Merge remote-tracking branch 'apache/master' into SPARK-16406

Author: hvanhovell

.github/PULL_REQUEST_TEMPLATE

@@ -2,11 +2,9 @@
 
 (Please fill in changes proposed in this fix)
 
-
 ## How was this patch tested?
 
 (Please explain how this patch was tested. E.g. unit tests, integration tests, manual tests)
-
-
 (If this patch involves UI changes, please attach a screenshot; otherwise, remove this)
 
+Please review http://spark.apache.org/contributing.html before opening a pull request.

.gitignore

@@ -24,6 +24,8 @@
 R-unit-tests.log
 R/unit-tests.out
 R/cran-check.out
+R/pkg/vignettes/sparkr-vignettes.html
+R/pkg/tests/fulltests/Rplots.pdf
 build/*.jar
 build/apache-maven*
 build/scala*
@@ -41,9 +43,12 @@ dependency-reduced-pom.xml
 derby.log
 dev/create-release/*final
 dev/create-release/*txt
+dev/pr-deps/
 dist/
 docs/_site
 docs/api
+sql/docs
+sql/site
 lib_managed/
 lint-r-report.log
 log/
@@ -56,6 +61,10 @@ project/plugins/project/build.properties
 project/plugins/src_managed/
 project/plugins/target/
 python/lib/pyspark.zip
+python/deps
+python/test_coverage/coverage_data
+python/test_coverage/htmlcov
+python/pyspark/python
 reports/
 scalastyle-on-compile.generated.xml
 scalastyle-output.xml
@@ -67,6 +76,7 @@ streaming-tests.log
 target/
 unit-tests.log
 work/
+docs/.jekyll-metadata
 
 # For Hive
 TempStatsStore/

.travis.yml

@@ -28,7 +28,6 @@ dist: trusty
 # 2. Choose language and target JDKs for parallel builds.
 language: java
 jdk:
-  - oraclejdk7
   - oraclejdk8
 
 # 3. Setup cache directory for SBT and Maven.
@@ -44,7 +43,7 @@ notifications:
 # 5. Run maven install before running lint-java.
 install:
   - export MAVEN_SKIP_RC=1
-  - build/mvn -T 4 -q -DskipTests -Pmesos -Pyarn -Phadoop-2.3 -Pkinesis-asl -Phive -Phive-thriftserver install
+  - build/mvn -T 4 -q -DskipTests -Pkubernetes -Pmesos -Pyarn -Pkinesis-asl -Phive -Phive-thriftserver install
 
 # 6. Run lint-java.
 script:

CONTRIBUTING.md

@@ -1,12 +1,12 @@
 ## Contributing to Spark
 
 *Before opening a pull request*, review the 
-[Contributing to Spark wiki](https://cwiki.apache.org/confluence/display/SPARK/Contributing+to+Spark). 
+[Contributing to Spark guide](http://spark.apache.org/contributing.html). 
 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 this a new feature that can stand alone as a [third party project](http://spark.apache.org/third-party-projects.html) ?
 - Is the change being proposed clearly explained and motivated?
 
 When you contribute code, you affirm that the contribution is your original work and that you 

LICENSE

@@ -249,11 +249,11 @@ The text of each license is also included at licenses/LICENSE-[project].txt.
         (Interpreter classes (all .scala files in repl/src/main/scala
         except for Main.Scala, SparkHelper.scala and ExecutorClassLoader.scala),
         and for SerializableMapWrapper in JavaUtils.scala)
-     (BSD-like) Scala Actors library (org.scala-lang:scala-actors:2.11.7 - http://www.scala-lang.org/)
-     (BSD-like) Scala Compiler (org.scala-lang:scala-compiler:2.11.7 - http://www.scala-lang.org/)
-     (BSD-like) Scala Compiler (org.scala-lang:scala-reflect:2.11.7 - http://www.scala-lang.org/)
-     (BSD-like) Scala Library (org.scala-lang:scala-library:2.11.7 - http://www.scala-lang.org/)
-     (BSD-like) Scalap (org.scala-lang:scalap:2.11.7 - http://www.scala-lang.org/)
+     (BSD-like) Scala Actors library (org.scala-lang:scala-actors:2.11.8 - http://www.scala-lang.org/)
+     (BSD-like) Scala Compiler (org.scala-lang:scala-compiler:2.11.8 - http://www.scala-lang.org/)
+     (BSD-like) Scala Compiler (org.scala-lang:scala-reflect:2.11.8 - http://www.scala-lang.org/)
+     (BSD-like) Scala Library (org.scala-lang:scala-library:2.11.8 - http://www.scala-lang.org/)
+     (BSD-like) Scalap (org.scala-lang:scalap:2.11.8 - http://www.scala-lang.org/)
      (BSD-style) scalacheck (org.scalacheck:scalacheck_2.11:1.10.0 - http://www.scalacheck.org)
      (BSD-style) spire (org.spire-math:spire_2.11:0.7.1 - http://spire-math.org)
      (BSD-style) spire-macros (org.spire-math:spire-macros_2.11:0.7.1 - http://spire-math.org)
@@ -263,12 +263,14 @@ The text of each license is also included at licenses/LICENSE-[project].txt.
      (New BSD license) Protocol Buffer Java API (org.spark-project.protobuf:protobuf-java:2.4.1-shaded - http://code.google.com/p/protobuf)
      (The BSD License) Fortran to Java ARPACK (net.sourceforge.f2j:arpack_combined_all:0.1 - http://f2j.sourceforge.net)
      (The BSD License) xmlenc Library (xmlenc:xmlenc:0.52 - http://xmlenc.sourceforge.net)
-     (The New BSD License) Py4J (net.sf.py4j:py4j:0.10.3 - http://py4j.sourceforge.net/)
+     (The New BSD License) Py4J (net.sf.py4j:py4j:0.10.6 - http://py4j.sourceforge.net/)
      (Two-clause BSD-style license) JUnit-Interface (com.novocode:junit-interface:0.10 - http://github.com/szeiger/junit-interface/)
      (BSD licence) sbt and sbt-launch-lib.bash
      (BSD 3 Clause) d3.min.js (https://github.com/mbostock/d3/blob/master/LICENSE)
      (BSD 3 Clause) DPark (https://github.com/douban/dpark/blob/master/LICENSE)
      (BSD 3 Clause) CloudPickle (https://github.com/cloudpipe/cloudpickle/blob/master/LICENSE)
+     (BSD 2 Clause) Zstd-jni (https://github.com/luben/zstd-jni/blob/master/LICENSE)
+     (BSD license) Zstd (https://github.com/facebook/zstd/blob/v1.3.1/LICENSE)
 
 ========================================================================
 MIT licenses
@@ -297,3 +299,4 @@ The text of each license is also included at licenses/LICENSE-[project].txt.
      (MIT License) RowsGroup (http://datatables.net/license/mit)
      (MIT License) jsonFormatter (http://www.jqueryscript.net/other/jQuery-Plugin-For-Pretty-JSON-Formatting-jsonFormatter.html)
      (MIT License) modernizr (https://github.com/Modernizr/Modernizr/blob/master/LICENSE)
+     (MIT License) machinist (https://github.com/typelevel/machinist)

NOTICE

@@ -421,9 +421,6 @@ Copyright (c) 2011, Terrence Parr.
 This product includes/uses ASM (http://asm.ow2.org/),
 Copyright (c) 2000-2007 INRIA, France Telecom.
 
-This product includes/uses org.json (http://www.json.org/java/index.html),
-Copyright (c) 2002 JSON.org
-
 This product includes/uses JLine (http://jline.sourceforge.net/),
 Copyright (c) 2002-2006, Marc Prud'hommeaux <mwp1@cornell.edu>.
 
@@ -451,6 +448,12 @@ Copyright (C) 2011 Google Inc.
 Apache Commons Pool
 Copyright 1999-2009 The Apache Software Foundation
 
+This product includes/uses Kubernetes & OpenShift 3 Java Client (https://github.com/fabric8io/kubernetes-client)
+Copyright (C) 2015 Red Hat, Inc.
+
+This product includes/uses OkHttp (https://github.com/square/okhttp)
+Copyright (C) 2012 The Android Open Source Project
+
 =========================================================================
 ==  NOTICE file corresponding to section 4(d) of the Apache License,   ==
 ==  Version 2.0, in this case for the DataNucleus distribution.        ==

R/CRAN_RELEASE.md

@@ -0,0 +1,91 @@
+# SparkR CRAN Release
+
+To release SparkR as a package to CRAN, we would use the `devtools` package. Please work with the
+`dev@spark.apache.org` community and R package maintainer on this.
+
+### Release
+
+First, check that the `Version:` field in the `pkg/DESCRIPTION` file is updated. Also, check for stale files not under source control.
+
+Note that while `run-tests.sh` runs `check-cran.sh` (which runs `R CMD check`), it is doing so with `--no-manual --no-vignettes`, which skips a few vignettes or PDF checks - therefore it will be preferred to run `R CMD check` on the source package built manually before uploading a release. Also note that for CRAN checks for pdf vignettes to success, `qpdf` tool must be there (to install it, eg. `yum -q -y install qpdf`).
+
+To upload a release, we would need to update the `cran-comments.md`. This should generally contain the results from running the `check-cran.sh` script along with comments on status of all `WARNING` (should not be any) or `NOTE`. As a part of `check-cran.sh` and the release process, the vignettes is build - make sure `SPARK_HOME` is set and Spark jars are accessible.
+
+Once everything is in place, run in R under the `SPARK_HOME/R` directory:
+
+```R
+paths <- .libPaths(); .libPaths(c("lib", paths)); Sys.setenv(SPARK_HOME=tools::file_path_as_absolute("..")); devtools::release(); .libPaths(paths)
+```
+
+For more information please refer to http://r-pkgs.had.co.nz/release.html#release-check
+
+### Testing: build package manually
+
+To build package manually such as to inspect the resulting `.tar.gz` file content, we would also use the `devtools` package.
+
+Source package is what get released to CRAN. CRAN would then build platform-specific binary packages from the source package.
+
+#### Build source package
+
+To build source package locally without releasing to CRAN, run in R under the `SPARK_HOME/R` directory:
+
+```R
+paths <- .libPaths(); .libPaths(c("lib", paths)); Sys.setenv(SPARK_HOME=tools::file_path_as_absolute("..")); devtools::build("pkg"); .libPaths(paths)
+```
+
+(http://r-pkgs.had.co.nz/vignettes.html#vignette-workflow-2)
+
+Similarly, the source package is also created by `check-cran.sh` with `R CMD build pkg`.
+
+For example, this should be the content of the source package:
+
+```sh
+DESCRIPTION	R		inst		tests
+NAMESPACE	build		man		vignettes
+
+inst/doc/
+sparkr-vignettes.html
+sparkr-vignettes.Rmd
+sparkr-vignettes.Rman
+
+build/
+vignette.rds
+
+man/
+ *.Rd files...
+
+vignettes/
+sparkr-vignettes.Rmd
+```
+
+#### Test source package
+
+To install, run this:
+
+```sh
+R CMD INSTALL SparkR_2.1.0.tar.gz
+```
+
+With "2.1.0" replaced with the version of SparkR.
+
+This command installs SparkR to the default libPaths. Once that is done, you should be able to start R and run:
+
+```R
+library(SparkR)
+vignette("sparkr-vignettes", package="SparkR")
+```
+
+#### Build binary package
+
+To build binary package locally, run in R under the `SPARK_HOME/R` directory:
+
+```R
+paths <- .libPaths(); .libPaths(c("lib", paths)); Sys.setenv(SPARK_HOME=tools::file_path_as_absolute("..")); devtools::build("pkg", binary = TRUE); .libPaths(paths)
+```
+
+For example, this should be the content of the binary package:
+
+```sh
+DESCRIPTION	Meta		R		html		tests
+INDEX		NAMESPACE	help		profile		worker
+```

R/README.md

@@ -6,7 +6,7 @@ SparkR is an R package that provides a light-weight frontend to use Spark from R
 
 Libraries of sparkR need to be created in `$SPARK_HOME/R/lib`. This can be done by running the script `$SPARK_HOME/R/install-dev.sh`.
 By default the above script uses the system wide installation of R. However, this can be changed to any user installed location of R by setting the environment variable `R_HOME` the full path of the base directory where R is installed, before running install-dev.sh script.
-Example: 
+Example:
 ```bash
 # where /home/username/R is where R is installed and /home/username/R/bin contains the files R and RScript
 export R_HOME=/home/username/R
@@ -46,31 +46,27 @@ Sys.setenv(SPARK_HOME="/Users/username/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")
+sparkR.session()
 ```
 
 #### 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.
+The [instructions](http://spark.apache.org/contributing.html) 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 `R/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. Also, you may need to install these [prerequisites](https://github.com/apache/spark/tree/master/docs#prerequisites). See also, `R/DOCUMENTATION.md`
-    
+
 ### Examples, Unit tests
 
 SparkR comes with several sample programs in the `examples/src/main/r` directory.
 To run one of them, use `./bin/spark-submit <filename> <args>`. For example:
 ```bash
 ./bin/spark-submit examples/src/main/r/dataframe.R
 ```
-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:
-```bash
-R -e 'install.packages("testthat", repos="http://cran.us.r-project.org")'
-./R/run-tests.sh
-```
+You can run R unit tests by following the instructions under [Running R Tests](http://spark.apache.org/docs/latest/building-spark.html#running-r-tests).
 
 ### Running on YARN
 

R/WINDOWS.md

@@ -6,7 +6,7 @@ To build SparkR on Windows, the following steps are required
 include Rtools and R in `PATH`.
 
 2. Install
-[JDK7](http://www.oracle.com/technetwork/java/javase/downloads/jdk7-downloads-1880260.html) and set
+[JDK8](http://www.oracle.com/technetwork/java/javase/downloads/jdk8-downloads-2133151.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`
@@ -34,10 +34,9 @@ To run the SparkR unit tests on Windows, the following steps are required —ass
 
 4. Set the environment variable `HADOOP_HOME` to the full path to the newly created `hadoop` directory.
 
-5. Run unit tests for SparkR by running the command below. You need to install the [testthat](http://cran.r-project.org/web/packages/testthat/index.html) package first:
+5. Run unit tests for SparkR by running the command below. You need to install the needed packages following the instructions under [Running R Tests](http://spark.apache.org/docs/latest/building-spark.html#running-r-tests) first:
 
     ```
-    R -e "install.packages('testthat', repos='http://cran.us.r-project.org')"
-    .\bin\spark-submit2.cmd --conf spark.hadoop.fs.default.name="file:///" R\pkg\tests\run-all.R
+    .\bin\spark-submit2.cmd --conf spark.hadoop.fs.defaultFS="file:///" R\pkg\tests\run-all.R
     ```
 

R/check-cran.sh

@@ -20,30 +20,36 @@
 set -o pipefail
 set -e
 
-FWDIR="$(cd `dirname $0`; pwd)"
-pushd $FWDIR > /dev/null
+FWDIR="$(cd "`dirname "${BASH_SOURCE[0]}"`"; pwd)"
+pushd "$FWDIR" > /dev/null
 
-if [ ! -z "$R_HOME" ]
-  then
-    R_SCRIPT_PATH="$R_HOME/bin"
-  else
-    # if system wide R_HOME is not found, then exit
-    if [ ! `command -v R` ]; then
-      echo "Cannot find 'R_HOME'. Please specify 'R_HOME' or make sure R is properly installed."
-      exit 1
-    fi
-    R_SCRIPT_PATH="$(dirname $(which R))"
+. "$FWDIR/find-r.sh"
+
+# Install the package (this is required for code in vignettes to run when building it later)
+# Build the latest docs, but not vignettes, which is built with the package next
+. "$FWDIR/install-dev.sh"
+
+# Build source package with vignettes
+SPARK_HOME="$(cd "${FWDIR}"/..; pwd)"
+. "${SPARK_HOME}/bin/load-spark-env.sh"
+if [ -f "${SPARK_HOME}/RELEASE" ]; then
+  SPARK_JARS_DIR="${SPARK_HOME}/jars"
+else
+  SPARK_JARS_DIR="${SPARK_HOME}/assembly/target/scala-$SPARK_SCALA_VERSION/jars"
 fi
-echo "USING R_HOME = $R_HOME"
 
-# Build the latest docs
-$FWDIR/create-docs.sh
+if [ -d "$SPARK_JARS_DIR" ]; then
+  # Build a zip file containing the source package with vignettes
+  SPARK_HOME="${SPARK_HOME}" "$R_SCRIPT_PATH/R" CMD build "$FWDIR/pkg"
 
-# Build a zip file containing the source package
-"$R_SCRIPT_PATH/"R CMD build $FWDIR/pkg
+  find pkg/vignettes/. -not -name '.' -not -name '*.Rmd' -not -name '*.md' -not -name '*.pdf' -not -name '*.html' -delete
+else
+  echo "Error Spark JARs not found in '$SPARK_HOME'"
+  exit 1
+fi
 
 # Run check as-cran.
-VERSION=`grep Version $FWDIR/pkg/DESCRIPTION | awk '{print $NF}'`
+VERSION=`grep Version "$FWDIR/pkg/DESCRIPTION" | awk '{print $NF}'`
 
 CRAN_CHECK_OPTIONS="--as-cran"
 
@@ -54,11 +60,17 @@ fi
 
 if [ -n "$NO_MANUAL" ]
 then
-  CRAN_CHECK_OPTIONS=$CRAN_CHECK_OPTIONS" --no-manual"
+  CRAN_CHECK_OPTIONS=$CRAN_CHECK_OPTIONS" --no-manual --no-vignettes"
 fi
 
 echo "Running CRAN check with $CRAN_CHECK_OPTIONS options"
 
-"$R_SCRIPT_PATH/"R CMD check $CRAN_CHECK_OPTIONS SparkR_"$VERSION".tar.gz
+if [ -n "$NO_TESTS" ] && [ -n "$NO_MANUAL" ]
+then
+  "$R_SCRIPT_PATH/R" CMD check $CRAN_CHECK_OPTIONS "SparkR_$VERSION.tar.gz"
+else
+  # This will run tests and/or build vignettes, and require SPARK_HOME
+  SPARK_HOME="${SPARK_HOME}" "$R_SCRIPT_PATH/R" CMD check $CRAN_CHECK_OPTIONS "SparkR_$VERSION.tar.gz"
+fi
 
 popd > /dev/null