├── LICENSE ├── README.md ├── blobs_java_driver ├── .gitignore ├── LICENSE.txt ├── README.md ├── pom.xml └── src │ └── main │ └── java │ ├── CassandraImageStore.java │ ├── FileSystemImageStore.java │ └── LoadImage.java └── spark_kafka_streaming ├── .gitignore ├── README.md ├── build.sbt ├── data_model └── email_db.cql └── streaming └── src └── main └── scala └── sparkKafkaDemo ├── Email.scala └── StreamingDirectEmails.scala /LICENSE: -------------------------------------------------------------------------------- 1 | 2 | Apache License 3 | Version 2.0, January 2004 4 | http://www.apache.org/licenses/ 5 | 6 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 7 | 8 | 1. Definitions. 9 | 10 | "License" shall mean the terms and conditions for use, reproduction, 11 | and distribution as defined by Sections 1 through 9 of this document. 12 | 13 | "Licensor" shall mean the copyright owner or entity authorized by 14 | the copyright owner that is granting the License. 15 | 16 | "Legal Entity" shall mean the union of the acting entity and all 17 | other entities that control, are controlled by, or are under common 18 | control with that entity. For the purposes of this definition, 19 | "control" means (i) the power, direct or indirect, to cause the 20 | direction or management of such entity, whether by contract or 21 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 22 | outstanding shares, or (iii) beneficial ownership of such entity. 23 | 24 | "You" (or "Your") shall mean an individual or Legal Entity 25 | exercising permissions granted by this License. 26 | 27 | "Source" form shall mean the preferred form for making modifications, 28 | including but not limited to software source code, documentation 29 | source, and configuration files. 30 | 31 | "Object" form shall mean any form resulting from mechanical 32 | transformation or translation of a Source form, including but 33 | not limited to compiled object code, generated documentation, 34 | and conversions to other media types. 35 | 36 | "Work" shall mean the work of authorship, whether in Source or 37 | Object form, made available under the License, as indicated by a 38 | copyright notice that is included in or attached to the work 39 | (an example is provided in the Appendix below). 40 | 41 | "Derivative Works" shall mean any work, whether in Source or Object 42 | form, that is based on (or derived from) the Work and for which the 43 | editorial revisions, annotations, elaborations, or other modifications 44 | represent, as a whole, an original work of authorship. For the purposes 45 | of this License, Derivative Works shall not include works that remain 46 | separable from, or merely link (or bind by name) to the interfaces of, 47 | the Work and Derivative Works thereof. 48 | 49 | "Contribution" shall mean any work of authorship, including 50 | the original version of the Work and any modifications or additions 51 | to that Work or Derivative Works thereof, that is intentionally 52 | submitted to Licensor for inclusion in the Work by the copyright owner 53 | or by an individual or Legal Entity authorized to submit on behalf of 54 | the copyright owner. For the purposes of this definition, "submitted" 55 | means any form of electronic, verbal, or written communication sent 56 | to the Licensor or its representatives, including but not limited to 57 | communication on electronic mailing lists, source code control systems, 58 | and issue tracking systems that are managed by, or on behalf of, the 59 | Licensor for the purpose of discussing and improving the Work, but 60 | excluding communication that is conspicuously marked or otherwise 61 | designated in writing by the copyright owner as "Not a Contribution." 62 | 63 | "Contributor" shall mean Licensor and any individual or Legal Entity 64 | on behalf of whom a Contribution has been received by Licensor and 65 | subsequently incorporated within the Work. 66 | 67 | 2. Grant of Copyright License. Subject to the terms and conditions of 68 | this License, each Contributor hereby grants to You a perpetual, 69 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 70 | copyright license to reproduce, prepare Derivative Works of, 71 | publicly display, publicly perform, sublicense, and distribute the 72 | Work and such Derivative Works in Source or Object form. 73 | 74 | 3. Grant of Patent License. Subject to the terms and conditions of 75 | this License, each Contributor hereby grants to You a perpetual, 76 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 77 | (except as stated in this section) patent license to make, have made, 78 | use, offer to sell, sell, import, and otherwise transfer the Work, 79 | where such license applies only to those patent claims licensable 80 | by such Contributor that are necessarily infringed by their 81 | Contribution(s) alone or by combination of their Contribution(s) 82 | with the Work to which such Contribution(s) was submitted. If You 83 | institute patent litigation against any entity (including a 84 | cross-claim or counterclaim in a lawsuit) alleging that the Work 85 | or a Contribution incorporated within the Work constitutes direct 86 | or contributory patent infringement, then any patent licenses 87 | granted to You under this License for that Work shall terminate 88 | as of the date such litigation is filed. 89 | 90 | 4. Redistribution. You may reproduce and distribute copies of the 91 | Work or Derivative Works thereof in any medium, with or without 92 | modifications, and in Source or Object form, provided that You 93 | meet the following conditions: 94 | 95 | (a) You must give any other recipients of the Work or 96 | Derivative Works a copy of this License; and 97 | 98 | (b) You must cause any modified files to carry prominent notices 99 | stating that You changed the files; and 100 | 101 | (c) You must retain, in the Source form of any Derivative Works 102 | that You distribute, all copyright, patent, trademark, and 103 | attribution notices from the Source form of the Work, 104 | excluding those notices that do not pertain to any part of 105 | the Derivative Works; and 106 | 107 | (d) If the Work includes a "NOTICE" text file as part of its 108 | distribution, then any Derivative Works that You distribute must 109 | include a readable copy of the attribution notices contained 110 | within such NOTICE file, excluding those notices that do not 111 | pertain to any part of the Derivative Works, in at least one 112 | of the following places: within a NOTICE text file distributed 113 | as part of the Derivative Works; within the Source form or 114 | documentation, if provided along with the Derivative Works; or, 115 | within a display generated by the Derivative Works, if and 116 | wherever such third-party notices normally appear. The contents 117 | of the NOTICE file are for informational purposes only and 118 | do not modify the License. You may add Your own attribution 119 | notices within Derivative Works that You distribute, alongside 120 | or as an addendum to the NOTICE text from the Work, provided 121 | that such additional attribution notices cannot be construed 122 | as modifying the License. 123 | 124 | You may add Your own copyright statement to Your modifications and 125 | may provide additional or different license terms and conditions 126 | for use, reproduction, or distribution of Your modifications, or 127 | for any such Derivative Works as a whole, provided Your use, 128 | reproduction, and distribution of the Work otherwise complies with 129 | the conditions stated in this License. 130 | 131 | 5. Submission of Contributions. Unless You explicitly state otherwise, 132 | any Contribution intentionally submitted for inclusion in the Work 133 | by You to the Licensor shall be under the terms and conditions of 134 | this License, without any additional terms or conditions. 135 | Notwithstanding the above, nothing herein shall supersede or modify 136 | the terms of any separate license agreement you may have executed 137 | with Licensor regarding such Contributions. 138 | 139 | 6. Trademarks. This License does not grant permission to use the trade 140 | names, trademarks, service marks, or product names of the Licensor, 141 | except as required for reasonable and customary use in describing the 142 | origin of the Work and reproducing the content of the NOTICE file. 143 | 144 | 7. Disclaimer of Warranty. Unless required by applicable law or 145 | agreed to in writing, Licensor provides the Work (and each 146 | Contributor provides its Contributions) on an "AS IS" BASIS, 147 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 148 | implied, including, without limitation, any warranties or conditions 149 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 150 | PARTICULAR PURPOSE. You are solely responsible for determining the 151 | appropriateness of using or redistributing the Work and assume any 152 | risks associated with Your exercise of permissions under this License. 153 | 154 | 8. Limitation of Liability. In no event and under no legal theory, 155 | whether in tort (including negligence), contract, or otherwise, 156 | unless required by applicable law (such as deliberate and grossly 157 | negligent acts) or agreed to in writing, shall any Contributor be 158 | liable to You for damages, including any direct, indirect, special, 159 | incidental, or consequential damages of any character arising as a 160 | result of this License or out of the use or inability to use the 161 | Work (including but not limited to damages for loss of goodwill, 162 | work stoppage, computer failure or malfunction, or any and all 163 | other commercial damages or losses), even if such Contributor 164 | has been advised of the possibility of such damages. 165 | 166 | 9. Accepting Warranty or Additional Liability. While redistributing 167 | the Work or Derivative Works thereof, You may choose to offer, 168 | and charge a fee for, acceptance of support, warranty, indemnity, 169 | or other liability obligations and/or rights consistent with this 170 | License. However, in accepting such obligations, You may act only 171 | on Your own behalf and on Your sole responsibility, not on behalf 172 | of any other Contributor, and only if You agree to indemnify, 173 | defend, and hold each Contributor harmless for any liability 174 | incurred by, or claims asserted against, such Contributor by reason 175 | of your accepting any such warranty or additional liability. 176 | 177 | END OF TERMS AND CONDITIONS 178 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # Code Samples 2 | 3 | Code samples from DataStax - Coming Soon! 4 | 5 | ## Support 6 | 7 | The code, examples, and snippets provided in this repository are not "Supported Software" under any DataStax subscriptions or other agreements. 8 | 9 | ## License 10 | 11 | Copyright 2013-2018, DataStax 12 | 13 | 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 14 | 15 | http://www.apache.org/licenses/LICENSE-2.0 16 | 17 | 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. 18 | -------------------------------------------------------------------------------- /blobs_java_driver/.gitignore: -------------------------------------------------------------------------------- 1 | *.class 2 | 3 | # Mobile Tools for Java (J2ME) 4 | .mtj.tmp/ 5 | 6 | # Package Files # 7 | *.jar 8 | *.war 9 | *.ear 10 | 11 | # virtual machine crash logs, see http://www.java.com/en/download/help/error_hotspot.xml 12 | hs_err_pid* 13 | 14 | .idea 15 | .project 16 | *.iml 17 | -------------------------------------------------------------------------------- /blobs_java_driver/LICENSE.txt: -------------------------------------------------------------------------------- 1 | License 2 | 3 | Copyright 2014, DataStax 4 | 5 | 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 6 | 7 | http://www.apache.org/licenses/LICENSE-2.0 8 | 9 | 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. 10 | 11 | This software is not "Supported Software" and, is not supported by DataStax under any software subscription or other agreement. 12 | 13 | See the License for the specific language governing permissions and limitations under the License. -------------------------------------------------------------------------------- /blobs_java_driver/README.md: -------------------------------------------------------------------------------- 1 | You can use any code from this repository in verbatim or modified form as all examples in this repository are covered by the Apache License v2.0. 2 | 3 | But the code, examples, and snippets are not "Supported Software" under any DataStax subscriptions or other agreements. -------------------------------------------------------------------------------- /blobs_java_driver/pom.xml: -------------------------------------------------------------------------------- 1 | 2 | 5 | 4.0.0 6 | 7 | com.datastax 8 | blog_example 9 | 1.0-SNAPSHOT 10 | 11 | 12 | com.datastax.cassandra 13 | cassandra-driver-core 14 | 2.0.2 15 | 16 | 17 | 18 | -------------------------------------------------------------------------------- /blobs_java_driver/src/main/java/CassandraImageStore.java: -------------------------------------------------------------------------------- 1 | import com.datastax.driver.core.Cluster; 2 | import com.datastax.driver.core.ResultSet; 3 | import com.datastax.driver.core.Row; 4 | import com.datastax.driver.core.Session; 5 | 6 | import java.nio.ByteBuffer; 7 | import java.util.ArrayList; 8 | import java.util.List; 9 | 10 | /* Copyright 2014 DataStax 11 | * 12 | * Licensed under the Apache License, Version 2.0 (the "License"); 13 | * you may not use this file except in compliance with the License. 14 | * You may obtain a copy of the License at 15 | * 16 | * http://www.apache.org/licenses/LICENSE-2.0 17 | * 18 | * Unless required by applicable law or agreed to in writing, software 19 | * distributed under the License is distributed on an "AS IS" BASIS, 20 | * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 21 | * See the License for the specific language governing permissions and 22 | * limitations under the License. 23 | */ 24 | public class CassandraImageStore { 25 | /* The code below is intended as a usage example for the blob datatype, 26 | * not as data modeling advice. Cassandra is not designed to be a file 27 | * store and is unlikely to work well as such. 28 | */ 29 | 30 | private final Session session; 31 | private final Cluster cluster; 32 | 33 | public CassandraImageStore(){ 34 | cluster = Cluster.builder() 35 | .addContactPoint("127.0.0.1") 36 | .build(); 37 | session = cluster.connect("est"); 38 | } 39 | public void storeImage(ByteBuffer fileBlob, String imageId){ 40 | session.execute("INSERT INTO images ( image_id, image) values ( ?, ? )", imageId, fileBlob); 41 | } 42 | 43 | public ByteBuffer getImage(String imageId){ 44 | ResultSet rows = session.execute("SELECT image FROM images WHERE image_id = ?", imageId); 45 | List buffers = new ArrayList(); 46 | for(Row row: rows){ 47 | buffers.add(row.getBytes("image")); 48 | } 49 | if(buffers.size() == 1){ 50 | return buffers.get(0); 51 | }else if(buffers.size()>1){ 52 | throw new RuntimeException("More than one matching image for id '" + imageId + "' found"); 53 | } 54 | throw new RuntimeException("None matching images for id '" + imageId + "' found"); 55 | } 56 | 57 | public void shutDown(){ 58 | session.close(); 59 | cluster.close(); 60 | } 61 | } 62 | -------------------------------------------------------------------------------- /blobs_java_driver/src/main/java/FileSystemImageStore.java: -------------------------------------------------------------------------------- 1 | import java.io.IOException; 2 | import java.io.RandomAccessFile; 3 | import java.nio.ByteBuffer; 4 | import java.nio.channels.FileChannel; 5 | 6 | /* Copyright 2014 DataStax 7 | * 8 | * Licensed under the Apache License, Version 2.0 (the "License"); 9 | * you may not use this file except in compliance with the License. 10 | * You may obtain a copy of the License at 11 | * 12 | * http://www.apache.org/licenses/LICENSE-2.0 13 | * 14 | * Unless required by applicable law or agreed to in writing, software 15 | * distributed under the License is distributed on an "AS IS" BASIS, 16 | * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 17 | * See the License for the specific language governing permissions and 18 | * limitations under the License. 19 | */ 20 | public class FileSystemImageStore { 21 | 22 | public void write(String location, ByteBuffer blob) throws IOException { 23 | 24 | ByteBuffer buf = ByteBuffer.allocate(blob.limit()); 25 | buf.clear(); 26 | buf.put(blob); 27 | buf.flip(); 28 | 29 | RandomAccessFile file = new RandomAccessFile(location, "rw"); 30 | FileChannel channel = file.getChannel(); 31 | try { 32 | while (buf.hasRemaining()) { 33 | channel.write(buf); 34 | } 35 | }finally { 36 | channel.force(true); 37 | channel.close(); 38 | } 39 | } 40 | 41 | public ByteBuffer read(String location) throws IOException { 42 | RandomAccessFile file = new RandomAccessFile(location, "r"); 43 | FileChannel channel = file.getChannel(); 44 | ByteBuffer buf = ByteBuffer.allocate((int)channel.size()); 45 | 46 | try { 47 | while(channel.read(buf) > 0 ) { 48 | buf.flip(); 49 | buf.clear(); 50 | } 51 | }finally{ 52 | channel.force(true); 53 | channel.close(); 54 | } 55 | return buf; 56 | } 57 | } 58 | -------------------------------------------------------------------------------- /blobs_java_driver/src/main/java/LoadImage.java: -------------------------------------------------------------------------------- 1 | import java.io.IOException; 2 | import java.nio.ByteBuffer; 3 | 4 | /* Copyright 2014 DataStax 5 | * 6 | * Licensed under the Apache License, Version 2.0 (the "License"); 7 | * you may not use this file except in compliance with the License. 8 | * You may obtain a copy of the License at 9 | * 10 | * http://www.apache.org/licenses/LICENSE-2.0 11 | * 12 | * Unless required by applicable law or agreed to in writing, software 13 | * distributed under the License is distributed on an "AS IS" BASIS, 14 | * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 15 | * See the License for the specific language governing permissions and 16 | * limitations under the License. 17 | */ 18 | public class LoadImage { 19 | 20 | public static void main(String[] args) throws ClassNotFoundException, IOException { 21 | 22 | CassandraImageStore cassandraImageStore = new CassandraImageStore(); 23 | FileSystemImageStore fileSystemImageStore = new FileSystemImageStore(); 24 | try { 25 | String userHome = System.getProperty("user.home"); 26 | String file2 = userHome + "/deleteMe/1.png"; 27 | 28 | ByteBuffer imageBytes = fileSystemImageStore.read(file2); 29 | cassandraImageStore.storeImage(imageBytes, "001"); 30 | fileSystemImageStore.write(userHome + "/deleteMe/writeToFile.png", imageBytes); 31 | 32 | ByteBuffer byteBuffer = cassandraImageStore.getImage("001"); 33 | fileSystemImageStore.write(userHome + "/deleteMe/001.png", byteBuffer); 34 | 35 | System.exit(0); 36 | }finally{ 37 | cassandraImageStore.shutDown(); 38 | } 39 | } 40 | 41 | } -------------------------------------------------------------------------------- /spark_kafka_streaming/.gitignore: -------------------------------------------------------------------------------- 1 | *.class 2 | 3 | # Mobile Tools for Java (J2ME) 4 | .mtj.tmp/ 5 | 6 | # Package Files # 7 | *.jar 8 | *.war 9 | *.ear 10 | 11 | # virtual machine crash logs, see http://www.java.com/en/download/help/error_hotspot.xml 12 | hs_err_pid* 13 | 14 | .idea 15 | .project 16 | *.iml 17 | -------------------------------------------------------------------------------- /spark_kafka_streaming/README.md: -------------------------------------------------------------------------------- 1 | # Spark Streaming with Kafka Direct API Demo 2 | 3 | This demo simulates a stream of email metadata. This example assumes the user has an existing Kafka cluster with email data formatted as "**msg_id::tenant_id::mailbox_id::time_delivered::time_forwarded::time_read::time_replied**". 4 | It is assumed these fields have the following datatypes: 5 | 6 | * msg_id: String 7 | * tenant_id: UUID 8 | * mailbox_id: UUID 9 | * time_delivered: Long 10 | * time_forwarded: Long 11 | * time_read: Long 12 | * time_replied: Long 13 | 14 | ### Setup the KS/Table 15 | 16 | **Note: You can change RF and compaction settings in this CQL script if needed.** 17 | 18 | `cqlsh -f data_model/email_db.cql` 19 | 20 | ### Run Spark Streaming 21 | 22 | ###### Build the streaming jar 23 | `sbt streaming/assembly` 24 | 25 | Parameters: 26 | 27 | 1. kafka broker: Ex. 10.200.185.103:9092 28 | 29 | 2. debug flag (limited use): Ex. true or false 30 | 31 | 3. checkpoint directory name: Ex. dsefs://[optional-ip-address]/emails_checkpoint 32 | 33 | 4. [spark.streaming.kafka.maxRatePerPartition](http://spark.apache.org/docs/latest/configuration.html#spark-streaming): Maximum rate (number of records per second) 34 | 35 | 5. batch interval (ms) 36 | 37 | 6. [auto.offset.reset](http://spark.apache.org/docs/latest/api/scala/index.html#org.apache.spark.streaming.kafka.KafkaUtils$): Ex. smallest or largest 38 | 39 | 7. topic name 40 | 41 | 8. kafka stream type: ex. direct or receiver 42 | 43 | 9. number of partitions to consume per topic (controls read parallelism) (receiver approach: you'll want to match whatever used when creating the topic) 44 | 45 | 10. processesing parallelism (controls write parallelism) (receiver approach: you'll want to match whatever used when creating the topic) 46 | 47 | 11. group.id that id's the consumer processes (receiver approach: you'll want to match whatever used when creating the topic) 48 | 49 | 12. zookeeper connect string (e.g localhost:2181) (receiver approach: you'll want to match whatever used when creating the topic) 50 | 51 | ###### Running on a server in foreground 52 | `dse spark-submit --driver-memory 2G --class sparkKafkaDemo.StreamingDirectEmails streaming/target/scala-2.10/streaming-assembly-0.1.jar :9092 true dsefs://[optional-ip-address]/emails_checkpoint 50000 5000 smallest emails direct 1 100 test-consumer-group localhost:2181` 53 | 54 | ## Support 55 | 56 | The code, examples, and snippets provided in this repository are not "Supported Software" under any DataStax subscriptions or other agreements. 57 | 58 | ## License 59 | 60 | Copyright 2016, DataStax 61 | 62 | 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 63 | 64 | http://www.apache.org/licenses/LICENSE-2.0 65 | 66 | 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. -------------------------------------------------------------------------------- /spark_kafka_streaming/build.sbt: -------------------------------------------------------------------------------- 1 | val DSE_HOME = sys.env.getOrElse("DSE_HOME", sys.env("HOME")+"dse") 2 | val sparkClasspathStr = s"dse spark-classpath".!!.trim 3 | val sparkClasspathArr = sparkClasspathStr.split(':') 4 | 5 | val dseScalaVersionStr = Seq("/bin/sh", "-c", s"ls ${DSE_HOME}/resources/spark/lib/scala-compiler*jar").!!.trim 6 | val dseScalaVersionArr = dseScalaVersionStr.split("-").last.split(".jar")(0).split('.') 7 | val dseScalaVersion = dseScalaVersionArr.mkString(".") 8 | val dseScalaMajorMinorVersion = Seq(dseScalaVersionArr(0), dseScalaVersionArr(1)).mkString(".") 9 | 10 | val DSE_BIN = s"$DSE_HOME/bin/dse" 11 | val dseVersionArr = s"$DSE_BIN -v".!!.trim.split('.') 12 | val dseVersion = Seq(dseVersionArr(0), dseVersionArr(1)).mkString(".") 13 | 14 | // This needs to match whatever Spark version being used in DSE 15 | val sparkVersionStr = Seq("/bin/sh", "-c", s"ls ${DSE_HOME}/resources/spark/lib/spark-core_*jar").!!.trim 16 | val sparkVersionArr = sparkVersionStr.split('-')(2).split('.') // expected: spark-core_2.11-2.0.0.1-2cf48f7.jar 17 | val sparkVersion = Seq(sparkVersionArr(0), sparkVersionArr(1), sparkVersionArr(2)).mkString(".") 18 | val kafkaVersion = "0.8.2.1" // we'll want to generalize this once spark officially supports newer versions 19 | val kafkaMajorVersion = kafkaVersion.split('.')(0) 20 | val kafkaMinorVersion = kafkaVersion.split('.')(1) 21 | val scalaTestVersion = "2.2.4" 22 | val jodaVersion = "2.9" 23 | 24 | val sparkStreamingKafkaDep: String = { 25 | if (dseVersion.toDouble >= 5.1) { 26 | s"spark-streaming-kafka-${kafkaMajorVersion}-${kafkaMinorVersion}" 27 | } else { 28 | "spark-streaming-kafka" 29 | } 30 | } 31 | 32 | // Find all Jars on dse spark-classpath 33 | val sparkClasspath = { 34 | for ( dseJar <- sparkClasspathArr if dseJar.endsWith("jar")) 35 | yield Attributed.blank(file(dseJar)) 36 | }.toSeq 37 | 38 | val globalSettings = Seq( 39 | version := "0.1", 40 | scalaVersion := dseScalaVersion 41 | ) 42 | 43 | lazy val streaming = (project in file("streaming")) 44 | .settings(name := "streaming") 45 | .settings(globalSettings:_*) 46 | .settings(libraryDependencies ++= streamingDeps) 47 | 48 | val akkaVersion = "2.3.11" 49 | 50 | // Do not define in streaming deps if we reference them in existing DSE libs 51 | lazy val streamingDeps = Seq( 52 | "joda-time" % "joda-time" % jodaVersion % "provided", 53 | "org.apache.spark" %% "spark-mllib" % sparkVersion % "provided", 54 | "org.apache.spark" %% "spark-graphx" % sparkVersion % "provided", 55 | "org.apache.spark" %% "spark-sql" % sparkVersion % "provided", 56 | "org.apache.spark" %% "spark-streaming" % sparkVersion % "provided", 57 | "org.apache.spark" %% sparkStreamingKafkaDep % sparkVersion exclude("org.spark-project.spark", "unused"), 58 | "com.databricks" %% "spark-csv" % "1.2.0" 59 | ) 60 | 61 | lazy val printenv = taskKey[Unit]("Prints classpaths and dependencies") 62 | val env = Map("DSE_HOME" -> DSE_HOME, 63 | "dseScalaVersion" -> dseScalaVersion, 64 | "dseVersion" -> dseVersion, 65 | "sparkClasspath" -> sparkClasspath) 66 | 67 | printenv := println(env) 68 | 69 | //Add dse jars to classpath 70 | unmanagedJars in Compile ++= sparkClasspath 71 | unmanagedJars in Test ++= sparkClasspath 72 | -------------------------------------------------------------------------------- /spark_kafka_streaming/data_model/email_db.cql: -------------------------------------------------------------------------------- 1 | CREATE KEYSPACE IF NOT EXISTS email_db WITH replication = {'class':'NetworkTopologyStrategy', 'Analytics':1}; 2 | 3 | CREATE TABLE IF NOT EXISTS email_db.email_msg_tracker ( 4 | msg_id text, 5 | tenant_id uuid, 6 | mailbox_id uuid, 7 | time_delivered timestamp, 8 | time_forwarded timestamp, 9 | time_read timestamp, 10 | time_replied timestamp, 11 | PRIMARY KEY ((msg_id, tenant_id), mailbox_id) 12 | ) WITH CLUSTERING ORDER BY (mailbox_id ASC); 13 | -------------------------------------------------------------------------------- /spark_kafka_streaming/streaming/src/main/scala/sparkKafkaDemo/Email.scala: -------------------------------------------------------------------------------- 1 | package sparkKafkaDemo 2 | 3 | import java.util.UUID 4 | import org.joda.time.DateTime 5 | 6 | case class Email( 7 | msg_id: String, 8 | tenant_id: String, 9 | mailbox_id: String, 10 | time_delivered: Long, 11 | time_forwarded: Long, 12 | time_read: Long, 13 | time_replied: Long 14 | ) 15 | -------------------------------------------------------------------------------- /spark_kafka_streaming/streaming/src/main/scala/sparkKafkaDemo/StreamingDirectEmails.scala: -------------------------------------------------------------------------------- 1 | package sparkKafkaDemo 2 | 3 | import java.util.UUID 4 | import scala.sys 5 | import kafka.serializer.StringDecoder 6 | import org.apache.hadoop.conf.Configuration 7 | import org.apache.spark.storage.StorageLevel 8 | import org.apache.spark.deploy.SparkHadoopUtil 9 | import org.apache.spark.{SparkConf, SparkContext} 10 | import org.apache.spark.rdd.RDD 11 | import org.apache.spark.sql.{SQLContext, SaveMode} 12 | import org.apache.spark.streaming.kafka.{KafkaUtils,OffsetRange,HasOffsetRanges} 13 | import org.apache.spark.streaming.{Milliseconds, StreamingContext, Time} 14 | import org.joda.time.DateTime 15 | 16 | /** This uses the Kafka Direct API introduced in Spark 1.4 17 | * 18 | */ 19 | object StreamingDirectEmails { 20 | 21 | def main(args: Array[String]) { 22 | 23 | if (args.length < 3) { 24 | println("1st paramteter is kafka broker ") 25 | println("2nd param whether to display debug output (true|false) ") 26 | println("3rd param is the checkpoint path ") 27 | println("4th param is the maxRatePerPartition (records/sec to read from each kafka partition) ") 28 | println("5th param is the batch interval in milliseconds") 29 | println("6th param is the auto.offset.reset type (smallest|largest)") 30 | println("7th param is the topic name") 31 | println("8th param is the type of kafka stream (direct|receiver)") 32 | println("9th param is the number of partitions to consume per topic (used with receiver-based input stream)") 33 | println("10th param is the amount of parallelism used for processing data (used with receiver-based input stream)") 34 | println("11th param is the group.id that id's the consumer processes (used with receiver-based input stream)") 35 | println("12th param is the zookeeper connect string (e.g. localhost:2181) (used with receiver-based input stream)") 36 | } 37 | 38 | val brokers = args(0) 39 | val debugOutput = args(1).toBoolean 40 | val checkpoint_path = args(2) 41 | val maxRatePerPartition = args(3) 42 | val batchIntervalInMillis = args(4).toInt 43 | val offsetResetType = args(5) 44 | val topicName = args(6) 45 | val streamType = args(7) 46 | val numPartitions = args(8).toInt 47 | val processingParallelism = args(9).toInt 48 | val groupId = args(10) 49 | val zookeeper = args(11) 50 | val storageLevel = StorageLevel.MEMORY_AND_DISK_SER 51 | val conf = new SparkConf() 52 | .set("spark.streaming.kafka.maxRatePerPartition", maxRatePerPartition) 53 | .set("spark.locality.wait", "0") 54 | .set("spark.cassandra.connection.keep_alive_ms", (batchIntervalInMillis*5).toString) 55 | 56 | if (checkpoint_path == "dont_checkpoint") { 57 | conf.set("spark.streaming.receiver.writeAheadLog.enable", "false") 58 | } else { 59 | conf.set("spark.streaming.receiver.writeAheadLog.enable", "true") 60 | } 61 | 62 | val sc = SparkContext.getOrCreate(conf) 63 | 64 | def createStreamingContext(): StreamingContext = { 65 | // Create a new StreamingContext 66 | val newSsc = new StreamingContext(sc, Milliseconds(batchIntervalInMillis)) 67 | 68 | if (checkpoint_path == "dont_checkpoint") { 69 | println("dont_checkpoint was provided in checkpoint path, so we're not checkpointing.") 70 | } else { 71 | println(s"Creating new StreamingContext $newSsc with checkpoint path of: $checkpoint_path") 72 | newSsc.checkpoint(checkpoint_path) 73 | } 74 | 75 | // Setup Kafka params 76 | val kafkaParams = Map[String, String]("metadata.broker.list" -> brokers, 77 | "auto.offset.reset"-> offsetResetType, 78 | "group.id"->groupId, 79 | "zookeeper.connect"->zookeeper) 80 | 81 | println(s"connecting to brokers: $brokers") 82 | println(s"kafkaParams: $kafkaParams") 83 | 84 | // Create the input stream 85 | val emailsStream = { 86 | if (streamType == "direct") { 87 | val topics = Set(topicName) 88 | KafkaUtils.createDirectStream[String, String, StringDecoder, StringDecoder](newSsc, kafkaParams, topics) 89 | 90 | } else if (streamType == "receiver") { 91 | // Changing this number controls the number of consumer threads per input DStream 92 | val topics = Map(topicName -> 1) 93 | 94 | // Controls the number of input dstreams 95 | val streams = (1 to numPartitions) map { _ => 96 | KafkaUtils.createStream[String, String, StringDecoder, StringDecoder](newSsc, kafkaParams, topics, storageLevel) 97 | } 98 | 99 | // Below is way to change parallelism for downstream processing, for now we'll stick with numPartitions 100 | val unifiedStream = newSsc.union(streams) 101 | unifiedStream.repartition(processingParallelism) 102 | 103 | } else { 104 | println(s"The streaming type provided is NOT supported: $streamType") 105 | sys.exit() 106 | } 107 | } 108 | 109 | emailsStream.foreachRDD { 110 | (message: RDD[(String, String)], batchTime: Time) => { 111 | var offsetRanges = Array[OffsetRange]() 112 | 113 | if (streamType == "direct") { 114 | offsetRanges = message.asInstanceOf[HasOffsetRanges].offsetRanges 115 | for (o <- offsetRanges) { 116 | println(s"\nTopic: ${o.topic} Partition: ${o.partition} FromOffset: ${o.fromOffset} UntilOffset: ${o.untilOffset}") 117 | } 118 | } 119 | 120 | // Needs to be here: We have to create a SQLContext using the SparkContext that the StreamingContext is using. 121 | // We need to lazily instantiate a singelton instance of the SQLContext in order to recover from a checkpoint. 122 | val sqlContext = SQLContext.getOrCreate(message.sparkContext) 123 | import sqlContext.implicits._ 124 | 125 | // Convert each RDD from the batch into a Email DataFrame 126 | // email data has the format msg_id:tenant_id:mailbox_id:time_delivered:time_forwarded:time_read:time_replied 127 | val df = message.map { 128 | case (key, nxtEmail) => nxtEmail.split("::") 129 | }.map(email => { 130 | val time_delivered: Long = email(3).trim.toLong 131 | val time_forwarded: Long = email(4).trim.toLong 132 | val time_read: Long = email(5).trim.toLong 133 | val time_replied: Long = email(6).trim.toLong 134 | Email(email(0).trim.toString, email(1).trim.toString, email(2).trim.toString, time_delivered, time_forwarded, time_read, time_replied) 135 | }).toDF("msg_id", "tenant_id", "mailbox_id", "time_delivered", "time_forwarded", "time_read", "time_replied") 136 | 137 | // Save the DataFrame to Cassandra 138 | // Note: Cassandra has been initialized through dse spark-submit, so we don't have to explicitly set the connection 139 | df.write.format("org.apache.spark.sql.cassandra") 140 | .mode(SaveMode.Append) 141 | .options(Map("keyspace" -> "email_db", "table" -> "email_msg_tracker")) 142 | .save() 143 | 144 | if (debugOutput) { 145 | val count = df.count() 146 | println(s"Successfully saved $count") 147 | df.show() 148 | } 149 | } 150 | } 151 | newSsc 152 | } 153 | 154 | val ssc = StreamingContext.getActiveOrCreate(checkpoint_path, createStreamingContext) 155 | 156 | ssc.start() 157 | ssc.awaitTermination() 158 | } 159 | } 160 | --------------------------------------------------------------------------------