awswrangler/s3/_write_text.py [436:515]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        )

    glue_table_settings = cast(
        GlueTableSettings,
        glue_table_settings if glue_table_settings else {},
    )

    table_type = glue_table_settings.get("table_type")
    description = glue_table_settings.get("description")
    parameters = glue_table_settings.get("parameters")
    columns_comments = glue_table_settings.get("columns_comments")
    columns_parameters = glue_table_settings.get("columns_parameters")
    regular_partitions = glue_table_settings.get("regular_partitions", True)

    _validate_args(
        df=df,
        table=table,
        database=database,
        dataset=dataset,
        path=path,
        partition_cols=partition_cols,
        bucketing_info=bucketing_info,
        mode=mode,
        description=description,
        parameters=parameters,
        columns_comments=columns_comments,
        columns_parameters=columns_parameters,
        execution_engine=engine.get(),
    )

    # Initializing defaults
    partition_cols = partition_cols if partition_cols else []
    dtype = dtype if dtype else {}
    partitions_values: dict[str, list[str]] = {}
    mode = "append" if mode is None else mode

    filename_prefix = filename_prefix + uuid.uuid4().hex if filename_prefix else uuid.uuid4().hex
    s3_client = _utils.client(service_name="s3", session=boto3_session)

    # Sanitize table to respect Athena's standards
    if (sanitize_columns is True) or (database is not None and table is not None):
        df, dtype, partition_cols, bucketing_info = _sanitize(
            df=copy_df_shallow(df),
            dtype=dtype,
            partition_cols=partition_cols,
            bucketing_info=bucketing_info,
        )

    # Evaluating dtype
    catalog_table_input: dict[str, Any] | None = None
    if database and table:
        catalog_table_input = catalog._get_table_input(
            database=database,
            table=table,
            boto3_session=boto3_session,
            catalog_id=catalog_id,
        )

        catalog_path: str | None = None
        if catalog_table_input:
            table_type = catalog_table_input["TableType"]
            catalog_path = catalog_table_input.get("StorageDescriptor", {}).get("Location")
        if path is None:
            if catalog_path:
                path = catalog_path
            else:
                raise exceptions.InvalidArgumentValue(
                    "Glue table does not exist in the catalog. Please pass the `path` argument to create it."
                )
        elif path and catalog_path:
            if path.rstrip("/") != catalog_path.rstrip("/"):
                raise exceptions.InvalidArgumentValue(
                    f"The specified path: {path}, does not match the existing Glue catalog table path: {catalog_path}"
                )
        if pandas_kwargs.get("compression") not in ("gzip", "bz2", None):
            raise exceptions.InvalidArgumentCombination(
                "If database and table are given, you must use one of these compressions: gzip, bz2 or None."
            )

    df = _apply_dtype(df=df, dtype=dtype, catalog_table_input=catalog_table_input, mode=mode)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



awswrangler/s3/_write_text.py [886:965]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        )

    glue_table_settings = cast(
        GlueTableSettings,
        glue_table_settings if glue_table_settings else {},
    )

    table_type = glue_table_settings.get("table_type")
    description = glue_table_settings.get("description")
    parameters = glue_table_settings.get("parameters")
    columns_comments = glue_table_settings.get("columns_comments")
    columns_parameters = glue_table_settings.get("columns_parameters")
    regular_partitions = glue_table_settings.get("regular_partitions", True)

    _validate_args(
        df=df,
        table=table,
        database=database,
        dataset=dataset,
        path=path,
        partition_cols=partition_cols,
        bucketing_info=bucketing_info,
        mode=mode,
        description=description,
        parameters=parameters,
        columns_comments=columns_comments,
        columns_parameters=columns_parameters,
        execution_engine=engine.get(),
    )

    # Initializing defaults
    partition_cols = partition_cols if partition_cols else []
    dtype = dtype if dtype else {}
    partitions_values: dict[str, list[str]] = {}
    mode = "append" if mode is None else mode

    filename_prefix = filename_prefix + uuid.uuid4().hex if filename_prefix else uuid.uuid4().hex
    s3_client = _utils.client(service_name="s3", session=boto3_session)

    # Sanitize table to respect Athena's standards
    if (sanitize_columns is True) or (database is not None and table is not None):
        df, dtype, partition_cols, bucketing_info = _sanitize(
            df=copy_df_shallow(df),
            dtype=dtype,
            partition_cols=partition_cols,
            bucketing_info=bucketing_info,
        )

    # Evaluating dtype
    catalog_table_input: dict[str, Any] | None = None

    if database and table:
        catalog_table_input = catalog._get_table_input(
            database=database,
            table=table,
            boto3_session=boto3_session,
            catalog_id=catalog_id,
        )
        catalog_path: str | None = None
        if catalog_table_input:
            table_type = catalog_table_input["TableType"]
            catalog_path = catalog_table_input.get("StorageDescriptor", {}).get("Location")
        if path is None:
            if catalog_path:
                path = catalog_path
            else:
                raise exceptions.InvalidArgumentValue(
                    "Glue table does not exist in the catalog. Please pass the `path` argument to create it."
                )
        elif path and catalog_path:
            if path.rstrip("/") != catalog_path.rstrip("/"):
                raise exceptions.InvalidArgumentValue(
                    f"The specified path: {path}, does not match the existing Glue catalog table path: {catalog_path}"
                )
        if pandas_kwargs.get("compression") not in ("gzip", "bz2", None):
            raise exceptions.InvalidArgumentCombination(
                "If database and table are given, you must use one of these compressions: gzip, bz2 or None."
            )

    df = _apply_dtype(df=df, dtype=dtype, catalog_table_input=catalog_table_input, mode=mode)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -