ahnqirage · ahnqirage · Aug 1, 2016 · Jul 6, 2016 · Jul 6, 2016 · Jul 6, 2016
diff --git a/.gitignore b/.gitignore
@@ -17,6 +17,7 @@
 .idea/
 .idea_modules/
 .project
+.pydevproject
 .scala_dependencies
 .settings
 /lib/
@@ -77,3 +78,7 @@ spark-warehouse/
 # For R session data
 .RData
 .RHistory
+.Rhistory
+*.Rproj
+*.Rproj.*
+
diff --git a/LICENSE b/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:0.9.2 - http://py4j.sourceforge.net/)
+     (The New BSD License) Py4J (net.sf.py4j:py4j:0.10.1 - 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)
@@ -296,3 +296,4 @@ The text of each license is also included at licenses/LICENSE-[project].txt.
      (MIT License) blockUI (http://jquery.malsup.com/block/)
      (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)
diff --git a/NOTICE b/NOTICE
@@ -1,5 +1,5 @@
 Apache Spark
-Copyright 2014 The Apache Software Foundation.
+Copyright 2014 and onwards The Apache Software Foundation.
 
 This product includes software developed at
 The Apache Software Foundation (http://www.apache.org/).

diff --git a/R/DOCUMENTATION.md b/R/DOCUMENTATION.md
@@ -1,12 +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,
+SparkR documentation is generated by using in-source comments and annotated by using
+[`roxygen2`](https://cran.r-project.org/web/packages/roxygen2/index.html). After making changes to the documentation and generating 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"))
-
+```R
+library(devtools)
+devtools::document(pkg="./pkg", roclets=c("rd"))
+```
 You can verify if your changes are good by running
 
     R CMD check pkg/
diff --git a/R/README.md b/R/README.md
@@ -1,12 +1,13 @@
 # R on Spark
 
 SparkR is an R package that provides a light-weight frontend to use Spark from R.
+
 ### Installing sparkR
 
 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: 
-```
+```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
 ./install-dev.sh
@@ -17,8 +18,9 @@ export R_HOME=/home/username/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/mvn -DskipTests -Psparkr package
+
+```bash
+build/mvn -DskipTests -Psparkr package
 ```
 
 #### Running sparkR
@@ -37,8 +39,8 @@ To set other options like driver memory, executor memory etc. you can pass in th
 
 #### 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 
-```
+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
+```R
 # Set this to where Spark is installed
 Sys.setenv(SPARK_HOME="/Users/username/spark")
 # This line loads SparkR from the installed directory
@@ -55,23 +57,25 @@ Once you have made your changes, please include unit tests for them and run exis
 
 #### 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.
+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:
-
-    ./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):
-
-    R -e 'install.packages("testthat", repos="http://cran.us.r-project.org")'
-    ./R/run-tests.sh
+```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
+```
 
 ### Running on YARN
+
 The `./bin/spark-submit` 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
-```
+```bash
 export YARN_CONF_DIR=/etc/hadoop/conf
 ./bin/spark-submit --master yarn examples/src/main/r/dataframe.R
 ```
diff --git a/R/WINDOWS.md b/R/WINDOWS.md
@@ -11,3 +11,23 @@ include Rtools and R in `PATH`.
 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`
+
+##  Unit tests
+
+To run the SparkR unit tests on Windows, the following steps are required —assuming you are in the Spark root directory and do not have Apache Hadoop installed already:
+
+1. Create a folder to download Hadoop related files for Windows. For example, `cd ..` and `mkdir hadoop`.
+
+2. Download the relevant Hadoop bin package from [steveloughran/winutils](https://github.com/steveloughran/winutils). While these are not official ASF artifacts, they are built from the ASF release git hashes by a Hadoop PMC member on a dedicated Windows VM. For further reading, consult [Windows Problems on the Hadoop wiki](https://wiki.apache.org/hadoop/WindowsProblems).
+
+3. Install the files into `hadoop\bin`; make sure that `winutils.exe` and `hadoop.dll` are present.
+
+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:
+
+    ```
+    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
+    ```
+
diff --git a/R/check-cran.sh b/R/check-cran.sh
@@ -0,0 +1,52 @@
+#!/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.
+#
+
+set -o pipefail
+set -e
+
+FWDIR="$(cd `dirname $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))"
+fi
+echo "USING R_HOME = $R_HOME"
+
+# Build the latest docs
+$FWDIR/create-docs.sh
+
+# Build a zip file containing the source package
+"$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 --no-tests SparkR_"$VERSION".tar.gz 
+
+popd > /dev/null
diff --git a/R/install-dev.sh b/R/install-dev.sh
@@ -38,7 +38,12 @@ pushd $FWDIR > /dev/null
 if [ ! -z "$R_HOME" ]
   then
     R_SCRIPT_PATH="$R_HOME/bin"
-   else
+  else
+    # if system wide R_HOME is not found, then exit
+    if [ ! `command -v R` ]; then
+      echo "Cannot find 'R_HOME'. Please specify 'R_HOME' or make sure R is properly installed."
+      exit 1
+    fi
     R_SCRIPT_PATH="$(dirname $(which R))"
 fi
 echo "USING R_HOME = $R_HOME"

diff --git a/R/pkg/.Rbuildignore b/R/pkg/.Rbuildignore
@@ -0,0 +1,5 @@
+^.*\.Rproj$
+^\.Rproj\.user$
+^\.lintr$
+^src-native$
+^html$
diff --git a/R/pkg/DESCRIPTION b/R/pkg/DESCRIPTION
@@ -1,20 +1,18 @@
 Package: SparkR
 Type: Package
-Title: R frontend for Spark
+Title: R Frontend for Apache Spark
 Version: 2.0.0
-Date: 2013-09-09
+Date: 2016-07-07
 Author: The Apache Software Foundation
 Maintainer: Shivaram Venkataraman <shivaram@cs.berkeley.edu>
-Imports:
-    methods
 Depends:
     R (>= 3.0),
     methods,
 Suggests:
     testthat,
     e1071,
     survival
-Description: R frontend for Spark
+Description: The SparkR package provides an R frontend for Apache Spark.
 License: Apache License (== 2.0)
 Collate:
     'schema.R'

diff --git a/R/pkg/NAMESPACE b/R/pkg/NAMESPACE
@@ -6,10 +6,16 @@ importFrom(methods, setGeneric, setMethod, setOldClass)
 #useDynLib(SparkR, stringHashCode)
 
 # S3 methods exported
+export("sparkR.session")
 export("sparkR.init")
 export("sparkR.stop")
+export("sparkR.session.stop")
+export("sparkR.conf")
 export("print.jobj")
 
+export("sparkRSQL.init",
+       "sparkRHive.init")
+
 # MLlib integration
 exportMethods("glm",
               "spark.glm",
@@ -45,6 +51,7 @@ exportMethods("arrange",
               "corr",
               "covar_samp",
               "covar_pop",
+              "createOrReplaceTempView",
               "crosstab",
               "dapply",
               "dapplyCollect",
@@ -61,6 +68,8 @@ exportMethods("arrange",
               "filter",
               "first",
               "freqItems",
+              "gapply",
+              "gapplyCollect",
               "group_by",
               "groupBy",
               "head",
@@ -79,6 +88,7 @@ exportMethods("arrange",
               "orderBy",
               "persist",
               "printSchema",
+              "randomSplit",
               "rbind",
               "registerTempTable",
               "rename",
@@ -99,6 +109,7 @@ exportMethods("arrange",
               "summary",
               "take",
               "transform",
+              "union",
               "unionAll",
               "unique",
               "unpersist",
@@ -109,6 +120,7 @@ exportMethods("arrange",
               "write.df",
               "write.jdbc",
               "write.json",
+              "write.orc",
               "write.parquet",
               "write.text",
               "write.ml")
@@ -185,6 +197,8 @@ exportMethods("%in%",
               "isNaN",
               "isNotNull",
               "isNull",
+              "is.nan",
+              "isnan",
               "kurtosis",
               "lag",
               "last",
@@ -208,6 +222,7 @@ exportMethods("%in%",
               "mean",
               "min",
               "minute",
+              "monotonically_increasing_id",
               "month",
               "months_between",
               "n",
@@ -220,6 +235,7 @@ exportMethods("%in%",
               "over",
               "percent_rank",
               "pmod",
+              "posexplode",
               "quarter",
               "rand",
               "randn",
@@ -248,6 +264,7 @@ exportMethods("%in%",
               "skewness",
               "sort_array",
               "soundex",
+              "spark_partition_id",
               "stddev",
               "stddev_pop",
               "stddev_samp",
@@ -281,22 +298,22 @@ exportMethods("%in%",
 
 exportClasses("GroupedData")
 exportMethods("agg")
-
-export("sparkRSQL.init",
-       "sparkRHive.init")
+exportMethods("pivot")
 
 export("as.DataFrame",
        "cacheTable",
        "clearCache",
        "createDataFrame",
        "createExternalTable",
        "dropTempTable",
+       "dropTempView",
        "jsonFile",
        "loadDF",
        "parquetFile",
        "read.df",
        "read.jdbc",
        "read.json",
+       "read.orc",
        "read.parquet",
        "read.text",
        "spark.lapply",
@@ -324,5 +341,14 @@ export("partitionBy",
        "rowsBetween",
        "rangeBetween")
 
-export("window.partitionBy",
-       "window.orderBy")
+export("windowPartitionBy",
+       "windowOrderBy")
+
+S3method(print, jobj)
+S3method(print, structField)
+S3method(print, structType)
+S3method(print, summary.GeneralizedLinearRegressionModel)
+S3method(structField, character)
+S3method(structField, jobj)
+S3method(structType, jobj)
+S3method(structType, structField)