From 5c14890159a5711072bf395f662b2433a389edf9 Mon Sep 17 00:00:00 2001 From: "Zhang, Liye" Date: Tue, 25 Aug 2015 11:48:55 +0100 Subject: [DOC] add missing parameters in SparkContext.scala for scala doc Author: Zhang, Liye Closes #8412 from liyezhang556520/minorDoc. --- core/src/main/scala/org/apache/spark/SparkContext.scala | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/core/src/main/scala/org/apache/spark/SparkContext.scala b/core/src/main/scala/org/apache/spark/SparkContext.scala index 1ddaca8a5b..9849aff85d 100644 --- a/core/src/main/scala/org/apache/spark/SparkContext.scala +++ b/core/src/main/scala/org/apache/spark/SparkContext.scala @@ -114,6 +114,7 @@ class SparkContext(config: SparkConf) extends Logging with ExecutorAllocationCli * :: DeveloperApi :: * Alternative constructor for setting preferred locations where Spark will create executors. * + * @param config a [[org.apache.spark.SparkConf]] object specifying other Spark parameters * @param preferredNodeLocationData used in YARN mode to select nodes to launch containers on. * Can be generated using [[org.apache.spark.scheduler.InputFormatInfo.computePreferredLocations]] * from a list of input files or InputFormats for the application. @@ -145,6 +146,9 @@ class SparkContext(config: SparkConf) extends Logging with ExecutorAllocationCli * @param jars Collection of JARs to send to the cluster. These can be paths on the local file * system or HDFS, HTTP, HTTPS, or FTP URLs. * @param environment Environment variables to set on worker nodes. + * @param preferredNodeLocationData used in YARN mode to select nodes to launch containers on. + * Can be generated using [[org.apache.spark.scheduler.InputFormatInfo.computePreferredLocations]] + * from a list of input files or InputFormats for the application. */ def this( master: String, @@ -841,6 +845,9 @@ class SparkContext(config: SparkConf) extends Logging with ExecutorAllocationCli * @note Small files are preferred, large file is also allowable, but may cause bad performance. * @note On some filesystems, `.../path/*` can be a more efficient way to read all files * in a directory rather than `.../path/` or `.../path` + * + * @param path Directory to the input data files, the path can be comma separated paths as the + * list of inputs. * @param minPartitions A suggestion value of the minimal splitting number for input data. */ def wholeTextFiles( @@ -889,6 +896,9 @@ class SparkContext(config: SparkConf) extends Logging with ExecutorAllocationCli * @note Small files are preferred; very large files may cause bad performance. * @note On some filesystems, `.../path/*` can be a more efficient way to read all files * in a directory rather than `.../path/` or `.../path` + * + * @param path Directory to the input data files, the path can be comma separated paths as the + * list of inputs. * @param minPartitions A suggestion value of the minimal splitting number for input data. */ @Experimental @@ -918,8 +928,11 @@ class SparkContext(config: SparkConf) extends Logging with ExecutorAllocationCli * '''Note:''' We ensure that the byte array for each record in the resulting RDD * has the provided record length. * - * @param path Directory to the input data files + * @param path Directory to the input data files, the path can be comma separated paths as the + * list of inputs. * @param recordLength The length at which to split the records + * @param conf Configuration for setting up the dataset. + * * @return An RDD of data with values, represented as byte arrays */ @Experimental -- cgit v1.2.3