Skip to main content
Version: 1.2.4

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)#

add_csv_asset(name: str, *, id: <pydantic.v1.fields.DeferredType object at 0x7f25006d9fa0> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f25006da060> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f25006da1b0> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f25006da360> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f25006da420> = 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 0x7f2500715ee0> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f2500715fa0> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f25007160f0> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f25007162a0> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f2500716360> = 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 0x7f25007146e0> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f25007147a0> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f25007148f0> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f2500714aa0> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f2500714b60> = 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 0x7f2500717140> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f2500717200> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f2500717350> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f2500717500> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f25007175c0> = 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 0x7f2500565100> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f25005651c0> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f2500565310> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f25005654c0> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f2500565580> = 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 0x7f250057c320> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f250057c5c0> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f250057c440> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f250057c530> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f250057c4a0> = 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 0x7f250057d2e0> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f250057d3d0> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f250057d3a0> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f250057d310> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f250057ce00> = 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 0x7f250057e120> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f250057e180> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f250057e060> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f250057df10> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f250057e150> = 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 0x7f250072aa20> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f250072ac30> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f250072ad80> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f250072af30> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f250072aff0> = 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 0x7f2500567470> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f2500567530> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f2500567680> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f2500567830> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f25005678f0> = 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 0x7f250057cd70> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f250057cf80> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f250057cf50> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f250057cec0> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f250057cc80> = 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 0x7f250057dac0> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f250057db20> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f250057da00> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f250057d190> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f250057daf0> = 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.