rebase based on #1980

Author: WangTaoTheTonic

.gitattributes

@@ -0,0 +1,2 @@
+*.bat text eol=crlf
+*.cmd text eol=crlf

.gitignore

@@ -5,18 +5,23 @@
 *.ipr
 *.iml
 *.iws
+*.pyc
+*.pyo
 .idea/
 .idea_modules/
-sbt/*.jar
+build/*.jar
 .settings
 .cache
+cache
 .generated-mima*
-/build/
 work/
 out/
 .DS_Store
 third_party/libmesos.so
 third_party/libmesos.dylib
+build/apache-maven*
+build/zinc*
+build/scala*
 conf/java-opts
 conf/*.sh
 conf/*.cmd
@@ -49,12 +54,17 @@ dependency-reduced-pom.xml
 checkpoint
 derby.log
 dist/
-spark-*-bin.tar.gz
+dev/create-release/*txt
+dev/create-release/*final
+spark-*-bin-*.tgz
 unit-tests.log
 /lib/
+ec2/lib/
 rat-results.txt
 scalastyle.txt
 scalastyle-output.xml
+R-unit-tests.log
+R/unit-tests.out
 
 # For Hive
 metastore_db/

.rat-excludes

@@ -1,5 +1,7 @@
 target
+cache
 .gitignore
+.gitattributes
 .project
 .classpath
 .mima-excludes
@@ -17,6 +19,7 @@ fairscheduler.xml.template
 spark-defaults.conf.template
 log4j.properties
 log4j.properties.template
+metrics.properties
 metrics.properties.template
 slaves
 slaves.template
@@ -43,11 +46,13 @@ SparkImports.scala
 SparkJLineCompletion.scala
 SparkJLineReader.scala
 SparkMemberHandlers.scala
+SparkReplReporter.scala
 sbt
 sbt-launch-lib.bash
 plugins.sbt
 work
 .*\.q
+.*\.qv
 golden
 test.out/*
 .*iml
@@ -61,3 +66,6 @@ dist/*
 logs
 .*scalastyle-output.xml
 .*dependency-reduced-pom.xml
+known_translations
+DESCRIPTION
+NAMESPACE

CONTRIBUTING.md

@@ -1,12 +1,16 @@
 ## Contributing to Spark
 
-Contributions via GitHub pull requests are gladly accepted from their original
-author. Along with any pull requests, please state that the contribution is
-your original work and that you license the work to the project under the
-project's open source license. Whether or not you state this explicitly, by
-submitting any copyrighted material via pull request, email, or other means
-you agree to license the material under the project's open source license and
-warrant that you have the legal authority to do so.
+*Before opening a pull request*, review the 
+[Contributing to Spark wiki](https://cwiki.apache.org/confluence/display/SPARK/Contributing+to+Spark). 
+It lists steps that are required before creating a PR. In particular, consider:
+
+- Is the change important and ready enough to ask the community to spend time reviewing?
+- Have you searched for existing, related JIRAs and pull requests?
+- Is this a new feature that can stand alone as a package on http://spark-packages.org ?
+- Is the change being proposed clearly explained and motivated?
 
-Please see the [Contributing to Spark wiki page](https://cwiki.apache.org/SPARK/Contributing+to+Spark)
-for more information.
+When you contribute code, you affirm that the contribution is your original work and that you 
+license the work to the project under the project's open source license. Whether or not you 
+state this explicitly, by submitting any copyrighted material via pull request, email, or 
+other means you agree to license the material under the project's open source license and 
+warrant that you have the legal authority to do so.

LICENSE

@@ -646,7 +646,8 @@ THE SOFTWARE.
 
 ========================================================================
 For Scala Interpreter classes (all .scala files in repl/src/main/scala
-except for Main.Scala, SparkHelper.scala and ExecutorClassLoader.scala):
+except for Main.Scala, SparkHelper.scala and ExecutorClassLoader.scala),
+and for SerializableMapWrapper in JavaUtils.scala:
 ========================================================================
 
 Copyright (c) 2002-2013 EPFL
@@ -712,18 +713,6 @@ THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
 NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE,
 EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 
-========================================================================
-For colt:
-========================================================================
-
-Copyright (c) 1999 CERN - European Organization for Nuclear Research.
-Permission to use, copy, modify, distribute and sell this software and its documentation for any purpose is hereby granted without fee, provided that the above copyright notice appear in all copies and that both that copyright notice and this permission notice appear in supporting documentation. CERN makes no representations about the suitability of this software for any purpose. It is provided "as is" without expressed or implied warranty.
-
-Packages hep.aida.*
-
-Written by Pavel Binko, Dino Ferrero Merlino, Wolfgang Hoschek, Tony Johnson, Andreas Pfeiffer, and others. Check the FreeHEP home page for more info. Permission to use and/or redistribute this work is granted under the terms of the LGPL License, with the exception that any usage related to military applications is expressly forbidden. The software and documentation made available under the terms of this license are provided with no warranty.
-
-
 ========================================================================
 For SnapTree:
 ========================================================================
@@ -766,7 +755,7 @@ SUCH DAMAGE.
 
 
 ========================================================================
-For Timsort (core/src/main/java/org/apache/spark/util/collection/Sorter.java):
+For Timsort (core/src/main/java/org/apache/spark/util/collection/TimSort.java):
 ========================================================================
 Copyright (C) 2008 The Android Open Source Project
 
@@ -782,6 +771,41 @@ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 See the License for the specific language governing permissions and
 limitations under the License.
 
+========================================================================
+For TestTimSort (core/src/test/java/org/apache/spark/util/collection/TestTimSort.java):
+========================================================================
+Copyright (C) 2015 Stijn de Gouw
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+  http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+
+========================================================================
+For LimitedInputStream
+  (network/common/src/main/java/org/apache/spark/network/util/LimitedInputStream.java):
+========================================================================
+Copyright (C) 2007 The Guava Authors
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+     http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+
 
 ========================================================================
 BSD-style licenses

R/.gitignore

@@ -0,0 +1,6 @@
+*.o
+*.so
+*.Rd
+lib
+pkg/man
+pkg/html

R/DOCUMENTATION.md

@@ -0,0 +1,12 @@
+# SparkR Documentation
+
+SparkR documentation is generated using in-source comments annotated using using
+`roxygen2`. After making changes to the documentation, to generate man pages,
+you can run the following from an R console in the SparkR home directory
+
+    library(devtools)
+    devtools::document(pkg="./pkg", roclets=c("rd"))
+
+You can verify if your changes are good by running
+
+    R CMD check pkg/

R/README.md

@@ -0,0 +1,67 @@
+# R on Spark
+
+SparkR is an R package that provides a light-weight frontend to use Spark from R.
+
+### SparkR development
+
+#### 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/mvn -DskipTests -Psparkr package
+```
+
+#### Running sparkR
+
+You can start using SparkR by launching the SparkR shell with
+
+    ./bin/sparkR
+
+The `sparkR` script automatically creates a SparkContext with Spark by default in
+local mode. To specify the Spark master of a cluster for the automatically created
+SparkContext, you can run
+
+    ./bin/sparkR --master "local[2]"
+
+To set other options like driver memory, executor memory etc. you can pass in the [spark-submit](http://spark.apache.org/docs/latest/submitting-applications.html) arguments to `./bin/sparkR`
+
+#### Using SparkR from RStudio
+
+If you wish to use SparkR from RStudio or other R frontends you will need to set some environment variables which point SparkR to your Spark installation. For example 
+```
+# Set this to where Spark is installed
+Sys.setenv(SPARK_HOME="/Users/shivaram/spark")
+# This line loads SparkR from the installed directory
+.libPaths(c(file.path(Sys.getenv("SPARK_HOME"), "R", "lib"), .libPaths()))
+library(SparkR)
+sc <- sparkR.init(master="local")
+```
+
+#### Making changes to SparkR
+
+The [instructions](https://cwiki.apache.org/confluence/display/SPARK/Contributing+to+Spark) for making contributions to Spark also apply to SparkR.
+If you only make R file changes (i.e. no Scala changes) then you can just re-install the R package using `R/install-dev.sh` and test your changes.
+Once you have made your changes, please include unit tests for them and run existing unit tests using the `run-tests.sh` script as described below. 
+    
+#### Generating documentation
+
+The SparkR documentation (Rd files and HTML files) are not a part of the source repository. To generate them you can run the script `R/create-docs.sh`. This script uses `devtools` and `knitr` to generate the docs and these packages need to be installed on the machine before using the script.
+    
+### Examples, Unit tests
+
+SparkR comes with several sample programs in the `examples/src/main/r` directory.
+To run one of them, use `./bin/sparkR <filename> <args>`. For example:
+
+    ./bin/sparkR examples/src/main/r/pi.R local[2]
+
+You can also run the unit-tests for SparkR by running (you need to install the [testthat](http://cran.r-project.org/web/packages/testthat/index.html) package first):
+
+    R -e 'install.packages("testthat", repos="http://cran.us.r-project.org")'
+    ./R/run-tests.sh
+
+### Running on YARN
+The `./bin/spark-submit` and `./bin/sparkR` can also be used to submit jobs to YARN clusters. You will need to set YARN conf dir before doing so. For example on CDH you can run
+```
+export YARN_CONF_DIR=/etc/hadoop/conf
+./bin/spark-submit --master yarn examples/src/main/r/pi.R 4
+```

R/WINDOWS.md

@@ -0,0 +1,13 @@
+## Building SparkR on Windows
+
+To build SparkR on Windows, the following steps are required
+
+1. Install R (>= 3.1) and [Rtools](http://cran.r-project.org/bin/windows/Rtools/). Make sure to
+include Rtools and R in `PATH`.
+2. Install
+[JDK7](http://www.oracle.com/technetwork/java/javase/downloads/jdk7-downloads-1880260.html) and set
+`JAVA_HOME` in the system environment variables.
+3. Download and install [Maven](http://maven.apache.org/download.html). Also include the `bin`
+directory in Maven in `PATH`.
+4. Set `MAVEN_OPTS` as described in [Building Spark](http://spark.apache.org/docs/latest/building-spark.html).
+5. Open a command shell (`cmd`) in the Spark directory and run `mvn -DskipTests -Psparkr package`

R/create-docs.sh

@@ -0,0 +1,46 @@
+#!/bin/bash
+
+#
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+# Script to create API docs for SparkR
+# This requires `devtools` and `knitr` to be installed on the machine.
+
+# After running this script the html docs can be found in 
+# $SPARK_HOME/R/pkg/html
+
+# Figure out where the script is
+export FWDIR="$(cd "`dirname "$0"`"; pwd)"
+pushd $FWDIR
+
+# Generate Rd file
+Rscript -e 'library(devtools); devtools::document(pkg="./pkg", roclets=c("rd"))'
+
+# Install the package
+./install-dev.sh
+
+# Now create HTML files
+
+# knit_rd puts html in current working directory
+mkdir -p pkg/html
+pushd pkg/html
+
+Rscript -e 'library(SparkR, lib.loc="../../lib"); library(knitr); knit_rd("SparkR")'
+
+popd
+
+popd

R/install-dev.bat

@@ -0,0 +1,27 @@
+@echo off
+
+rem
+rem Licensed to the Apache Software Foundation (ASF) under one or more
+rem contributor license agreements.  See the NOTICE file distributed with
+rem this work for additional information regarding copyright ownership.
+rem The ASF licenses this file to You under the Apache License, Version 2.0
+rem (the "License"); you may not use this file except in compliance with
+rem the License.  You may obtain a copy of the License at
+rem
+rem    http://www.apache.org/licenses/LICENSE-2.0
+rem
+rem Unless required by applicable law or agreed to in writing, software
+rem distributed under the License is distributed on an "AS IS" BASIS,
+rem WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+rem See the License for the specific language governing permissions and
+rem limitations under the License.
+rem
+
+rem Install development version of SparkR
+rem
+
+set SPARK_HOME=%~dp0..
+
+MKDIR %SPARK_HOME%\R\lib
+
+R.exe CMD INSTALL --library="%SPARK_HOME%\R\lib"  %SPARK_HOME%\R\pkg\