Apache Spark 2.2.0 Homebrew

apache-spark.rb

class ApacheSpark < Formula
  desc "Engine for large-scale data processing"
  homepage "https://spark.apache.org/"
  url "https://archive.apache.org/dist/spark/spark-2.2.0/spark-2.2.0-bin-hadoop2.7.tgz"
  version "2.2.0"
  sha256 "97fd2cc58e08975d9c4e4ffa8d7f8012c0ac2792bcd9945ce2a561cf937aebcc"
  head "https://github.com/apache/spark.git"

  bottle :unneeded

  def install
    # Rename beeline to distinguish it from hive's beeline
    mv "bin/beeline", "bin/spark-beeline"

    rm_f Dir["bin/*.cmd"]
    libexec.install Dir["*"]
    bin.write_exec_script Dir["#{libexec}/bin/*"]
  end

  test do
    assert_match "Long = 1000", pipe_output(bin/"spark-shell", "sc.parallelize(1 to 1000).count()")
  end
end

Install with:

brew install https://gist.githubusercontent.com/eddies/bc148d83b1fc5555520d0cdf2dff8553/raw/c7ce091a083cacb3519502860695b56b0b806070/apache-spark.rb