update

.gitignore

@@ -1,9 +1,12 @@
 *~
+*.#*
+*#*#
 *.swp
 *.ipr
 *.iml
 *.iws
 .idea/
+.idea_modules/
 sbt/*.jar
 .settings
 .cache
@@ -15,11 +18,12 @@ out/
 third_party/libmesos.so
 third_party/libmesos.dylib
 conf/java-opts
-conf/spark-env.sh
-conf/streaming-env.sh
-conf/log4j.properties
-conf/spark-defaults.conf
-conf/hive-site.xml
+conf/*.sh
+conf/*.cmd
+conf/*.properties
+conf/*.conf
+conf/*.xml
+conf/slaves
 docs/_site
 docs/api
 target/
@@ -50,7 +54,6 @@ unit-tests.log
 /lib/
 rat-results.txt
 scalastyle.txt
-conf/*.conf
 scalastyle-output.xml
 
 # For Hive

.rat-excludes

@@ -19,7 +19,9 @@ log4j.properties
 log4j.properties.template
 metrics.properties.template
 slaves
+slaves.template
 spark-env.sh
+spark-env.cmd
 spark-env.sh.template
 log4j-defaults.properties
 bootstrap-tooltip.js
@@ -58,3 +60,4 @@ dist/*
 .*iws
 logs
 .*scalastyle-output.xml
+.*dependency-reduced-pom.xml

CONTRIBUTING.md

@@ -0,0 +1,12 @@
+## 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.
+
+Please see the [Contributing to Spark wiki page](https://cwiki.apache.org/SPARK/Contributing+to+Spark)
+for more information.

README.md

@@ -13,16 +13,19 @@ and Spark Streaming for stream processing.
 ## Online Documentation
 
 You can find the latest Spark documentation, including a programming
-guide, on the project webpage at <http://spark.apache.org/documentation.html>.
+guide, on the [project web page](http://spark.apache.org/documentation.html).
 This README file only contains basic setup instructions.
 
 ## Building Spark
 
-Spark is built on Scala 2.10. To build Spark and its example programs, run:
+Spark is built using [Apache Maven](http://maven.apache.org/).
+To build Spark and its example programs, run:
 
-    ./sbt/sbt assembly
+    mvn -DskipTests clean package
 
 (You do not need to do this if you downloaded a pre-built package.)
+More detailed documentation is available from the project site, at
+["Building Spark"](http://spark.apache.org/docs/latest/building-spark.html).
 
 ## Interactive Scala Shell
 
@@ -71,73 +74,24 @@ can be run using:
 
     ./dev/run-tests
 
+Please see the guidance on how to 
+[run all automated tests](https://cwiki.apache.org/confluence/display/SPARK/Contributing+to+Spark#ContributingtoSpark-AutomatedTesting).
+
 ## A Note About Hadoop Versions
 
 Spark uses the Hadoop core library to talk to HDFS and other Hadoop-supported
 storage systems. Because the protocols have changed in different versions of
 Hadoop, you must build Spark against the same version that your cluster runs.
-You can change the version by setting `-Dhadoop.version` when building Spark.
-
-For Apache Hadoop versions 1.x, Cloudera CDH MRv1, and other Hadoop
-versions without YARN, use:
-
-    # Apache Hadoop 1.2.1
-    $ sbt/sbt -Dhadoop.version=1.2.1 assembly
-
-    # Cloudera CDH 4.2.0 with MapReduce v1
-    $ sbt/sbt -Dhadoop.version=2.0.0-mr1-cdh4.2.0 assembly
-
-For Apache Hadoop 2.2.X, 2.1.X, 2.0.X, 0.23.x, Cloudera CDH MRv2, and other Hadoop versions
-with YARN, also set `-Pyarn`:
-
-    # Apache Hadoop 2.0.5-alpha
-    $ sbt/sbt -Dhadoop.version=2.0.5-alpha -Pyarn assembly
-
-    # Cloudera CDH 4.2.0 with MapReduce v2
-    $ sbt/sbt -Dhadoop.version=2.0.0-cdh4.2.0 -Pyarn assembly
-
-    # Apache Hadoop 2.2.X and newer
-    $ sbt/sbt -Dhadoop.version=2.2.0 -Pyarn assembly
-
-When developing a Spark application, specify the Hadoop version by adding the
-"hadoop-client" artifact to your project's dependencies. For example, if you're
-using Hadoop 1.2.1 and build your application using SBT, add this entry to
-`libraryDependencies`:
-
-    "org.apache.hadoop" % "hadoop-client" % "1.2.1"
 
-If your project is built with Maven, add this to your POM file's `<dependencies>` section:
-
-    <dependency>
-      <groupId>org.apache.hadoop</groupId>
-      <artifactId>hadoop-client</artifactId>
-      <version>1.2.1</version>
-    </dependency>
-
-
-## A Note About Thrift JDBC server and CLI for Spark SQL
-
-Spark SQL supports Thrift JDBC server and CLI.
-See sql-programming-guide.md for more information about using the JDBC server and CLI.
-You can use those features by setting `-Phive` when building Spark as follows.
-
-    $ sbt/sbt -Phive  assembly
+Please refer to the build documentation at
+["Specifying the Hadoop Version"](http://spark.apache.org/docs/latest/building-spark.html#specifying-the-hadoop-version)
+for detailed guidance on building for a particular distribution of Hadoop, including
+building for particular Hive and Hive Thriftserver distributions. See also
+["Third Party Hadoop Distributions"](http://spark.apache.org/docs/latest/hadoop-third-party-distributions.html)
+for guidance on building a Spark application that works with a particular
+distribution.
 
 ## Configuration
 
 Please refer to the [Configuration guide](http://spark.apache.org/docs/latest/configuration.html)
 in the online documentation for an overview on how to configure Spark.
-
-
-## 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.
-
-Please see [Contributing to Spark wiki page](https://cwiki.apache.org/SPARK/Contributing+to+Spark)
-for more information.

assembly/pom.xml

@@ -141,7 +141,9 @@
                     <include>com.google.common.**</include>
                   </includes>
                   <excludes>
-                    <exclude>com.google.common.base.Optional**</exclude>
+                    <exclude>com/google/common/base/Absent*</exclude>
+                    <exclude>com/google/common/base/Optional*</exclude>
+                    <exclude>com/google/common/base/Present*</exclude>
                   </excludes>
                 </relocation>
               </relocations>
@@ -347,5 +349,15 @@
         </plugins>
       </build>
     </profile>
+    <profile>
+      <id>kinesis-asl</id>
+      <dependencies>
+        <dependency>
+          <groupId>org.apache.httpcomponents</groupId>
+          <artifactId>httpclient</artifactId>
+          <version>${commons.httpclient.version}</version>
+        </dependency>
+      </dependencies>
+    </profile>
   </profiles>
 </project>

bagel/src/test/resources/log4j.properties

@@ -21,7 +21,7 @@ log4j.appender.file=org.apache.log4j.FileAppender
 log4j.appender.file.append=false
 log4j.appender.file.file=target/unit-tests.log
 log4j.appender.file.layout=org.apache.log4j.PatternLayout
-log4j.appender.file.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss.SSS} %p %c{1}: %m%n
+log4j.appender.file.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss.SSS} %t %p %c{1}: %m%n
 
 # Ignore messages below warning level from Jetty, because it's a bit verbose
 log4j.logger.org.eclipse.jetty=WARN

bin/compute-classpath.cmd

@@ -36,7 +36,13 @@ rem Load environment variables from conf\spark-env.cmd, if it exists
 if exist "%FWDIR%conf\spark-env.cmd" call "%FWDIR%conf\spark-env.cmd"
 
 rem Build up classpath
-set CLASSPATH=%SPARK_CLASSPATH%;%SPARK_SUBMIT_CLASSPATH%;%FWDIR%conf
+set CLASSPATH=%SPARK_CLASSPATH%;%SPARK_SUBMIT_CLASSPATH%
+
+if not "x%SPARK_CONF_DIR%"=="x" (
+  set CLASSPATH=%CLASSPATH%;%SPARK_CONF_DIR%
+) else (
+  set CLASSPATH=%CLASSPATH%;%FWDIR%conf
+)
 
 if exist "%FWDIR%RELEASE" (
   for %%d in ("%FWDIR%lib\spark-assembly*.jar") do (

bin/compute-classpath.sh

@@ -27,8 +27,14 @@ FWDIR="$(cd "`dirname "$0"`"/..; pwd)"
 
 . "$FWDIR"/bin/load-spark-env.sh
 
+CLASSPATH="$SPARK_CLASSPATH:$SPARK_SUBMIT_CLASSPATH"
+
 # Build up classpath
-CLASSPATH="$SPARK_CLASSPATH:$SPARK_SUBMIT_CLASSPATH:$FWDIR/conf"
+if [ -n "$SPARK_CONF_DIR" ]; then
+  CLASSPATH="$CLASSPATH:$SPARK_CONF_DIR"
+else
+  CLASSPATH="$CLASSPATH:$FWDIR/conf"
+fi
 
 ASSEMBLY_DIR="$FWDIR/assembly/target/scala-$SCALA_VERSION"
 

bin/pyspark

@@ -50,9 +50,44 @@ fi
 
 . "$FWDIR"/bin/load-spark-env.sh
 
-# Figure out which Python executable to use
+# In Spark <= 1.1, setting IPYTHON=1 would cause the driver to be launched using the `ipython`
+# executable, while the worker would still be launched using PYSPARK_PYTHON.
+#
+# In Spark 1.2, we removed the documentation of the IPYTHON and IPYTHON_OPTS variables and added
+# PYSPARK_DRIVER_PYTHON and PYSPARK_DRIVER_PYTHON_OPTS to allow IPython to be used for the driver.
+# Now, users can simply set PYSPARK_DRIVER_PYTHON=ipython to use IPython and set
+# PYSPARK_DRIVER_PYTHON_OPTS to pass options when starting the Python driver
+# (e.g. PYSPARK_DRIVER_PYTHON_OPTS='notebook').  This supports full customization of the IPython
+# and executor Python executables.
+#
+# For backwards-compatibility, we retain the old IPYTHON and IPYTHON_OPTS variables.
+
+# Determine the Python executable to use if PYSPARK_PYTHON or PYSPARK_DRIVER_PYTHON isn't set:
+if hash python2.7 2>/dev/null; then
+  # Attempt to use Python 2.7, if installed:
+  DEFAULT_PYTHON="python2.7"
+else
+  DEFAULT_PYTHON="python"
+fi
+
+# Determine the Python executable to use for the driver:
+if [[ -n "$IPYTHON_OPTS" || "$IPYTHON" == "1" ]]; then
+  # If IPython options are specified, assume user wants to run IPython
+  # (for backwards-compatibility)
+  PYSPARK_DRIVER_PYTHON_OPTS="$PYSPARK_DRIVER_PYTHON_OPTS $IPYTHON_OPTS"
+  PYSPARK_DRIVER_PYTHON="ipython"
+elif [[ -z "$PYSPARK_DRIVER_PYTHON" ]]; then
+  PYSPARK_DRIVER_PYTHON="${PYSPARK_PYTHON:-"$DEFAULT_PYTHON"}"
+fi
+
+# Determine the Python executable to use for the executors:
 if [[ -z "$PYSPARK_PYTHON" ]]; then
-  PYSPARK_PYTHON="python"
+  if [[ $PYSPARK_DRIVER_PYTHON == *ipython* && $DEFAULT_PYTHON != "python2.7" ]]; then
+    echo "IPython requires Python 2.7+; please install python2.7 or set PYSPARK_PYTHON" 1>&2
+    exit 1
+  else
+    PYSPARK_PYTHON="$DEFAULT_PYTHON"
+  fi
 fi
 export PYSPARK_PYTHON
 
@@ -64,11 +99,6 @@ export PYTHONPATH="$SPARK_HOME/python/lib/py4j-0.8.2.1-src.zip:$PYTHONPATH"
 export OLD_PYTHONSTARTUP="$PYTHONSTARTUP"
 export PYTHONSTARTUP="$FWDIR/python/pyspark/shell.py"
 
-# If IPython options are specified, assume user wants to run IPython
-if [[ -n "$IPYTHON_OPTS" ]]; then
-  IPYTHON=1
-fi
-
 # Build up arguments list manually to preserve quotes and backslashes.
 # We export Spark submit arguments as an environment variable because shell.py must run as a
 # PYTHONSTARTUP script, which does not take in arguments. This is required for IPython notebooks.
@@ -88,9 +118,9 @@ if [[ -n "$SPARK_TESTING" ]]; then
   unset YARN_CONF_DIR
   unset HADOOP_CONF_DIR
   if [[ -n "$PYSPARK_DOC_TEST" ]]; then
-    exec "$PYSPARK_PYTHON" -m doctest $1
+    exec "$PYSPARK_DRIVER_PYTHON" -m doctest $1
   else
-    exec "$PYSPARK_PYTHON" $1
+    exec "$PYSPARK_DRIVER_PYTHON" $1
   fi
   exit
 fi
@@ -106,10 +136,5 @@ if [[ "$1" =~ \.py$ ]]; then
 else
   # PySpark shell requires special handling downstream
   export PYSPARK_SHELL=1
-  # Only use ipython if no command line arguments were provided [SPARK-1134]
-  if [[ "$IPYTHON" = "1" ]]; then
-    exec ${PYSPARK_PYTHON:-ipython} $IPYTHON_OPTS
-  else
-    exec "$PYSPARK_PYTHON"
-  fi
+  exec "$PYSPARK_DRIVER_PYTHON" $PYSPARK_DRIVER_PYTHON_OPTS
 fi

bin/pyspark2.cmd

@@ -33,7 +33,7 @@ for %%d in ("%FWDIR%assembly\target\scala-%SCALA_VERSION%\spark-assembly*hadoop*
 )
 if [%FOUND_JAR%] == [0] (
   echo Failed to find Spark assembly JAR.
-  echo You need to build Spark with sbt\sbt assembly before running this program.
+  echo You need to build Spark before running this program.
   goto exit
 )
 :skip_build_test

bin/run-example2.cmd

@@ -52,7 +52,7 @@ if exist "%FWDIR%RELEASE" (
 )
 if "x%SPARK_EXAMPLES_JAR%"=="x" (
   echo Failed to find Spark examples assembly JAR.
-  echo You need to build Spark with sbt\sbt assembly before running this program.
+  echo You need to build Spark before running this program.
   goto exit
 )
 

bin/spark-class

@@ -105,7 +105,7 @@ else
     exit 1
   fi
 fi
-JAVA_VERSION=$("$RUNNER" -version 2>&1 | sed 's/.* version "\(.*\)\.\(.*\)\..*"/\1\2/; 1q')
+JAVA_VERSION=$("$RUNNER" -version 2>&1 | grep 'version' | sed 's/.* version "\(.*\)\.\(.*\)\..*"/\1\2/; 1q')
 
 # Set JAVA_OPTS to be able to load native libraries and to set heap size
 if [ "$JAVA_VERSION" -ge 18 ]; then
@@ -146,7 +146,7 @@ fi
 if [[ "$1" =~ org.apache.spark.tools.* ]]; then
   if test -z "$SPARK_TOOLS_JAR"; then
     echo "Failed to find Spark Tools Jar in $FWDIR/tools/target/scala-$SCALA_VERSION/" 1>&2
-    echo "You need to build spark before running $1." 1>&2
+    echo "You need to build Spark before running $1." 1>&2
     exit 1
   fi
   CLASSPATH="$CLASSPATH:$SPARK_TOOLS_JAR"

bin/spark-class2.cmd

@@ -104,7 +104,7 @@ for %%d in ("%FWDIR%assembly\target\scala-%SCALA_VERSION%\spark-assembly*hadoop*
 )
 if "%FOUND_JAR%"=="0" (
   echo Failed to find Spark assembly JAR.
-  echo You need to build Spark with sbt\sbt assembly before running this program.
+  echo You need to build Spark before running this program.
   goto exit
 )
 :skip_build_test

bin/spark-shell.cmd

@@ -17,6 +17,7 @@ rem See the License for the specific language governing permissions and
 rem limitations under the License.
 rem
 
-set SPARK_HOME=%~dp0..
+rem This is the entry point for running Spark shell. To avoid polluting the
+rem environment, it just launches a new cmd to do the real work.
 
-cmd /V /E /C %SPARK_HOME%\bin\spark-submit.cmd --class org.apache.spark.repl.Main %* spark-shell
+cmd /V /E /C %~dp0spark-shell2.cmd %*