Re: [PR] Implement ParquetFormatModel and update write_file to use the format API [iceberg-python]

["nssalian (via GitHub)" <gi...@apache.org>]

nssalian commented on code in PR #3381:
URL: https://github.com/apache/iceberg-python/pull/3381#discussion_r3503367453


##########
pyiceberg/io/pyarrow.py:
##########
@@ -2602,21 +2609,91 @@ def data_file_statistics_from_parquet_metadata(
     )
 
 
+class ParquetFormatWriter(FileFormatWriter):
+    """Writes Arrow tables to a Parquet file."""
+
+    def __init__(self, output_file: OutputFile, file_schema: Schema, properties: Properties) -> None:
+        self._output_file = output_file
+        self._file_schema = file_schema
+        self._properties = properties
+        self._writer: pq.ParquetWriter | None = None
+        self._fos: OutputStream | None = None
+        self._parquet_writer_kwargs = _get_parquet_writer_kwargs(properties)
+        self._row_group_size = property_as_int(
+            properties=properties,
+            property_name=TableProperties.PARQUET_ROW_GROUP_LIMIT,
+            default=TableProperties.PARQUET_ROW_GROUP_LIMIT_DEFAULT,
+        )
+
+    def write(self, table: pa.Table) -> None:
+        if self._writer is None:
+            self._fos = self._output_file.create(overwrite=True)
+            self._writer = pq.ParquetWriter(
+                cast(IO[Any], self._fos),
+                schema=table.schema,
+                store_decimal_as_integer=True,
+                **self._parquet_writer_kwargs,
+            )
+        self._writer.write(table, row_group_size=self._row_group_size)
+
+    def close(self) -> DataFileStatistics:

Review Comment:
   Will add. 



-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: issues-unsubscribe@iceberg.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@iceberg.apache.org
For additional commands, e-mail: issues-help@iceberg.apache.org