Merge branch 'master' of github.com:apache/spark into SPARK-3974

.gitignore

@@ -5,18 +5,22 @@
 *.ipr
 *.iml
 *.iws
+*.pyc
 .idea/
 .idea_modules/
-sbt/*.jar
+build/*.jar
 .settings
 .cache
+cache
 .generated-mima*
-/build/
 work/
 out/
 .DS_Store
 third_party/libmesos.so
 third_party/libmesos.dylib
+build/apache-maven*
+build/zinc*
+build/scala*
 conf/java-opts
 conf/*.sh
 conf/*.cmd
@@ -49,9 +53,12 @@ dependency-reduced-pom.xml
 checkpoint
 derby.log
 dist/
-spark-*-bin.tar.gz
+dev/create-release/*txt
+dev/create-release/*final
+spark-*-bin-*.tgz
 unit-tests.log
 /lib/
+ec2/lib/
 rat-results.txt
 scalastyle.txt
 scalastyle-output.xml

.rat-excludes

@@ -64,3 +64,4 @@ dist/*
 logs
 .*scalastyle-output.xml
 .*dependency-reduced-pom.xml
+known_translations

LICENSE

@@ -646,7 +646,8 @@ THE SOFTWARE.
 
 ========================================================================
 For Scala Interpreter classes (all .scala files in repl/src/main/scala
-except for Main.Scala, SparkHelper.scala and ExecutorClassLoader.scala):
+except for Main.Scala, SparkHelper.scala and ExecutorClassLoader.scala),
+and for SerializableMapWrapper in JavaUtils.scala:
 ========================================================================
 
 Copyright (c) 2002-2013 EPFL

README.md

@@ -26,7 +26,7 @@ To build Spark and its example programs, run:
 
 (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 with Maven"](http://spark.apache.org/docs/latest/building-with-maven.html).
+["Building Spark with Maven"](http://spark.apache.org/docs/latest/building-spark.html).
 
 ## Interactive Scala Shell
 

assembly/pom.xml

@@ -21,7 +21,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent</artifactId>
-    <version>1.2.0-SNAPSHOT</version>
+    <version>1.3.0-SNAPSHOT</version>
     <relativePath>../pom.xml</relativePath>
   </parent>
 
@@ -142,8 +142,10 @@
                   </includes>
                   <excludes>
                     <exclude>com/google/common/base/Absent*</exclude>
+                    <exclude>com/google/common/base/Function</exclude>
                     <exclude>com/google/common/base/Optional*</exclude>
                     <exclude>com/google/common/base/Present*</exclude>
+                    <exclude>com/google/common/base/Supplier</exclude>
                   </excludes>
                 </relocation>
               </relocations>
@@ -169,16 +171,6 @@
   </build>
 
   <profiles>
-    <profile>
-      <id>yarn-alpha</id>
-      <dependencies>
-        <dependency>
-          <groupId>org.apache.spark</groupId>
-          <artifactId>spark-yarn-alpha_${scala.binary.version}</artifactId>
-          <version>${project.version}</version>
-        </dependency>
-      </dependencies>
-    </profile>
     <profile>
       <id>yarn</id>
       <dependencies>
@@ -364,5 +356,25 @@
         </dependency>
       </dependencies>
     </profile>
+
+    <!-- Profiles that disable inclusion of certain dependencies. -->
+    <profile>
+      <id>hadoop-provided</id>
+      <properties>
+        <hadoop.deps.scope>provided</hadoop.deps.scope>
+      </properties>
+    </profile>
+    <profile>
+      <id>hive-provided</id>
+      <properties>
+        <hive.deps.scope>provided</hive.deps.scope>
+      </properties>
+    </profile>
+    <profile>
+      <id>parquet-provided</id>
+      <properties>
+        <parquet.deps.scope>provided</parquet.deps.scope>
+      </properties>
+    </profile>
   </profiles>
 </project>

bagel/pom.xml

@@ -21,7 +21,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent</artifactId>
-    <version>1.2.0-SNAPSHOT</version>
+    <version>1.3.0-SNAPSHOT</version>
     <relativePath>../pom.xml</relativePath>
   </parent>
 
@@ -40,15 +40,6 @@
       <artifactId>spark-core_${scala.binary.version}</artifactId>
       <version>${project.version}</version>
     </dependency>
-    <dependency>
-      <groupId>org.eclipse.jetty</groupId>
-      <artifactId>jetty-server</artifactId>
-    </dependency>
-    <dependency>
-      <groupId>org.scalatest</groupId>
-      <artifactId>scalatest_${scala.binary.version}</artifactId>
-      <scope>test</scope>
-    </dependency>
     <dependency>
       <groupId>org.scalacheck</groupId>
       <artifactId>scalacheck_${scala.binary.version}</artifactId>
@@ -58,11 +49,5 @@
   <build>
     <outputDirectory>target/scala-${scala.binary.version}/classes</outputDirectory>
     <testOutputDirectory>target/scala-${scala.binary.version}/test-classes</testOutputDirectory>
-    <plugins>
-      <plugin>
-        <groupId>org.scalatest</groupId>
-        <artifactId>scalatest-maven-plugin</artifactId>
-      </plugin>
-    </plugins>
   </build>
 </project>

bagel/src/test/resources/log4j.properties

@@ -15,10 +15,10 @@
 # limitations under the License.
 #
 
-# Set everything to be logged to the file bagel/target/unit-tests.log
+# Set everything to be logged to the file target/unit-tests.log
 log4j.rootCategory=INFO, file
 log4j.appender.file=org.apache.log4j.FileAppender
-log4j.appender.file.append=false
+log4j.appender.file.append=true
 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} %t %p %c{1}: %m%n

bin/beeline.cmd

@@ -0,0 +1,21 @@
+@echo off
+
+rem
+rem Licensed to the Apache Software Foundation (ASF) under one or more
+rem contributor license agreements.  See the NOTICE file distributed with
+rem this work for additional information regarding copyright ownership.
+rem The ASF licenses this file to You under the Apache License, Version 2.0
+rem (the "License"); you may not use this file except in compliance with
+rem the License.  You may obtain a copy of the License at
+rem
+rem    http://www.apache.org/licenses/LICENSE-2.0
+rem
+rem Unless required by applicable law or agreed to in writing, software
+rem distributed under the License is distributed on an "AS IS" BASIS,
+rem WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+rem See the License for the specific language governing permissions and
+rem limitations under the License.
+rem
+
+set SPARK_HOME=%~dp0..
+cmd /V /E /C %SPARK_HOME%\bin\spark-class.cmd org.apache.hive.beeline.BeeLine %*

bin/compute-classpath.cmd

@@ -109,6 +109,13 @@ if "x%YARN_CONF_DIR%"=="x" goto no_yarn_conf_dir
   set CLASSPATH=%CLASSPATH%;%YARN_CONF_DIR%
 :no_yarn_conf_dir
 
+rem To allow for distributions to append needed libraries to the classpath (e.g. when
+rem using the "hadoop-provided" profile to build Spark), check SPARK_DIST_CLASSPATH and
+rem append it to tbe final classpath.
+if not "x%$SPARK_DIST_CLASSPATH%"=="x" (
+  set CLASSPATH=%CLASSPATH%;%SPARK_DIST_CLASSPATH%
+)
+
 rem A bit of a hack to allow calling this script within run2.cmd without seeing output
 if "%DONT_PRINT_CLASSPATH%"=="1" goto exit
 

bin/compute-classpath.sh

@@ -25,7 +25,11 @@ FWDIR="$(cd "`dirname "$0"`"/..; pwd)"
 
 . "$FWDIR"/bin/load-spark-env.sh
 
-CLASSPATH="$SPARK_CLASSPATH:$SPARK_SUBMIT_CLASSPATH"
+if [ -n "$SPARK_CLASSPATH" ]; then
+  CLASSPATH="$SPARK_CLASSPATH:$SPARK_SUBMIT_CLASSPATH"
+else
+  CLASSPATH="$SPARK_SUBMIT_CLASSPATH"
+fi
 
 # Build up classpath
 if [ -n "$SPARK_CONF_DIR" ]; then
@@ -68,22 +72,25 @@ else
   assembly_folder="$ASSEMBLY_DIR"
 fi
 
-num_jars="$(ls "$assembly_folder" | grep "spark-assembly.*hadoop.*\.jar" | wc -l)"
-if [ "$num_jars" -eq "0" ]; then
-  echo "Failed to find Spark assembly in $assembly_folder"
-  echo "You need to build Spark before running this program."
-  exit 1
-fi
+num_jars=0
+
+for f in ${assembly_folder}/spark-assembly*hadoop*.jar; do
+  if [[ ! -e "$f" ]]; then
+    echo "Failed to find Spark assembly in $assembly_folder" 1>&2
+    echo "You need to build Spark before running this program." 1>&2
+    exit 1
+  fi
+  ASSEMBLY_JAR="$f"
+  num_jars=$((num_jars+1))
+done
+
 if [ "$num_jars" -gt "1" ]; then
-  jars_list=$(ls "$assembly_folder" | grep "spark-assembly.*hadoop.*.jar")
-  echo "Found multiple Spark assembly jars in $assembly_folder:"
-  echo "$jars_list"
-  echo "Please remove all but one jar."
+  echo "Found multiple Spark assembly jars in $assembly_folder:" 1>&2
+  ls ${assembly_folder}/spark-assembly*hadoop*.jar 1>&2
+  echo "Please remove all but one jar." 1>&2
   exit 1
 fi
 
-ASSEMBLY_JAR="$(ls "$assembly_folder"/spark-assembly*hadoop*.jar 2>/dev/null)"
-
 # Verify that versions of java used to build the jars and run Spark are compatible
 jar_error_check=$("$JAR_CMD" -tf "$ASSEMBLY_JAR" nonexistent/class/path 2>&1)
 if [[ "$jar_error_check" =~ "invalid CEN header" ]]; then
@@ -108,7 +115,7 @@ else
   datanucleus_dir="$FWDIR"/lib_managed/jars
 fi
 
-datanucleus_jars="$(find "$datanucleus_dir" 2>/dev/null | grep "datanucleus-.*\\.jar")"
+datanucleus_jars="$(find "$datanucleus_dir" 2>/dev/null | grep "datanucleus-.*\\.jar$")"
 datanucleus_jars="$(echo "$datanucleus_jars" | tr "\n" : | sed s/:$//g)"
 
 if [ -n "$datanucleus_jars" ]; then
@@ -142,4 +149,11 @@ if [ -n "$YARN_CONF_DIR" ]; then
   CLASSPATH="$CLASSPATH:$YARN_CONF_DIR"
 fi
 
+# To allow for distributions to append needed libraries to the classpath (e.g. when
+# using the "hadoop-provided" profile to build Spark), check SPARK_DIST_CLASSPATH and
+# append it to tbe final classpath.
+if [ -n "$SPARK_DIST_CLASSPATH" ]; then
+  CLASSPATH="$CLASSPATH:$SPARK_DIST_CLASSPATH"
+fi
+
 echo "$CLASSPATH"

bin/pyspark

@@ -132,7 +132,5 @@ if [[ "$1" =~ \.py$ ]]; then
   gatherSparkSubmitOpts "$@"
   exec "$FWDIR"/bin/spark-submit "${SUBMISSION_OPTS[@]}" "$primary" "${APPLICATION_OPTS[@]}"
 else
-  # PySpark shell requires special handling downstream
-  export PYSPARK_SHELL=1
   exec "$PYSPARK_DRIVER_PYTHON" $PYSPARK_DRIVER_PYTHON_OPTS
 fi

bin/pyspark2.cmd

@@ -59,7 +59,6 @@ for /f %%i in ('echo %1^| findstr /R "\.py"') do (
 )
 
 if [%PYTHON_FILE%] == [] (
-  set PYSPARK_SHELL=1
   if [%IPYTHON%] == [1] (
 	ipython %IPYTHON_OPTS%
   ) else (

bin/run-example

@@ -35,17 +35,32 @@ else
 fi
 
 if [ -f "$FWDIR/RELEASE" ]; then
-  export SPARK_EXAMPLES_JAR="`ls "$FWDIR"/lib/spark-examples-*hadoop*.jar`"
-elif [ -e "$EXAMPLES_DIR"/target/scala-$SPARK_SCALA_VERSION/spark-examples-*hadoop*.jar ]; then
-  export SPARK_EXAMPLES_JAR="`ls "$EXAMPLES_DIR"/target/scala-$SPARK_SCALA_VERSION/spark-examples-*hadoop*.jar`"
+  JAR_PATH="${FWDIR}/lib"
+else
+  JAR_PATH="${EXAMPLES_DIR}/target/scala-${SPARK_SCALA_VERSION}"
 fi
 
-if [[ -z "$SPARK_EXAMPLES_JAR" ]]; then
-  echo "Failed to find Spark examples assembly in $FWDIR/lib or $FWDIR/examples/target" 1>&2
-  echo "You need to build Spark before running this program" 1>&2
+JAR_COUNT=0
+
+for f in ${JAR_PATH}/spark-examples-*hadoop*.jar; do
+  if [[ ! -e "$f" ]]; then
+    echo "Failed to find Spark examples assembly in $FWDIR/lib or $FWDIR/examples/target" 1>&2
+    echo "You need to build Spark before running this program" 1>&2
+    exit 1
+  fi
+  SPARK_EXAMPLES_JAR="$f"
+  JAR_COUNT=$((JAR_COUNT+1))
+done
+
+if [ "$JAR_COUNT" -gt "1" ]; then
+  echo "Found multiple Spark examples assembly jars in ${JAR_PATH}" 1>&2
+  ls ${JAR_PATH}/spark-examples-*hadoop*.jar 1>&2
+  echo "Please remove all but one jar." 1>&2
   exit 1
 fi
 
+export SPARK_EXAMPLES_JAR
+
 EXAMPLE_MASTER=${MASTER:-"local[*]"}
 
 if [[ ! $EXAMPLE_CLASS == org.apache.spark.examples* ]]; then

bin/spark-class

@@ -29,6 +29,7 @@ FWDIR="$(cd "`dirname "$0"`"/..; pwd)"
 
 # Export this as SPARK_HOME
 export SPARK_HOME="$FWDIR"
+export SPARK_CONF_DIR="${SPARK_CONF_DIR:-"$SPARK_HOME/conf"}"
 
 . "$FWDIR"/bin/load-spark-env.sh
 
@@ -71,6 +72,8 @@ case "$1" in
   'org.apache.spark.executor.MesosExecutorBackend')
     OUR_JAVA_OPTS="$SPARK_JAVA_OPTS $SPARK_EXECUTOR_OPTS"
     OUR_JAVA_MEM=${SPARK_EXECUTOR_MEMORY:-$DEFAULT_MEM}
+    export PYTHONPATH="$FWDIR/python:$PYTHONPATH"
+    export PYTHONPATH="$FWDIR/python/lib/py4j-0.8.2.1-src.zip:$PYTHONPATH"
     ;;
 
   # Spark submit uses SPARK_JAVA_OPTS + SPARK_SUBMIT_OPTS +
@@ -118,8 +121,8 @@ fi
 JAVA_OPTS="$JAVA_OPTS -Xms$OUR_JAVA_MEM -Xmx$OUR_JAVA_MEM"
 
 # Load extra JAVA_OPTS from conf/java-opts, if it exists
-if [ -e "$FWDIR/conf/java-opts" ] ; then
-  JAVA_OPTS="$JAVA_OPTS `cat "$FWDIR"/conf/java-opts`"
+if [ -e "$SPARK_CONF_DIR/java-opts" ] ; then
+  JAVA_OPTS="$JAVA_OPTS `cat "$SPARK_CONF_DIR"/java-opts`"
 fi
 
 # Attention: when changing the way the JAVA_OPTS are assembled, the change must be reflected in CommandUtils.scala!
@@ -148,7 +151,7 @@ fi
 if [[ "$1" =~ org.apache.spark.tools.* ]]; then
   if test -z "$SPARK_TOOLS_JAR"; then
     echo "Failed to find Spark Tools Jar in $FWDIR/tools/target/scala-$SPARK_SCALA_VERSION/" 1>&2
-    echo "You need to build Spark before running $1." 1>&2
+    echo "You need to run \"build/sbt tools/package\" before running $1." 1>&2
     exit 1
   fi
   CLASSPATH="$CLASSPATH:$SPARK_TOOLS_JAR"

bin/spark-shell

@@ -45,6 +45,13 @@ source "$FWDIR"/bin/utils.sh
 SUBMIT_USAGE_FUNCTION=usage
 gatherSparkSubmitOpts "$@"
 
+# SPARK-4161: scala does not assume use of the java classpath,
+# so we need to add the "-Dscala.usejavacp=true" flag mnually. We
+# do this specifically for the Spark shell because the scala REPL
+# has its own class loader, and any additional classpath specified
+# through spark.driver.extraClassPath is not automatically propagated.
+SPARK_SUBMIT_OPTS="$SPARK_SUBMIT_OPTS -Dscala.usejavacp=true"
+
 function main() {
   if $cygwin; then
     # Workaround for issue involving JLine and Cygwin