Merge remote-tracking branch 'upstream/master' into mllib_pmml_model_export_SPARK-1406

Author: selvinsource

.gitignore

@@ -8,16 +8,19 @@
 *.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
@@ -51,10 +54,11 @@ checkpoint
 derby.log
 dist/
 dev/create-release/*txt
-dev/create-release/*new
+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"](http://spark.apache.org/docs/latest/building-spark.html).
 
 ## Interactive Scala Shell
 

assembly/pom.xml

@@ -39,16 +39,10 @@
     <deb.pkg.name>spark</deb.pkg.name>
     <deb.install.path>/usr/share/spark</deb.install.path>
     <deb.user>root</deb.user>
-    <deb.bin.filemode>744</deb.bin.filemode>
+    <deb.bin.filemode>755</deb.bin.filemode>
   </properties>
 
   <dependencies>
-    <!-- Promote Guava to compile scope in this module so it's included while shading. -->
-    <dependency>
-      <groupId>com.google.guava</groupId>
-      <artifactId>guava</artifactId>
-      <scope>compile</scope>
-    </dependency>
     <dependency>
       <groupId>org.apache.spark</groupId>
       <artifactId>spark-core_${scala.binary.version}</artifactId>
@@ -133,20 +127,6 @@
               <goal>shade</goal>
             </goals>
             <configuration>
-              <relocations>
-                <relocation>
-                  <pattern>com.google</pattern>
-                  <shadedPattern>org.spark-project.guava</shadedPattern>
-                  <includes>
-                    <include>com.google.common.**</include>
-                  </includes>
-                  <excludes>
-                    <exclude>com/google/common/base/Absent*</exclude>
-                    <exclude>com/google/common/base/Optional*</exclude>
-                    <exclude>com/google/common/base/Present*</exclude>
-                  </excludes>
-                </relocation>
-              </relocations>
               <transformers>
                 <transformer implementation="org.apache.maven.plugins.shade.resource.ServicesResourceTransformer" />
                 <transformer implementation="org.apache.maven.plugins.shade.resource.AppendingTransformer">
@@ -169,16 +149,6 @@
   </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>
@@ -310,7 +280,7 @@
                         <user>${deb.user}</user>
                         <group>${deb.user}</group>
                         <prefix>${deb.install.path}/conf</prefix>
-                        <filemode>744</filemode>
+                        <filemode>${deb.bin.filemode}</filemode>
                       </mapper>
                     </data>
                     <data>
@@ -332,7 +302,7 @@
                         <user>${deb.user}</user>
                         <group>${deb.user}</group>
                         <prefix>${deb.install.path}/sbin</prefix>
-                        <filemode>744</filemode>
+                        <filemode>${deb.bin.filemode}</filemode>
                       </mapper>
                     </data>
                     <data>
@@ -343,7 +313,7 @@
                         <user>${deb.user}</user>
                         <group>${deb.user}</group>
                         <prefix>${deb.install.path}/python</prefix>
-                        <filemode>744</filemode>
+                        <filemode>${deb.bin.filemode}</filemode>
                       </mapper>
                     </data>
                   </dataSet>
@@ -364,5 +334,25 @@
         </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

@@ -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/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 "$SPARK_CONF_DIR" ]; then
@@ -46,8 +50,8 @@ fi
 if [ -n "$SPARK_PREPEND_CLASSES" ]; then
   echo "NOTE: SPARK_PREPEND_CLASSES is set, placing locally compiled Spark"\
     "classes ahead of assembly." >&2
+  # Spark classes
   CLASSPATH="$CLASSPATH:$FWDIR/core/target/scala-$SPARK_SCALA_VERSION/classes"
-  CLASSPATH="$CLASSPATH:$FWDIR/core/target/jars/*"
   CLASSPATH="$CLASSPATH:$FWDIR/repl/target/scala-$SPARK_SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/mllib/target/scala-$SPARK_SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/bagel/target/scala-$SPARK_SCALA_VERSION/classes"
@@ -59,6 +63,8 @@ if [ -n "$SPARK_PREPEND_CLASSES" ]; then
   CLASSPATH="$CLASSPATH:$FWDIR/sql/hive/target/scala-$SPARK_SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/sql/hive-thriftserver/target/scala-$SPARK_SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/yarn/stable/target/scala-$SPARK_SCALA_VERSION/classes"
+  # Jars for shaded deps in their original form (copied here during build)
+  CLASSPATH="$CLASSPATH:$FWDIR/core/target/jars/*"
 fi
 
 # Use spark-assembly jar from either RELEASE or assembly directory
@@ -68,22 +74,25 @@ 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 +117,7 @@ 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 "$datanucleus_jars" ]; then
@@ -142,4 +151,11 @@ if [ -n "$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/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