S3ExcelSource ¶

class S3ExcelSource(TypedDict, closed=True):
    name: "capo_glue.types.node_name.NodeName"
    """<p>The name of the S3 Excel data source.</p>"""
    paths: "capo_glue.types.enclosed_in_string_properties.EnclosedInStringProperties"
    """<p>The S3 paths where the Excel files are located.</p>"""
    compression_type: NotRequired[
        "capo_glue.types.parquet_compression_type.ParquetCompressionType"
    ]
    """<p>The compression format used for the Excel files.</p>"""
    exclusions: NotRequired[
        "capo_glue.types.enclosed_in_string_properties.EnclosedInStringProperties"
    ]
    """<p>Patterns to exclude specific files or paths from processing.</p>"""
    group_size: NotRequired[
        "capo_glue.types.enclosed_in_string_property.EnclosedInStringProperty"
    ]
    """<p>Defines the size of file groups for batch processing.</p>"""
    group_files: NotRequired[
        "capo_glue.types.enclosed_in_string_property.EnclosedInStringProperty"
    ]
    """<p>Specifies how files should be grouped for processing.</p>"""
    recurse: NotRequired["capo_glue.types.boxed_boolean.BoxedBoolean"]
    """<p>Indicates whether to recursively process subdirectories.</p>"""
    max_band: NotRequired["capo_glue.types.boxed_non_negative_int.BoxedNonNegativeInt"]
    """<p>The maximum number of processing bands to use.</p>"""
    max_files_in_band: NotRequired[
        "capo_glue.types.boxed_non_negative_int.BoxedNonNegativeInt"
    ]
    """<p>The maximum number of files to process in each band.</p>"""
    additional_options: NotRequired[
        "capo_glue.types.s3_direct_source_additional_options.S3DirectSourceAdditionalOptions"
    ]
    """<p>Additional configuration options for S3 direct source processing.</p>"""
    number_rows: NotRequired["capo_glue.types.boxed_long.BoxedLong"]
    """<p>The number of rows to process from each Excel file.</p>"""
    skip_footer: NotRequired[
        "capo_glue.types.boxed_non_negative_int.BoxedNonNegativeInt"
    ]
    """<p>The number of rows to skip at the end of each Excel file.</p>"""
    output_schemas: NotRequired["capo_glue.types.glue_schemas.GlueSchemas"]
    """<p>The Glue schemas to apply to the processed data.</p>"""