Fix computation of classpath when we launch java directly

The previous version assumed that a CLASSPATH environment variable was
set by the "run" script when launching the process that starts the
ExecutorRunner, but unfortunately this is not true in tests. Instead, we
factor the classpath calculation into an extenral script and call that.

NOTE: This includes a Windows version but hasn't yet been tested there.

2 files changed, 141 insertions, 0 deletions

diff --git a/bin/compute-classpath.cmd b/bin/compute-classpath.cmd
new file mode 100644
index 0000000000..1dff8fea22
--- /dev/null
+++ b/bin/compute-classpath.cmd
@@ -0,0 +1,52 @@
+@echo off
+
+rem This script computes Spark's classpath and prints it to stdout; it's used by both the "run"
+rem script and the ExecutorRunner in standalone cluster mode.
+
+set SCALA_VERSION=2.9.3
+
+rem Figure out where the Spark framework is installed
+set FWDIR=%~dp0\..
+
+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"
+
+set CORE_DIR=%FWDIR%core
+set REPL_DIR=%FWDIR%repl
+set EXAMPLES_DIR=%FWDIR%examples
+set BAGEL_DIR=%FWDIR%bagel
+set STREAMING_DIR=%FWDIR%streaming
+set PYSPARK_DIR=%FWDIR%python
+
+rem Build up classpath
+set CLASSPATH=%SPARK_CLASSPATH%;%MESOS_CLASSPATH%;%FWDIR%conf;%CORE_DIR%\target\scala-%SCALA_VERSION%\classes
+set CLASSPATH=%CLASSPATH%;%CORE_DIR%\target\scala-%SCALA_VERSION%\test-classes;%CORE_DIR%\src\main\resources
+set CLASSPATH=%CLASSPATH%;%STREAMING_DIR%\target\scala-%SCALA_VERSION%\classes;%STREAMING_DIR%\target\scala-%SCALA_VERSION%\test-classes
+set CLASSPATH=%CLASSPATH%;%STREAMING_DIR%\lib\org\apache\kafka\kafka\0.7.2-spark\*
+set CLASSPATH=%CLASSPATH%;%REPL_DIR%\target\scala-%SCALA_VERSION%\classes;%EXAMPLES_DIR%\target\scala-%SCALA_VERSION%\classes
+set CLASSPATH=%CLASSPATH%;%FWDIR%lib_managed\jars\*
+set CLASSPATH=%CLASSPATH%;%FWDIR%lib_managed\bundles\*
+set CLASSPATH=%CLASSPATH%;%FWDIR%repl\lib\*
+set CLASSPATH=%CLASSPATH%;%FWDIR%python\lib\*
+set CLASSPATH=%CLASSPATH%;%BAGEL_DIR%\target\scala-%SCALA_VERSION%\classes
+
+rem Add hadoop conf dir - else FileSystem.*, etc fail
+rem Note, this assumes that there is either a HADOOP_CONF_DIR or YARN_CONF_DIR which hosts
+rem the configurtion files.
+if "x%HADOOP_CONF_DIR%"=="x" goto no_hadoop_conf_dir
+  set CLASSPATH=%CLASSPATH%;%HADOOP_CONF_DIR%
+:no_hadoop_conf_dir
+
+if "x%YARN_CONF_DIR%"=="x" goto no_yarn_conf_dir
+  set CLASSPATH=%CLASSPATH%;%YARN_CONF_DIR%
+:no_yarn_conf_dir
+
+rem Add Scala standard library
+set CLASSPATH=%CLASSPATH%;%SCALA_HOME%\lib\scala-library.jar;%SCALA_HOME%\lib\scala-compiler.jar;%SCALA_HOME%\lib\jline.jar
+
+rem A bit of a hack to allow calling this script within run2.cmd without seeing output
+if "x%DONT_PRINT_CLASSPATH%"=="x1" goto exit
+
+echo %CLASSPATH%
+
+:exit
diff --git a/bin/compute-classpath.sh b/bin/compute-classpath.sh
new file mode 100755
index 0000000000..3a78880290
--- /dev/null
+++ b/bin/compute-classpath.sh
@@ -0,0 +1,89 @@
+#!/bin/bash
+
+# This script computes Spark's classpath and prints it to stdout; it's used by both the "run"
+# script and the ExecutorRunner in standalone cluster mode.
+
+SCALA_VERSION=2.9.3
+
+# Figure out where Spark is installed
+FWDIR="$(cd `dirname $0`/..; pwd)"
+
+# Load environment variables from conf/spark-env.sh, if it exists
+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"
+STREAMING_DIR="$FWDIR/streaming"
+PYSPARK_DIR="$FWDIR/python"
+
+# Build up classpath
+CLASSPATH="$SPARK_CLASSPATH"
+CLASSPATH="$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-hadoop*.jar'`; do
+    CLASSPATH="$CLASSPATH:$jar"
+  done
+  # The shaded JAR doesn't contain examples, so include those separately
+  EXAMPLES_JAR=`ls "$EXAMPLES_DIR/target/spark-examples"*[0-9T].jar`
+  CLASSPATH+=":$EXAMPLES_JAR"
+fi
+CLASSPATH="$CLASSPATH:$BAGEL_DIR/target/scala-$SCALA_VERSION/classes"
+for jar in `find $PYSPARK_DIR/lib -name '*jar'`; do
+  CLASSPATH="$CLASSPATH:$jar"
+done
+
+# Figure out the JAR file that our examples were packaged into. This includes a bit of a hack
+# to avoid the -sources and -doc packages that are built by publish-local.
+if [ -e "$EXAMPLES_DIR/target/scala-$SCALA_VERSION/spark-examples"*[0-9T].jar ]; then
+  # Use the JAR from the SBT build
+  export SPARK_EXAMPLES_JAR=`ls "$EXAMPLES_DIR/target/scala-$SCALA_VERSION/spark-examples"*[0-9T].jar`
+fi
+if [ -e "$EXAMPLES_DIR/target/spark-examples"*[0-9T].jar ]; then
+  # Use the JAR from the Maven build
+  export SPARK_EXAMPLES_JAR=`ls "$EXAMPLES_DIR/target/spark-examples"*[0-9T].jar`
+fi
+
+# Add hadoop conf dir - else FileSystem.*, etc fail !
+# Note, this assumes that there is either a HADOOP_CONF_DIR or YARN_CONF_DIR which hosts
+# the configurtion files.
+if [ "x" != "x$HADOOP_CONF_DIR" ]; then
+  CLASSPATH="$CLASSPATH:$HADOOP_CONF_DIR"
+fi
+if [ "x" != "x$YARN_CONF_DIR" ]; then
+  CLASSPATH="$CLASSPATH:$YARN_CONF_DIR"
+fi
+
+# Add Scala standard library
+if [ -z "$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"
+
+echo "$CLASSPATH"