build.sbt for Spark 1.4.0 + HBase CDH 5.2.0 + elasticsearch-spark 2.1.0 + and so on

build.sbt

import AssemblyKeys._

name := "elasticsearch-spark-project"

version := "1.0-SNAPSHOT"

scalaVersion := "2.10.5"

libraryDependencies ++= Seq(
  "org.apache.spark" %% "spark-core" % "1.4.0" % "provided",
  "org.apache.hadoop" % "hadoop-client" % "2.5.0-cdh5.2.0" % "provided",
  "org.apache.hbase" % "hbase-common" % "0.98.6-cdh5.2.0"
    exclude("tomcat", "jasper-compiler")
    exclude("tomcat", "jasper-runtime")
    exclude("org.apache.hadoop", "hadoop-annotation"),
  "org.apache.hbase" % "hbase-client" % "0.98.6-cdh5.2.0"
    exclude("org.apache.hadoop", "hadoop-annotation")
    exclude("tomcat", "jasper-compiler")
    exclude("tomcat", "jasper-runtime")
    exclude("io.netty", "netty"),
  "org.apache.hbase" % "hbase-server" % "0.98.6-cdh5.2.0"
    exclude("org.apache.hadoop", "hadoop-core")
    exclude("org.apache.hadoop", "hadoop-annotation")
    exclude("org.apache.hadoop", "hadoop-client")
    exclude("org.apache.hadoop", "hadoop-mapreduce-client-jobclient")
    exclude("org.apache.hadoop", "hadoop-mapreduce-client-core")
    exclude("org.apache.hadoop", "hadoop-auth")
    exclude("org.apache.hadoop", "hadoop-annotations")
    exclude("org.apache.hadoop", "hadoop-hdfs")
    exclude("org.apache.hbase", "hadoop-hadoop1-compat")
    exclude("org.apache.commons", "commons-math")
    exclude("com.sun.jersey", "jersey-core")
    exclude("com.sun.jersey", "jersey-server")
    exclude("com.sun.jersey", "jersey-json")
    exclude("org.slf4j", "slf4j-api")
    exclude("commons-io", "commons-io")
    exclude("tomcat", "jasper-compiler")
    exclude("tomcat", "jasper-runtime"),
  "org.json4s" %% "json4s-jackson" % "3.2.11",
  "com.github.nscala-time" %% "nscala-time" % "2.0.0",
  // persistance
  "com.typesafe.slick" %% "slick" % "2.1.0",
  "mysql" % "mysql-connector-java" % "5.1.24",
  "com.mchange" % "c3p0" % "0.9.5",
  // elasticsearch-spark, it only supports scala version 2.10 officially
  // https://www.elastic.co/guide/en/elasticsearch/hadoop/current/install.html#_minimalistic_binaries
  "org.elasticsearch" %% "elasticsearch-spark" % "2.1.0" % "provided",
  "org.scalatest" %% "scalatest" % "2.2.4" % "test"
)

dependencyOverrides += "com.google.guava" % "guava" % "12.0"

dependencyOverrides += "commons-codec" % "commons-codec" % "1.10"

// If using CDH, also add Cloudera repo
resolvers ++= Seq(
  "Cloudera repos" at "https://repository.cloudera.com/artifactory/cloudera-repos"
)

resolvers += Resolver.sonatypeRepo("public")

resolvers += Resolver.mavenLocal

mergeStrategy in assembly := { (old) => old match {
  case PathList("javax", "servlet", xs@_*) => MergeStrategy.first
  case PathList("javax", "transaction", xs@_*) => MergeStrategy.first
  case PathList("javax", "mail", xs@_*) => MergeStrategy.first
  case PathList("javax", "activation", xs@_*) => MergeStrategy.first
  case PathList(ps@_*) if ps.last endsWith ".html" => MergeStrategy.first
  case "application.conf" => MergeStrategy.concat
  case "unwanted.txt" => MergeStrategy.discard
  case x => defaultMergeStrategy(x)
}
}

net.virtualvoid.sbt.graph.Plugin.graphSettings

Include elasticsearch-spark library
spark-submit --packages ...
https://spark-packages.org/package/elastic/elasticsearch-hadoop