARQUET_DICT_SIZE_BYTES_DEFAULT,
),
"write_batch_size": property_as_int(
}
# pyarrow added max_rows_per_page, the per-page row limit, in 23.0.0.
if tuple(map(int, pa.__version__.split(".")[:2])) >= (23, 0):
kwargs["max_rows_per_page"] = property_as_int(
properties=table_properties,
property_name=TableProperties.PARQUET_PAGE_ROW_LIMIT,
default=TableProperties.PARQUET_PAGE_ROW_LIMIT_DEFAULT,
),
}
)
elif TableProperties.PARQUET_PAGE_ROW_LIMIT in table_properties:
warnings.warn(f"{TableProperties.PARQUET_PAGE_ROW_LIMIT} requires pyarrow >= 23.0.0", stacklevel=2)
return kwargs


def _dataframe_to_data_files(
Expand Down
1 change: 1 addition & 0 deletions tests/integration/test_writes/test_writes.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -669,6 +669,7 @@ def test_write_parquet_compression_properties(
[
({"write.parquet.page-size-bytes": "42"}, {"data_page_size": 42}),
({"write.parquet.dict-size-bytes": "42"}, {"dictionary_pagesize_limit": 42}),
({"write.parquet.page-row-limit": "42"}, {"max_rows_per_page": 42, "write_batch_size": None}),
],
)
def test_write_parquet_other_properties(
Expand Down
Loading