Class PySparkJob (4.43.0)

public final class PySparkJob extends GeneratedMessageV3 implements PySparkJobOrBuilder

A Dataproc job for running Apache PySpark applications on YARN.

Protobuf type google.cloud.dataproc.v1.PySparkJob

Implements

PySparkJobOrBuilder

Static Fields

ARCHIVE_URIS_FIELD_NUMBER

public static final int ARCHIVE_URIS_FIELD_NUMBER
Field Value
Type Description
int

ARGS_FIELD_NUMBER

public static final int ARGS_FIELD_NUMBER
Field Value
Type Description
int

FILE_URIS_FIELD_NUMBER

public static final int FILE_URIS_FIELD_NUMBER
Field Value
Type Description
int

JAR_FILE_URIS_FIELD_NUMBER

public static final int JAR_FILE_URIS_FIELD_NUMBER
Field Value
Type Description
int

LOGGING_CONFIG_FIELD_NUMBER

public static final int LOGGING_CONFIG_FIELD_NUMBER
Field Value
Type Description
int

MAIN_PYTHON_FILE_URI_FIELD_NUMBER

public static final int MAIN_PYTHON_FILE_URI_FIELD_NUMBER
Field Value
Type Description
int

PROPERTIES_FIELD_NUMBER

public static final int PROPERTIES_FIELD_NUMBER
Field Value
Type Description
int

PYTHON_FILE_URIS_FIELD_NUMBER

public static final int PYTHON_FILE_URIS_FIELD_NUMBER
Field Value
Type Description
int

Static Methods

getDefaultInstance()

public static PySparkJob getDefaultInstance()
Returns
Type Description
PySparkJob

getDescriptor()

public static final Descriptors.Descriptor getDescriptor()
Returns
Type Description
Descriptor

newBuilder()

public static PySparkJob.Builder newBuilder()
Returns
Type Description
PySparkJob.Builder

newBuilder(PySparkJob prototype)

public static PySparkJob.Builder newBuilder(PySparkJob prototype)
Parameter
Name Description
prototype PySparkJob
Returns
Type Description
PySparkJob.Builder

parseDelimitedFrom(InputStream input)

public static PySparkJob parseDelimitedFrom(InputStream input)
Parameter
Name Description
input InputStream
Returns
Type Description
PySparkJob
Exceptions
Type Description
IOException

parseDelimitedFrom(InputStream input, ExtensionRegistryLite extensionRegistry)

public static PySparkJob parseDelimitedFrom(InputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
Name Description
input InputStream
extensionRegistry ExtensionRegistryLite
Returns
Type Description
PySparkJob
Exceptions
Type Description
IOException

parseFrom(byte[] data)

public static PySparkJob parseFrom(byte[] data)
Parameter
Name Description
data byte[]
Returns
Type Description
PySparkJob
Exceptions
Type Description
InvalidProtocolBufferException

parseFrom(byte[] data, ExtensionRegistryLite extensionRegistry)

public static PySparkJob parseFrom(byte[] data, ExtensionRegistryLite extensionRegistry)
Parameters
Name Description
data byte[]
extensionRegistry ExtensionRegistryLite
Returns
Type Description
PySparkJob
Exceptions
Type Description
InvalidProtocolBufferException

parseFrom(ByteString data)

public static PySparkJob parseFrom(ByteString data)
Parameter
Name Description
data ByteString
Returns
Type Description
PySparkJob
Exceptions
Type Description
InvalidProtocolBufferException

parseFrom(ByteString data, ExtensionRegistryLite extensionRegistry)

public static PySparkJob parseFrom(ByteString data, ExtensionRegistryLite extensionRegistry)
Parameters
Name Description
data ByteString
extensionRegistry ExtensionRegistryLite
Returns
Type Description
PySparkJob
Exceptions
Type Description
InvalidProtocolBufferException

parseFrom(CodedInputStream input)

public static PySparkJob parseFrom(CodedInputStream input)
Parameter
Name Description
input CodedInputStream
Returns
Type Description
PySparkJob
Exceptions
Type Description
IOException

parseFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)

public static PySparkJob parseFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
Name Description
input CodedInputStream
extensionRegistry ExtensionRegistryLite
Returns
Type Description
PySparkJob
Exceptions
Type Description
IOException

parseFrom(InputStream input)

public static PySparkJob parseFrom(InputStream input)
Parameter
Name Description
input InputStream
Returns
Type Description
PySparkJob
Exceptions
Type Description
IOException

parseFrom(InputStream input, ExtensionRegistryLite extensionRegistry)

public static PySparkJob parseFrom(InputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
Name Description
input InputStream
extensionRegistry ExtensionRegistryLite
Returns
Type Description
PySparkJob
Exceptions
Type Description
IOException

parseFrom(ByteBuffer data)

public static PySparkJob parseFrom(ByteBuffer data)
Parameter
Name Description
data ByteBuffer
Returns
Type Description
PySparkJob
Exceptions
Type Description
InvalidProtocolBufferException

parseFrom(ByteBuffer data, ExtensionRegistryLite extensionRegistry)

public static PySparkJob parseFrom(ByteBuffer data, ExtensionRegistryLite extensionRegistry)
Parameters
Name Description
data ByteBuffer
extensionRegistry ExtensionRegistryLite
Returns
Type Description
PySparkJob
Exceptions
Type Description
InvalidProtocolBufferException

parser()

public static Parser<PySparkJob> parser()
Returns
Type Description
Parser<PySparkJob>

Methods

containsProperties(String key)

public boolean containsProperties(String key)

Optional. A mapping of property names to values, used to configure PySpark. Properties that conflict with values set by the Dataproc API may be overwritten. Can include properties set in /etc/spark/conf/spark-defaults.conf and classes in user code.

map<string, string> properties = 7 [(.google.api.field_behavior) = OPTIONAL];

Parameter
Name Description
key String
Returns
Type Description
boolean

equals(Object obj)

public boolean equals(Object obj)
Parameter
Name Description
obj Object
Returns
Type Description
boolean
Overrides

getArchiveUris(int index)

public String getArchiveUris(int index)

Optional. HCFS URIs of archives to be extracted into the working directory of each executor. Supported file types: .jar, .tar, .tar.gz, .tgz, and .zip.

repeated string archive_uris = 6 [(.google.api.field_behavior) = OPTIONAL];

Parameter
Name Description
index int

The index of the element to return.

Returns
Type Description
String

The archiveUris at the given index.

getArchiveUrisBytes(int index)

public ByteString getArchiveUrisBytes(int index)

Optional. HCFS URIs of archives to be extracted into the working directory of each executor. Supported file types: .jar, .tar, .tar.gz, .tgz, and .zip.

repeated string archive_uris = 6 [(.google.api.field_behavior) = OPTIONAL];

Parameter
Name Description
index int

The index of the value to return.

Returns
Type Description
ByteString

The bytes of the archiveUris at the given index.

getArchiveUrisCount()

public int getArchiveUrisCount()

Optional. HCFS URIs of archives to be extracted into the working directory of each executor. Supported file types: .jar, .tar, .tar.gz, .tgz, and .zip.

repeated string archive_uris = 6 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type Description
int

The count of archiveUris.

getArchiveUrisList()

public ProtocolStringList getArchiveUrisList()

Optional. HCFS URIs of archives to be extracted into the working directory of each executor. Supported file types: .jar, .tar, .tar.gz, .tgz, and .zip.

repeated string archive_uris = 6 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type Description
ProtocolStringList

A list containing the archiveUris.

getArgs(int index)

public String getArgs(int index)

Optional. The arguments to pass to the driver. Do not include arguments, such as --conf, that can be set as job properties, since a collision may occur that causes an incorrect job submission.

repeated string args = 2 [(.google.api.field_behavior) = OPTIONAL];

Parameter
Name Description
index int

The index of the element to return.

Returns
Type Description
String

The args at the given index.

getArgsBytes(int index)

public ByteString getArgsBytes(int index)

Optional. The arguments to pass to the driver. Do not include arguments, such as --conf, that can be set as job properties, since a collision may occur that causes an incorrect job submission.

repeated string args = 2 [(.google.api.field_behavior) = OPTIONAL];

Parameter
Name Description
index int

The index of the value to return.

Returns
Type Description
ByteString

The bytes of the args at the given index.

getArgsCount()

public int getArgsCount()

Optional. The arguments to pass to the driver. Do not include arguments, such as --conf, that can be set as job properties, since a collision may occur that causes an incorrect job submission.

repeated string args = 2 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type Description
int

The count of args.

getArgsList()

public ProtocolStringList getArgsList()

Optional. The arguments to pass to the driver. Do not include arguments, such as --conf, that can be set as job properties, since a collision may occur that causes an incorrect job submission.

repeated string args = 2 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type Description
ProtocolStringList

A list containing the args.

getDefaultInstanceForType()

public PySparkJob getDefaultInstanceForType()
Returns
Type Description
PySparkJob

getFileUris(int index)

public String getFileUris(int index)

Optional. HCFS URIs of files to be placed in the working directory of each executor. Useful for naively parallel tasks.

repeated string file_uris = 5 [(.google.api.field_behavior) = OPTIONAL];

Parameter
Name Description
index int

The index of the element to return.

Returns
Type Description
String

The fileUris at the given index.

getFileUrisBytes(int index)

public ByteString getFileUrisBytes(int index)

Optional. HCFS URIs of files to be placed in the working directory of each executor. Useful for naively parallel tasks.

repeated string file_uris = 5 [(.google.api.field_behavior) = OPTIONAL];

Parameter
Name Description
index int

The index of the value to return.

Returns
Type Description
ByteString

The bytes of the fileUris at the given index.

getFileUrisCount()

public int getFileUrisCount()

Optional. HCFS URIs of files to be placed in the working directory of each executor. Useful for naively parallel tasks.

repeated string file_uris = 5 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type Description
int

The count of fileUris.

getFileUrisList()

public ProtocolStringList getFileUrisList()

Optional. HCFS URIs of files to be placed in the working directory of each executor. Useful for naively parallel tasks.

repeated string file_uris = 5 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type Description
ProtocolStringList

A list containing the fileUris.

getJarFileUris(int index)

public String getJarFileUris(int index)

Optional. HCFS URIs of jar files to add to the CLASSPATHs of the Python driver and tasks.

repeated string jar_file_uris = 4 [(.google.api.field_behavior) = OPTIONAL];

Parameter
Name Description
index int

The index of the element to return.

Returns
Type Description
String

The jarFileUris at the given index.

getJarFileUrisBytes(int index)

public ByteString getJarFileUrisBytes(int index)

Optional. HCFS URIs of jar files to add to the CLASSPATHs of the Python driver and tasks.

repeated string jar_file_uris = 4 [(.google.api.field_behavior) = OPTIONAL];

Parameter
Name Description
index int

The index of the value to return.

Returns
Type Description
ByteString

The bytes of the jarFileUris at the given index.

getJarFileUrisCount()

public int getJarFileUrisCount()

Optional. HCFS URIs of jar files to add to the CLASSPATHs of the Python driver and tasks.

repeated string jar_file_uris = 4 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type Description
int

The count of jarFileUris.

getJarFileUrisList()

public ProtocolStringList getJarFileUrisList()

Optional. HCFS URIs of jar files to add to the CLASSPATHs of the Python driver and tasks.

repeated string jar_file_uris = 4 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type Description
ProtocolStringList

A list containing the jarFileUris.

getLoggingConfig()

public LoggingConfig getLoggingConfig()

Optional. The runtime log config for job execution.

.google.cloud.dataproc.v1.LoggingConfig logging_config = 8 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type Description
LoggingConfig

The loggingConfig.

getLoggingConfigOrBuilder()

public LoggingConfigOrBuilder getLoggingConfigOrBuilder()

Optional. The runtime log config for job execution.

.google.cloud.dataproc.v1.LoggingConfig logging_config = 8 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type Description
LoggingConfigOrBuilder

getMainPythonFileUri()

public String getMainPythonFileUri()

Required. The HCFS URI of the main Python file to use as the driver. Must be a .py file.

string main_python_file_uri = 1 [(.google.api.field_behavior) = REQUIRED];

Returns
Type Description
String

The mainPythonFileUri.

getMainPythonFileUriBytes()

public ByteString getMainPythonFileUriBytes()

Required. The HCFS URI of the main Python file to use as the driver. Must be a .py file.

string main_python_file_uri = 1 [(.google.api.field_behavior) = REQUIRED];

Returns
Type Description
ByteString

The bytes for mainPythonFileUri.

getParserForType()

public Parser<PySparkJob> getParserForType()
Returns
Type Description
Parser<PySparkJob>
Overrides

getProperties() (deprecated)

public Map<String,String> getProperties()

Use #getPropertiesMap() instead.

Returns
Type Description
Map<String,String>

getPropertiesCount()

public int getPropertiesCount()

Optional. A mapping of property names to values, used to configure PySpark. Properties that conflict with values set by the Dataproc API may be overwritten. Can include properties set in /etc/spark/conf/spark-defaults.conf and classes in user code.

map<string, string> properties = 7 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type Description
int

getPropertiesMap()

public Map<String,String> getPropertiesMap()

Optional. A mapping of property names to values, used to configure PySpark. Properties that conflict with values set by the Dataproc API may be overwritten. Can include properties set in /etc/spark/conf/spark-defaults.conf and classes in user code.

map<string, string> properties = 7 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type Description
Map<String,String>

getPropertiesOrDefault(String key, String defaultValue)

public String getPropertiesOrDefault(String key, String defaultValue)

Optional. A mapping of property names to values, used to configure PySpark. Properties that conflict with values set by the Dataproc API may be overwritten. Can include properties set in /etc/spark/conf/spark-defaults.conf and classes in user code.

map<string, string> properties = 7 [(.google.api.field_behavior) = OPTIONAL];

Parameters
Name Description
key String
defaultValue String
Returns
Type Description
String

getPropertiesOrThrow(String key)

public String getPropertiesOrThrow(String key)

Optional. A mapping of property names to values, used to configure PySpark. Properties that conflict with values set by the Dataproc API may be overwritten. Can include properties set in /etc/spark/conf/spark-defaults.conf and classes in user code.

map<string, string> properties = 7 [(.google.api.field_behavior) = OPTIONAL];

Parameter
Name Description
key String
Returns
Type Description
String

getPythonFileUris(int index)

public String getPythonFileUris(int index)

Optional. HCFS file URIs of Python files to pass to the PySpark framework. Supported file types: .py, .egg, and .zip.

repeated string python_file_uris = 3 [(.google.api.field_behavior) = OPTIONAL];

Parameter
Name Description
index int

The index of the element to return.

Returns
Type Description
String

The pythonFileUris at the given index.

getPythonFileUrisBytes(int index)

public ByteString getPythonFileUrisBytes(int index)

Optional. HCFS file URIs of Python files to pass to the PySpark framework. Supported file types: .py, .egg, and .zip.

repeated string python_file_uris = 3 [(.google.api.field_behavior) = OPTIONAL];

Parameter
Name Description
index int

The index of the value to return.

Returns
Type Description
ByteString

The bytes of the pythonFileUris at the given index.

getPythonFileUrisCount()

public int getPythonFileUrisCount()

Optional. HCFS file URIs of Python files to pass to the PySpark framework. Supported file types: .py, .egg, and .zip.

repeated string python_file_uris = 3 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type Description
int

The count of pythonFileUris.

getPythonFileUrisList()

public ProtocolStringList getPythonFileUrisList()

Optional. HCFS file URIs of Python files to pass to the PySpark framework. Supported file types: .py, .egg, and .zip.

repeated string python_file_uris = 3 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type Description
ProtocolStringList

A list containing the pythonFileUris.

getSerializedSize()

public int getSerializedSize()
Returns
Type Description
int
Overrides

hasLoggingConfig()

public boolean hasLoggingConfig()

Optional. The runtime log config for job execution.

.google.cloud.dataproc.v1.LoggingConfig logging_config = 8 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type Description
boolean

Whether the loggingConfig field is set.

hashCode()

public int hashCode()
Returns
Type Description
int
Overrides

internalGetFieldAccessorTable()

protected GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()
Returns
Type Description
FieldAccessorTable
Overrides

internalGetMapFieldReflection(int number)

protected MapFieldReflectionAccessor internalGetMapFieldReflection(int number)
Parameter
Name Description
number int
Returns
Type Description
com.google.protobuf.MapFieldReflectionAccessor
Overrides
com.google.protobuf.GeneratedMessageV3.internalGetMapFieldReflection(int)

isInitialized()

public final boolean isInitialized()
Returns
Type Description
boolean
Overrides

newBuilderForType()

public PySparkJob.Builder newBuilderForType()
Returns
Type Description
PySparkJob.Builder

newBuilderForType(GeneratedMessageV3.BuilderParent parent)

protected PySparkJob.Builder newBuilderForType(GeneratedMessageV3.BuilderParent parent)
Parameter
Name Description
parent BuilderParent
Returns
Type Description
PySparkJob.Builder
Overrides

newInstance(GeneratedMessageV3.UnusedPrivateParameter unused)

protected Object newInstance(GeneratedMessageV3.UnusedPrivateParameter unused)
Parameter
Name Description
unused UnusedPrivateParameter
Returns
Type Description
Object
Overrides

toBuilder()

public PySparkJob.Builder toBuilder()
Returns
Type Description
PySparkJob.Builder

writeTo(CodedOutputStream output)

public void writeTo(CodedOutputStream output)
Parameter
Name Description
output CodedOutputStream
Overrides
Exceptions
Type Description
IOException