connector

The root package of Cassandra connector for Apache Spark. Offers handy implicit conversions that add Cassandra-specific methods to SparkContext and RDD.

Call cassandraTable method on the SparkContext object to create a CassandraRDD exposing Cassandra tables as Spark RDDs.

Call RDDFunctions saveToCassandra function on any RDD to save distributed collection to a Cassandra table.

Example:

CREATE KEYSPACE test WITH replication = {'class': 'SimpleStrategy', 'replication_factor': 1 };
CREATE TABLE test.words (word text PRIMARY KEY, count int);
INSERT INTO test.words(word, count) VALUES ("and", 50);

import com.datastax.spark.connector._

val sparkMasterHost = "127.0.0.1"
val cassandraHost = "127.0.0.1"
val keyspace = "test"
val table = "words"

// Tell Spark the address of one Cassandra node:
val conf = new SparkConf(true).set("spark.cassandra.connection.host", cassandraHost)

// Connect to the Spark cluster:
val sc = new SparkContext("spark://" + sparkMasterHost + ":7077", "example", conf)

// Read the table and print its contents:
val rdd = sc.cassandraTable(keyspace, table)
rdd.toArray().foreach(println)

// Write two rows to the table:
val col = sc.parallelize(Seq(("of", 1200), ("the", "863")))
col.saveToCassandra(keyspace, table)

sc.stop()

Linear Supertypes

AnyRef, Any

Type Members

trait AbstractGettableData extends AnyRef
sealed trait BatchSize extends AnyRef
case class BytesInBatch(batchSize: Int) extends BatchSize with Product with Serializable
final class CassandraRow extends ScalaGettableData with Serializable

Represents a single row fetched from Cassandra.
case class ColumnIndex(columnIndex: Int) extends ColumnRef with Product with Serializable

References a column by its index in the row.
case class ColumnName(columnName: String, alias: Option[String] = scala.None) extends NamedColumnRef with Product with Serializable

References a column by name.
implicit final class ColumnNameFunctions extends AnyVal
class ColumnNotFoundException extends Exception

Thrown when the requested column does not exist in the result set.
sealed trait ColumnRef extends AnyRef

Unambiguous reference to a column in the query result set row.
sealed trait ColumnSelector extends AnyRef
sealed trait NamedColumnRef extends SelectableColumnRef

A selectable column based on a real, non-virtual column with a name in the table
class PairRDDFunctions[K, V] extends Serializable
class RDDFunctions[T] extends WritableToCassandra[T] with Serializable

Provides Cassandra-specific methods on RDD
case class RowsInBatch(batchSize: Int) extends BatchSize with Product with Serializable
trait ScalaGettableData extends AbstractGettableData
sealed trait SelectableColumnRef extends ColumnRef

A column that can be selected from CQL results set by name
case class SomeColumns(columns: SelectableColumnRef*) extends ColumnSelector with Product with Serializable
class SparkContextFunctions extends Serializable

Provides Cassandra-specific methods on SparkContext
case class TTL(columnName: String, alias: Option[String] = scala.None) extends NamedColumnRef with Product with Serializable
final class UDTValue extends ScalaGettableData with Serializable
case class WriteTime(columnName: String, alias: Option[String] = scala.None) extends NamedColumnRef with Product with Serializable

Value Members

object AbstractGettableData
object AllColumns extends ColumnSelector with Product with Serializable
object BatchSize
object CassandraRow extends Serializable
object NamedColumnRef
object PartitionKeyColumns extends ColumnSelector with Product with Serializable
object RowCountRef extends SelectableColumnRef with Product with Serializable
object SelectableColumnRef
object SomeColumns extends Serializable
object UDTValue extends Serializable
package cql

Contains a cql.CassandraConnector object which is used to connect to a Cassandra cluster and to send CQL statements to it.
package mapper

Provides machinery for mapping Cassandra tables to user defined Scala classes or tuples.
package metrics
package rdd

Contains com.datastax.spark.connector.rdd.CassandraTableScanRDD class that is the main entry point for analyzing Cassandra data from Spark.
package streaming
implicit def toNamedColumnRef(columnName: String): ColumnName
implicit def toPairRDDFunctions[K, V](rdd: RDD[(K, V)]): PairRDDFunctions[K, V]
implicit def toRDDFunctions[T](rdd: RDD[T]): RDDFunctions[T]
implicit def toSparkContextFunctions(sc: SparkContext): SparkContextFunctions
package types

Offers type conversion magic, so you can receive Cassandra column values in a form you like the most.
package util

Useful stuff that didn't fit elsewhere.
package writer

Contains components for writing RDDs to Cassandra

package connector

Type Members

trait AbstractGettableData extends AnyRef

sealed trait BatchSize extends AnyRef

case class BytesInBatch(batchSize: Int) extends BatchSize with Product with Serializable

final class CassandraRow extends ScalaGettableData with Serializable

case class ColumnIndex(columnIndex: Int) extends ColumnRef with Product with Serializable

case class ColumnName(columnName: String, alias: Option[String] = scala.None) extends NamedColumnRef with Product with Serializable

implicit final class ColumnNameFunctions extends AnyVal

class ColumnNotFoundException extends Exception

sealed trait ColumnRef extends AnyRef

sealed trait ColumnSelector extends AnyRef

sealed trait NamedColumnRef extends SelectableColumnRef

class PairRDDFunctions[K, V] extends Serializable

class RDDFunctions[T] extends WritableToCassandra[T] with Serializable

case class RowsInBatch(batchSize: Int) extends BatchSize with Product with Serializable

trait ScalaGettableData extends AbstractGettableData

sealed trait SelectableColumnRef extends ColumnRef

case class SomeColumns(columns: SelectableColumnRef*) extends ColumnSelector with Product with Serializable

class SparkContextFunctions extends Serializable

case class TTL(columnName: String, alias: Option[String] = scala.None) extends NamedColumnRef with Product with Serializable

final class UDTValue extends ScalaGettableData with Serializable

case class WriteTime(columnName: String, alias: Option[String] = scala.None) extends NamedColumnRef with Product with Serializable

Value Members

object AbstractGettableData

object AllColumns extends ColumnSelector with Product with Serializable

object BatchSize

object CassandraRow extends Serializable

object NamedColumnRef

object PartitionKeyColumns extends ColumnSelector with Product with Serializable

object RowCountRef extends SelectableColumnRef with Product with Serializable

object SelectableColumnRef

object SomeColumns extends Serializable

object UDTValue extends Serializable

package cql

package mapper

package metrics

package rdd

package streaming

implicit def toNamedColumnRef(columnName: String): ColumnName

implicit def toPairRDDFunctions[K, V](rdd: RDD[(K, V)]): PairRDDFunctions[K, V]

implicit def toRDDFunctions[T](rdd: RDD[T]): RDDFunctions[T]

implicit def toSparkContextFunctions(sc: SparkContext): SparkContextFunctions

package types

package util

package writer

Inherited from AnyRef

Inherited from Any

Ungrouped