Skip to main content
Version: 1.0 prerelease

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 0x7f7789cabe50> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f7789cabf10> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f7789cb7070> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f7789cb71c0> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f7789cb7310> = 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 0x7f7789c0df10> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f7789c0dfd0> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f7789c13130> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f7789c13280> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f7789c133d0> = 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 0x7f7789c07610> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f7789c076d0> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f7789c077f0> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f7789c07940> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f7789c07a90> = 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 0x7f7789c13f70> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f7789c19070> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f7789c19190> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f7789c192e0> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f7789c19430> = 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 0x7f7789bd0df0> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f7789bd0eb0> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f7789bd0fd0> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f7789bda160> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f7789bda2b0> = 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 0x7f7789bee5e0> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f7789bee6a0> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f7789bee7c0> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f7789bee910> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f7789beea60> = 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 0x7f7789b8e070> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f7789b8e130> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f7789b8e250> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f7789b8e3a0> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f7789b8e4f0> = 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 0x7f7789b9db20> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f7789b9da00> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f7789b9daf0> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f7789b9dac0> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f7789b9da60> = 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 0x7f7789c3e8b0> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f7789c3e970> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f7789c3ea90> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f7789c3ebe0> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f7789c3ed60> = 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 0x7f7789be7100> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f7789be71c0> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f7789be72e0> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f7789be7430> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f7789be7580> = 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 0x7f7789bffaf0> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f7789bffbb0> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f7789bffca0> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f7789bffdf0> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f7789bfff40> = 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 0x7f7789b9d2b0> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f7789b9d370> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f7789b9d490> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f7789b9d5e0> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f7789b9d700> = 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#