林子雨编著《大数据基础编程、实验和案例教程》教材第11章的代码

大数据技术原理与应用

林子雨编著《大数据基础编程、实验和案例教程》(教材官网)教材中的代码,在纸质教材中的印刷效果不是很好,可能会影响读者对代码的理解,为了方便读者正确理解代码或者直接拷贝代码用于上机实验,这里提供全书配套的所有代码。
查看教材所有章节的代码

第11章 数据采集工具的安装和使用

教材第218页

(温馨提示:代码框上方的复制代码按钮,也就是“两张A4纸图标”,用鼠标点击复制代码按钮,就可以把代码框中的代码复制到粘贴板,粘贴到其他地方。但是,有的浏览器可能不支持该功能)

cd ~
sudo tar -zxvf ./下载/apache-flume-1.7.0-bin.tar.gz -C /usr/local

教材第219页

cd /usr/local
sudo mv ./apache-flume-1.7.0-bin ./flume
sudo vim ~/.bashrc
export JAVA_HOME=/usr/lib/jvm/java-8-openjdk-amd64;
export FLUME_HOME=/usr/local/flume                   
export FLUME_CONF_DIR=$FLUME_HOME/conf
export PATH=$PATH:$FLUME_HOME/bin
source ~/.bashrc
cd /usr/local/flume
sudo mv flume-env.sh.template flume-env.sh
sudo vim flume-env.sh
export JAVA_HOME=/usr/lib/jvm/java-8-openjdk-amd64;

教材第220页

cd /usr/local/flume
./bin/flume-ng version
cd /usr/local/hbase/conf
sudo vim hbase-env.sh
export HBASE_CLASSPATH=/home/hadoop/hbase/conf
cd /usr/local/flume
sudo vim ./conf/avro.conf
a1.sources = r1
a1.sinks = k1
a1.channels = c1
# Describe/configure the source
a1.sources.r1.type = avro
a1.sources.r1.channels = c1
a1.sources.r1.bind = 0.0.0.0
a1.sources.r1.port = 4141 #注意这个端口名,在后面的教程中会用得到
# Describe the sink
a1.sinks.k1.type = logger
# Use a channel which buffers events in memory
a1.channels.c1.type = memory
a1.channels.c1.capacity = 1000
a1.channels.c1.transactionCapacity = 100
# Bind the source and sink to the channel
a1.sources.r1.channels = c1
a1.sinks.k1.channel = c1

教材第221页

/usr/local/flume/bin/flume-ng agent -c . -f /usr/local/flume/conf/avro.conf -n a1 -Dflume.root.logger=INFO,console

教材第222页

cd /usr/local/flume
sudo sh -c 'echo "hello world" > /usr/local/flume/log.00'
cd /usr/local/flume
./bin/flume-ng avro-client --conf conf -H localhost -p 4141 -F /usr/local/flume/log.00
cd /usr/local/flume
sudo vim ./conf/example.conf

教材第223页

#example.conf: A single-node Flume configuration
# Name the components on this agent
a1.sources = r1
a1.sinks = k1
a1.channels = c1
# Describe/configure the source
a1.sources.r1.type = netcat
a1.sources.r1.bind = localhost
a1.sources.r1.port = 44444  #记住该端口号,后面会用到
# Describe the sink
a1.sinks.k1.type = logger
# Use a channel which buffers events in memory
a1.channels.c1.type = memory
a1.channels.c1.capacity = 1000
a1.channels.c1.transactionCapacity = 100
# Bind the source and sink to the channel
a1.sources.r1.channels = c1
a1.sinks.k1.channel = c1
/usr/local/flume/bin/flume-ng agent --conf ./conf --conf-file ./example.conf --name a1 -Dflume.root.logger=INFO,console

教材第224页

telnet localhost 44444

教材第225页

cd ~/下载
sudo tar -zxf kafka_2.10-0.10.1.0.tgz -C /usr/local
cd /usr/local
sudo mv kafka_2.10-0.10.1.0/ ./kafka
sudo chown -R hadoop ./kafka
cd /usr/local/kafka
bin/zookeeper-server-start.sh config/zookeeper.properties

教材第226页

cd /usr/local/kafka
./bin/kafka-server-start.sh config/server.properties
cd /usr/local/kafka
./bin/kafka-topics.sh --create --zookeeper localhost:2181 --replication-factor 1 --partitions 1 --topic dblab
cd /usr/local/kafka
./bin/kafka-topics.sh --list --zookeeper localhost:2181
cd /usr/local/kafka
./bin/kafka-console-producer.sh --broker-list localhost:9092 --topic dblab
hello hadoop
hello xmu
hadoop world
cd /usr/local/kafka
./bin/kafka-console-consumer.sh --zookeeper localhost:2181 --topic dblab --from-beginning

教材第227页

cd ~/下载
sudo tar -zxvf  sqoop-1.4.6.bin__hadoop-2.0.4-alpha.tar.gz -C /usr/local
cd /usr/local
sudo mv sqoop-1.4.6.bin__hadoop-2.0.4-alpha sqoop
sudo chown -R hadoop:hadoop sqoop

教材第228页

cd sqoop/conf/
cat sqoop-env-template.sh >> sqoop-env.sh
cd /usr/local/sqoop/conf/
vim sqoop-env.sh
export HADOOP_COMMON_HOME=/usr/local/hadoop
export HADOOP_MAPRED_HOME=/usr/local/hadoop
export HBASE_HOME=/usr/local/hbase
export HIVE_HOME=/usr/local/hive
#export ZOOCFGDIR= #如果读者配置了ZooKeeper,也需要在此配置ZooKeeper的路径
vim ~/.bashrc
export SQOOP_HOME=/usr/local/sqoop
export PATH=$PATH:$SBT_HOME/bin:$SQOOP_HOME/bin
export CLASSPATH=$CLASSPATH:$SQOOP_HOME/lib
source ~/.bashrc

教材第229页

cd ~/下载
sudo tar -zxvf  mysql-connector-java-5.1.40.tar.gz  #解压MySQL驱动包
#注意,如果第8章已经解压缩了该文件,这里不用重复执行解压缩命令
ls #这时就可以看到解压缩后得到的目录mysql-connector-java-5.1.40
cp ./mysql-connector-java-5.1.40/mysql-connector-java-5.1.40-bin.jar /usr/local/sqoop/lib
service mysql start
sqoop list-databases --connect jdbc:mysql://127.0.0.1:3306/ --username root -P

教材第230页

cd /usr/local/kafka
./bin/zookeeper-server-start.sh config/zookeeper.properties
cd /usr/local/kafka
./bin/kafka-server-start.sh config/server.properties
cd /usr/local/kafka
bin/kafka-server-start.sh config/server.properties &

教材第231页

cd /usr/local/kafka
./bin/kafka-topics.sh --create --zookeeper localhost:2181 --replication-factor 1 --partitions 1 --topic wordsendertest
#这个topic叫wordsendertest,2181是Zookeeper默认的端口号,partition是topic里面的分区数,replication-factor是备份的数量,在Kafka集群中使用,这里单机版就不用备份了
#可以用list列出所有创建的topics,来查看上面创建的topic是否存在
./bin/kafka-topics.sh --list --zookeeper localhost:2181
./bin/kafka-console-producer.sh --broker-list localhost:9092 --topic wordsendertest
hello hadoop
hello spark
cd /usr/local/kafka
./bin/kafka-console-consumer.sh --zookeeper localhost:2181 --topic wordsender --from-beginning

教材第232页

cd /usr/local/spark
./bin/spark-shell
scala> import org.apache.spark.streaming.kafka._
cd /usr/local/spark/lib
mkdir kafka
cd ~
cd 下载
cp ./spark-streaming-kafka_2.10-1.6.2.jar /usr/local/spark/lib/kafka

教材第233页

cd /usr/local/spark/lib
cd ~
cd 下载
cp ./spark-streaming_2.10-1.6.1.jar /usr/local/spark/lib/kafka
cd /usr/local/kafka/libs
ls
cp ./* /usr/local/spark/lib/kafka
cd /usr/local/kafka/libs
ls
rm log4j*
rm jackson*
cd /usr/local/spark/conf
vim spark-env.sh

教材第234页

export SPARK_CLASSPATH=$SPARK_CLASSPATH:/usr/local/spark/lib/hbase/*:/usr/local/spark/lib/kafka/*
export SPARK_DIST_CLASSPATH=$(/usr/local/hadoop/bin/hadoop classpath)
cd /usr/local/spark
./bin/spark-shell
scala> import org.apache.spark.streaming.kafka._
cd /usr/local/spark/mycode
mkdir kafka
cd kafka
mkdir –p src/main/scala
cd src/main/scala
vim KafkaWordProducer.scala
import java.util.HashMap
import org.apache.kafka.clients.producer.{ProducerConfig, KafkaProducer, ProducerRecord}
import org.apache.spark.streaming._
import org.apache.spark.streaming.kafka._
import org.apache.spark.SparkConf
object KafkaWordProducer {
  def main(args: Array[String]) {
    if (args.length < 4) {
      System.err.println("Usage: KafkaWordCountProducer <metadataBrokerList> <topic> " +
        "<messagesPerSec> <wordsPerMessage>")
      System.exit(1)
    }
    val Array(brokers, topic, messagesPerSec, wordsPerMessage) = args
    // Zookeeper connection properties
    val props = new HashMap[String, Object]()
    props.put(ProducerConfig.BOOTSTRAP_SERVERS_CONFIG, brokers)
    props.put(ProducerConfig.VALUE_SERIALIZER_CLASS_CONFIG,
      "org.apache.kafka.common.serialization.StringSerializer")
    props.put(ProducerConfig.KEY_SERIALIZER_CLASS_CONFIG,
      "org.apache.kafka.common.serialization.StringSerializer")
    val producer = new KafkaProducer[String, String](props)

教材第235页

vim KafkaWordCount.scala
import org.apache.spark._
import org.apache.spark.SparkConf
import org.apache.spark.streaming._
import org.apache.spark.streaming.kafka._
import org.apache.spark.streaming.StreamingContext._
import org.apache.spark.streaming.kafka.KafkaUtils
object KafkaWordCount{
def main(args:Array[String]){
StreamingExamples.setStreamingLogLevels()
val sc = new SparkConf().setAppName("KafkaWordCount").setMaster("local[2]")
val ssc = new StreamingContext(sc,Seconds(10))
ssc.checkpoint("file:///usr/local/spark/mycode/kafka/checkpoint") //设置检查点,如果存放在HDFS上面,则写成类似ssc.checkpoint("/user/hadoop/checkpoint")这种形式,但是,要启动hadoop
val zkQuorum = "localhost:2181" //Zookeeper服务器地址
val group = "1"  //topic所在的group,可以设置为自己想要的名称,比如不用1,而是val group = "test-consumer-group" 
val topics = "wordsender"  //topics的名称          
val numThreads = 1  //每个topic的分区数
val topicMap =topics.split(",").map((_,numThreads.toInt)).toMap
val lineMap = KafkaUtils.createStream(ssc,zkQuorum,group,topicMap)
val lines = lineMap.map(_._2)
val words = lines.flatMap(_.split(" "))
val pair = words.map(x => (x,1))
val wordCounts = pair.reduceByKeyAndWindow(_ + _,_ - _,Minutes(2),Seconds(10),2) //这行代码的含义在下一节的窗口转换操作中会有介绍
wordCounts.print
ssc.start
ssc.awaitTermination
}
} 

教材第236页

vim StreamingExamples.scala
import org.apache.spark.Logging
import org.apache.log4j.{Level, Logger}
/** Utility functions for Spark Streaming examples. */
object StreamingExamples extends Logging {
  /** Set reasonable logging levels for streaming if the user has not configured log4j. */
  def setStreamingLogLevels() {
    val log4jInitialized = Logger.getRootLogger.getAllAppenders.hasMoreElements
    if (!log4jInitialized) {
      // We first log something to initialize Spark's default logging, then we override the
      // logging level.
      logInfo("Setting log level to [WARN] for streaming example." +
        " To override add a custom log4j.properties to the classpath.")
      Logger.getRootLogger.setLevel(Level.WARN)
    }
  }
}

教材第237页

cd /usr/local/spark/mycode/kafka/
vim simple.sbt
name := "Simple Project"
version := "1.0"
scalaVersion := "2.10.5"
libraryDependencies += "org.apache.spark" %% "spark-core" % "1.6.2"
libraryDependencies += "org.apache.spark" % "spark-streaming_2.10" % "1.6.2"
libraryDependencies += "org.apache.spark" % "spark-streaming-kafka_2.10" % "1.6.2"  
cd /usr/local/spark/mycode/kafka/
/usr/local/sbt/sbt package

教材第238页

cd /usr/local/hadoop
./sbin/start-dfs.sh
cd /usr/local/spark
/usr/local/spark/bin/spark-submit --class "KafkaWordProducer"  /usr/local/spark/mycode/kafka/target/scala-2.10/simple-project_2.10-1.0.jar localhost:9092 wordsender 3 5

教材第239页

cd /usr/local/spark
/usr/local/spark/bin/spark-submit --class "KafkaWordCount" /usr/local/spark/mycode/kafka/target/scala-2.10/simple-project_2.10-1.0.jar