SparkDBFSDatasource

Signature

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.

Methods

Signature

add_csv_asset(name: str, *, id: <pydantic.v1.fields.DeferredType object at 0x7f4617e4e810> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f4617e4e8d0> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f4617e4ea20> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f4617e4ebd0> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f4617e4ec90> = 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 a csv asset to the datasource.

Signature

add_delta_asset(name: str, *, id: <pydantic.v1.fields.DeferredType object at 0x7f4617d127b0> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f4617d12870> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f4617d129c0> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f4617d12b70> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f4617d12c30> = None, timestampAsOf: typing.Optional[str] = None, versionAsOf: typing.Optional[str] = None) → pydantic.BaseModel

Add a delta asset to the datasource.

Signature

add_directory_csv_asset(name: str, *, id: <pydantic.v1.fields.DeferredType object at 0x7f4617d10f50> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f4617d11010> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f4617d11160> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f4617d11310> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f4617d113d0> = 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 a directory_csv asset to the datasource.

Signature

add_directory_delta_asset(name: str, *, id: <pydantic.v1.fields.DeferredType object at 0x7f4617d13a40> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f4617d13b00> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f4617d13c50> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f4617d13e00> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f4617d13ec0> = None, timestampAsOf: typing.Optional[str] = None, versionAsOf: typing.Optional[str] = None, data_directory: pathlib.Path) → pydantic.BaseModel

Add a directory_delta asset to the datasource.

Signature

add_directory_json_asset(name: str, *, id: <pydantic.v1.fields.DeferredType object at 0x7f4617d59970> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f4617d59a30> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f4617d59b80> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f4617d59d30> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f4617d59df0> = 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 a directory_json asset to the datasource.

Signature

add_directory_orc_asset(name: str, *, id: <pydantic.v1.fields.DeferredType object at 0x7f4617d74d10> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f4617d74e00> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f4617d749b0> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f4617d74d40> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f4617d74e30> = 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 a directory_orc asset to the datasource.

Signature

add_directory_parquet_asset(name: str, *, id: <pydantic.v1.fields.DeferredType object at 0x7f4617d75b80> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f4617d75c70> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f4617d75c40> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f4617d75bb0> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f4617d75580> = 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 a directory_parquet asset to the datasource.

Signature

add_directory_text_asset(name: str, *, id: <pydantic.v1.fields.DeferredType object at 0x7f4617d76a50> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f4617d76ab0> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f4617d76990> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f4617d768d0> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f4617d76a80> = 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 a directory_text asset to the datasource.

Signature

add_json_asset(name: str, *, id: <pydantic.v1.fields.DeferredType object at 0x7f4617d37260> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f4617d37440> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f4617d375f0> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f4617d377a0> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f4617d37860> = 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 a json asset to the datasource.

Signature

add_orc_asset(name: str, *, id: <pydantic.v1.fields.DeferredType object at 0x7f4617d5bc20> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f4617d5bce0> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f4617d5be30> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f4617d5bfe0> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f4617d740e0> = 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 an orc asset to the datasource.

Signature

add_parquet_asset(name: str, *, id: <pydantic.v1.fields.DeferredType object at 0x7f4617d752b0> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f4617d75820> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f4617d757f0> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f4617d75760> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f4617d75640> = 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 a parquet asset to the datasource.

Signature

add_text_asset(name: str, *, id: <pydantic.v1.fields.DeferredType object at 0x7f4617d763f0> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f4617d76450> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f4617d76330> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f4617d76240> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f4617d76420> = 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

Add a text asset to the datasource.

Signature

delete_asset(name: str) → None

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

Parameters

Name	Description
name	name of DataAsset to be deleted.

Signature

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

Returns the DataAsset referred to by asset_name

Parameters

Name	Description
name	name of DataAsset sought.

Returns

Type	Description
great_expectations.datasource.fluent.interfaces._DataAssetT	if named "DataAsset" object exists; otherwise, exception is raised.