cassandra_model_spark 0.0.1.5-java

data/ext/scala_helper/marshal_row_mapping.scala

@@ -0,0 +1,85 @@
+package org.apache.spark.api.cassandra_model
+
+import scala.collection.mutable._
+import org.apache.spark.rdd._
+import org.apache.spark.sql._
+import com.datastax.spark.connector._
+import com.datastax.spark.connector.rdd._
+import org.apache.spark.sql.types._
+
+object MapStringStringRowMapping {
+  private def canDecode(blob: Array[Byte]) = {
+    new String(blob.slice(0, 4)) == "MRSH"
+  }
+
+  private def decodeValue(blob: Array[Byte]): AnyRef = {
+    if (canDecode(blob)) {
+      val decoder = new MarshalLoader(blob)
+      val value = decoder.getValue()
+
+      value match {
+        case (m: Map[_, _]) => m map { case (key, value) => (String.valueOf(key), String.valueOf(value)) }
+        case _ => new IllegalArgumentException("Unsupported Ruby Type")
+      }
+    } else {
+      blob
+    }
+  }
+
+  private def updatedRow(row: CassandraRow): CassandraRow = {
+    val columns = row.columnNames
+    val values = row.columnValues.map{
+      value => value match {
+        case (blob: Array[Byte]) => decodeValue(blob)
+        case _ => value
+      }
+    }
+
+    new CassandraRow(columns, values)
+  }
+
+  def mappedRDD(rdd: RDD[CassandraRow]): RDD[CassandraRow] = {
+    rdd.map(
+      row => updatedRow(row)
+    )
+  }
+}
+
+object SparkRowRowMapping {
+  private def canDecode(blob: Array[Byte]) = {
+    new String(blob.slice(0, 4)) == "MRSH"
+  }
+
+  private def decodeValue(blob: Array[Byte]): AnyRef = {
+    if (canDecode(blob)) {
+      val decoder = new MarshalLoader(blob)
+      val value = decoder.getValue()
+
+      value match {
+        case (m: Map[_, _]) => Row.fromSeq(m.values.toSeq)
+        case (a: Array[_]) => Row.fromSeq(a.toSeq)
+        case _ => new IllegalArgumentException("Unsupported Ruby Type")
+      }
+    } else {
+      blob
+    }
+  }
+
+  private def updatedRow(row: CassandraRow): CassandraRow = {
+    val columns = row.columnNames
+    val values = row.columnValues.map{
+      value => value match {
+        case (blob: Array[Byte]) => decodeValue(blob)
+        case _ => value
+      }
+    }
+
+    new CassandraRow(columns, values)
+  }
+
+  def mappedRDD(rdd: RDD[CassandraRow]): RDD[CassandraRow] = {
+    rdd.map(
+      row => updatedRow(row)
+    )
+  }
+}

data/ext/scala_helper/project/plugins.sbt

@@ -0,0 +1,6 @@
+
+resolvers += Resolver.url("artifactory", url("http://scalasbt.artifactoryonline.com/scalasbt/sbt-plugin-releases"))(Resolver.ivyStylePatterns)
+resolvers += "Typesafe Repository" at "http://repo.typesafe.com/typesafe/releases/"
+resolvers += "Spray Repository" at "http://repo.spray.cc/"
+addSbtPlugin("com.eed3si9n" % "sbt-assembly" % "0.10.2")
+addSbtPlugin("com.github.gseitz" % "sbt-protobuf" % "0.3.3")

data/ext/scala_helper/sbin/spark-config.sh

@@ -0,0 +1,30 @@
+#
+# 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.
+#
+
+# included in all the spark scripts with source command
+# should not be executable directly
+# also should not be passed any arguments, since we need original $*
+
+# symlink and absolute path should rely on SPARK_HOME to resolve
+if [ -z "${SPARK_HOME}" ]; then
+  export SPARK_HOME="$(cd "`dirname "$0"`"/..; pwd)"
+fi
+
+export SPARK_CONF_DIR="${SPARK_CONF_DIR:-"${SPARK_HOME}/conf"}"
+# Add the PySpark classes to the PYTHONPATH:
+export PYTHONPATH="${SPARK_HOME}/python:${PYTHONPATH}"
+export PYTHONPATH="${SPARK_HOME}/python/lib/py4j-0.9-src.zip:${PYTHONPATH}"

data/ext/scala_helper/sbin/spark-daemon.sh

@@ -0,0 +1,223 @@
+#!/usr/bin/env 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.
+#
+
+# Runs a Spark command as a daemon.
+#
+# Environment Variables
+#
+#   SPARK_CONF_DIR  Alternate conf dir. Default is ${SPARK_HOME}/conf.
+#   SPARK_LOG_DIR   Where log files are stored. ${SPARK_HOME}/logs by default.
+#   SPARK_MASTER    host:path where spark code should be rsync'd from
+#   SPARK_PID_DIR   The pid files are stored. /tmp by default.
+#   SPARK_IDENT_STRING   A string representing this instance of spark. $USER by default
+#   SPARK_NICENESS The scheduling priority for daemons. Defaults to 0.
+##
+
+usage="Usage: spark-daemon.sh [--config <conf-dir>] (start|stop|submit|status) <spark-command> <spark-instance-number> <args...>"
+
+# if no args specified, show usage
+if [ $# -le 1 ]; then
+  echo $usage
+  exit 1
+fi
+
+if [ -z "${SPARK_HOME}" ]; then
+  export SPARK_HOME="$(cd "`dirname "$0"`"/..; pwd)"
+fi
+
+. "${SPARK_HOME}/sbin/spark-config.sh"
+
+# get arguments
+
+# Check if --config is passed as an argument. It is an optional parameter.
+# Exit if the argument is not a directory.
+
+if [ "$1" == "--config" ]
+then
+  shift
+  conf_dir="$1"
+  if [ ! -d "$conf_dir" ]
+  then
+    echo "ERROR : $conf_dir is not a directory"
+    echo $usage
+    exit 1
+  else
+    export SPARK_CONF_DIR="$conf_dir"
+  fi
+  shift
+fi
+
+option=$1
+shift
+command=$1
+shift
+instance=$1
+shift
+
+spark_rotate_log ()
+{
+    log=$1;
+    num=5;
+    if [ -n "$2" ]; then
+	num=$2
+    fi
+    if [ -f "$log" ]; then # rotate logs
+	while [ $num -gt 1 ]; do
+	    prev=`expr $num - 1`
+	    [ -f "$log.$prev" ] && mv "$log.$prev" "$log.$num"
+	    num=$prev
+	done
+	mv "$log" "$log.$num";
+    fi
+}
+
+. "${SPARK_HOME}/bin/load-spark-env.sh"
+
+if [ "$SPARK_IDENT_STRING" = "" ]; then
+  export SPARK_IDENT_STRING="$USER"
+fi
+
+
+export SPARK_PRINT_LAUNCH_COMMAND="1"
+
+# get log directory
+if [ "$SPARK_LOG_DIR" = "" ]; then
+  export SPARK_LOG_DIR="${SPARK_HOME}/logs"
+fi
+mkdir -p "$SPARK_LOG_DIR"
+touch "$SPARK_LOG_DIR"/.spark_test > /dev/null 2>&1
+TEST_LOG_DIR=$?
+if [ "${TEST_LOG_DIR}" = "0" ]; then
+  rm -f "$SPARK_LOG_DIR"/.spark_test
+else
+  chown "$SPARK_IDENT_STRING" "$SPARK_LOG_DIR"
+fi
+
+if [ "$SPARK_PID_DIR" = "" ]; then
+  SPARK_PID_DIR=/tmp
+fi
+
+# some variables
+log="$SPARK_LOG_DIR/spark-$SPARK_IDENT_STRING-$command-$instance-$HOSTNAME.out"
+pid="$SPARK_PID_DIR/spark-$SPARK_IDENT_STRING-$command-$instance.pid"
+
+# Set default scheduling priority
+if [ "$SPARK_NICENESS" = "" ]; then
+    export SPARK_NICENESS=0
+fi
+
+run_command() {
+  mode="$1"
+  shift
+
+  mkdir -p "$SPARK_PID_DIR"
+
+  if [ -f "$pid" ]; then
+    TARGET_ID="$(cat "$pid")"
+    if [[ $(ps -p "$TARGET_ID" -o comm=) =~ "java" ]]; then
+      echo "$command running as process $TARGET_ID.  Stop it first."
+      exit 1
+    fi
+  fi
+
+  if [ "$SPARK_MASTER" != "" ]; then
+    echo rsync from "$SPARK_MASTER"
+    rsync -a -e ssh --delete --exclude=.svn --exclude='logs/*' --exclude='contrib/hod/logs/*' "$SPARK_MASTER/" "${SPARK_HOME}"
+  fi
+
+  spark_rotate_log "$log"
+  echo "starting $command, logging to $log"
+
+  case "$mode" in
+    (class)
+      nohup nice -n "$SPARK_NICENESS" "${SPARK_HOME}"/bin/spark-class $command "$@" >> "$log" 2>&1 < /dev/null &
+      newpid="$!"
+      ;;
+
+    (submit)
+      nohup nice -n "$SPARK_NICENESS" "${SPARK_HOME}"/bin/spark-submit --class $command "$@" >> "$log" 2>&1 < /dev/null &
+      newpid="$!"
+      ;;
+
+    (*)
+      echo "unknown mode: $mode"
+      exit 1
+      ;;
+  esac
+
+  echo "$newpid" > "$pid"
+  sleep 2
+  # Check if the process has died; in that case we'll tail the log so the user can see
+  if [[ ! $(ps -p "$newpid" -o comm=) =~ "java" ]]; then
+    echo "failed to launch $command:"
+    tail -2 "$log" | sed 's/^/  /'
+    echo "full log in $log"
+  fi
+}
+
+case $option in
+
+  (submit)
+    run_command submit "$@"
+    ;;
+
+  (start)
+    run_command class "$@"
+    ;;
+
+  (stop)
+
+    if [ -f $pid ]; then
+      TARGET_ID="$(cat "$pid")"
+      if [[ $(ps -p "$TARGET_ID" -o comm=) =~ "java" ]]; then
+        echo "stopping $command"
+        kill "$TARGET_ID" && rm -f "$pid"
+      else
+        echo "no $command to stop"
+      fi
+    else
+      echo "no $command to stop"
+    fi
+    ;;
+
+  (status)
+
+    if [ -f $pid ]; then
+      TARGET_ID="$(cat "$pid")"
+      if [[ $(ps -p "$TARGET_ID" -o comm=) =~ "java" ]]; then
+        echo $command is running.
+        exit 0
+      else
+        echo $pid file is present but $command not running
+        exit 1
+      fi
+    else
+      echo $command not running.
+      exit 2
+    fi
+    ;;
+
+  (*)
+    echo $usage
+    exit 1
+    ;;
+
+esac
+
+

data/ext/scala_helper/schema_builder.scala

@@ -0,0 +1,35 @@
+package org.apache.spark.api.cassandra_model
+
+import org.apache.spark.rdd._
+import com.datastax.spark.connector._
+import com.datastax.spark.connector.rdd._
+import org.apache.spark.sql._
+import org.apache.spark.sql.types._
+
+class SchemaBuilder {
+  var fields = Array[StructField]()
+
+  def build = StructType(fields)
+
+  def cassandraRDDToRDD(rdd: RDD[CassandraRow]) = {
+    rdd.map(
+      p => Row.fromSeq(
+        p.columnValues.map{
+          p => p match {
+              case (d: java.util.Date) => new java.sql.Timestamp(d.getTime())
+              case _ => p
+            }
+          }
+        )
+    )
+  }
+
+  def createDataFrame(sqlc: SQLContext, rdd: RDD[CassandraRow]) = {
+    val new_rdd = cassandraRDDToRDD(rdd)
+    sqlc.createDataFrame(new_rdd, build)
+  }
+
+  def addColumn(name: String, sql_type: DataType) = {
+    fields :+= StructField(name, sql_type, true)
+  }
+}

data/ext/scala_helper/worker.scala

@@ -0,0 +1,13 @@
+package org.apache.spark.deploy.worker
+
+import org.apache.spark.SparkConf
+
+object RubyWorkerStarter {
+  def startWorker(master_url: String, host: String, port: Int, web_ui_port: Int, conf: SparkConf) = {
+    val temp_conf = new SparkConf
+    val argv = Array(master_url)
+    val args = new WorkerArguments(argv, temp_conf)
+
+    Worker.startRpcEnvAndEndpoint(host, port, web_ui_port, args.cores, args.memory, args.masters, args.workDir, conf = conf)
+  }
+}

data/lib/cassandra_model_spark.rb

@@ -0,0 +1,42 @@
+#--
+# Copyright 2015 Thomas RM Rogers
+#
+# Licensed 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.
+#++
+
+require 'yaml'
+require 'logger'
+
+require 'concurrent'
+require 'cassandra'
+require 'active_support/all'
+require 'active_support/core_ext/class/attribute_accessors'
+require 'thomas_utils'
+require 'batch_reactor'
+require 'cassandra_model'
+require 'rjb' unless RUBY_ENGINE == 'jruby' || CassandraModel.const_defined?('NO_BRIDGE')
+require 'cassandra_model_spark/spark'
+
+unless CassandraModel.const_defined?('NO_BRIDGE')
+  require 'cassandra_model_spark/java_bridge'
+  Dir["#{CassandraModel::Spark.classpath}/*.jar"].each { |file| require file }
+  initialize_java_engine
+  require 'cassandra_model_spark/java_classes'
+end
+
+require 'cassandra_model_spark/raw_connection'
+require 'cassandra_model_spark/connection_cache'
+require 'cassandra_model_spark/record'
+require 'cassandra_model_spark/query_builder'
+require 'cassandra_model_spark/data_frame'
+require 'cassandra_model_spark/column_cast'

data/lib/cassandra_model_spark/build.rb

@@ -0,0 +1,24 @@
+require 'optparse'
+require_relative 'spark'
+
+options = {}
+OptionParser.new do |opts|
+  opts.banner = 'Usage: build.rb [--only-ext]'
+  opts.on('-e', '--only-ext', 'Build only extension') do
+    options[:only_ext] = true
+  end
+end.parse!
+
+ASSEMBLY_PATH = '/ext/scala_helper'
+
+Dir.chdir("#{CassandraModel::Spark.root}#{ASSEMBLY_PATH}") do
+  puts '=> building extension...'
+  cmd = 'sbt package'
+  cmd << ' assemblyPackageDependency' unless options[:only_ext]
+  system(ENV.to_hash.merge('TARGET_DIR' => CassandraModel::Spark.classpath), cmd)
+  %w(bin sbin).each do |path|
+    puts "=> copying #{path}/ to #{CassandraModel::Spark.home}/"
+    `cp -R #{CassandraModel::Spark.root}#{ASSEMBLY_PATH}/#{path}/ #{CassandraModel::Spark.home}/`
+  end
+  `touch #{CassandraModel::Spark.home}/RELEASE`
+end