Я пытаюсь провести анализ твиттера с помощью Flume и Hive. Для получения твитов из твиттера я установил все необходимые параметры (consumerKey, ConsumerSecret, accessToken и accessTokenSecret) в файлах flume.conf.
TwitterAgent.sources = Twitter TwitterAgent.channels = MemChannel
TwitterAgent.sinks = HDFS TwitterAgent.sources.Twitter.type =
com.cloudera.flume.source.TwitterSource
TwitterAgent.sources.Twitter.channels = MemChannel
TwitterAgent.sources.Twitter.consumerKey = <consumerKey>
TwitterAgent.sources.Twitter.consumerSecret = <consumerSecret>
TwitterAgent.sources.Twitter.accessToken = <accessToken>
TwitterAgent.sources.Twitter.accessTokenSecret = <accessTokenSecret
TwitterAgent.sources.Twitter.keywords = hadoop, big data, analytics,
bigdata, cloudera, data science, data scientiest, business
intelligence, mapreduce, data warehouse, data warehousing, mahout,
hbase, nosql, newsql, businessintelligence, cloudcomputing
TwitterAgent.sinks.HDFS.channel = MemChannel
TwitterAgent.sinks.HDFS.type = hdfs TwitterAgent.sinks.HDFS.hdfs.path
= hdfs://localhost:9000/user/flume/tweets/ TwitterAgent.sinks.HDFS.hdfs.fileType = DataStream
TwitterAgent.sinks.HDFS.hdfs.writeFormat = Text
TwitterAgent.sinks.HDFS.hdfs.batchSize = 1000
TwitterAgent.sinks.HDFS.hdfs.rollSize = 0
TwitterAgent.sinks.HDFS.hdfs.rollCount = 10000
TwitterAgent.channels.MemChannel.type = memory
TwitterAgent.channels.MemChannel.capacity = 10000
TwitterAgent.channels.MemChannel.transactionCapacity = 100
Я установил путь к классу для tar-шара Flume и файла jar исходного снимка Flume, используя bash rc .
export FLUME_HOME=/home/students/apache-flume-1.4.0-bin
export FLUME_SRC=/home/students/flume-sources-1.0-SNAPSHOT.jar
export PATH=$FLUME_HOME/bin:$FLUME_SRC/bin:$PATH
Когда я запускаю Flume Agent
flume-ng agent --conf-file twitter_flume.conf --name TwitterAgent -Dflume.root.logger=INFO,console -n TwitterAgent
я вижу приведенную ниже трассировку журнала, и ничего не происходит
15/06/23 23:41:55 INFO source.DefaultSourceFactory: Creating instance
of source Twitter, type com.cloudera.flume.source.TwitterSource
15/06/23 23:41:55 ERROR
node.PollingPropertiesFileConfigurationProvider: Failed to load
configuration data. Exception follows.
org.apache.flume.FlumeException: Unable to load source type:
com.cloudera.flume.source.TwitterSource, class:
com.cloudera.flume.source.TwitterSource at
org.apache.flume.source.DefaultSourceFactory.getClass(DefaultSourceFactory.java:67)
at
org.apache.flume.source.DefaultSourceFactory.create(DefaultSourceFactory.java:40)
at
org.apache.flume.node.AbstractConfigurationProvider.loadSources(AbstractConfigurationProvider.java:327)
at
org.apache.flume.node.AbstractConfigurationProvider.getConfiguration(AbstractConfigurationProvider.java:102)
at
org.apache.flume.node.PollingPropertiesFileConfigurationProvider$FileWatcherRunnable.run(PollingPropertiesFileConfigurationProvider.java:140)
at
java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.runAndReset(FutureTask.java:304)
at
java.util.concurrent.ScheduledThreadPoolExecutor$ScheduledFutureTask.access$301(ScheduledThreadPoolExecutor.java:178)
at
java.util.concurrent.ScheduledThreadPoolExecutor$ScheduledFutureTask.run(ScheduledThreadPoolExecutor.java:293)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:744) Caused by:
java.lang.ClassNotFoundException:
com.cloudera.flume.source.TwitterSource at
java.net.URLClassLoader$1.run(URLClassLoader.java:366) at
java.net.URLClassLoader$1.run(URLClassLoader.java:355) at
java.security.AccessController.doPrivileged(Native Method) at
java.net.URLClassLoader.findClass(URLClassLoader.java:354) at
java.lang.ClassLoader.loadClass(ClassLoader.java:425) at
sun.misc.Launcher$AppClassLoader.loadClass(Launcher.java:308) at
java.lang.ClassLoader.loadClass(ClassLoader.java:358) at
java.lang.Class.forName0(Native Method) at
java.lang.Class.forName(Class.java:190) at
org.apache.flume.source.DefaultSourceFactory.getClass(DefaultSourceFactory.java:65)
... 11 more
Могу ли я узнать, почему эта ошибка выдается, когда я уже установил исходный файл .jar. Пожалуйста, помогите мне в этом.