Merge branch 'master' into SPARK-8103

Conflicts:
	core/src/main/scala/org/apache/spark/scheduler/Stage.scala

Author: squito

.rat-excludes

@@ -91,3 +91,5 @@ help/*
 html/*
 INDEX
 .lintr
+gen-java.*
+.*avpr

LICENSE

@@ -948,6 +948,6 @@ The following components are provided under the MIT License. See project link fo
      (MIT License) SLF4J LOG4J-12 Binding (org.slf4j:slf4j-log4j12:1.7.5 - http://www.slf4j.org)
      (MIT License) pyrolite (org.spark-project:pyrolite:2.0.1 - http://pythonhosted.org/Pyro4/)
      (MIT License) scopt (com.github.scopt:scopt_2.10:3.2.0 - https://github.com/scopt/scopt)
-     (The MIT License) Mockito (org.mockito:mockito-core:1.8.5 - http://www.mockito.org)
+     (The MIT License) Mockito (org.mockito:mockito-core:1.9.5 - http://www.mockito.org)
      (MIT License) jquery (https://jquery.org/license/)
      (MIT License) AnchorJS (https://github.com/bryanbraun/anchorjs)

R/README.md

@@ -6,7 +6,7 @@ SparkR is an R package that provides a light-weight frontend to use Spark from R
 
 #### Build Spark
 
-Build Spark with [Maven](http://spark.apache.org/docs/latest/building-spark.html#building-with-buildmvn) and include the `-PsparkR` profile to build the R package. For example to use the default Hadoop versions you can run
+Build Spark with [Maven](http://spark.apache.org/docs/latest/building-spark.html#building-with-buildmvn) and include the `-Psparkr` profile to build the R package. For example to use the default Hadoop versions you can run
 ```
   build/mvn -DskipTests -Psparkr package
 ```

R/install-dev.bat

@@ -25,3 +25,8 @@ set SPARK_HOME=%~dp0..
 MKDIR %SPARK_HOME%\R\lib
 
 R.exe CMD INSTALL --library="%SPARK_HOME%\R\lib"  %SPARK_HOME%\R\pkg\
+
+rem Zip the SparkR package so that it can be distributed to worker nodes on YARN
+pushd %SPARK_HOME%\R\lib
+%JAVA_HOME%\bin\jar.exe cfM "%SPARK_HOME%\R\lib\sparkr.zip" SparkR
+popd

R/install-dev.sh

@@ -34,12 +34,16 @@ LIB_DIR="$FWDIR/lib"
 
 mkdir -p $LIB_DIR
 
-pushd $FWDIR
+pushd $FWDIR > /dev/null
 
 # Generate Rd files if devtools is installed
 Rscript -e ' if("devtools" %in% rownames(installed.packages())) { library(devtools); devtools::document(pkg="./pkg", roclets=c("rd")) }'
 
 # Install SparkR to $LIB_DIR
 R CMD INSTALL --library=$LIB_DIR $FWDIR/pkg/
 
-popd
+# Zip the SparkR package so that it can be distributed to worker nodes on YARN
+cd $LIB_DIR
+jar cfM "$LIB_DIR/sparkr.zip" SparkR
+
+popd > /dev/null

R/pkg/DESCRIPTION

@@ -32,4 +32,3 @@ Collate:
     'serialize.R'
     'sparkR.R'
     'utils.R'
-    'zzz.R'

R/pkg/R/DataFrame.R

@@ -169,8 +169,8 @@ setMethod("isLocal",
 #'}
 setMethod("showDF",
           signature(x = "DataFrame"),
-          function(x, numRows = 20) {
-            s <- callJMethod(x@sdf, "showString", numToInt(numRows))
+          function(x, numRows = 20, truncate = TRUE) {
+            s <- callJMethod(x@sdf, "showString", numToInt(numRows), truncate)
             cat(s)
           })
 

R/pkg/R/RDD.R

@@ -165,7 +165,6 @@ setMethod("getJRDD", signature(rdd = "PipelinedRDD"),
                                    serializedFuncArr,
                                    rdd@env$prev_serializedMode,
                                    packageNamesArr,
-                                   as.character(.sparkREnv[["libname"]]),
                                    broadcastArr,
                                    callJMethod(prev_jrdd, "classTag"))
             } else {
@@ -175,7 +174,6 @@ setMethod("getJRDD", signature(rdd = "PipelinedRDD"),
                                    rdd@env$prev_serializedMode,
                                    serializedMode,
                                    packageNamesArr,
-                                   as.character(.sparkREnv[["libname"]]),
                                    broadcastArr,
                                    callJMethod(prev_jrdd, "classTag"))
             }

R/pkg/R/SQLContext.R

@@ -86,7 +86,9 @@ infer_type <- function(x) {
 createDataFrame <- function(sqlContext, data, schema = NULL, samplingRatio = 1.0) {
   if (is.data.frame(data)) {
       # get the names of columns, they will be put into RDD
-      schema <- names(data)
+      if (is.null(schema)) {
+        schema <- names(data)
+      }
       n <- nrow(data)
       m <- ncol(data)
       # get rid of factor type

R/pkg/R/generics.R

@@ -20,7 +20,8 @@
 # @rdname aggregateRDD
 # @seealso reduce
 # @export
-setGeneric("aggregateRDD", function(x, zeroValue, seqOp, combOp) { standardGeneric("aggregateRDD") })
+setGeneric("aggregateRDD",
+           function(x, zeroValue, seqOp, combOp) { standardGeneric("aggregateRDD") })
 
 # @rdname cache-methods
 # @export