diff --git a/pyiceberg/io/pyarrow.py b/pyiceberg/io/pyarrow.py index 6259f311e9..e1496244a2 100644 --- a/pyiceberg/io/pyarrow.py +++ b/pyiceberg/io/pyarrow.py @@ -2881,8 +2881,7 @@ def _dataframe_to_data_files( For a ``pa.RecordBatchReader`` batches are streamed and microbatched into target-sized files using bounded memory (see :func:`bin_pack_record_batches`). Streaming writes are currently only supported on unpartitioned tables; - partitioned support is tracked in - https://github.com/apache/iceberg-python/issues/2152. + partitioned streaming support is not yet implemented. Returns: An iterable that supplies datafiles that represent the input data. @@ -2909,8 +2908,7 @@ def _dataframe_to_data_files( if not table_metadata.spec().is_unpartitioned(): raise NotImplementedError( "Writing a pa.RecordBatchReader to a partitioned table is not yet supported. " - "Materialise the reader as a pa.Table first, or follow " - "https://github.com/apache/iceberg-python/issues/2152 for partitioned streaming support." + "Materialise the reader as a pa.Table first." ) yield from write_file( io=io, diff --git a/pyiceberg/table/__init__.py b/pyiceberg/table/__init__.py index 63b87d290e..4b43a3a77b 100644 --- a/pyiceberg/table/__init__.py +++ b/pyiceberg/table/__init__.py @@ -473,8 +473,7 @@ def append( Streaming writes are currently only supported on unpartitioned tables; passing a ``pa.RecordBatchReader`` for a partitioned table raises - ``NotImplementedError``. See - https://github.com/apache/iceberg-python/issues/2152. + ``NotImplementedError``. Note: When ``df`` is a ``pa.RecordBatchReader`` the reader is consumed @@ -621,8 +620,7 @@ def overwrite( Streaming writes are currently only supported on unpartitioned tables; passing a ``pa.RecordBatchReader`` for a partitioned table raises - ``NotImplementedError``. See - https://github.com/apache/iceberg-python/issues/2152. + ``NotImplementedError``. Note: When ``df`` is a ``pa.RecordBatchReader`` the reader is consumed diff --git a/tests/catalog/test_catalog_behaviors.py b/tests/catalog/test_catalog_behaviors.py index b859e2d541..2026886727 100644 --- a/tests/catalog/test_catalog_behaviors.py +++ b/tests/catalog/test_catalog_behaviors.py @@ -1216,7 +1216,7 @@ def test_drop_namespace_raises_error_when_namespace_not_empty( # RecordBatchReader streaming append/overwrite tests # # Streaming writes accept a pa.RecordBatchReader and microbatch it into target-sized -# Parquet files instead of materialising the full Arrow Table in memory. Tracks +# Parquet files instead of materialising the full Arrow Table in memory. Introduced in # https://github.com/apache/iceberg-python/issues/2152.