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 0x7f143f8aa760> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f143f8aa820> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f143f8aa940> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f143f8aaac0> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f143f8aac10> = 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 0x7f143f8c89a0> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f143f8c8a60> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f143f8c8b80> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f143f8c8d00> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f143f8c8e50> = 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 0x7f143f8b9f70> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f143f8c5070> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f143f8c5190> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f143f8c5310> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f143f8c5460> = 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 0x7f143f8cfa90> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f143f8cfb50> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f143f8cfc70> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f143f8cfe50> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f143f8cffa0> = 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 0x7f143f88ba90> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f143f88bb50> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f143f88bc70> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f143f88bdf0> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f143f88bf40> = 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 0x7f143f8a9400> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f143f8a94c0> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f143f8a95e0> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f143f8a9760> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f143f8a98b0> = 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 0x7f143f841fd0> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f143f84a0d0> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f143f84a1f0> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f143f84a370> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f143f84a4c0> = 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 0x7f143f859790> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f143f8598e0> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f143f859a90> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f143f8599d0> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f143f859940> = 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 0x7f143f87b4f0> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f143f87b580> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f143f87b6a0> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f143f87b820> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f143f87b970> = 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 0x7f143f89ae80> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f143f89af40> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f143f8a3070> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f143f8a31f0> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f143f8a3340> = 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 0x7f143f83a9d0> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f143f83aa60> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f143f83abb0> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f143f83ad30> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f143f83ae80> = 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 0x7f143f859340> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f143f859400> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f143f859520> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f143f859610> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f143f859550> = 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#