ca9f4ebb8e
Author: hlin09 <hlin09pu@gmail.com> Closes #5568 from hlin09/zipPartitions and squashes the following commits: 12c08a5 [hlin09] Fix comments d2d32db [hlin09] Merge branch 'master' into zipPartitions ec56d2f [hlin09] Fix test. 27655d3 [hlin09] Adds support for zipPartitions.
198 lines
4.6 KiB
Plaintext
198 lines
4.6 KiB
Plaintext
#exportPattern("^[[:alpha:]]+")
|
|
exportClasses("RDD")
|
|
exportClasses("Broadcast")
|
|
exportMethods(
|
|
"aggregateByKey",
|
|
"aggregateRDD",
|
|
"cache",
|
|
"cartesian",
|
|
"checkpoint",
|
|
"coalesce",
|
|
"cogroup",
|
|
"collect",
|
|
"collectAsMap",
|
|
"collectPartition",
|
|
"combineByKey",
|
|
"count",
|
|
"countByKey",
|
|
"countByValue",
|
|
"distinct",
|
|
"Filter",
|
|
"filterRDD",
|
|
"first",
|
|
"flatMap",
|
|
"flatMapValues",
|
|
"fold",
|
|
"foldByKey",
|
|
"foreach",
|
|
"foreachPartition",
|
|
"fullOuterJoin",
|
|
"glom",
|
|
"groupByKey",
|
|
"intersection",
|
|
"join",
|
|
"keyBy",
|
|
"keys",
|
|
"length",
|
|
"lapply",
|
|
"lapplyPartition",
|
|
"lapplyPartitionsWithIndex",
|
|
"leftOuterJoin",
|
|
"lookup",
|
|
"map",
|
|
"mapPartitions",
|
|
"mapPartitionsWithIndex",
|
|
"mapValues",
|
|
"maximum",
|
|
"minimum",
|
|
"numPartitions",
|
|
"partitionBy",
|
|
"persist",
|
|
"pipeRDD",
|
|
"reduce",
|
|
"reduceByKey",
|
|
"reduceByKeyLocally",
|
|
"repartition",
|
|
"rightOuterJoin",
|
|
"sampleByKey",
|
|
"sampleRDD",
|
|
"saveAsTextFile",
|
|
"saveAsObjectFile",
|
|
"sortBy",
|
|
"sortByKey",
|
|
"subtract",
|
|
"subtractByKey",
|
|
"sumRDD",
|
|
"take",
|
|
"takeOrdered",
|
|
"takeSample",
|
|
"top",
|
|
"unionRDD",
|
|
"unpersist",
|
|
"value",
|
|
"values",
|
|
"zipPartitions",
|
|
"zipRDD",
|
|
"zipWithIndex",
|
|
"zipWithUniqueId"
|
|
)
|
|
|
|
# S3 methods exported
|
|
export(
|
|
"textFile",
|
|
"objectFile",
|
|
"parallelize",
|
|
"hashCode",
|
|
"includePackage",
|
|
"broadcast",
|
|
"setBroadcastValue",
|
|
"setCheckpointDir"
|
|
)
|
|
export("sparkR.init")
|
|
export("sparkR.stop")
|
|
export("print.jobj")
|
|
useDynLib(SparkR, stringHashCode)
|
|
importFrom(methods, setGeneric, setMethod, setOldClass)
|
|
|
|
# SparkRSQL
|
|
|
|
exportClasses("DataFrame")
|
|
|
|
exportMethods("columns",
|
|
"distinct",
|
|
"dtypes",
|
|
"except",
|
|
"explain",
|
|
"filter",
|
|
"groupBy",
|
|
"head",
|
|
"insertInto",
|
|
"intersect",
|
|
"isLocal",
|
|
"limit",
|
|
"orderBy",
|
|
"names",
|
|
"printSchema",
|
|
"registerTempTable",
|
|
"repartition",
|
|
"sampleDF",
|
|
"saveAsParquetFile",
|
|
"saveAsTable",
|
|
"saveDF",
|
|
"schema",
|
|
"select",
|
|
"selectExpr",
|
|
"show",
|
|
"showDF",
|
|
"sortDF",
|
|
"toJSON",
|
|
"toRDD",
|
|
"unionAll",
|
|
"where",
|
|
"withColumn",
|
|
"withColumnRenamed")
|
|
|
|
exportClasses("Column")
|
|
|
|
exportMethods("abs",
|
|
"alias",
|
|
"approxCountDistinct",
|
|
"asc",
|
|
"avg",
|
|
"cast",
|
|
"contains",
|
|
"countDistinct",
|
|
"desc",
|
|
"endsWith",
|
|
"getField",
|
|
"getItem",
|
|
"isNotNull",
|
|
"isNull",
|
|
"last",
|
|
"like",
|
|
"lower",
|
|
"max",
|
|
"mean",
|
|
"min",
|
|
"rlike",
|
|
"sqrt",
|
|
"startsWith",
|
|
"substr",
|
|
"sum",
|
|
"sumDistinct",
|
|
"upper")
|
|
|
|
exportClasses("GroupedData")
|
|
exportMethods("agg")
|
|
|
|
export("sparkRSQL.init",
|
|
"sparkRHive.init")
|
|
|
|
export("cacheTable",
|
|
"clearCache",
|
|
"createDataFrame",
|
|
"createExternalTable",
|
|
"dropTempTable",
|
|
"jsonFile",
|
|
"jsonRDD",
|
|
"loadDF",
|
|
"parquetFile",
|
|
"sql",
|
|
"table",
|
|
"tableNames",
|
|
"tables",
|
|
"toDF",
|
|
"uncacheTable")
|
|
|
|
export("sparkRSQL.init",
|
|
"sparkRHive.init")
|
|
|
|
export("structField",
|
|
"structField.jobj",
|
|
"structField.character",
|
|
"print.structField",
|
|
"structType",
|
|
"structType.jobj",
|
|
"structType.structField",
|
|
"print.structType")
|