merge master

Author: mengxr

.gitignore

@@ -1,9 +1,12 @@
 *~
+*.#*
+*#*#
 *.swp
 *.ipr
 *.iml
 *.iws
 .idea/
+.idea_modules/
 sbt/*.jar
 .settings
 .cache
@@ -16,9 +19,11 @@ third_party/libmesos.so
 third_party/libmesos.dylib
 conf/java-opts
 conf/*.sh
+conf/*.cmd
 conf/*.properties
 conf/*.conf
 conf/*.xml
+conf/slaves
 docs/_site
 docs/api
 target/

.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

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

@@ -52,10 +52,20 @@ fi
 
 # Figure out which Python executable to use
 if [[ -z "$PYSPARK_PYTHON" ]]; then
-  PYSPARK_PYTHON="python"
+  if [[ "$IPYTHON" = "1" || -n "$IPYTHON_OPTS" ]]; then
+    # for backward compatibility
+    PYSPARK_PYTHON="ipython"
+  else
+    PYSPARK_PYTHON="python"
+  fi
 fi
 export PYSPARK_PYTHON
 
+if [[ -z "$PYSPARK_PYTHON_OPTS" && -n "$IPYTHON_OPTS" ]]; then
+  # for backward compatibility
+  PYSPARK_PYTHON_OPTS="$IPYTHON_OPTS"
+fi
+
 # Add the PySpark classes to the Python path:
 export PYTHONPATH="$SPARK_HOME/python/:$PYTHONPATH"
 export PYTHONPATH="$SPARK_HOME/python/lib/py4j-0.8.2.1-src.zip:$PYTHONPATH"
@@ -64,11 +74,6 @@ export PYTHONPATH="$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.
@@ -106,10 +111,5 @@ 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_PYTHON" $PYSPARK_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

@@ -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"