Version: 1.0 prerelease

SparkGoogleCloudStorageDatasource

class great_expectations.datasource.fluent.SparkGoogleCloudStorageDatasource(*, type: Literal['spark_gcs'] = 'spark_gcs', 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, bucket_or_name: str, gcs_options: Dict[str, Union[great_expectations.datasource.fluent.config_str.ConfigStr, Any]] = )#

add_csv_asset(name: str, *, id: <pydantic.v1.fields.DeferredType object at 0x7f4de3617520> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f4de36175e0> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f4de3617700> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f4de3617850> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f4de36179a0> = 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 0x7f4de35b8580> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f4de35b86a0> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f4de35b87c0> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f4de35b8910> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f4de35b8a90> = 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 0x7f4de3626ca0> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f4de3626d60> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f4de3626e80> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f4de3626fd0> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f4de35b0160> = 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 0x7f4de35be640> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f4de35be700> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f4de35be820> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f4de35be970> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f4de35beac0> = 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 0x7f4de357c4c0> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f4de357c580> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f4de357c6a0> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f4de357c7f0> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f4de357c940> = 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 0x7f4de3594c70> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f4de3594d30> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f4de3594e50> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f4de3594fa0> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f4de359a130> = 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 0x7f4de3531730> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f4de35317f0> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f4de3531910> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f4de3531a60> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f4de3531bb0> = 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 0x7f4de354a250> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f4de354a160> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f4de354a040> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f4de354a220> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f4de354a1c0> = 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 0x7f4de35dff40> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f4de356d040> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f4de356d160> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f4de356d2b0> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f4de356d400> = 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 0x7f4de358a7c0> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f4de358a880> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f4de358a9a0> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f4de358aaf0> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f4de358ac40> = 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 0x7f4de352c190> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f4de352c250> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f4de352c370> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f4de352c4c0> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f4de352c610> = 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 0x7f4de353f970> = None, order_by: <pydantic.v1.fields.DeferredType object at 0x7f4de353fa30> = None, batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f4de353fb50> = None, batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f4de353fd00> = None, connect_options: <pydantic.v1.fields.DeferredType object at 0x7f4de353fe20> = 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#