odps/mars_extension/legacy/dataframe/datasource.py [754:792]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        else:
            pd_size = arrow_size * 10 if n_strings else arrow_size

        ctx[op.outputs[0].key] = (pd_size, pd_size + arrow_size)

    @classmethod
    def _cast_string_to_binary(cls, arrow_table):
        import pyarrow as pa

        new_schema = []
        for field in arrow_table.schema:
            if field.type == pa.string():
                new_schema.append(pa.field(field.name, pa.binary()))
            else:
                new_schema.append(field)

        return arrow_table.cast(pa.schema(new_schema))

    @classmethod
    def _append_partition_values(cls, arrow_table, op):
        import pyarrow as pa

        if op.append_partitions and op.partition_spec:
            from odps.types import PartitionSpec

            spec = PartitionSpec(op.partition_spec)

            for col_name, pt_val in spec.items():
                arrow_table = arrow_table.append_column(
                    col_name, pa.array([pt_val] * arrow_table.num_rows, pa.string())
                )

        return arrow_table

    @staticmethod
    def _align_columns(data, expected_dtypes):
        data_columns = data.dtypes.index
        expected_columns = expected_dtypes.index
        if not data_columns.equals(expected_columns):
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



odps/mars_extension/oscar/dataframe/datasource.py [553:591]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        else:
            pd_size = arrow_size * 10 if n_strings else arrow_size

        ctx[op.outputs[0].key] = (pd_size, pd_size + arrow_size)

    @classmethod
    def _cast_string_to_binary(cls, arrow_table):
        import pyarrow as pa

        new_schema = []
        for field in arrow_table.schema:
            if field.type == pa.string():
                new_schema.append(pa.field(field.name, pa.binary()))
            else:
                new_schema.append(field)

        return arrow_table.cast(pa.schema(new_schema))

    @classmethod
    def _append_partition_values(cls, arrow_table, op):
        import pyarrow as pa

        if op.append_partitions and op.partition_spec:
            from odps.types import PartitionSpec

            spec = PartitionSpec(op.partition_spec)

            for col_name, pt_val in spec.items():
                arrow_table = arrow_table.append_column(
                    col_name, pa.array([pt_val] * arrow_table.num_rows, pa.string())
                )

        return arrow_table

    @staticmethod
    def _align_columns(data, expected_dtypes):
        data_columns = data.dtypes.index
        expected_columns = expected_dtypes.index
        if not data_columns.equals(expected_columns):
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -