first commit

.gitignore

@@ -0,0 +1,19 @@
+**/target/**/*.*
+**/*.log
+**/logs/**/*.*
+vf.gf.*
+**/build/**/*.*
+**/bin/**/*.*
+*.log
+**/.idea/**/*.*
+**/.gradle/**/*.*
+**/gradle/**/*.*
+**/.class
+**/.Rapp.history
+**/.settings
+**/.cache-main
+**/.DS_store
+**/.classpath
+**/.springBeans
+**/server1/**/*.*
+**/locator/**/*.*

ClusteringService/.gitignore

@@ -0,0 +1 @@
+/bin/

ClusteringService/.project

@@ -0,0 +1,31 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<projectDescription>
+	<name>ClusteringService</name>
+	<comment>Apache Spark + Hadoop meetup group. Intro workshop Apr 20</comment>
+	<projects>
+	</projects>
+	<buildSpec>
+		<buildCommand>
+			<name>org.eclipse.wst.common.project.facet.core.builder</name>
+			<arguments>
+			</arguments>
+		</buildCommand>
+		<buildCommand>
+			<name>org.scala-ide.sdt.core.scalabuilder</name>
+			<arguments>
+			</arguments>
+		</buildCommand>
+		<buildCommand>
+			<name>org.springframework.ide.eclipse.core.springbuilder</name>
+			<arguments>
+			</arguments>
+		</buildCommand>
+	</buildSpec>
+	<natures>
+		<nature>org.springframework.ide.eclipse.core.springnature</nature>
+		<nature>org.springsource.ide.eclipse.gradle.core.nature</nature>
+		<nature>org.eclipse.jdt.core.javanature</nature>
+		<nature>org.scala-ide.sdt.core.scalanature</nature>
+		<nature>org.eclipse.wst.common.project.facet.core.nature</nature>
+	</natures>
+</projectDescription>

ClusteringService/all-modules.properties

@@ -0,0 +1,44 @@
+source.file=maven://org.springframework.cloud.stream.app:file-source-rabbit:1.0.0.BUILD-SNAPSHOT
+source.ftp=maven://org.springframework.cloud.stream.app:ftp-source-rabbit:1.0.0.BUILD-SNAPSHOT
+source.jdbc=maven://org.springframework.cloud.stream.app:jdbc-source-rabbit:1.0.0.BUILD-SNAPSHOT
+source.jms=maven://org.springframework.cloud.stream.app:jms-source-rabbit:1.0.0.BUILD-SNAPSHOT
+source.http=maven://org.springframework.cloud.stream.app:http-source-rabbit:1.0.0.BUILD-SNAPSHOT
+source.load-generator=maven://org.springframework.cloud.stream.app:load-generator-source-rabbit:1.0.0.BUILD-SNAPSHOT
+source.rabbit=maven://org.springframework.cloud.stream.app:rabbit-source-rabbit:1.0.0.BUILD-SNAPSHOT
+source.sftp=maven://org.springframework.cloud.stream.app:sftp-source-rabbit:1.0.0.BUILD-SNAPSHOT
+source.tcp=maven://org.springframework.cloud.stream.app:tcp-source-rabbit:1.0.0.BUILD-SNAPSHOT
+source.time=maven://org.springframework.cloud.stream.app:time-source-rabbit:1.0.0.BUILD-SNAPSHOT
+source.trigger=maven://org.springframework.cloud.stream.app:trigger-source-rabbit:1.0.0.BUILD-SNAPSHOT
+source.twitterstream=maven://org.springframework.cloud.stream.app:twitterstream-source-rabbit:1.0.0.BUILD-SNAPSHOT
+processor.bridge=maven://org.springframework.cloud.stream.app:bridge-processor-rabbit:1.0.0.BUILD-SNAPSHOT
+processor.filter=maven://org.springframework.cloud.stream.app:filter-processor-rabbit:1.0.0.BUILD-SNAPSHOT
+processor.groovy-filter=maven://org.springframework.cloud.stream.app:groovy-filter-processor-rabbit:1.0.0.BUILD-SNAPSHOT
+processor.groovy-transform=maven://org.springframework.cloud.stream.app:groovy-transform-processor-rabbit:1.0.0.BUILD-SNAPSHOT
+processor.httpclient=maven://org.springframework.cloud.stream.app:httpclient-processor-rabbit:1.0.0.BUILD-SNAPSHOT
+
+#processor.pmml=maven://org.springframework.cloud.stream.app:pmml-processor-rabbit:1.0.0.BUILD-SNAPSHOT
+# PATCHED PMML MODULE
+processor.pmml=file:///Users/fmelo/roadshow/PivotalRoadshow2016/pmml-processor-rabbit-1.0.0.BUILD-SNAPSHOT.jar
+
+processor.scriptable-transform=maven://org.springframework.cloud.stream.app:scriptable-transform-processor-rabbit:1.0.0.BUILD-SNAPSHOT
+processor.splitter=maven://org.springframework.cloud.stream.app:splitter-processor-rabbit:1.0.0.BUILD-SNAPSHOT
+processor.transform=maven://org.springframework.cloud.stream.app:transform-processor-rabbit:1.0.0.BUILD-SNAPSHOT
+sink.aggregate-counter=maven://org.springframework.cloud.stream.app:aggregate-counter-sink-rabbit:1.0.0.BUILD-SNAPSHOT
+sink.cassandra=maven://org.springframework.cloud.stream.app:cassandra-sink-rabbit:1.0.0.BUILD-SNAPSHOT
+sink.counter=maven://org.springframework.cloud.stream.app:counter-sink-rabbit:1.0.0.BUILD-SNAPSHOT
+sink.field-value-counter=maven://org.springframework.cloud.stream.app:field-value-counter-sink-rabbit:1.0.0.BUILD-SNAPSHOT
+sink.file=maven://org.springframework.cloud.stream.app:file-sink-rabbit:1.0.0.BUILD-SNAPSHOT
+sink.ftp=maven://org.springframework.cloud.stream.app:ftp-sink-rabbit:1.0.0.BUILD-SNAPSHOT
+sink.gemfire=maven://org.springframework.cloud.stream.app:gemfire-sink-rabbit:1.0.0.BUILD-SNAPSHOT
+sink.gpfdist=maven://org.springframework.cloud.stream.app:gpfdist-sink-rabbit:1.0.0.BUILD-SNAPSHOT
+sink.hdfs=maven://org.springframework.cloud.stream.app:hdfs-sink-rabbit:1.0.0.BUILD-SNAPSHOT
+sink.jdbc=maven://org.springframework.cloud.stream.app:jdbc-sink-rabbit:1.0.0.BUILD-SNAPSHOT
+sink.log=maven://org.springframework.cloud.stream.app:log-sink-rabbit:1.0.0.BUILD-SNAPSHOT
+sink.rabbit=maven://org.springframework.cloud.stream.app:rabbit-sink-rabbit:1.0.0.BUILD-SNAPSHOT
+sink.redis=maven://org.springframework.cloud.stream.app:redis-sink-rabbit:1.0.0.BUILD-SNAPSHOT
+sink.router=maven://org.springframework.cloud.stream.app:router-sink-rabbit:1.0.0.BUILD-SNAPSHOT
+sink.tcp=maven://org.springframework.cloud.stream.app:tcp-sink-rabbit:1.0.0.BUILD-SNAPSHOT
+sink.throughput=maven://org.springframework.cloud.stream.app:throughput-sink-rabbit:1.0.0.BUILD-SNAPSHOT
+sink.websocket=maven://org.springframework.cloud.stream.app:websocket-sink-rabbit:1.0.0.BUILD-SNAPSHOT
+task.timestamp=maven://org.springframework.cloud.task.app:timestamp-task:1.0.0.BUILD-SNAPSHOT
+

ClusteringService/build.gradle

@@ -0,0 +1,129 @@
+buildscript {
+	ext {
+		springBootVersion = '1.3.3.RELEASE'
+	}
+	repositories {
+		mavenCentral()
+		flatDir dir: "${projectDir}/gradle/plugins"
+
+	}
+	dependencies {
+		classpath("org.springframework.boot:spring-boot-gradle-plugin:${springBootVersion}") 
+		classpath("io.spring.gradle:dependency-management-plugin:0.5.6.RELEASE")		
+	}
+}
+
+apply plugin: 'scala'
+apply plugin: 'eclipse'
+apply plugin: 'java'
+apply plugin: 'spring-boot' 
+apply plugin: "io.spring.dependency-management"
+
+
+sourceCompatibility = 1.8
+targetCompatibility = 1.8
+version = '1.0'
+
+sourceSets.main.scala.srcDir "src/main/java"
+sourceSets.main.java.srcDirs = []
+
+
+
+def scalaVersion = '2.10.6'
+
+jar {
+    manifest {
+        attributes 'Main-Class': 'io.pivotal.demo.ClusterTrainingApp'
+    }
+}
+
+
+repositories {
+    mavenCentral()
+    mavenLocal()
+    maven { url "https://repo.spring.io/libs-release/" }
+    maven { url "https://repo.spring.io/libs-snapshot/" }
+    maven { url "http://repo.spring.io/milestone" }
+}
+
+configurations {
+    idea {
+        transitive = true
+    }
+}
+
+
+dependencies {
+
+    compile "org.scala-lang:scala-library:$scalaVersion"
+
+    compile ('org.apache.spark:spark-core_2.10:1.6.0'){
+    	exclude group: 'com.fasterxml.jackson.core'
+		exclude group: 'com.fasterxml.jackson.module'
+		exclude group: 'org.slf4j'
+		exclude group: 'org.eclipse.jetty.orbit'
+	}
+
+
+	compile ('org.apache.spark:spark-mllib_2.10:1.6.0'){
+    	exclude group: 'com.fasterxml.jackson.core'
+		exclude group: 'com.fasterxml.jackson.module'
+		exclude group: 'org.slf4j'
+		exclude group: 'org.eclipse.jetty.orbit'
+	}
+
+	compile('org.springframework.boot:spring-boot-starter-web'){
+		exclude group: 'com.fasterxml.jackson.core'
+		exclude (group: 'org.springframework.boot', module: 'spring-boot-starter-logging')
+
+	}
+
+	compile ('com.fasterxml.jackson.core:jackson-databind:2.6.5')
+
+	compile ('com.fasterxml.jackson.module:jackson-module-scala_2.10:2.6.5')
+
+	compile ('postgresql:postgresql:9.1-901-1.jdbc4')
+
+	compile ('com.databricks:spark-csv_2.10:1.4.0')
+
+	compile ('org.springframework.cloud:spring-cloud-spring-service-connector:1.2.2.RELEASE'){
+		exclude group: 'com.fasterxml.jackson.core'
+		exclude (group: 'org.springframework.boot', module: 'spring-boot-starter-logging')	
+	}
+
+	compile ('org.springframework.cloud:spring-cloud-cloudfoundry-connector:1.2.2.RELEASE'){
+		exclude group: 'com.fasterxml.jackson.core'
+		exclude (group: 'org.springframework.boot', module: 'spring-boot-starter-logging')	
+	}	
+
+	// Spring Cloud Stream	
+	//compile ('org.springframework.cloud:spring-cloud-stream:1.0.0.RELEASE')
+	//compile ('org.springframework.boot:spring-boot-configuration-processor')
+	//compile ('org.springframework.integration:spring-integration-xml'){
+	// 	exclude group: 'commons-logging'
+	//}
+	compile ('org.springframework.boot:spring-boot-starter-logging')
+
+	compile ('com.redislabs:spark-redis:0.1.1'){
+    	exclude group: 'org.slf4j'	
+		exclude group: 'org.scala-lang'
+		exclude group: 'org.apache.spark'	
+	}
+}
+
+
+eclipse {
+	classpath {
+		 containers.remove('org.eclipse.jdt.launching.JRE_CONTAINER')
+		 containers 'org.eclipse.jdt.launching.JRE_CONTAINER/org.eclipse.jdt.internal.debug.ui.launcher.StandardVMType/JavaSE-1.8'
+	}
+}
+
+
+tasks.withType(ScalaCompile) {
+    scalaCompileOptions.useAnt = false
+}
+
+
+
+

ClusteringService/gradle.properties

@@ -0,0 +1,4 @@
+sparkVersion=1.3.1
+spring-cloud-connectors.version=1.2.1.RELEASE
+# speed up gradle invocations with the daemon process
+org.gradle.daemon=true

ClusteringService/gradlew

@@ -0,0 +1,164 @@
+#!/usr/bin/env bash
+
+##############################################################################
+##
+##  Gradle start up script for UN*X
+##
+##############################################################################
+
+# Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script.
+DEFAULT_JVM_OPTS=""
+
+APP_NAME="Gradle"
+APP_BASE_NAME=`basename "$0"`
+
+# Use the maximum available, or set MAX_FD != -1 to use that value.
+MAX_FD="maximum"
+
+warn ( ) {
+    echo "$*"
+}
+
+die ( ) {
+    echo
+    echo "$*"
+    echo
+    exit 1
+}
+
+# OS specific support (must be 'true' or 'false').
+cygwin=false
+msys=false
+darwin=false
+case "`uname`" in
+  CYGWIN* )
+    cygwin=true
+    ;;
+  Darwin* )
+    darwin=true
+    ;;
+  MINGW* )
+    msys=true
+    ;;
+esac
+
+# For Cygwin, ensure paths are in UNIX format before anything is touched.
+if $cygwin ; then
+    [ -n "$JAVA_HOME" ] && JAVA_HOME=`cygpath --unix "$JAVA_HOME"`
+fi
+
+# Attempt to set APP_HOME
+# Resolve links: $0 may be a link
+PRG="$0"
+# Need this for relative symlinks.
+while [ -h "$PRG" ] ; do
+    ls=`ls -ld "$PRG"`
+    link=`expr "$ls" : '.*-> \(.*\)$'`
+    if expr "$link" : '/.*' > /dev/null; then
+        PRG="$link"
+    else
+        PRG=`dirname "$PRG"`"/$link"
+    fi
+done
+SAVED="`pwd`"
+cd "`dirname \"$PRG\"`/" >&-
+APP_HOME="`pwd -P`"
+cd "$SAVED" >&-
+
+CLASSPATH=$APP_HOME/gradle/wrapper/gradle-wrapper.jar
+
+# Determine the Java command to use to start the JVM.
+if [ -n "$JAVA_HOME" ] ; then
+    if [ -x "$JAVA_HOME/jre/sh/java" ] ; then
+        # IBM's JDK on AIX uses strange locations for the executables
+        JAVACMD="$JAVA_HOME/jre/sh/java"
+    else
+        JAVACMD="$JAVA_HOME/bin/java"
+    fi
+    if [ ! -x "$JAVACMD" ] ; then
+        die "ERROR: JAVA_HOME is set to an invalid directory: $JAVA_HOME
+
+Please set the JAVA_HOME variable in your environment to match the
+location of your Java installation."
+    fi
+else
+    JAVACMD="java"
+    which java >/dev/null 2>&1 || die "ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH.
+
+Please set the JAVA_HOME variable in your environment to match the
+location of your Java installation."
+fi
+
+# Increase the maximum file descriptors if we can.
+if [ "$cygwin" = "false" -a "$darwin" = "false" ] ; then
+    MAX_FD_LIMIT=`ulimit -H -n`
+    if [ $? -eq 0 ] ; then
+        if [ "$MAX_FD" = "maximum" -o "$MAX_FD" = "max" ] ; then
+            MAX_FD="$MAX_FD_LIMIT"
+        fi
+        ulimit -n $MAX_FD
+        if [ $? -ne 0 ] ; then
+            warn "Could not set maximum file descriptor limit: $MAX_FD"
+        fi
+    else
+        warn "Could not query maximum file descriptor limit: $MAX_FD_LIMIT"
+    fi
+fi
+
+# For Darwin, add options to specify how the application appears in the dock
+if $darwin; then
+    GRADLE_OPTS="$GRADLE_OPTS \"-Xdock:name=$APP_NAME\" \"-Xdock:icon=$APP_HOME/media/gradle.icns\""
+fi
+
+# For Cygwin, switch paths to Windows format before running java
+if $cygwin ; then
+    APP_HOME=`cygpath --path --mixed "$APP_HOME"`
+    CLASSPATH=`cygpath --path --mixed "$CLASSPATH"`
+
+    # We build the pattern for arguments to be converted via cygpath
+    ROOTDIRSRAW=`find -L / -maxdepth 1 -mindepth 1 -type d 2>/dev/null`
+    SEP=""
+    for dir in $ROOTDIRSRAW ; do
+        ROOTDIRS="$ROOTDIRS$SEP$dir"
+        SEP="|"
+    done
+    OURCYGPATTERN="(^($ROOTDIRS))"
+    # Add a user-defined pattern to the cygpath arguments
+    if [ "$GRADLE_CYGPATTERN" != "" ] ; then
+        OURCYGPATTERN="$OURCYGPATTERN|($GRADLE_CYGPATTERN)"
+    fi
+    # Now convert the arguments - kludge to limit ourselves to /bin/sh
+    i=0
+    for arg in "$@" ; do
+        CHECK=`echo "$arg"|egrep -c "$OURCYGPATTERN" -`
+        CHECK2=`echo "$arg"|egrep -c "^-"`                                 ### Determine if an option
+
+        if [ $CHECK -ne 0 ] && [ $CHECK2 -eq 0 ] ; then                    ### Added a condition
+            eval `echo args$i`=`cygpath --path --ignore --mixed "$arg"`
+        else
+            eval `echo args$i`="\"$arg\""
+        fi
+        i=$((i+1))
+    done
+    case $i in
+        (0) set -- ;;
+        (1) set -- "$args0" ;;
+        (2) set -- "$args0" "$args1" ;;
+        (3) set -- "$args0" "$args1" "$args2" ;;
+        (4) set -- "$args0" "$args1" "$args2" "$args3" ;;
+        (5) set -- "$args0" "$args1" "$args2" "$args3" "$args4" ;;
+        (6) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" ;;
+        (7) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" ;;
+        (8) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" "$args7" ;;
+        (9) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" "$args7" "$args8" ;;
+    esac
+fi
+
+# Split up the JVM_OPTS And GRADLE_OPTS values into an array, following the shell quoting and substitution rules
+function splitJvmOpts() {
+    JVM_OPTS=("$@")
+}
+eval splitJvmOpts $DEFAULT_JVM_OPTS $JAVA_OPTS $GRADLE_OPTS
+JVM_OPTS[${#JVM_OPTS[*]}]="-Dorg.gradle.appname=$APP_BASE_NAME"
+
+exec "$JAVACMD" "${JVM_OPTS[@]}" -classpath "$CLASSPATH" org.gradle.wrapper.GradleWrapperMain "$@"