├── .gitignore ├── LICENSE ├── README.md ├── build.sbt ├── doc └── stream_processing.png ├── es-mapping └── mapping.sh ├── libexec └── activator-launch-1.3.10.jar ├── project └── build.properties └── src ├── main └── scala │ └── com │ └── knoldus │ └── streaming │ ├── StreamingApp.scala │ ├── StreamingProcessor.scala │ ├── core │ └── SentimentAnalyzer.scala │ ├── json │ └── JsonHelper.scala │ ├── kafka │ └── KafkaUtility.scala │ ├── persist │ └── PersistanceFactory.scala │ └── util │ └── DateUtil.scala └── test ├── resources └── issues.txt └── scala └── com └── knoldus └── streaming └── core └── SentimentAnalyzerTest.scala /.gitignore: -------------------------------------------------------------------------------- 1 | project/boot/ 2 | project/plugins/project/ 3 | project/plugins/target/ 4 | project/target/ 5 | target/ 6 | project/boot/* 7 | project/plugins/project/* 8 | project/plugins/target/* 9 | project/target/* 10 | target/* 11 | .idea 12 | .idea/* 13 | *.iml 14 | *.ipr 15 | *.iws 16 | .classpath 17 | .project 18 | .scala_dependencies 19 | .target/ 20 | .cache 21 | logs/* 22 | .settings/ 23 | /bin/ 24 | .cache-main 25 | .cache-tests 26 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "{}" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright {yyyy} {name of copyright owner} 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | #real-time-stream-processing-engine 2 | 3 | This is an example of real time stream processing using Spark Streaming, Kafka & Elasticsearch. 4 | 5 | ![alt tag](/doc/stream_processing.png) 6 | 7 | #Pre-Requisites for this project 8 | ####Elasticsearch Setup 9 | i) [Download](https://www.elastic.co/downloads/elasticsearch) the Elasticsearch 5.0.0-alpha5 or latest version and unzip it. 10 | 11 | ii) Run the following command. 12 | 13 | $ bin/elasticsearch 14 | 15 | 16 | ####Kafka Setup 17 | i) [Download](http://kafka.apache.org/downloads.html) the Kafka-0.10.0.1 or latest version and unzip it. 18 | 19 | ii) Run the following commands for starting Zookeeper & Kafka: 20 | 21 | $ bin/zookeeper-server-start.sh config/zookeeper.properties 22 | $ bin/kafka-server-start.sh config/server.properties 23 | 24 | ----------------------------------------------------------------------- 25 | ###Getting Started: 26 | ----------------------------------------------------------------------- 27 | 28 | Clone and run in local mode: 29 | 30 | $ git@github.com:knoldus/sentiment-analysis-engine.git 31 | $ cd sentiment-analysis-engine 32 | $ bin/activator run 33 | 34 | 35 | ##Limitations 36 | 1) Elasticsearch 5.0.0-alpha5 is not production ready. 37 | 38 | 2) Kafka-0.10.0.1 is experimental in current spark version(spark-2.0.0). 39 | -------------------------------------------------------------------------------- /build.sbt: -------------------------------------------------------------------------------- 1 | name := """real-time-stream-processing-engine""" 2 | 3 | version := "1.0" 4 | 5 | scalaVersion := "2.11.8" 6 | 7 | 8 | libraryDependencies ++= Seq( 9 | "org.apache.spark" %% "spark-streaming" % "2.0.0", 10 | "org.apache.spark" %% "spark-streaming-kafka-0-10" % "2.0.0", 11 | "org.json4s" %% "json4s-native" % "3.4.0", 12 | "org.elasticsearch" %% "elasticsearch-spark-20" % "5.0.0-alpha5", 13 | "edu.stanford.nlp" % "stanford-corenlp" % "3.6.0" artifacts (Artifact("stanford-corenlp", "models"), Artifact("stanford-corenlp")), 14 | "org.scalatest" %% "scalatest" % "3.0.0" 15 | ) 16 | 17 | 18 | //resolvers += "clojars" at "https://clojars.org/repo" 19 | //resolvers += "conjars" at "http://conjars.org/repo" 20 | -------------------------------------------------------------------------------- /doc/stream_processing.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NashTech-Labs/real-time-stream-processing-engine/0f6f8a9a8e16c70a49405b58b4590c3875e168d6/doc/stream_processing.png -------------------------------------------------------------------------------- /es-mapping/mapping.sh: -------------------------------------------------------------------------------- 1 | curl -XPOST localhost:9200/analysis_index -d '{ 2 | "mappings": { 3 | "_default_": { 4 | "dynamic":"strict", 5 | "properties": { 6 | "author_username": { 7 | "type": "keyword" 8 | }, 9 | "clean_text": { 10 | "type": "text" 11 | }, 12 | "created_at": { 13 | "type": "date", 14 | "format":"basic_date||date_optional_time||EEE, dd MMM yyyy HH:mm:ss Z" 15 | }, 16 | "media_type": { 17 | "type": "keyword" 18 | }, 19 | "retweets": { 20 | "type": "long" 21 | }, 22 | "sentiment": { 23 | "type": "keyword" 24 | }, 25 | "text": { 26 | "type": "text" 27 | }, 28 | "id": { 29 | "type": "keyword" 30 | } 31 | } 32 | } 33 | } 34 | }' 35 | -------------------------------------------------------------------------------- /libexec/activator-launch-1.3.10.jar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NashTech-Labs/real-time-stream-processing-engine/0f6f8a9a8e16c70a49405b58b4590c3875e168d6/libexec/activator-launch-1.3.10.jar -------------------------------------------------------------------------------- /project/build.properties: -------------------------------------------------------------------------------- 1 | #Activator-generated Properties 2 | #Sun Aug 07 16:48:34 IST 2016 3 | template.uuid=e17acfbb-1ff5-41f5-b8cf-2c40be6a8340 4 | sbt.version=0.13.8 5 | -------------------------------------------------------------------------------- /src/main/scala/com/knoldus/streaming/StreamingApp.scala: -------------------------------------------------------------------------------- 1 | package com.knoldus.streaming 2 | 3 | import org.apache.spark.SparkConf 4 | import org.apache.spark.streaming.{Seconds, StreamingContext} 5 | 6 | 7 | object StreamingApp extends App { 8 | 9 | val sparkConf = new SparkConf().setAppName("StreamingApp").setMaster("local[*]") 10 | sparkConf.set("es.index.auto.create", "true") 11 | sparkConf.set("es.mapping.id", "id") 12 | 13 | val ssc: StreamingContext = new StreamingContext(sparkConf, Seconds(5)) 14 | 15 | StreamingProcessor.process(ssc, List("tweet_queue"), "analysis_index2", "twitter") 16 | ssc.start() 17 | ssc.awaitTermination() 18 | 19 | } 20 | -------------------------------------------------------------------------------- /src/main/scala/com/knoldus/streaming/StreamingProcessor.scala: -------------------------------------------------------------------------------- 1 | package com.knoldus.streaming 2 | 3 | import com.knoldus.streaming.core.SentimentAnalyzer 4 | import com.knoldus.streaming.json.JsonHelper._ 5 | import com.knoldus.streaming.kafka.KafkaUtility 6 | import com.knoldus.streaming.persist.PersistenceFactory 7 | import com.knoldus.streaming.util.DateUtil 8 | import org.apache.spark.streaming.StreamingContext 9 | 10 | object StreamingProcessor { 11 | 12 | 13 | def process(ssc: StreamingContext, topics: List[String], indexName: String, `type`: String): Unit = { 14 | val messages = KafkaUtility.createDStreamFromKafka(ssc, topics) 15 | val tweets = messages.map { record => parse(record.value()).extract[Map[String, String]] } 16 | val tweetSentiments = 17 | tweets.map { tweet => 18 | val sentiment = SentimentAnalyzer.getSentiment(tweet("text")) 19 | val esDate = DateUtil.getESDateFormat(tweet("created_at")) 20 | tweet + ("sentiment" -> sentiment) + ("created_at" -> esDate) 21 | } 22 | PersistenceFactory.persist(tweetSentiments, indexName, `type`) 23 | } 24 | 25 | } 26 | -------------------------------------------------------------------------------- /src/main/scala/com/knoldus/streaming/core/SentimentAnalyzer.scala: -------------------------------------------------------------------------------- 1 | package com.knoldus.streaming.core 2 | 3 | 4 | import java.util.Properties 5 | 6 | import edu.stanford.nlp.ling.CoreAnnotations 7 | import edu.stanford.nlp.neural.rnn.RNNCoreAnnotations 8 | import edu.stanford.nlp.pipeline.{Annotation, StanfordCoreNLP} 9 | import edu.stanford.nlp.sentiment.SentimentCoreAnnotations 10 | 11 | import scala.collection.convert.wrapAll._ 12 | 13 | object SentimentAnalyzer { 14 | 15 | private val props = new Properties() 16 | props.setProperty("annotators", "tokenize, ssplit, parse, sentiment") 17 | private val pipeline: StanfordCoreNLP = new StanfordCoreNLP(props) 18 | 19 | def getSentiment(input: String): String = { 20 | if (Option(input).isDefined && !input.trim.isEmpty) { 21 | val annotation: Annotation = pipeline.process(input) 22 | val (_, sentiment) = 23 | annotation.get(classOf[CoreAnnotations.SentencesAnnotation]) 24 | .map { sentence => (sentence, sentence.get(classOf[SentimentCoreAnnotations.SentimentAnnotatedTree])) } 25 | .map { case (sentence, tree) => (sentence.toString, getSentimentType(RNNCoreAnnotations.getPredictedClass(tree))) } 26 | .maxBy { case (sentence, _) => sentence.length } 27 | sentiment 28 | } else { 29 | throw new IllegalArgumentException("Text should not empty or null") 30 | } 31 | } 32 | 33 | 34 | private def getSentimentType(sentiment: Int): String = sentiment match { 35 | case x if x == 3 || x == 4 => "positive" 36 | case x if x == 0 || x == 1 => "negative" 37 | case 2 => "neutral" 38 | } 39 | } 40 | -------------------------------------------------------------------------------- /src/main/scala/com/knoldus/streaming/json/JsonHelper.scala: -------------------------------------------------------------------------------- 1 | package com.knoldus.streaming.json 2 | 3 | 4 | import org.json4s.DefaultFormats 5 | import org.json4s.JsonAST.JValue 6 | import org.json4s.native.Serialization 7 | import org.json4s.native.JsonMethods 8 | 9 | 10 | 11 | object JsonHelper { 12 | 13 | implicit val formats = DefaultFormats 14 | 15 | def write[T <: AnyRef](value: T): String = Serialization.write(value) 16 | 17 | def parse(json:String):JValue = JsonMethods.parse(json) 18 | } 19 | 20 | -------------------------------------------------------------------------------- /src/main/scala/com/knoldus/streaming/kafka/KafkaUtility.scala: -------------------------------------------------------------------------------- 1 | package com.knoldus.streaming.kafka 2 | 3 | import org.apache.kafka.clients.consumer.ConsumerRecord 4 | import org.apache.kafka.common.serialization.StringDeserializer 5 | import org.apache.spark.streaming.StreamingContext 6 | import org.apache.spark.streaming.dstream.InputDStream 7 | import org.apache.spark.streaming.kafka010.{ConsumerStrategies, KafkaUtils, LocationStrategies} 8 | 9 | 10 | object KafkaUtility { 11 | 12 | //TODO It should read from config 13 | private val kafkaParams = Map( 14 | "bootstrap.servers" -> "localhost:9092", 15 | "key.deserializer" -> classOf[StringDeserializer], 16 | "value.deserializer" -> classOf[StringDeserializer], 17 | "auto.offset.reset" -> "earliest", 18 | "group.id" -> "tweet-consumer" 19 | ) 20 | 21 | private val preferredHosts = LocationStrategies.PreferConsistent 22 | 23 | 24 | def createDStreamFromKafka(ssc: StreamingContext, topics: List[String]): InputDStream[ConsumerRecord[String, String]] = 25 | KafkaUtils.createDirectStream[String, String]( 26 | ssc, 27 | preferredHosts, 28 | ConsumerStrategies.Subscribe[String, String](topics.distinct, kafkaParams) 29 | ) 30 | 31 | } 32 | -------------------------------------------------------------------------------- /src/main/scala/com/knoldus/streaming/persist/PersistanceFactory.scala: -------------------------------------------------------------------------------- 1 | package com.knoldus.streaming.persist 2 | 3 | import org.apache.spark.streaming.dstream.DStream 4 | import org.elasticsearch.spark._ 5 | 6 | 7 | object PersistenceFactory { 8 | 9 | def persist(mapDStream: DStream[Map[String, String]], indexName: String, `type`: String): Unit = 10 | mapDStream.foreachRDD { 11 | tweetRDD => tweetRDD.saveToEs(indexName + "/" + `type`) 12 | } 13 | 14 | } 15 | -------------------------------------------------------------------------------- /src/main/scala/com/knoldus/streaming/util/DateUtil.scala: -------------------------------------------------------------------------------- 1 | package com.knoldus.streaming.util 2 | 3 | import java.text.SimpleDateFormat 4 | import java.util.Date 5 | 6 | 7 | object DateUtil { 8 | 9 | 10 | private val dateFormats = List( 11 | "yyyyMMdd'T'HHmmss.SSSZ", 12 | "EEE, dd MMM yyyy HH:mm:ss Z", 13 | "yyyy-MM-dd HH:mm:ss", 14 | "EEE MMM dd HH:mm:ss Z yyyy", 15 | "MMM dd, yyyy, HH:mm a", 16 | "MMM dd, yyyy HH:mm a", 17 | "yyyy-MM-dd'T'HH:mm:ss", 18 | "dd MMM yyyy HH:mm:ss:S Z", 19 | "E MMM dd HH:mm:ss z yyyy", 20 | "dd MMM yyyy HH:mm:ss:SSS", 21 | "dd MMM yyyy H:mm:ss:SSS", 22 | "MM-dd-yyyy HH:mm:ss:SSS", 23 | "MM/dd/yyyy HH:mm:ss:SSS", 24 | "dd/MM/yyyy HH:mm:ss:SSS", 25 | "dd-MM-yyyy HH:mm:ss:SSS", 26 | "MMM/dd/yyyy HH:mm:ss:SSS", 27 | "MMM-dd-yyyy HH:mm:ss:SSS", 28 | "dd-MMM-yyyy HH:mm:ss:SSS", 29 | "MM-dd-yyyy H:mm:ss:SSS", 30 | "MM/dd/yyyy H:mm:ss:SSS", 31 | "dd/MM/yyyy H:mm:ss:SSS", 32 | "dd-MM-yyyy H:mm:ss:SSS", 33 | "MMM/dd/yyyy H:mm:ss:SSS", 34 | "MMM-dd-yyyy H:mm:ss:SSS", 35 | "dd-MMM-yyyy H:mm:ss:SSS", 36 | "MM-dd-yyyy HH:mm:ss", 37 | "MM/dd/yyyy HH:mm:ss", 38 | "dd/MM/yyyy HH:mm:ss", 39 | "dd-MM-yyyy HH:mm:ss", 40 | "MMM/dd/yyyy HH:mm:ss", 41 | "MMM-dd-yyyy HH:mm:ss", 42 | "dd-MMM-yyyy HH:mm:ss", 43 | "MM-dd-yyyy H:mm:ss", 44 | "MM/dd/yyyy H:mm:ss", 45 | "dd/MM/yyyy H:mm:ss", 46 | "dd-MM-yyyy H:mm:ss", 47 | "MMM/dd/yyyy H:mm:ss", 48 | "MMM-dd-yyyy H:mm:ss", 49 | "dd-MMM-yyyy H:mm:ss", 50 | "yyyy-MM-dd", 51 | "MM-dd-yyyy", 52 | "MM/dd/yyyy", 53 | "dd/MM/yyyy", 54 | "dd-MM-yyyy", 55 | "MMM/dd/yyyy", 56 | "MMM-dd-yyyy", 57 | "dd-MMM-yyyy") 58 | 59 | 60 | private val esDateFormat = new SimpleDateFormat("yyyy-MM-dd'T'HH:mm:ss.SSSZ") 61 | 62 | def getESDateFormat(dateString: String): String = { 63 | def getDate(dateFormats: Seq[String], dateString: String): String = 64 | try { 65 | val dateFormat = new SimpleDateFormat(dateFormats.head) 66 | val date = dateFormat.parse(dateString) 67 | esDateFormat.format(date) 68 | } catch { 69 | case _ if (dateFormats.size > 1) => getDate(dateFormats.tail, dateString) 70 | case _: Exception => esDateFormat.format(new Date()) 71 | } 72 | getDate(dateFormats, dateString) 73 | } 74 | 75 | } 76 | 77 | -------------------------------------------------------------------------------- /src/test/resources/issues.txt: -------------------------------------------------------------------------------- 1 | //known issue with netty4 2 | // bin/elasticsearch -Ehttp.type=netty3 3 | //https://www.elastic.co/guide/en/elasticsearch/reference/master/breaking-changes-5.0.html 4 | //https://discuss.elastic.co/t/write-es-error-with-spark-2-0-release/56967/6 5 | 6 | //https://github.com/apache/spark/blob/master/external/kafka-0-10/src/test/scala/org/apache/spark/streaming/kafka010/DirectKafkaStreamSuite.scala 7 | // https://github.com/shekhargulati/52-technologies-in-2016/tree/master/03-stanford-corenlp -------------------------------------------------------------------------------- /src/test/scala/com/knoldus/streaming/core/SentimentAnalyzerTest.scala: -------------------------------------------------------------------------------- 1 | package com.knoldus.streaming.core 2 | 3 | import org.scalatest.{Matchers, WordSpecLike} 4 | 5 | 6 | class SentimentAnalyzerTest extends WordSpecLike with Matchers{ 7 | 8 | "SentimentAnalyzer " must { 9 | 10 | "analyze positive sentiment" in { 11 | SentimentAnalyzer.getSentiment("I am very happy with spark") shouldBe "positive" 12 | } 13 | 14 | "analyze negative sentiment" in { 15 | SentimentAnalyzer.getSentiment("I am very frustrated") shouldBe "negative" 16 | } 17 | 18 | 19 | "analyze neutral sentiment" in { 20 | SentimentAnalyzer.getSentiment("I am a developer" ) shouldBe "neutral" 21 | } 22 | 23 | } 24 | 25 | 26 | 27 | } 28 | --------------------------------------------------------------------------------