MongoSpark

Instance Constructors

new MongoSpark(sparkSession: SparkSession, connector: MongoConnector, readConfig: ReadConfig, pipeline: Seq[BsonDocument])

Value Members

final def !=(arg0: Any): Boolean

Definition Classes
AnyRef → Any
final def ##(): Int

Definition Classes
AnyRef → Any
final def ==(arg0: Any): Boolean

Definition Classes
AnyRef → Any
final def asInstanceOf[T0]: T0

Definition Classes
Any
def clone(): AnyRef

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( ... )
val connector: MongoConnector
final def eq(arg0: AnyRef): Boolean

Definition Classes
AnyRef
def finalize(): Unit

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( classOf[java.lang.Throwable] )
final def getClass(): Class[_]

Definition Classes
AnyRef → Any
final def isInstanceOf[T0]: Boolean

Definition Classes
Any
final def ne(arg0: AnyRef): Boolean

Definition Classes
AnyRef
final def notify(): Unit

Definition Classes
AnyRef
final def notifyAll(): Unit

Definition Classes
AnyRef
val pipeline: Seq[BsonDocument]
val readConfig: ReadConfig
val sparkSession: SparkSession
final def synchronized[T0](arg0: ⇒ T0): T0

Definition Classes
AnyRef
def toDF(schema: StructType): DataFrame

Creates a DataFrame based on the provided schema.
Creates a DataFrame based on the provided schema.
schema
the schema representing the DataFrame.
returns
a DataFrame.
def toDF[T](beanClass: Class[T]): DataFrame

Creates a DataFrame based on the schema derived from the bean class.
Creates a DataFrame based on the schema derived from the bean class.
Note: Prefer toDS[T](beanClass:Class[T])* as computations will be more efficient.
T
The bean class type to shape the data from MongoDB into
beanClass
encapsulating the data from MongoDB
returns
a DataFrame
def toDF[T <: Product]()(implicit arg0: scala.reflect.api.JavaUniverse.TypeTag[T]): DataFrame

Creates a DataFrame based on the schema derived from the optional type.
Creates a DataFrame based on the schema derived from the optional type.
Note: Prefer toDS[T<:Product]()* as computations will be more efficient. The rdd must contain an _id for MongoDB versions < 3.2.
T
The optional type of the data from MongoDB, if not provided the schema will be inferred from the collection
returns
a DataFrame
def toDS[T](beanClass: Class[T]): Dataset[T]

Creates a Dataset from the RDD strongly typed to the provided java bean.
Creates a Dataset from the RDD strongly typed to the provided java bean.
T
The type of the data from MongoDB
def toDS[T <: Product]()(implicit arg0: scala.reflect.api.JavaUniverse.TypeTag[T], arg1: NotNothing[T]): Dataset[T]

Creates a Dataset from the collection strongly typed to the provided case class.
Creates a Dataset from the collection strongly typed to the provided case class.
T
The type of the data from MongoDB
def toJavaRDD[D](clazz: Class[D]): JavaMongoRDD[D]

Creates a JavaRDD for the collection
Creates a JavaRDD for the collection
D
the type of the data in the RDD
clazz
the class of the data contained in the RDD
returns
the javaRDD
def toJavaRDD(): JavaMongoRDD[Document]

Creates a JavaRDD for the collection
Creates a JavaRDD for the collection
returns
a JavaMongoRDD[Document]
def toRDD[D]()(implicit arg0: ClassTag[D], e: DefaultsTo[D, Document]): MongoRDD[D]

Creates a RDD for the collection
Creates a RDD for the collection
D
the datatype for the collection
returns
a MongoRDD[D]
final def wait(): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
final def wait(arg0: Long, arg1: Int): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
final def wait(arg0: Long): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )

Related Docs: object MongoSpark | package spark

case class MongoSpark(sparkSession: SparkSession, connector: MongoConnector, readConfig: ReadConfig, pipeline: Seq[BsonDocument]) extends Product with Serializable

Instance Constructors

new MongoSpark(sparkSession: SparkSession, connector: MongoConnector, readConfig: ReadConfig, pipeline: Seq[BsonDocument])

Value Members

final def !=(arg0: Any): Boolean

final def ##(): Int

final def ==(arg0: Any): Boolean

final def asInstanceOf[T0]: T0

def clone(): AnyRef

val connector: MongoConnector

final def eq(arg0: AnyRef): Boolean

def finalize(): Unit

final def getClass(): Class[_]

final def isInstanceOf[T0]: Boolean

final def ne(arg0: AnyRef): Boolean

final def notify(): Unit

final def notifyAll(): Unit

val pipeline: Seq[BsonDocument]

val readConfig: ReadConfig

val sparkSession: SparkSession

final def synchronized[T0](arg0: ⇒ T0): T0

def toDF(schema: StructType): DataFrame

def toDF[T](beanClass: Class[T]): DataFrame

def toDF[T <: Product]()(implicit arg0: scala.reflect.api.JavaUniverse.TypeTag[T]): DataFrame

def toDS[T](beanClass: Class[T]): Dataset[T]

def toDS[T <: Product]()(implicit arg0: scala.reflect.api.JavaUniverse.TypeTag[T], arg1: NotNothing[T]): Dataset[T]

def toJavaRDD[D](clazz: Class[D]): JavaMongoRDD[D]

def toJavaRDD(): JavaMongoRDD[Document]

def toRDD[D]()(implicit arg0: ClassTag[D], e: DefaultsTo[D, Document]): MongoRDD[D]

final def wait(): Unit

final def wait(arg0: Long, arg1: Int): Unit

final def wait(arg0: Long): Unit

Inherited from Serializable

Inherited from Serializable

Inherited from Product

Inherited from Equals

Inherited from AnyRef

Inherited from Any

Ungrouped