Storm完整例子

时间：2023-03-09 16:34:55
Storm完整例子
  1. import backtype.storm.spout.SpoutOutputCollector;
  2. import backtype.storm.task.TopologyContext;
  3. import backtype.storm.topology.base.BaseRichSpout;
  4. import backtype.storm.utils.Utils;
  5. import backtype.storm.Config;
  6. import backtype.storm.LocalCluster;
  7. import backtype.storm.StormSubmitter;
  8. import backtype.storm.task.ShellBolt;
  9. import backtype.storm.topology.BasicOutputCollector;
  10. import backtype.storm.topology.IRichBolt;
  11. import backtype.storm.topology.OutputFieldsDeclarer;
  12. import backtype.storm.topology.TopologyBuilder;
  13. import backtype.storm.topology.base.BaseBasicBolt;
  14. import backtype.storm.tuple.Fields;
  15. import backtype.storm.tuple.Tuple;
  16. import backtype.storm.tuple.Values;
  17. import java.util.*;
  18. //import java.util.HashMap;
  19. //import java.util.Map;
  20. //import java.util.Random;
  21. //import java.util.StringTokenizer;
  22. /*
  23. ** WordCountTopolopgyAllInJava类（单词计数）
  24. */
  25. public class  WordCountTopolopgyAllInJava{
  26. // 定义一个喷头，用于产生数据。该类继承自BaseRichSpout
  27. public static class RandomSentenceSpout extends BaseRichSpout {
  28. SpoutOutputCollector _collector;
  29. Random _rand;
  30. @Override
  31. public void open(Map conf, TopologyContext context, SpoutOutputCollector collector){
  32. _collector = collector;
  33. _rand = new Random();
  34. }
  35. @Override
  36. public void nextTuple(){
  37. // 睡眠一段时间后再产生一个数据
  38. Utils.sleep(100);
  39. // 句子数组
  40. String[] sentences = new String[]{ "the cow jumped over the moon", "an apple a day keeps the doctor away",
  41. "four score and seven years ago", "snow white and the seven dwarfs", "i am at two with nature" };
  42. // 随机选择一个句子
  43. String sentence = sentences[_rand.nextInt(sentences.length)];
  44. // 发射该句子给Bolt
  45. _collector.emit(new Values(sentence));
  46. }
  47. // 确认函数
  48. @Override
  49. public void ack(Object id){
  50. }
  51. // 处理失败的时候调用
  52. @Override
  53. public void fail(Object id){
  54. }
  55. @Override
  56. public void declareOutputFields(OutputFieldsDeclarer declarer){
  57. // 定义一个字段word
  58. declarer.declare(new Fields("word"));
  59. }
  60. }
  61. // 定义个Bolt，用于将句子切分为单词
  62. public static class SplitSentence extends BaseBasicBolt{
  63. @Override
  64. public void execute(Tuple tuple, BasicOutputCollector collector){
  65. // 接收到一个句子
  66. String sentence = tuple.getString(0);
  67. // 把句子切割为单词
  68. StringTokenizer iter = new StringTokenizer(sentence);
  69. // 发送每一个单词
  70. while(iter.hasMoreElements()){
  71. collector.emit(new Values(iter.nextToken()));
  72. }
  73. }
  74. @Override
  75. public void declareOutputFields(OutputFieldsDeclarer declarer){
  76. // 定义一个字段
  77. declarer.declare(new Fields("word"));
  78. }
  79. }
  80. // 定义一个Bolt，用于单词计数
  81. public static class WordCount extends BaseBasicBolt {
  82. Map<String, Integer> counts = new HashMap<String, Integer>();
  83. @Override
  84. public void execute(Tuple tuple, BasicOutputCollector collector){
  85. // 接收一个单词
  86. String word = tuple.getString(0);
  87. // 获取该单词对应的计数
  88. Integer count = counts.get(word);
  89. if(count == null)
  90. count = 0;
  91. // 计数增加
  92. count++;
  93. // 将单词和对应的计数加入map中
  94. counts.put(word,count);
  95. System.out.println("hello word!");
  96. System.out.println(word +"  "+count);
  97. // 发送单词和计数（分别对应字段word和count）
  98. collector.emit(new Values(word, count));
  99. }
  100. @Override
  101. public void declareOutputFields(OutputFieldsDeclarer declarer){
  102. // 定义两个字段word和count
  103. declarer.declare(new Fields("word","count"));
  104. }
  105. }
  106. public static void main(String[] args) throws Exception
  107. {
  108. // 创建一个拓扑
  109. TopologyBuilder builder = new TopologyBuilder();
  110. // 设置Spout，这个Spout的名字叫做"Spout"，设置并行度为5
  111. builder.setSpout("Spout", new RandomSentenceSpout(), 5);
  112. // 设置slot——“split”，并行度为8，它的数据来源是spout的
  113. builder.setBolt("split", new SplitSentence(), 8).shuffleGrouping("spout");
  114. // 设置slot——“count”,你并行度为12，它的数据来源是split的word字段
  115. builder.setBolt("count", new WordCount(), 12).fieldsGrouping("split", new Fields("word"));
  116. Config conf = new Config();
  117. conf.setDebug(false);
  118. //if(args != null && args.length > 0){
  119. //if(false){
  120. //  conf.setNumWorkers(3);
  121. //  StormSubmitter.submitTopology(args[0], conf, builder.createTopology());
  122. //}else{
  123. conf.setMaxTaskParallelism(3);
  124. // 本地集群
  125. LocalCluster cluster = new LocalCluster();
  126. // 提交拓扑（该拓扑的名字叫word-count）
  127. cluster.submitTopology("word-count", conf, builder.createTopology() );
  128. Thread.sleep(10000);
  129. //  cluster.shutdown();
  130. //}
  131. }
  132. }

使用maven编译该项目： mvn clean package

运行：storm jar word-count-1.0.jar WordCountTopolopgyAllInJava

结果如下：

hello word!
moon    811
hello word!
an      829
hello word!
apple   829
hello word!
a       829
hello word!
keeps   829
hello word!
day     829
hello word!
score   800
hello word!

pom.xml文件定义如下

    1. <project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
    2. xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    3. <modelVersion>4.0.0</modelVersion>
    4. <groupId>storm-yqj</groupId>
    5. <artifactId>word-count</artifactId>
    6. <version>1.0</version>
    7. <packaging>jar</packaging>
    8. <name>word-count</name>
    9. <url>http://maven.apache.org</url>
    10. <properties>
    11. <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
    12. </properties>
    13. <dependencies>
    14. <dependency>
    15. <groupId>junit</groupId>
    16. <artifactId>junit</artifactId>
    17. <version>3.8.1</version>
    18. <scope>test</scope>
    19. </dependency>
    20. <dependency>
    21. <groupId>org.testng</groupId>
    22. <artifactId>testng</artifactId>
    23. <version>6.8.5</version>
    24. <scope>test</scope>
    25. </dependency>
    26. <dependency>
    27. <groupId>org.mockito</groupId>
    28. <artifactId>mockito-all</artifactId>
    29. <version>1.9.0</version>
    30. <scope>test</scope>
    31. </dependency>
    32. <dependency>
    33. <groupId>org.easytesting</groupId>
    34. <artifactId>fest-assert-core</artifactId>
    35. <version>2.0M8</version>
    36. <scope>test</scope>
    37. </dependency>
    38. <dependency>
    39. <groupId>org.jmock</groupId>
    40. <artifactId>jmock</artifactId>
    41. <version>2.6.0</version>
    42. <scope>test</scope>
    43. </dependency>
    44. <dependency>
    45. <groupId>org.apache.storm</groupId>
    46. <artifactId>storm-core</artifactId>
    47. <version>0.9.1-incubating</version>
    48. </dependency>
    49. <dependency>
    50. <groupId>commons-collections</groupId>
    51. <artifactId>commons-collections</artifactId>
    52. <version>3.2.1</version>
    53. </dependency>
    54. <dependency>
    55. <groupId>com.google.guava</groupId>
    56. <artifactId>guava</artifactId>
    57. <version>15.0</version>
    58. </dependency>
    59. </dependencies>
    60. <build>
    61. <resources>
    62. <resource>
    63. <directory>${basedir}/multilang</directory>
    64. </resource>
    65. </resources>
    66. <plugins>
    67. <plugin>
    68. <artifactId>maven-assembly-plugin</artifactId>
    69. <configuration>
    70. <descriptorRefs>
    71. <descriptorRef>jar-with-dependencies</descriptorRef>
    72. </descriptorRefs>
    73. <archive>
    74. <manifest>
    75. <mainClass></mainClass>
    76. </manifest>
    77. </archive>
    78. </configuration>
    79. <executions>
    80. <execution>
    81. <id>make-assembly</id>
    82. <phase>package</phase>
    83. <goals>
    84. <goal>single</goal>
    85. </goals>
    86. </execution>
    87. </executions>
    88. </plugin>
    89. <plugin>
    90. <groupId>com.theoryinpractise</groupId>
    91. <artifactId>clojure-maven-plugin</artifactId>
    92. <version>1.3.12</version>
    93. <extensions>true</extensions>
    94. <configuration>
    95. <sourceDirectories>
    96. <sourceDirectory>src/clj</sourceDirectory>
    97. </sourceDirectories>
    98. </configuration>
    99. <executions>
    100. <execution>
    101. <id>compile</id>
    102. <phase>compile</phase>
    103. <goals>
    104. <goal>compile</goal>
    105. </goals>
    106. </execution>
    107. <execution>
    108. <id>test</id>
    109. <phase>test</phase>
    110. <goals>
    111. <goal>test</goal>
    112. </goals>
    113. </execution>
    114. </executions>
    115. </plugin>
    116. <plugin>
    117. <groupId>org.codehaus.mojo</groupId>
    118. <artifactId>exec-maven-plugin</artifactId>
    119. <version>1.2.1</version>
    120. <executions>
    121. <execution>
    122. <goals>
    123. <goal>exec</goal>
    124. </goals>
    125. </execution>
    126. </executions>
    127. <configuration>
    128. <executable>java</executable>
    129. <includeProjectDependencies>true</includeProjectDependencies>
    130. <includePluginDependencies>false</includePluginDependencies>
    131. <classpathScope>compile</classpathScope>
    132. <mainClass>${storm.topology}</mainClass>
    133. </configuration>
    134. </plugin>
    135. <plugin>
    136. <groupId>org.apache.maven.plugins</groupId>
    137. <artifactId>maven-compiler-plugin</artifactId>
    138. <configuration>
    139. <source>1.6</source>
    140. <target>1.6</target>
    141. </configuration>
    142. </plugin>
    143. </plugins>
    144. </build>
    145. </project>

相关文章