blob: 4c539649a25fa8ed69d343bd66447c4157955647 (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
|
#!/bin/bash
#
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements. See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
# 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"
MLLIB_DIR="$FWDIR/mllib"
STREAMING_DIR="$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-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-$SCALA_VERSION/classes"
CLASSPATH="$CLASSPATH:$MLLIB_DIR/target/scala-$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 "$EXAMPLES_DIR/target/spark-examples"*[0-9T].jar`
fi
# Add Scala standard library
if [ -z "$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/*"
}
if [ -f "$FWDIR/RELEASE" ]; then
release_classpath
else
dev_classpath
fi
# Add hadoop conf dir - else FileSystem.*, etc fail !
# Note, this assumes that there is either a HADOOP_CONF_DIR or YARN_CONF_DIR which hosts
# the configurtion files.
if [ "x" != "x$HADOOP_CONF_DIR" ]; then
CLASSPATH="$CLASSPATH:$HADOOP_CONF_DIR"
fi
if [ "x" != "x$YARN_CONF_DIR" ]; then
CLASSPATH="$CLASSPATH:$YARN_CONF_DIR"
fi
echo "$CLASSPATH"
|
