Skip to main content
Version: 1.2.5

SparkDBFSDatasource

class great_expectations.datasource.fluent.SparkDBFSDatasource(*, type: Literal['spark_dbfs'] = 'spark_dbfs', name: str, id: Optional[uuid.UUID] = None, assets: List[Union[great_expectations.datasource.fluent.data_asset.path.spark.csv_asset.CSVAsset, great_expectations.datasource.fluent.data_asset.path.spark.csv_asset.DirectoryCSVAsset, great_expectations.datasource.fluent.data_asset.path.spark.parquet_asset.ParquetAsset, great_expectations.datasource.fluent.data_asset.path.spark.parquet_asset.DirectoryParquetAsset, great_expectations.datasource.fluent.data_asset.path.spark.orc_asset.ORCAsset, great_expectations.datasource.fluent.data_asset.path.spark.orc_asset.DirectoryORCAsset, great_expectations.datasource.fluent.data_asset.path.spark.json_asset.JSONAsset, great_expectations.datasource.fluent.data_asset.path.spark.json_asset.DirectoryJSONAsset, great_expectations.datasource.fluent.data_asset.path.spark.text_asset.TextAsset, great_expectations.datasource.fluent.data_asset.path.spark.text_asset.DirectoryTextAsset, great_expectations.datasource.fluent.data_asset.path.spark.delta_asset.DeltaAsset, great_expectations.datasource.fluent.data_asset.path.spark.delta_asset.DirectoryDeltaAsset]] = [], spark_config: Optional[Dict[pydantic.v1.types.StrictStr, Union[pydantic.v1.types.StrictStr, pydantic.v1.types.StrictInt, pydantic.v1.types.StrictFloat, pydantic.v1.types.StrictBool]]] = None, force_reuse_spark_context: bool = True, persist: bool = True, base_directory: pathlib.Path, data_context_root_directory: Optional[pathlib.Path] = None)#

Spark based Datasource for DataBricks File System (DBFS) based data assets.

add_csv_asset(name: str, *, id: <pydantic.v1.fields.DeferredType object at 0x7f6bb2c7ac90> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f6bb2c7ad50> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f6bb2c7aea0> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f6bb2c7b050> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f6bb2c7b110> = None, pathGlobFilter: typing.Optional[typing.Union[bool, str]] = None, recursiveFileLookup: typing.Optional[typing.Union[bool, str]] = None, modifiedBefore: typing.Optional[typing.Union[bool, str]] = None, modifiedAfter: typing.Optional[typing.Union[bool, str]] = None, schema: typing.Optional[typing.Union[great_expectations.datasource.fluent.serializable_types.pyspark.SerializableStructType, str]] = None, sep: typing.Optional[str] = None, encoding: typing.Optional[str] = None, quote: typing.Optional[str] = None, escape: typing.Optional[str] = None, comment: typing.Optional[str] = None, header: typing.Optional[typing.Union[bool, str]] = None, inferSchema: typing.Optional[typing.Union[bool, str]] = None, ignoreLeadingWhiteSpace: typing.Optional[typing.Union[bool, str]] = None, ignoreTrailingWhiteSpace: typing.Optional[typing.Union[bool, str]] = None, nullValue: typing.Optional[str] = None, nanValue: typing.Optional[str] = None, positiveInf: typing.Optional[str] = None, negativeInf: typing.Optional[str] = None, dateFormat: typing.Optional[str] = None, timestampFormat: typing.Optional[str] = None, maxColumns: typing.Optional[typing.Union[int, str]] = None, maxCharsPerColumn: typing.Optional[typing.Union[int, str]] = None, maxMalformedLogPerPartition: typing.Optional[typing.Union[int, str]] = None, mode: typing.Optional[typing.Literal['PERMISSIVE', 'DROPMALFORMED', 'FAILFAST']] = None, columnNameOfCorruptRecord: typing.Optional[str] = None, multiLine: typing.Optional[typing.Union[bool, str]] = None, charToEscapeQuoteEscaping: typing.Optional[str] = None, samplingRatio: typing.Optional[typing.Union[float, str]] = None, enforceSchema: typing.Optional[typing.Union[bool, str]] = None, emptyValue: typing.Optional[str] = None, locale: typing.Optional[str] = None, lineSep: typing.Optional[str] = None, unescapedQuoteHandling: typing.Optional[typing.Literal['STOP_AT_CLOSING_QUOTE', 'BACK_TO_DELIMITER', 'STOP_AT_DELIMITER', 'SKIP_VALUE', 'RAISE_ERROR']] = None) pydantic.BaseModel#

add_delta_asset(name: str, *, id: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b22c60> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b22d20> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b22e70> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b23020> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b230e0> = None, timestampAsOf: typing.Optional[str] = None, versionAsOf: typing.Optional[str] = None) pydantic.BaseModel#

add_directory_csv_asset(name: str, *, id: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b21400> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b214c0> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b21610> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b217c0> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b21880> = None, pathGlobFilter: typing.Optional[typing.Union[bool, str]] = None, recursiveFileLookup: typing.Optional[typing.Union[bool, str]] = None, modifiedBefore: typing.Optional[typing.Union[bool, str]] = None, modifiedAfter: typing.Optional[typing.Union[bool, str]] = None, schema: typing.Optional[typing.Union[great_expectations.datasource.fluent.serializable_types.pyspark.SerializableStructType, str]] = None, sep: typing.Optional[str] = None, encoding: typing.Optional[str] = None, quote: typing.Optional[str] = None, escape: typing.Optional[str] = None, comment: typing.Optional[str] = None, header: typing.Optional[typing.Union[bool, str]] = None, inferSchema: typing.Optional[typing.Union[bool, str]] = None, ignoreLeadingWhiteSpace: typing.Optional[typing.Union[bool, str]] = None, ignoreTrailingWhiteSpace: typing.Optional[typing.Union[bool, str]] = None, nullValue: typing.Optional[str] = None, nanValue: typing.Optional[str] = None, positiveInf: typing.Optional[str] = None, negativeInf: typing.Optional[str] = None, dateFormat: typing.Optional[str] = None, timestampFormat: typing.Optional[str] = None, maxColumns: typing.Optional[typing.Union[int, str]] = None, maxCharsPerColumn: typing.Optional[typing.Union[int, str]] = None, maxMalformedLogPerPartition: typing.Optional[typing.Union[int, str]] = None, mode: typing.Optional[typing.Literal['PERMISSIVE', 'DROPMALFORMED', 'FAILFAST']] = None, columnNameOfCorruptRecord: typing.Optional[str] = None, multiLine: typing.Optional[typing.Union[bool, str]] = None, charToEscapeQuoteEscaping: typing.Optional[str] = None, samplingRatio: typing.Optional[typing.Union[float, str]] = None, enforceSchema: typing.Optional[typing.Union[bool, str]] = None, emptyValue: typing.Optional[str] = None, locale: typing.Optional[str] = None, lineSep: typing.Optional[str] = None, unescapedQuoteHandling: typing.Optional[typing.Literal['STOP_AT_CLOSING_QUOTE', 'BACK_TO_DELIMITER', 'STOP_AT_DELIMITER', 'SKIP_VALUE', 'RAISE_ERROR']] = None, data_directory: pathlib.Path) pydantic.BaseModel#

add_directory_delta_asset(name: str, *, id: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b23ef0> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b23fb0> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b3c140> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b3c2f0> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b3c3b0> = None, timestampAsOf: typing.Optional[str] = None, versionAsOf: typing.Optional[str] = None, data_directory: pathlib.Path) pydantic.BaseModel#

add_directory_json_asset(name: str, *, id: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b65e80> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b65f40> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b66090> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b66240> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b66300> = None, pathGlobFilter: typing.Optional[typing.Union[bool, str]] = None, recursiveFileLookup: typing.Optional[typing.Union[bool, str]] = None, modifiedBefore: typing.Optional[typing.Union[bool, str]] = None, modifiedAfter: typing.Optional[typing.Union[bool, str]] = None, schema: typing.Optional[typing.Union[great_expectations.datasource.fluent.serializable_types.pyspark.SerializableStructType, str]] = None, primitivesAsString: typing.Optional[typing.Union[bool, str]] = None, prefersDecimal: typing.Optional[typing.Union[bool, str]] = None, allowComments: typing.Optional[typing.Union[bool, str]] = None, allowUnquotedFieldNames: typing.Optional[typing.Union[bool, str]] = None, allowSingleQuotes: typing.Optional[typing.Union[bool, str]] = None, allowNumericLeadingZero: typing.Optional[typing.Union[bool, str]] = None, allowBackslashEscapingAnyCharacter: typing.Optional[typing.Union[bool, str]] = None, mode: typing.Optional[typing.Literal['PERMISSIVE', 'DROPMALFORMED', 'FAILFAST']] = None, columnNameOfCorruptRecord: typing.Optional[str] = None, dateFormat: typing.Optional[str] = None, timestampFormat: typing.Optional[str] = None, multiLine: typing.Optional[typing.Union[bool, str]] = None, allowUnquotedControlChars: typing.Optional[typing.Union[bool, str]] = None, lineSep: typing.Optional[str] = None, samplingRatio: typing.Optional[typing.Union[float, str]] = None, dropFieldIfAllNull: typing.Optional[typing.Union[bool, str]] = None, encoding: typing.Optional[str] = None, locale: typing.Optional[str] = None, allowNonNumericNumbers: typing.Optional[typing.Union[bool, str]] = None, data_directory: pathlib.Path) pydantic.BaseModel#

add_directory_orc_asset(name: str, *, id: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b85280> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b85340> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b84f50> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b85220> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b852b0> = None, pathGlobFilter: typing.Optional[typing.Union[bool, str]] = None, recursiveFileLookup: typing.Optional[typing.Union[bool, str]] = None, modifiedBefore: typing.Optional[typing.Union[bool, str]] = None, modifiedAfter: typing.Optional[typing.Union[bool, str]] = None, mergeSchema: typing.Optional[typing.Union[bool, str]] = False, data_directory: pathlib.Path) pydantic.BaseModel#

add_directory_parquet_asset(name: str, *, id: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b85fd0> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b860c0> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b86090> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b86000> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b85b50> = None, pathGlobFilter: typing.Optional[typing.Union[bool, str]] = None, recursiveFileLookup: typing.Optional[typing.Union[bool, str]] = None, modifiedBefore: typing.Optional[typing.Union[bool, str]] = None, modifiedAfter: typing.Optional[typing.Union[bool, str]] = None, mergeSchema: typing.Optional[typing.Union[bool, str]] = None, datetimeRebaseMode: typing.Optional[typing.Literal['EXCEPTION', 'CORRECTED', 'LEGACY']] = None, int96RebaseMode: typing.Optional[typing.Literal['EXCEPTION', 'CORRECTED', 'LEGACY']] = None, data_directory: pathlib.Path) pydantic.BaseModel#

add_directory_text_asset(name: str, *, id: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b86ea0> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b86f00> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b86de0> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b86ae0> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b86ed0> = None, pathGlobFilter: typing.Optional[typing.Union[bool, str]] = None, recursiveFileLookup: typing.Optional[typing.Union[bool, str]] = None, modifiedBefore: typing.Optional[typing.Union[bool, str]] = None, modifiedAfter: typing.Optional[typing.Union[bool, str]] = None, wholetext: bool = False, lineSep: typing.Optional[str] = None, data_directory: pathlib.Path) pydantic.BaseModel#

add_json_asset(name: str, *, id: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b3f6e0> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b3f9b0> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b3fb00> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b3fcb0> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b3fd70> = None, pathGlobFilter: typing.Optional[typing.Union[bool, str]] = None, recursiveFileLookup: typing.Optional[typing.Union[bool, str]] = None, modifiedBefore: typing.Optional[typing.Union[bool, str]] = None, modifiedAfter: typing.Optional[typing.Union[bool, str]] = None, schema: typing.Optional[typing.Union[great_expectations.datasource.fluent.serializable_types.pyspark.SerializableStructType, str]] = None, primitivesAsString: typing.Optional[typing.Union[bool, str]] = None, prefersDecimal: typing.Optional[typing.Union[bool, str]] = None, allowComments: typing.Optional[typing.Union[bool, str]] = None, allowUnquotedFieldNames: typing.Optional[typing.Union[bool, str]] = None, allowSingleQuotes: typing.Optional[typing.Union[bool, str]] = None, allowNumericLeadingZero: typing.Optional[typing.Union[bool, str]] = None, allowBackslashEscapingAnyCharacter: typing.Optional[typing.Union[bool, str]] = None, mode: typing.Optional[typing.Literal['PERMISSIVE', 'DROPMALFORMED', 'FAILFAST']] = None, columnNameOfCorruptRecord: typing.Optional[str] = None, dateFormat: typing.Optional[str] = None, timestampFormat: typing.Optional[str] = None, multiLine: typing.Optional[typing.Union[bool, str]] = None, allowUnquotedControlChars: typing.Optional[typing.Union[bool, str]] = None, lineSep: typing.Optional[str] = None, samplingRatio: typing.Optional[typing.Union[float, str]] = None, dropFieldIfAllNull: typing.Optional[typing.Union[bool, str]] = None, encoding: typing.Optional[str] = None, locale: typing.Optional[str] = None, allowNonNumericNumbers: typing.Optional[typing.Union[bool, str]] = None) pydantic.BaseModel#

add_orc_asset(name: str, *, id: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b84200> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b842c0> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b84410> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b845c0> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b84680> = None, pathGlobFilter: typing.Optional[typing.Union[bool, str]] = None, recursiveFileLookup: typing.Optional[typing.Union[bool, str]] = None, modifiedBefore: typing.Optional[typing.Union[bool, str]] = None, modifiedAfter: typing.Optional[typing.Union[bool, str]] = None, mergeSchema: typing.Optional[typing.Union[bool, str]] = False) pydantic.BaseModel#

add_parquet_asset(name: str, *, id: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b85ac0> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b85cd0> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b85ca0> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b85c10> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b85880> = None, pathGlobFilter: typing.Optional[typing.Union[bool, str]] = None, recursiveFileLookup: typing.Optional[typing.Union[bool, str]] = None, modifiedBefore: typing.Optional[typing.Union[bool, str]] = None, modifiedAfter: typing.Optional[typing.Union[bool, str]] = None, mergeSchema: typing.Optional[typing.Union[bool, str]] = None, datetimeRebaseMode: typing.Optional[typing.Literal['EXCEPTION', 'CORRECTED', 'LEGACY']] = None, int96RebaseMode: typing.Optional[typing.Literal['EXCEPTION', 'CORRECTED', 'LEGACY']] = None) pydantic.BaseModel#

add_text_asset(name: str, *, id: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b86870> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b868d0> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b867b0> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b866c0> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f6bb2b868a0> = None, pathGlobFilter: typing.Optional[typing.Union[bool, str]] = None, recursiveFileLookup: typing.Optional[typing.Union[bool, str]] = None, modifiedBefore: typing.Optional[typing.Union[bool, str]] = None, modifiedAfter: typing.Optional[typing.Union[bool, str]] = None, wholetext: bool = False, lineSep: typing.Optional[str] = None) pydantic.BaseModel#

delete_asset(name: str) None#

Removes the DataAsset referred to by asset_name from internal list of available DataAsset objects.

Parameters

name – name of DataAsset to be deleted.

get_asset(name: str) great_expectations.datasource.fluent.interfaces._DataAssetT#

Returns the DataAsset referred to by asset_name

Parameters

name – name of DataAsset sought.

Returns

_DataAssetT – if named “DataAsset” object exists; otherwise, exception is raised.