SparkFilesystemDatasource
SparkFilesystemDatasource is a subclass of SparkDatasource which connects to the filesystem.
Add a csv asset to the datasource.
Add a delta asset to the datasource.
Add a directory_csv asset to the datasource.
Add a directory_delta asset to the datasource.
Add a directory_json asset to the datasource.
Add a directory_orc asset to the datasource.
Add a directory_parquet asset to the datasource.
Add a directory_text asset to the datasource.
Add a json asset to the datasource.
Add an orc asset to the datasource.
Add a parquet asset to the datasource.
Add a text asset to the datasource.
Removes the DataAsset referred to by asset_name from internal list of available DataAsset objects.
Parameters
Name Description name
name of DataAsset to be deleted.
Returns the DataAsset referred to by asset_name
Parameters
Name Description name
name of DataAsset sought.
Returns
Type Description great_expectations.datasource.fluent.interfaces._DataAssetT
if named "DataAsset" object exists; otherwise, exception is raised.
Signature
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
)
Methods
add_csv_asset
Signature
add_csv_asset(
name: str,
*,
id: <pydantic.v1.fields.DeferredType object at 0x7f60f22d0a70> = None,
order_by: <pydantic.v1.fields.DeferredType object at 0x7f60f22d0b30> = None,
batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f60f22d0c80> = None,
batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f60f22d0e30> = None,
connect_options: <pydantic.v1.fields.DeferredType object at 0x7f60f22d0ef0> = 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
Signature
add_delta_asset(
name: str,
*,
id: <pydantic.v1.fields.DeferredType object at 0x7f60f22ec980> = None,
order_by: <pydantic.v1.fields.DeferredType object at 0x7f60f22eca40> = None,
batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f60f22ecb90> = None,
batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f60f22ecd40> = None,
connect_options: <pydantic.v1.fields.DeferredType object at 0x7f60f22ece00> = None,
timestampAsOf: typing.Optional[str] = None,
versionAsOf: typing.Optional[str] = None
) → pydantic.BaseModel
add_directory_csv_asset
Signature
add_directory_csv_asset(
name: str,
*,
id: <pydantic.v1.fields.DeferredType object at 0x7f60f22d3170> = None,
order_by: <pydantic.v1.fields.DeferredType object at 0x7f60f22d3230> = None,
batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f60f22d3380> = None,
batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f60f22d3530> = None,
connect_options: <pydantic.v1.fields.DeferredType object at 0x7f60f22d35f0> = 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
Signature
add_directory_delta_asset(
name: str,
*,
id: <pydantic.v1.fields.DeferredType object at 0x7f60f22edbe0> = None,
order_by: <pydantic.v1.fields.DeferredType object at 0x7f60f22edca0> = None,
batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f60f22eddf0> = None,
batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f60f22edfa0> = None,
connect_options: <pydantic.v1.fields.DeferredType object at 0x7f60f22ee060> = None,
timestampAsOf: typing.Optional[str] = None,
versionAsOf: typing.Optional[str] = None,
data_directory: pathlib.Path
) → pydantic.BaseModel
add_directory_json_asset
Signature
add_directory_json_asset(
name: str,
*,
id: <pydantic.v1.fields.DeferredType object at 0x7f60f230ba70> = None,
order_by: <pydantic.v1.fields.DeferredType object at 0x7f60f230bb30> = None,
batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f60f230bc80> = None,
batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f60f230be30> = None,
connect_options: <pydantic.v1.fields.DeferredType object at 0x7f60f230bef0> = 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
Signature
add_directory_orc_asset(
name: str,
*,
id: <pydantic.v1.fields.DeferredType object at 0x7f60f21472f0> = None,
order_by: <pydantic.v1.fields.DeferredType object at 0x7f60f21473b0> = None,
batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f60f2147500> = None,
batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f60f21476b0> = None,
connect_options: <pydantic.v1.fields.DeferredType object at 0x7f60f2147770> = 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
Signature
add_directory_parquet_asset(
name: str,
*,
id: <pydantic.v1.fields.DeferredType object at 0x7f60f215ee40> = None,
order_by: <pydantic.v1.fields.DeferredType object at 0x7f60f215ef00> = None,
batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f60f215f050> = None,
batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f60f215f200> = None,
connect_options: <pydantic.v1.fields.DeferredType object at 0x7f60f215f2c0> = 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
Signature
add_directory_text_asset(
name: str,
*,
id: <pydantic.v1.fields.DeferredType object at 0x7f60f217a6f0> = None,
order_by: <pydantic.v1.fields.DeferredType object at 0x7f60f217a7b0> = None,
batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f60f217a900> = None,
batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f60f217aab0> = None,
connect_options: <pydantic.v1.fields.DeferredType object at 0x7f60f217ab70> = 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
Signature
add_json_asset(
name: str,
*,
id: <pydantic.v1.fields.DeferredType object at 0x7f60f23094f0> = None,
order_by: <pydantic.v1.fields.DeferredType object at 0x7f60f2309640> = None,
batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f60f2309790> = None,
batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f60f2309940> = None,
connect_options: <pydantic.v1.fields.DeferredType object at 0x7f60f2309a00> = 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
Signature
add_orc_asset(
name: str,
*,
id: <pydantic.v1.fields.DeferredType object at 0x7f60f2145dc0> = None,
order_by: <pydantic.v1.fields.DeferredType object at 0x7f60f2145e80> = None,
batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f60f2145fd0> = None,
batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f60f2146180> = None,
connect_options: <pydantic.v1.fields.DeferredType object at 0x7f60f2146240> = 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
Signature
add_parquet_asset(
name: str,
*,
id: <pydantic.v1.fields.DeferredType object at 0x7f60f215d880> = None,
order_by: <pydantic.v1.fields.DeferredType object at 0x7f60f215d940> = None,
batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f60f215da90> = None,
batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f60f215dc40> = None,
connect_options: <pydantic.v1.fields.DeferredType object at 0x7f60f215dd00> = 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
Signature
add_text_asset(
name: str,
*,
id: <pydantic.v1.fields.DeferredType object at 0x7f60f2179190> = None,
order_by: <pydantic.v1.fields.DeferredType object at 0x7f60f2179250> = None,
batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f60f21793a0> = None,
batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f60f2179550> = None,
connect_options: <pydantic.v1.fields.DeferredType object at 0x7f60f2179610> = 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
Signature
delete_asset(
name: str
) → None
get_asset
Signature
get_asset(
name: str
) → great_expectations.datasource.fluent.interfaces._DataAssetT