SparkFilesystemDatasource

class great_expectations.datasource.fluent.SparkFilesystemDatasource(*, type: Literal['spark_filesystem'] = 'spark_filesystem', 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)#

SparkFilesystemDatasource is a subclass of SparkDatasource which connects to the filesystem.

Methods

add_csv_asset(name: str, *, id: <pydantic.v1.fields.DeferredType object at 0x7f905f63f380> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f905f63f440> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f905f63f590> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f905f63f740> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f905f63f800> = 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.

add_delta_asset(name: str, *, id: <pydantic.v1.fields.DeferredType object at 0x7f905f69b2f0> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f905f69b3b0> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f905f69b500> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f905f69b6b0> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f905f69b770> = None, timestampAsOf: typing.Optional[str] = None, versionAsOf: typing.Optional[str] = None) → pydantic.BaseModel#

Add a delta asset to the datasource.

add_directory_csv_asset(name: str, *, id: <pydantic.v1.fields.DeferredType object at 0x7f905f699ac0> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f905f699b80> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f905f699cd0> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f905f699e80> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f905f699f40> = 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.

add_directory_delta_asset(name: str, *, id: <pydantic.v1.fields.DeferredType object at 0x7f905f6bc590> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f905f6bc650> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f905f6bc7a0> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f905f6bc950> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f905f6bca10> = 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.

add_directory_json_asset(name: str, *, id: <pydantic.v1.fields.DeferredType object at 0x7f905f4ea4b0> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f905f4ea570> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f905f4ea6c0> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f905f4ea870> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f905f4ea930> = 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.

add_directory_orc_asset(name: str, *, id: <pydantic.v1.fields.DeferredType object at 0x7f905f4fd8b0> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f905f4fd970> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f905f4fd580> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f905f4fd850> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f905f4fd8e0> = 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.

add_directory_parquet_asset(name: str, *, id: <pydantic.v1.fields.DeferredType object at 0x7f905f4fe660> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f905f4fe750> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f905f4fe720> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f905f4fe690> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f905f4fe090> = 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.

add_directory_text_asset(name: str, *, id: <pydantic.v1.fields.DeferredType object at 0x7f905f4ff4d0> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f905f4ff530> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f905f4ff410> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f905f4ff2c0> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f905f4ff500> = 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.

add_json_asset(name: str, *, id: <pydantic.v1.fields.DeferredType object at 0x7f905f6bfd10> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f905f6bffe0> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f905f4e8170> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f905f4e8320> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f905f4e83e0> = 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.

add_orc_asset(name: str, *, id: <pydantic.v1.fields.DeferredType object at 0x7f905f4fc830> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f905f4fc8f0> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f905f4fca40> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f905f4fcbf0> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f905f4fccb0> = 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.

add_parquet_asset(name: str, *, id: <pydantic.v1.fields.DeferredType object at 0x7f905f4fddf0> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f905f4fe330> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f905f4fe300> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f905f4fe270> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f905f4fe150> = 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.

add_text_asset(name: str, *, id: <pydantic.v1.fields.DeferredType object at 0x7f905f4fee70> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f905f4feed0> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f905f4fedb0> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f905f4ff350> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f905f4feea0> = 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.

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.