def _build_parquet_columnar_job(self, row_type: RowType): source = FileSource.for_bulk_file_format( ParquetColumnarRowInputFormat(row_type, Configuration(), 10, True, False), self.parquet_file_name ).build() ds = self.env.from_source(source, WatermarkStrategy.no_watermarks(), 'parquet-source') ds.map(lambda e: e).add_sink(self.test_sink)
def _build_parquet_columnar_job(self, row_type: RowType, parquet_file_name: str): source = FileSource.for_bulk_file_format( ParquetColumnarRowInputFormat(Configuration(), row_type, 10, True, True), parquet_file_name).build() ds = self.env.from_source(source, WatermarkStrategy.no_watermarks(), 'parquet-source') ds.map(PassThroughMapFunction()).add_sink(self.test_sink)