FacetedLuceneRDD

Value Members

1. final def !=(arg0: Any): Boolean

   

   Definition Classes

   AnyRef → Any

2. final def ##(): Int

   

   Definition Classes

   AnyRef → Any

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

   

   Definition Classes

   RDD

4. final def ==(arg0: Any): Boolean

   

   Definition Classes

   AnyRef → Any

5. val DefaultFacetNum: Int

   

   Attributes

   protected

   Definition Classes

   LuceneRDDConfigurable

6. val DefaultTopK: Int

   

   Default value for topK queries

   Default value for topK queries

   Attributes

   protected

   Definition Classes

   LuceneRDDConfigurable

7. val MaxDefaultTopKValue: Int

   

   Attributes

   protected

   Definition Classes

   LuceneRDDConfigurable

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

   

   Definition Classes

   RDD

9. final def asInstanceOf[T0]: T0

   

   Definition Classes

   Any

10. def cache(): FacetedLuceneRDD.this.type

    

    Definition Classes

    FacetedLuceneRDD → LuceneRDD → RDD

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

    

    Definition Classes

    RDD

12. def checkpoint(): Unit

    

    Definition Classes

    RDD

13. def clearDependencies(): Unit

    

    Attributes

    protected

    Definition Classes

    RDD

14. def clone(): AnyRef

    

    Attributes

    protected[java.lang]

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )

15. def close(): Unit

    

    Definition Classes

    LuceneRDD

16. def coalesce(numPartitions: Int, shuffle: Boolean, partitionCoalescer: Option[PartitionCoalescer])(implicit ord: Ordering[T]): RDD[T]

    

    Definition Classes

    RDD

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

    

    Definition Classes

    RDD

18. def collect(): Array[T]

    

    Definition Classes

    RDD

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

    

    RDD compute method.

    RDD compute method.

    Definition Classes

    LuceneRDD → RDD

20. val config: Config

    

    Definition Classes

    Configurable

21. def context: SparkContext

    

    Definition Classes

    RDD

22. def count(): Long

    

    Definition Classes

    LuceneRDD → RDD

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

    

    Definition Classes

    RDD

24. def countApproxDistinct(relativeSD: Double): Long

    

    Definition Classes

    RDD

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

    

    Definition Classes

    RDD

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

    

    Definition Classes

    RDD

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

    

    Definition Classes

    RDD

28. def dedup[T1](searchQueryGen: (T1) ⇒ String, topK: Int = DefaultTopK)(implicit arg0: ClassTag[T1]): RDD[(T1, Array[SparkScoreDoc])]

    

    Deduplication of self

    Deduplication of self

    searchQueryGen

    Search query mapper function

    topK

    Number of results to deduplication

    Definition Classes

    LuceneRDD

29. final def dependencies: Seq[Dependency[_]]

    

    Definition Classes

    RDD

30. def distinct(): RDD[T]

    

    Definition Classes

    RDD

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

    

    Definition Classes

    RDD

32. final def eq(arg0: AnyRef): Boolean

    

    Definition Classes

    AnyRef

33. def equals(arg0: Any): Boolean

    

    Definition Classes

    AnyRef → Any

34. def exists(elem: T): Boolean

    

    Definition Classes

    LuceneRDD

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

    

    Lucene generic query

    Lucene generic query

    Definition Classes

    LuceneRDD

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

    

    Faceted query with multiple facets

    Faceted query with multiple facets

    searchString

    Lucene query string

    facetFields

    Fields on which to compute facets

    topK

    Number of results

    facetNum

    Number of faceted results

37. def facetQuery(searchString: String, facetField: String, topK: Int = DefaultTopK, facetNum: Int = DefaultFacetNum): (LuceneRDDResponse, SparkFacetResult)

    

    Faceted query

    Faceted query

    searchString

    Lucene query string

    facetField

    Field on which to compute facet

    topK

    Number of results

    facetNum

    Number of faceted results

38. def fields(): Set[String]

    

    Return all document fields

    Return all document fields

    Definition Classes

    LuceneRDD

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

    

    Definition Classes

    LuceneRDD → RDD

40. def finalize(): Unit

    

    Attributes

    protected[java.lang]

    Definition Classes

    AnyRef

    Annotations

    @throws( classOf[java.lang.Throwable] )

41. def first(): T

    

    Definition Classes

    RDD

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

    

    Attributes

    protected[org.apache.spark]

    Definition Classes

    RDD

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

    

    Definition Classes

    RDD

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

    

    Definition Classes

    RDD

45. def foreach(f: (T) ⇒ Unit): Unit

    

    Definition Classes

    RDD

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

    

    Definition Classes

    RDD

47. def fuzzyQuery(fieldName: String, query: String, maxEdits: Int, topK: Int = DefaultTopK): LuceneRDDResponse

    

    Lucene fuzzy query

    Lucene fuzzy query

    fieldName

    Name of field

    query

    Query text

    maxEdits

    Fuzziness, edit distance

    topK

    Number of documents to return

    Definition Classes

    LuceneRDD

48. def getCheckpointFile: Option[String]

    

    Definition Classes

    RDD

49. final def getClass(): Class[_]

    

    Definition Classes

    AnyRef → Any

50. def getDependencies: Seq[Dependency[_]]

    

    Attributes

    protected

    Definition Classes

    RDD

51. final def getNumPartitions: Int

    

    Definition Classes

    RDD

    Annotations

    @Since( "1.6.0" )

52. def getPartitions: Array[Partition]

    

    Attributes

    protected

    Definition Classes

    LuceneRDD → RDD

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

    

    Attributes

    protected

    Definition Classes

    LuceneRDD → RDD

54. def getStorageLevel: StorageLevel

    

    Definition Classes

    RDD

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

    

    Definition Classes

    RDD

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

    

    Definition Classes

    RDD

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

    

    Definition Classes

    RDD

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

    

    Definition Classes

    RDD

59. def hashCode(): Int

    

    Definition Classes

    AnyRef → Any

60. val id: Int

    

    Definition Classes

    RDD

61. def initializeLogIfNecessary(isInterpreter: Boolean): Unit

    

    Attributes

    protected

    Definition Classes

    Logging

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

    

    Definition Classes

    RDD

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

    

    Definition Classes

    RDD

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

    

    Definition Classes

    RDD

65. def isCheckpointed: Boolean

    

    Definition Classes

    RDD

66. def isEmpty(): Boolean

    

    Definition Classes

    RDD

67. final def isInstanceOf[T0]: Boolean

    

    Definition Classes

    Any

68. def isTraceEnabled(): Boolean

    

    Attributes

    protected

    Definition Classes

    Logging

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

    

    Definition Classes

    RDD

70. def keyBy[K](f: (T) ⇒ K): RDD[(K, T)]

    

    Definition Classes

    RDD

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

    

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

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

    T1

    A type

    other

    RDD to be linked

    searchQueryGen

    Function that generates a search query for each element of other

    returns

    an RDD of Tuple2 that contains the linked search Lucene documents in the second Note: Currently the query strings of the other RDD are collected to the driver and broadcast to the workers.

    Definition Classes

    LuceneRDD

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

    

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

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

    T1

    A type

    other

    RDD to be linked

    searchQueryGen

    Function that generates a Lucene Query object for each element of other

    returns

    an RDD of Tuple2 that contains the linked search Lucene Document in the second position

    Definition Classes

    LuceneRDD

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

    

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

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

    other

    DataFrame to be linked

    searchQueryGen

    Function that generates a search query for each element of other

    returns

    an RDD of Tuple2 that contains the linked search Lucene documents in the second

    Definition Classes

    LuceneRDD

74. def localCheckpoint(): FacetedLuceneRDD.this.type

    

    Definition Classes

    RDD

75. def log: Logger

    

    Attributes

    protected

    Definition Classes

    Logging

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

    

    Attributes

    protected

    Definition Classes

    Logging

77. def logDebug(msg: ⇒ String): Unit

    

    Attributes

    protected

    Definition Classes

    Logging

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

    

    Attributes

    protected

    Definition Classes

    Logging

79. def logError(msg: ⇒ String): Unit

    

    Attributes

    protected

    Definition Classes

    Logging

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

    

    Attributes

    protected

    Definition Classes

    Logging

81. def logInfo(msg: ⇒ String): Unit

    

    Attributes

    protected

    Definition Classes

    Logging

82. def logName: String

    

    Attributes

    protected

    Definition Classes

    Logging

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

    

    Attributes

    protected

    Definition Classes

    Logging

84. def logTrace(msg: ⇒ String): Unit

    

    Attributes

    protected

    Definition Classes

    Logging

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

    

    Attributes

    protected

    Definition Classes

    Logging

86. def logWarning(msg: ⇒ String): Unit

    

    Attributes

    protected

    Definition Classes

    Logging

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

    

    Definition Classes

    RDD

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

    

    Definition Classes

    RDD

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

    

    Definition Classes

    RDD

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

    

    Definition Classes

    RDD

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

    

    Definition Classes

    RDD

92. var name: String

    

    Definition Classes

    RDD

93. final def ne(arg0: AnyRef): Boolean

    

    Definition Classes

    AnyRef

94. final def notify(): Unit

    

    Definition Classes

    AnyRef

95. final def notifyAll(): Unit

    

    Definition Classes

    AnyRef

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

    

    Attributes

    protected[org.apache.spark]

    Definition Classes

    RDD

97. def partitionMapper(f: (AbstractLuceneRDDPartition[T]) ⇒ LuceneRDDResponsePartition, k: Int): LuceneRDDResponse

    

    Maps partition results

    Maps partition results

    f

    Function to apply on each partition / distributed index

    k

    number of documents to return

    Attributes

    protected

    Definition Classes

    LuceneRDD

98. val partitioner: Option[Partitioner]

    

    Definition Classes

    RDD

99. final def partitions: Array[Partition]

    

    Definition Classes

    RDD

100. val partitionsRDD: RDD[AbstractLuceneRDDPartition[T]]

     

     Attributes

     protected

     Definition Classes

     FacetedLuceneRDD → LuceneRDD

101. def persist(newLevel: StorageLevel): FacetedLuceneRDD.this.type

     

     Definition Classes

     FacetedLuceneRDD → LuceneRDD → RDD

102. def persist(): FacetedLuceneRDD.this.type

     

     Definition Classes

     RDD

103. def phraseQuery(fieldName: String, query: String, topK: Int = DefaultTopK): LuceneRDDResponse

     

     Lucene phrase Query

     Lucene phrase Query

     fieldName

     Name of field

     query

     Query text

     topK

     Number of documents to return

     Definition Classes

     LuceneRDD

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

     

     Definition Classes

     RDD

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

     

     Definition Classes

     RDD

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

     

     Definition Classes

     RDD

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

     

     Definition Classes

     RDD

108. def prefixQuery(fieldName: String, query: String, topK: Int = DefaultTopK): LuceneRDDResponse

     

     Lucene prefix query

     Lucene prefix query

     fieldName

     Name of field

     query

     Prefix query text

     topK

     Number of documents to return

     Definition Classes

     LuceneRDD

109. def query(searchString: String, topK: Int = DefaultTopK): LuceneRDDResponse

     

     Generic query using Lucene's query parser

     Generic query using Lucene's query parser

     searchString

     Query String

     Definition Classes

     LuceneRDD

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

     

     Definition Classes

     RDD

111. def reduce(f: (T, T) ⇒ T): T

     

     Definition Classes

     RDD

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

     

     Definition Classes

     RDD

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

     

     Definition Classes

     RDD

114. def saveAsObjectFile(path: String): Unit

     

     Definition Classes

     RDD

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

     

     Definition Classes

     RDD

116. def saveAsTextFile(path: String): Unit

     

     Definition Classes

     RDD

117. def setName(_name: String): FacetedLuceneRDD.this.type

     

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

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

     Definition Classes

     LuceneRDD → RDD

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

     

     Definition Classes

     RDD

119. def sparkContext: SparkContext

     

     Definition Classes

     RDD

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

     

     Definition Classes

     RDD

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

     

     Definition Classes

     RDD

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

     

     Definition Classes

     RDD

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

     

     Definition Classes

     AnyRef

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

     

     Definition Classes

     RDD

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

     

     Definition Classes

     RDD

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

     

     Definition Classes

     RDD

127. def termQuery(fieldName: String, query: String, topK: Int = DefaultTopK): LuceneRDDResponse

     

     Lucene term query

     Lucene term query

     fieldName

     Name of field

     query

     Term to search on

     topK

     Number of documents to return

     Definition Classes

     LuceneRDD

128. def toDebugString: String

     

     Definition Classes

     RDD

129. def toJavaRDD(): JavaRDD[T]

     

     Definition Classes

     RDD

130. def toLocalIterator: Iterator[T]

     

     Definition Classes

     RDD

131. def toString(): String

     

     Definition Classes

     RDD → AnyRef → Any

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

     

     Definition Classes

     RDD

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

     

     Definition Classes

     RDD

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

     

     Definition Classes

     RDD

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

     

     Definition Classes

     RDD

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

     

     Definition Classes

     FacetedLuceneRDD → LuceneRDD → RDD

137. final def wait(): Unit

     

     Definition Classes

     AnyRef

     Annotations

     @throws( ... )

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

     

     Definition Classes

     AnyRef

     Annotations

     @throws( ... )

139. final def wait(arg0: Long): Unit

     

     Definition Classes

     AnyRef

     Annotations

     @throws( ... )

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

     

     Definition Classes

     RDD

141. 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]

     

     Definition Classes

     RDD

142. 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]

     

     Definition Classes

     RDD

143. 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]

     

     Definition Classes

     RDD

144. 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]

     

     Definition Classes

     RDD

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

     

     Definition Classes

     RDD

146. 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]

     

     Definition Classes

     RDD

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

     

     Definition Classes

     RDD

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

     

     Definition Classes

     RDD