Allow setting write.parquet.page-row-limit (apache#1017)

Fokko · sungwy · commit 324b2ee97100 · 2024-12-07T04:11:18.000Z
* 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
diff --git 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
@@ -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"},
     ],

Original file line number	Diff line number	Diff line change
`@@ -528,7 +528,6 @@ def test_write_parquet_other_properties(`
`528`	`528`	`"properties",`
`529`	`529`	`[`
`530`	`530`	`{"write.parquet.row-group-size-bytes": "42"},`
`531`		`- {"write.parquet.page-row-limit": "42"},`
`532`	`531`	`{"write.parquet.bloom-filter-enabled.column.bool": "42"},`
`533`	`532`	`{"write.parquet.bloom-filter-max-bytes": "42"},`
`534`	`533`	`],`