diff options
Diffstat (limited to 'bin/compute-classpath.sh')
-rwxr-xr-x | bin/compute-classpath.sh | 34 |
1 files changed, 25 insertions, 9 deletions
diff --git a/bin/compute-classpath.sh b/bin/compute-classpath.sh index 7df43a555d..2cf4e381c1 100755 --- a/bin/compute-classpath.sh +++ b/bin/compute-classpath.sh @@ -38,8 +38,10 @@ else JAR_CMD="jar" fi -# First check if we have a dependencies jar. If so, include binary classes with the deps jar -if [ -f "$ASSEMBLY_DIR"/spark-assembly*hadoop*-deps.jar ]; then +# A developer option to prepend more recently compiled Spark classes +if [ -n "$SPARK_PREPEND_CLASSES" ]; then + echo "NOTE: SPARK_PREPEND_CLASSES is set, placing locally compiled Spark"\ + "classes ahead of assembly." >&2 CLASSPATH="$CLASSPATH:$FWDIR/core/target/scala-$SCALA_VERSION/classes" CLASSPATH="$CLASSPATH:$FWDIR/repl/target/scala-$SCALA_VERSION/classes" CLASSPATH="$CLASSPATH:$FWDIR/mllib/target/scala-$SCALA_VERSION/classes" @@ -51,17 +53,31 @@ if [ -f "$ASSEMBLY_DIR"/spark-assembly*hadoop*-deps.jar ]; then CLASSPATH="$CLASSPATH:$FWDIR/sql/core/target/scala-$SCALA_VERSION/classes" CLASSPATH="$CLASSPATH:$FWDIR/sql/hive/target/scala-$SCALA_VERSION/classes" CLASSPATH="$CLASSPATH:$FWDIR/yarn/stable/target/scala-$SCALA_VERSION/classes" +fi - ASSEMBLY_JAR=$(ls "$ASSEMBLY_DIR"/spark-assembly*hadoop*-deps.jar 2>/dev/null) +# Use spark-assembly jar from either RELEASE or assembly directory +if [ -f "$FWDIR/RELEASE" ]; then + assembly_folder="$FWDIR"/lib else - # Else use spark-assembly jar from either RELEASE or assembly directory - if [ -f "$FWDIR/RELEASE" ]; then - ASSEMBLY_JAR=$(ls "$FWDIR"/lib/spark-assembly*hadoop*.jar 2>/dev/null) - else - ASSEMBLY_JAR=$(ls "$ASSEMBLY_DIR"/spark-assembly*hadoop*.jar 2>/dev/null) - fi + 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 $assembly_folder" + echo "You need to build Spark before running this program." + exit 1 +fi +if [ "$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." + 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 |