LuceneRDD

final def !=(arg0: Any): Boolean

final def ##(): Int

def ++(other: RDD[T]): RDD[T]

final def ==(arg0: Any): Boolean

val DefaultFacetNum: Int

val DefaultTopK: Int

Default value for topK queries

val MaxDefaultTopKValue: Int

val SparkDocTopKMonoid: TopKMonoid[SparkScoreDoc]

def aggregate[U](zeroValue: U)(seqOp: (U, T) ⇒ U, combOp: (U, U) ⇒ U)(implicit arg0: ClassTag[U]): U

final def asInstanceOf[T0]: T0

def cache(): LuceneRDD.this.type

def cartesian[U](other: RDD[U])(implicit arg0: ClassTag[U]): RDD[(T, U)]

def checkpoint(): Unit

def clearDependencies(): Unit

def clone(): AnyRef

def close(): Unit

def coalesce(numPartitions: Int, shuffle: Boolean)(implicit ord: Ordering[T]): RDD[T]

def collect[U](f: PartialFunction[T, U])(implicit arg0: ClassTag[U]): RDD[U]

def collect(): Array[T]

def compute(part: Partition, context: TaskContext): Iterator[T]

RDD compute method.

val config: Config

def context: SparkContext

def count(): Long

def countApprox(timeout: Long, confidence: Double): PartialResult[BoundedDouble]

def countApproxDistinct(relativeSD: Double): Long

def countApproxDistinct(p: Int, sp: Int): Long

def countByValue()(implicit ord: Ordering[T]): Map[T, Long]

def countByValueApprox(timeout: Long, confidence: Double)(implicit ord: Ordering[T]): PartialResult[Map[T, BoundedDouble]]

final def dependencies: Seq[Dependency[_]]

def distinct(): RDD[T]

def distinct(numPartitions: Int)(implicit ord: Ordering[T]): RDD[T]

final def eq(arg0: AnyRef): Boolean

def equals(arg0: Any): Boolean

def exists(elem: T): Boolean

def exists(doc: Map[String, String]): Boolean

Lucene generic query

def facetQueries(searchString: String, facetFields: Seq[String], topK: Int = DefaultTopK, facetNum: Int = DefaultFacetNum): (Iterable[SparkScoreDoc], Map[String, SparkFacetResult])

Faceted query with multiple facets

def facetQuery(searchString: String, facetField: String, topK: Int = DefaultTopK, facetNum: Int = DefaultFacetNum): (Iterable[SparkScoreDoc], SparkFacetResult)

Faceted query

def fields(): Set[String]

Return all document fields

def filter(pred: (T) ⇒ Boolean): LuceneRDD[T]

def finalize(): Unit

def first(): T

def firstParent[U](implicit arg0: ClassTag[U]): RDD[U]

def flatMap[U](f: (T) ⇒ TraversableOnce[U])(implicit arg0: ClassTag[U]): RDD[U]

def fold(zeroValue: T)(op: (T, T) ⇒ T): T

def foreach(f: (T) ⇒ Unit): Unit

def foreachPartition(f: (Iterator[T]) ⇒ Unit): Unit

def fuzzyQuery(fieldName: String, query: String, maxEdits: Int, topK: Int = DefaultTopK): Iterable[SparkScoreDoc]

Lucene fuzzy query

def getCheckpointFile: Option[String]

final def getClass(): Class[_]

def getDependencies: Seq[Dependency[_]]

final def getNumPartitions: Int

def getPartitions: Array[Partition]

def getPreferredLocations(s: Partition): Seq[String]

def getStorageLevel: StorageLevel

def glom(): RDD[Array[T]]

def groupBy[K](f: (T) ⇒ K, p: Partitioner)(implicit kt: ClassTag[K], ord: Ordering[K]): RDD[(K, Iterable[T])]

def groupBy[K](f: (T) ⇒ K, numPartitions: Int)(implicit kt: ClassTag[K]): RDD[(K, Iterable[T])]

def groupBy[K](f: (T) ⇒ K)(implicit kt: ClassTag[K]): RDD[(K, Iterable[T])]

def hashCode(): Int

val id: Int

def intersection(other: RDD[T], numPartitions: Int): RDD[T]

def intersection(other: RDD[T], partitioner: Partitioner)(implicit ord: Ordering[T]): RDD[T]

def intersection(other: RDD[T]): RDD[T]

def isCheckpointed: Boolean

def isEmpty(): Boolean

final def isInstanceOf[T0]: Boolean

def isTraceEnabled(): Boolean

final def iterator(split: Partition, context: TaskContext): Iterator[T]

def keyBy[K](f: (T) ⇒ K): RDD[(K, T)]

def link[T1](other: RDD[T1], searchQueryGen: (T1) ⇒ String, topK: Int = DefaultTopK)(implicit arg0: ClassTag[T1]): RDD[(T1, List[SparkScoreDoc])]

Entity linkage via Lucene query over all elements of an RDD.

def linkByQuery[T1](other: RDD[T1], searchQueryGen: (T1) ⇒ Query, topK: Int = DefaultTopK)(implicit arg0: ClassTag[T1]): RDD[(T1, List[SparkScoreDoc])]

Entity linkage via Lucene query over all elements of an RDD.

def linkDataFrame(other: DataFrame, searchQueryGen: (Row) ⇒ String, topK: Int = DefaultTopK): RDD[(Row, List[SparkScoreDoc])]

Entity linkage via Lucene query over all elements of an RDD.

def localCheckpoint(): LuceneRDD.this.type

def log: Logger

def logDebug(msg: ⇒ String, throwable: Throwable): Unit

def logDebug(msg: ⇒ String): Unit

def logError(msg: ⇒ String, throwable: Throwable): Unit

def logError(msg: ⇒ String): Unit

def logInfo(msg: ⇒ String, throwable: Throwable): Unit

def logInfo(msg: ⇒ String): Unit

def logName: String

def logTrace(msg: ⇒ String, throwable: Throwable): Unit

def logTrace(msg: ⇒ String): Unit

def logWarning(msg: ⇒ String, throwable: Throwable): Unit

def logWarning(msg: ⇒ String): Unit

def map[U](f: (T) ⇒ U)(implicit arg0: ClassTag[U]): RDD[U]

def mapPartitions[U](f: (Iterator[T]) ⇒ Iterator[U], preservesPartitioning: Boolean)(implicit arg0: ClassTag[U]): RDD[U]

def mapPartitionsWithIndex[U](f: (Int, Iterator[T]) ⇒ Iterator[U], preservesPartitioning: Boolean)(implicit arg0: ClassTag[U]): RDD[U]

def max()(implicit ord: Ordering[T]): T

def min()(implicit ord: Ordering[T]): T

var name: String

final def ne(arg0: AnyRef): Boolean

final def notify(): Unit

final def notifyAll(): Unit

def parent[U](j: Int)(implicit arg0: ClassTag[U]): RDD[U]

val partitioner: Option[Partitioner]

final def partitions: Array[Partition]

val partitionsRDD: RDD[AbstractLuceneRDDPartition[T]]

def persist(newLevel: StorageLevel): LuceneRDD.this.type

def persist(): LuceneRDD.this.type

def phraseQuery(fieldName: String, query: String, topK: Int = DefaultTopK): Iterable[SparkScoreDoc]

Lucene phrase Query

def pipe(command: Seq[String], env: Map[String, String], printPipeContext: ((String) ⇒ Unit) ⇒ Unit, printRDDElement: (T, (String) ⇒ Unit) ⇒ Unit, separateWorkingDir: Boolean): RDD[String]

def pipe(command: String, env: Map[String, String]): RDD[String]

def pipe(command: String): RDD[String]

final def preferredLocations(split: Partition): Seq[String]

def prefixQuery(fieldName: String, query: String, topK: Int = DefaultTopK): Iterable[SparkScoreDoc]

Lucene prefix query

def query(searchString: String, topK: Int = DefaultTopK): Iterable[SparkScoreDoc]

Generic query using Lucene's query parser

def randomSplit(weights: Array[Double], seed: Long): Array[RDD[T]]

def reduce(f: (T, T) ⇒ T): T

def repartition(numPartitions: Int)(implicit ord: Ordering[T]): RDD[T]

def sample(withReplacement: Boolean, fraction: Double, seed: Long): RDD[T]

def saveAsObjectFile(path: String): Unit

def saveAsTextFile(path: String, codec: Class[_ <: CompressionCodec]): Unit

def saveAsTextFile(path: String): Unit

def setName(_name: String): LuceneRDD.this.type

Set the name for the RDD; By default set to "LuceneRDD"

def sortBy[K](f: (T) ⇒ K, ascending: Boolean, numPartitions: Int)(implicit ord: Ordering[K], ctag: ClassTag[K]): RDD[T]

def sparkContext: SparkContext

def subtract(other: RDD[T], p: Partitioner)(implicit ord: Ordering[T]): RDD[T]

def subtract(other: RDD[T], numPartitions: Int): RDD[T]

def subtract(other: RDD[T]): RDD[T]

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

def take(num: Int): Array[T]

def takeOrdered(num: Int)(implicit ord: Ordering[T]): Array[T]

def takeSample(withReplacement: Boolean, num: Int, seed: Long): Array[T]

def termQuery(fieldName: String, query: String, topK: Int = DefaultTopK): Iterable[SparkScoreDoc]

Lucene term query

def toDebugString: String

def toJavaRDD(): JavaRDD[T]

def toLocalIterator: Iterator[T]

def toString(): String

def top(num: Int)(implicit ord: Ordering[T]): Array[T]

def treeAggregate[U](zeroValue: U)(seqOp: (U, T) ⇒ U, combOp: (U, U) ⇒ U, depth: Int)(implicit arg0: ClassTag[U]): U

def treeReduce(f: (T, T) ⇒ T, depth: Int): T

def union(other: RDD[T]): RDD[T]

def unpersist(blocking: Boolean = true): LuceneRDD.this.type

final def wait(): Unit

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

final def wait(arg0: Long): Unit

def zip[U](other: RDD[U])(implicit arg0: ClassTag[U]): RDD[(T, U)]

def zipPartitions[B, C, D, V](rdd2: RDD[B], rdd3: RDD[C], rdd4: RDD[D])(f: (Iterator[T], Iterator[B], Iterator[C], Iterator[D]) ⇒ Iterator[V])(implicit arg0: ClassTag[B], arg1: ClassTag[C], arg2: ClassTag[D], arg3: ClassTag[V]): RDD[V]

def zipPartitions[B, C, D, V](rdd2: RDD[B], rdd3: RDD[C], rdd4: RDD[D], preservesPartitioning: Boolean)(f: (Iterator[T], Iterator[B], Iterator[C], Iterator[D]) ⇒ Iterator[V])(implicit arg0: ClassTag[B], arg1: ClassTag[C], arg2: ClassTag[D], arg3: ClassTag[V]): RDD[V]

def zipPartitions[B, C, V](rdd2: RDD[B], rdd3: RDD[C])(f: (Iterator[T], Iterator[B], Iterator[C]) ⇒ Iterator[V])(implicit arg0: ClassTag[B], arg1: ClassTag[C], arg2: ClassTag[V]): RDD[V]

def zipPartitions[B, C, V](rdd2: RDD[B], rdd3: RDD[C], preservesPartitioning: Boolean)(f: (Iterator[T], Iterator[B], Iterator[C]) ⇒ Iterator[V])(implicit arg0: ClassTag[B], arg1: ClassTag[C], arg2: ClassTag[V]): RDD[V]

def zipPartitions[B, V](rdd2: RDD[B])(f: (Iterator[T], Iterator[B]) ⇒ Iterator[V])(implicit arg0: ClassTag[B], arg1: ClassTag[V]): RDD[V]

def zipPartitions[B, V](rdd2: RDD[B], preservesPartitioning: Boolean)(f: (Iterator[T], Iterator[B]) ⇒ Iterator[V])(implicit arg0: ClassTag[B], arg1: ClassTag[V]): RDD[V]

def zipWithIndex(): RDD[(T, Long)]

def zipWithUniqueId(): RDD[(T, Long)]

def filterWith[A](constructA: (Int) ⇒ A)(p: (T, A) ⇒ Boolean): RDD[T]

def flatMapWith[A, U](constructA: (Int) ⇒ A, preservesPartitioning: Boolean)(f: (T, A) ⇒ Seq[U])(implicit arg0: ClassTag[U]): RDD[U]

def foreachWith[A](constructA: (Int) ⇒ A)(f: (T, A) ⇒ Unit): Unit

def mapPartitionsWithContext[U](f: (TaskContext, Iterator[T]) ⇒ Iterator[U], preservesPartitioning: Boolean)(implicit arg0: ClassTag[U]): RDD[U]

def mapPartitionsWithSplit[U](f: (Int, Iterator[T]) ⇒ Iterator[U], preservesPartitioning: Boolean)(implicit arg0: ClassTag[U]): RDD[U]

def mapWith[A, U](constructA: (Int) ⇒ A, preservesPartitioning: Boolean)(f: (T, A) ⇒ U)(implicit arg0: ClassTag[U]): RDD[U]

def toArray(): Array[T]