merge master

Author: coderxiang

.gitignore

@@ -66,6 +66,7 @@ scalastyle-output.xml
 R-unit-tests.log
 R/unit-tests.out
 python/lib/pyspark.zip
+lint-r-report.log
 
 # For Hive
 metastore_db/

.rat-excludes

@@ -28,6 +28,7 @@ spark-env.sh
 spark-env.cmd
 spark-env.sh.template
 log4j-defaults.properties
+log4j-defaults-repl.properties
 bootstrap-tooltip.js
 jquery-1.11.1.min.js
 d3.min.js
@@ -85,3 +86,4 @@ local-1430917381535_2
 DESCRIPTION
 NAMESPACE
 test_support/*
+.lintr

LICENSE

@@ -950,3 +950,4 @@ The following components are provided under the MIT License. See project link fo
      (MIT License) scopt (com.github.scopt:scopt_2.10:3.2.0 - https://github.com/scopt/scopt)
      (The MIT License) Mockito (org.mockito:mockito-all:1.8.5 - http://www.mockito.org)
      (MIT License) jquery (https://jquery.org/license/)
+     (MIT License) AnchorJS (https://github.com/bryanbraun/anchorjs)

R/log4j.properties

@@ -19,7 +19,7 @@
 log4j.rootCategory=INFO, file
 log4j.appender.file=org.apache.log4j.FileAppender
 log4j.appender.file.append=true
-log4j.appender.file.file=R-unit-tests.log
+log4j.appender.file.file=R/target/unit-tests.log
 log4j.appender.file.layout=org.apache.log4j.PatternLayout
 log4j.appender.file.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss.SSS} %t %p %c{1}: %m%n
 

R/pkg/.lintr

@@ -0,0 +1,2 @@
+linters: with_defaults(line_length_linter(100), camel_case_linter = NULL, open_curly_linter(allow_single_line = TRUE), closed_curly_linter(allow_single_line = TRUE))
+exclusions: list("inst/profile/general.R" = 1, "inst/profile/shell.R")

R/pkg/NAMESPACE

@@ -10,6 +10,11 @@ export("sparkR.init")
 export("sparkR.stop")
 export("print.jobj")
 
+# Job group lifecycle management methods
+export("setJobGroup",
+       "clearJobGroup",
+       "cancelJobGroup")
+
 exportClasses("DataFrame")
 
 exportMethods("arrange",

R/pkg/R/sparkR.R

@@ -278,3 +278,47 @@ sparkRHive.init <- function(jsc = NULL) {
   assign(".sparkRHivesc", hiveCtx, envir = .sparkREnv)
   hiveCtx
 }
+
+#' Assigns a group ID to all the jobs started by this thread until the group ID is set to a
+#' different value or cleared.
+#'
+#' @param sc existing spark context
+#' @param groupid the ID to be assigned to job groups
+#' @param description description for the the job group ID
+#' @param interruptOnCancel flag to indicate if the job is interrupted on job cancellation
+#' @examples
+#'\dontrun{
+#' sc <- sparkR.init()
+#' setJobGroup(sc, "myJobGroup", "My job group description", TRUE)
+#'}
+
+setJobGroup <- function(sc, groupId, description, interruptOnCancel) {
+  callJMethod(sc, "setJobGroup", groupId, description, interruptOnCancel)
+}
+
+#' Clear current job group ID and its description
+#'
+#' @param sc existing spark context
+#' @examples
+#'\dontrun{
+#' sc <- sparkR.init()
+#' clearJobGroup(sc)
+#'}
+
+clearJobGroup <- function(sc) {
+  callJMethod(sc, "clearJobGroup")
+}
+
+#' Cancel active jobs for the specified group
+#'
+#' @param sc existing spark context
+#' @param groupId the ID of job group to be cancelled
+#' @examples
+#'\dontrun{
+#' sc <- sparkR.init()
+#' cancelJobGroup(sc, "myJobGroup")
+#'}
+
+cancelJobGroup <- function(sc, groupId) {
+  callJMethod(sc, "cancelJobGroup", groupId)
+}

R/pkg/inst/tests/test_context.R

@@ -48,3 +48,10 @@ test_that("rdd GC across sparkR.stop", {
   count(rdd3)
   count(rdd4)
 })
+
+test_that("job group functions can be called", {
+  sc <- sparkR.init()
+  setJobGroup(sc, "groupId", "job description", TRUE)
+  cancelJobGroup(sc, "groupId")
+  clearJobGroup(sc)
+})

build/mvn

@@ -69,11 +69,14 @@ install_app() {
 
 # Install maven under the build/ folder
 install_mvn() {
+  local MVN_VERSION="3.3.3"
+
   install_app \
-    "http://archive.apache.org/dist/maven/maven-3/3.2.5/binaries" \
-    "apache-maven-3.2.5-bin.tar.gz" \
-    "apache-maven-3.2.5/bin/mvn"
-  MVN_BIN="${_DIR}/apache-maven-3.2.5/bin/mvn"
+    "http://archive.apache.org/dist/maven/maven-3/${MVN_VERSION}/binaries" \
+    "apache-maven-${MVN_VERSION}-bin.tar.gz" \
+    "apache-maven-${MVN_VERSION}/bin/mvn"
+
+  MVN_BIN="${_DIR}/apache-maven-${MVN_VERSION}/bin/mvn"
 }
 
 # Install zinc under the build/ folder
@@ -105,28 +108,16 @@ install_scala() {
   SCALA_LIBRARY="$(cd "$(dirname ${scala_bin})/../lib" && pwd)/scala-library.jar"
 }
 
-# Determines if a given application is already installed. If not, will attempt
-# to install
-## Arg1 - application name
-## Arg2 - Alternate path to local install under build/ dir
-check_and_install_app() {
-  # create the local environment variable in uppercase
-  local app_bin="`echo $1 | awk '{print toupper(\$0)}'`_BIN"
-  # some black magic to set the generated app variable (i.e. MVN_BIN) into the
-  # environment
-  eval "${app_bin}=`which $1 2>/dev/null`"
-
-  if [ -z "`which $1 2>/dev/null`" ]; then
-    install_$1
-  fi
-}
-
 # Setup healthy defaults for the Zinc port if none were provided from
 # the environment
 ZINC_PORT=${ZINC_PORT:-"3030"}
 
-# Check and install all applications necessary to build Spark
-check_and_install_app "mvn"
+# Install Maven if necessary
+MVN_BIN="$(command -v mvn)"
+
+if [ ! "$MVN_BIN" ]; then
+  install_mvn
+fi
 
 # Install the proper version of Scala and Zinc for the build
 install_zinc

core/src/main/resources/org/apache/spark/log4j-defaults-repl.properties

@@ -0,0 +1,12 @@
+# Set everything to be logged to the console
+log4j.rootCategory=WARN, console
+log4j.appender.console=org.apache.log4j.ConsoleAppender
+log4j.appender.console.target=System.err
+log4j.appender.console.layout=org.apache.log4j.PatternLayout
+log4j.appender.console.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss} %p %c{1}: %m%n
+
+# Settings to quiet third party logs that are too verbose
+log4j.logger.org.spark-project.jetty=WARN
+log4j.logger.org.spark-project.jetty.util.component.AbstractLifeCycle=ERROR
+log4j.logger.org.apache.spark.repl.SparkIMain$exprTyper=INFO
+log4j.logger.org.apache.spark.repl.SparkILoop$SparkILoopInterpreter=INFO