Change build and run instructions to use assemblies

This commit makes Spark invocation saner by using an assembly JAR to
find all of Spark's dependencies instead of adding all the JARs in
lib_managed. It also packages the examples into an assembly and uses
that as SPARK_EXAMPLES_JAR. Finally, it replaces the old "run" script
with two better-named scripts: "run-examples" for examples, and
"spark-class" for Spark internal classes (e.g. REPL, master, etc). This
is also designed to minimize the confusion people have in trying to use
"run" to run their own classes; it's not meant to do that, but now at
least if they look at it, they can modify run-examples to do a decent
job for them.

As part of this, Bagel's examples are also now properly moved to the
examples package instead of bagel.

2 files changed, 18 insertions, 72 deletions

diff --git a/bin/compute-classpath.sh b/bin/compute-classpath.sh
index 7a21b3c4a1..5dc86c51a4 100755
--- a/bin/compute-classpath.sh
+++ b/bin/compute-classpath.sh
@@ -30,79 +30,25 @@ if [ -e $FWDIR/conf/spark-env.sh ] ; then
   . $FWDIR/conf/spark-env.sh
 fi
 
-CORE_DIR="$FWDIR/core"
-REPL_DIR="$FWDIR/repl"
-REPL_BIN_DIR="$FWDIR/repl-bin"
-EXAMPLES_DIR="$FWDIR/examples"
-BAGEL_DIR="$FWDIR/bagel"
-MLLIB_DIR="$FWDIR/mllib"
-TOOLS_DIR="$FWDIR/tools"
-YARN_DIR="$FWDIR/yarn"
-STREAMING_DIR="$FWDIR/streaming"
-PYSPARK_DIR="$FWDIR/python"
-
 # Build up classpath
-CLASSPATH="$SPARK_CLASSPATH"
-
-function dev_classpath {
-  CLASSPATH="$CLASSPATH:$FWDIR/conf"
-  CLASSPATH="$CLASSPATH:$CORE_DIR/target/scala-$SCALA_VERSION/classes"
-  if [ -n "$SPARK_TESTING" ] ; then
-    CLASSPATH="$CLASSPATH:$CORE_DIR/target/scala-$SCALA_VERSION/test-classes"
-    CLASSPATH="$CLASSPATH:$STREAMING_DIR/target/scala-$SCALA_VERSION/test-classes"
-  fi
-  CLASSPATH="$CLASSPATH:$CORE_DIR/src/main/resources"
-  CLASSPATH="$CLASSPATH:$REPL_DIR/target/scala-$SCALA_VERSION/classes"
-  CLASSPATH="$CLASSPATH:$EXAMPLES_DIR/target/scala-$SCALA_VERSION/classes"
-  CLASSPATH="$CLASSPATH:$STREAMING_DIR/target/scala-$SCALA_VERSION/classes"
-  CLASSPATH="$CLASSPATH:$STREAMING_DIR/lib/org/apache/kafka/kafka/0.7.2-spark/*" # <-- our in-project Kafka Jar
-  if [ -e "$FWDIR/lib_managed" ]; then
-    CLASSPATH="$CLASSPATH:$FWDIR/lib_managed/jars/*"
-    CLASSPATH="$CLASSPATH:$FWDIR/lib_managed/bundles/*"
-  fi
-  CLASSPATH="$CLASSPATH:$REPL_DIR/lib/*"
-  # Add the shaded JAR for Maven builds
-  if [ -e $REPL_BIN_DIR/target ]; then
-    for jar in `find "$REPL_BIN_DIR/target" -name 'spark-repl-*-shaded.jar'`; do
-      CLASSPATH="$CLASSPATH:$jar"
-    done
-    # The shaded JAR doesn't contain examples, so include those separately
-    for jar in `find "$EXAMPLES_DIR/target" -name 'spark-examples*[0-9T].jar'`; do
-      CLASSPATH="$CLASSPATH:$jar"
-    done
-  fi
-  CLASSPATH="$CLASSPATH:$BAGEL_DIR/target/scala-$SCALA_VERSION/classes"
-  CLASSPATH="$CLASSPATH:$MLLIB_DIR/target/scala-$SCALA_VERSION/classes"
-  CLASSPATH="$CLASSPATH:$TOOLS_DIR/target/scala-$SCALA_VERSION/classes"
-  CLASSPATH="$CLASSPATH:$YARN_DIR/target/scala-$SCALA_VERSION/classes"
-  for jar in `find $PYSPARK_DIR/lib -name '*jar'`; do
-    CLASSPATH="$CLASSPATH:$jar"
-  done
-
-  # Add Scala standard library
-  if [ -z "$SCALA_LIBRARY_PATH" ]; then
-    if [ -z "$SCALA_HOME" ]; then
-      echo "SCALA_HOME is not set" >&2
-      exit 1
-    fi
-    SCALA_LIBRARY_PATH="$SCALA_HOME/lib"
-  fi
-  CLASSPATH="$CLASSPATH:$SCALA_LIBRARY_PATH/scala-library.jar"
-  CLASSPATH="$CLASSPATH:$SCALA_LIBRARY_PATH/scala-compiler.jar"
-  CLASSPATH="$CLASSPATH:$SCALA_LIBRARY_PATH/jline.jar"
-}
-
-function release_classpath {
-  CLASSPATH="$CLASSPATH:$FWDIR/jars/*"
-}
-
+CLASSPATH="$SPARK_CLASSPATH:$FWDIR/conf"
 if [ -f "$FWDIR/RELEASE" ]; then
-  release_classpath
+  ASSEMBLY_JAR=`ls "$FWDIR"/jars/spark-assembly*.jar`
 else
-  dev_classpath
+  ASSEMBLY_JAR=`ls "$FWDIR"/assembly/target/scala-$SCALA_VERSION/spark-assembly*.jar`
+fi
+CLASSPATH="$CLASSPATH:$ASSEMBLY_JAR"
+
+# Add test classes if we're running from SBT or Maven with SPARK_TESTING set to 1
+if [[ $SPARK_TESTING == 1 ]]; then
+  CLASSPATH="$CLASSPATH:$FWDIR/core/target/scala-$SCALA_VERSION/test-classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/repl/target/scala-$SCALA_VERSION/test-classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/mllib/target/scala-$SCALA_VERSION/test-classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/bagel/target/scala-$SCALA_VERSION/test-classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/streaming/target/scala-$SCALA_VERSION/test-classes"
 fi
 
-# Add hadoop conf dir - else FileSystem.*, etc fail !
+# Add hadoop conf dir if given -- otherwise FileSystem.*, etc fail !
 # Note, this assumes that there is either a HADOOP_CONF_DIR or YARN_CONF_DIR which hosts
 # the configurtion files.
 if [ "x" != "x$HADOOP_CONF_DIR" ]; then
diff --git a/bin/spark-daemon.sh b/bin/spark-daemon.sh
index 96c71e66ca..eac0774669 100755
--- a/bin/spark-daemon.sh
+++ b/bin/spark-daemon.sh
@@ -87,7 +87,7 @@ TEST_LOG_DIR=$?
 if [ "${TEST_LOG_DIR}" = "0" ]; then
   rm -f $SPARK_LOG_DIR/.spark_test
 else
-  chown $SPARK_IDENT_STRING $SPARK_LOG_DIR 
+  chown $SPARK_IDENT_STRING $SPARK_LOG_DIR
 fi
 
 if [ "$SPARK_PID_DIR" = "" ]; then
@@ -109,7 +109,7 @@ fi
 case $startStop in
 
   (start)
-    
+
     mkdir -p "$SPARK_PID_DIR"
 
     if [ -f $pid ]; then
@@ -128,11 +128,11 @@ case $startStop in
     echo starting $command, logging to $log
     echo "Spark Daemon: $command" > $log
     cd "$SPARK_PREFIX"
-    nohup nice -n $SPARK_NICENESS "$SPARK_PREFIX"/run $command "$@" >> "$log" 2>&1 < /dev/null &
+    nohup nice -n $SPARK_NICENESS "$SPARK_PREFIX"/spark-class $command "$@" >> "$log" 2>&1 < /dev/null &
     echo $! > $pid
     sleep 1; head "$log"
     ;;
-          
+
   (stop)
 
     if [ -f $pid ]; then