Snappy/v2.0.1

.gitignore

@@ -22,6 +22,7 @@
 /lib/
 R-unit-tests.log
 R/unit-tests.out
+R/cran-check.out
 build/*.jar
 build/apache-maven*
 build/scala*

CONTRIBUTING.md

@@ -6,7 +6,7 @@ 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](https://cwiki.apache.org/confluence/display/SPARK/Third+Party+Projects) ?
 - 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

@@ -263,7 +263,7 @@ 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:0.10.1 - http://py4j.sourceforge.net/)
+     (The New BSD License) Py4J (net.sf.py4j:py4j:0.10.3 - 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)

R/.gitignore

@@ -4,3 +4,5 @@
 lib
 pkg/man
 pkg/html
+SparkR.Rcheck/
+SparkR_*.tar.gz

R/check-cran.sh

@@ -43,10 +43,22 @@ $FWDIR/create-docs.sh
 "$R_SCRIPT_PATH/"R CMD build $FWDIR/pkg
 
 # Run check as-cran.
-# TODO(shivaram): Remove the skip tests once we figure out the install mechanism
-
 VERSION=`grep Version $FWDIR/pkg/DESCRIPTION | awk '{print $NF}'`
 
-"$R_SCRIPT_PATH/"R CMD check --as-cran SparkR_"$VERSION".tar.gz
+CRAN_CHECK_OPTIONS="--as-cran"
+
+if [ -n "$NO_TESTS" ]
+then
+  CRAN_CHECK_OPTIONS=$CRAN_CHECK_OPTIONS" --no-tests"
+fi
+
+if [ -n "$NO_MANUAL" ]
+then
+  CRAN_CHECK_OPTIONS=$CRAN_CHECK_OPTIONS" --no-manual"
+fi
+
+echo "Running CRAN check with $CRAN_CHECK_OPTIONS options"
+
+"$R_SCRIPT_PATH/"R CMD check $CRAN_CHECK_OPTIONS SparkR_"$VERSION".tar.gz
 
 popd > /dev/null

R/create-docs.sh

@@ -17,17 +17,26 @@
 # limitations under the License.
 #
 
-# Script to create API docs for SparkR
-# This requires `devtools` and `knitr` to be installed on the machine.
+# Script to create API docs and vignettes for SparkR
+# This requires `devtools`, `knitr` and `rmarkdown` to be installed on the machine.
 
 # After running this script the html docs can be found in 
 # $SPARK_HOME/R/pkg/html
+# The vignettes can be found in
+# $SPARK_HOME/R/pkg/vignettes/sparkr_vignettes.html
 
 set -o pipefail
 set -e
 
 # Figure out where the script is
 export FWDIR="$(cd "`dirname "$0"`"; pwd)"
+export SPARK_HOME="$(cd "`dirname "$0"`"/..; pwd)"
+
+# Required for setting SPARK_SCALA_VERSION
+. "${SPARK_HOME}"/bin/load-spark-env.sh
+
+echo "Using Scala $SPARK_SCALA_VERSION"
+
 pushd $FWDIR
 
 # Install the package (this will also generate the Rd files)
@@ -43,4 +52,21 @@ Rscript -e 'libDir <- "../../lib"; library(SparkR, lib.loc=libDir); library(knit
 
 popd
 
+# Find Spark jars.
+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
+
+# Only create vignettes if Spark JARs exist
+if [ -d "$SPARK_JARS_DIR" ]; then
+  # render creates SparkR vignettes
+  Rscript -e 'library(rmarkdown); paths <- .libPaths(); .libPaths(c("lib", paths)); Sys.setenv(SPARK_HOME=tools::file_path_as_absolute("..")); render("pkg/vignettes/sparkr-vignettes.Rmd"); .libPaths(paths)'
+
+  find pkg/vignettes/. -not -name '.' -not -name '*.Rmd' -not -name '*.md' -not -name '*.pdf' -not -name '*.html' -delete
+else
+  echo "Skipping R vignettes as Spark JARs not found in $SPARK_HOME"
+fi
+
 popd

R/pkg/DESCRIPTION

@@ -1,10 +1,17 @@
 Package: SparkR
 Type: Package
 Title: R Frontend for Apache Spark
-Version: 2.0.0
-Date: 2016-07-07
-Author: The Apache Software Foundation
-Maintainer: Shivaram Venkataraman <shivaram@cs.berkeley.edu>
+Version: 2.0.1
+Date: 2016-08-27
+Authors@R: c(person("Shivaram", "Venkataraman", role = c("aut", "cre"),
+                    email = "shivaram@cs.berkeley.edu"),
+             person("Xiangrui", "Meng", role = "aut",
+                    email = "meng@databricks.com"),
+             person("Felix", "Cheung", role = "aut",
+                    email = "felixcheung@apache.org"),
+             person(family = "The Apache Software Foundation", role = c("aut", "cph")))
+URL: http://www.apache.org/ http://spark.apache.org/
+BugReports: https://cwiki.apache.org/confluence/display/SPARK/Contributing+to+Spark#ContributingtoSpark-ContributingBugReports
 Depends:
     R (>= 3.0),
     methods
@@ -32,6 +39,7 @@ Collate:
     'deserialize.R'
     'functions.R'
     'install.R'
+    'jvm.R'
     'mllib.R'
     'serialize.R'
     'sparkR.R'

R/pkg/NAMESPACE

@@ -1,5 +1,9 @@
 # Imports from base R
-importFrom(methods, setGeneric, setMethod, setOldClass)
+# Do not include stats:: "rpois", "runif" - causes error at runtime
+importFrom("methods", "setGeneric", "setMethod", "setOldClass")
+importFrom("methods", "is", "new", "signature", "show")
+importFrom("stats", "gaussian", "setNames")
+importFrom("utils", "download.file", "packageVersion", "untar")
 
 # Disable native libraries till we figure out how to package it
 # See SPARKR-7839
@@ -11,8 +15,15 @@ export("sparkR.init")
 export("sparkR.stop")
 export("sparkR.session.stop")
 export("sparkR.conf")
+export("sparkR.version")
 export("print.jobj")
 
+export("sparkR.newJObject")
+export("sparkR.callJMethod")
+export("sparkR.callJStatic")
+
+export("install.spark")
+
 export("sparkRSQL.init",
        "sparkRHive.init")
 
@@ -352,5 +363,3 @@ S3method(structField, character)
 S3method(structField, jobj)
 S3method(structType, jobj)
 S3method(structType, structField)
-
-export("install.spark")