HBase数据库
由于 org.apache.hadoop.hbase.mapreduce.TableInputFormat 类的实现，Spark 可以通过Hadoop输入格式访问HBase。
这个输入格式会返回键值对数据，
其中键的类型为org. apache.hadoop.hbase.io.ImmutableBytesWritable，
而值的类型为org.apache.hadoop.hbase.client.Result。

1、HBase读取

import org.apache.hadoop.hbase.HBaseConfiguration
import org.apache.hadoop.hbase.mapreduce.TableInputFormat
import org.apache.hadoop.hbase.util.Bytes
import org.apache.spark.{SparkConf, SparkContext}
import org.apache.log4j.Logger

object HbaseRedTest extends java.io.Serializable{

  val logger = Logger.getLogger(HbaseRedTest.getClass)

  def main(args: Array[String]): Unit = {

    val sparkConf = new SparkConf().setAppName("HBaseApp")//.setMaster("local[*]")
    val sc = new SparkContext(sparkConf)

    val conf = HBaseConfiguration.create()
    //HBase中的表名
    conf.set(TableInputFormat.INPUT_TABLE, "fruit")

    val hBaseRDD = sc.newAPIHadoopRDD(conf, classOf[TableInputFormat],
      classOf[org.apache.hadoop.hbase.io.ImmutableBytesWritable],
      classOf[org.apache.hadoop.hbase.client.Result])

    val count = hBaseRDD.count()
    println("hBaseRDD RDD Count:"+ count)
    hBaseRDD.cache()
    hBaseRDD.foreach {
      case (_, result) =>
        val key = Bytes.toString(result.getRow)
        val name = Bytes.toString(result.getValue("info".getBytes, "name".getBytes))
        val color = Bytes.toString(result.getValue("info".getBytes, "color".getBytes))
        println("Row key:" + key + " Name:" + name + " Color:" + color)
    }
    sc.stop()
  }
}

2、HBase写入

import org.apache.hadoop.hbase.client.{HBaseAdmin, Put}
import org.apache.hadoop.hbase.io.ImmutableBytesWritable
import org.apache.hadoop.hbase.{HBaseConfiguration, HColumnDescriptor, HTableDescriptor, TableName}
import org.apache.hadoop.hbase.mapred.TableOutputFormat
import org.apache.hadoop.hbase.util.Bytes
import org.apache.hadoop.mapred.JobConf
import org.apache.spark.{SparkConf, SparkContext}


object HbaseWriTest extends java.io.Serializable{
  def main(args: Array[String]): Unit = {
    val sparkConf = new SparkConf().setAppName("HBaseApp")//.setMaster("local[*]")
    val sc = new SparkContext(sparkConf)

    val conf = HBaseConfiguration.create()
    val jobConf = new JobConf(conf)
    jobConf.setOutputFormat(classOf[TableOutputFormat])
    jobConf.set(TableOutputFormat.OUTPUT_TABLE, "fruit_spark")

    val fruitTable = TableName.valueOf("fruit_spark")
    val tableDescr = new HTableDescriptor(fruitTable)
    tableDescr.addFamily(new HColumnDescriptor("info".getBytes))

    val admin = new HBaseAdmin(conf)
    if (admin.tableExists(fruitTable)) {
      admin.disableTable(fruitTable)
      admin.deleteTable(fruitTable)
    }
    admin.createTable(tableDescr)

    def convert(triple: (Int, String, Int)) = {
      val put = new Put(Bytes.toBytes(triple._1))
      put.addImmutable(Bytes.toBytes("info"), Bytes.toBytes("name"), Bytes.toBytes(triple._2))
      put.addImmutable(Bytes.toBytes("info"), Bytes.toBytes("price"), Bytes.toBytes(triple._3))
      (new ImmutableBytesWritable, put)
    }
    val initialRDD = sc.parallelize(List((1,"apple",11), (2,"banana",12), (3,"pear",13)))
    val localData = initialRDD.map(convert)
    localData.saveAsHadoopDataset(jobConf)
  }
}

3、Hbase -> pom.xml

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>

    <groupId>com.heihouzi.sparkhbase</groupId>
    <artifactId>sparkhbase</artifactId>
    <version>1.0-SNAPSHOT</version>

    <properties>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <log4j.version>1.2.17</log4j.version>
        <slf4j.version>1.7.22</slf4j.version>
        <spark.version>2.1.1</spark.version>
        <scala.version>2.11.8</scala.version>
    </properties>

    <dependencies>
        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>jcl-over-slf4j</artifactId>
            <version>${slf4j.version}</version>
        </dependency>
        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-api</artifactId>
            <version>${slf4j.version}</version>
        </dependency>
        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-log4j12</artifactId>
            <version>${slf4j.version}</version>
        </dependency>
        <dependency>
            <groupId>log4j</groupId>
            <artifactId>log4j</artifactId>
            <version>${log4j.version}</version>
        </dependency>

        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>3.8.1</version>
            <scope>test</scope>
        </dependency>

        <dependency>
            <groupId>org.apache.hbase</groupId>
            <artifactId>hbase-server</artifactId>
            <version>1.3.1</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hbase</groupId>
            <artifactId>hbase-client</artifactId>
            <version>1.3.1</version>
        </dependency>

        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
            <version>${scala.version}</version>
            <!--<scope>provided</scope>-->
        </dependency>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.11</artifactId>
            <version>${spark.version}</version>
            <!--<scope>provided</scope>-->
        </dependency>

    </dependencies>

    <build>
        <finalName>SparkHbase</finalName>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>3.6.1</version>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                </configuration>
            </plugin>

            <plugin>
                <groupId>net.alchim31.maven</groupId>
                <artifactId>scala-maven-plugin</artifactId>
                <version>3.2.2</version>
                <executions>
                    <execution>
                        <goals>
                            <goal>compile</goal>
                            <goal>testCompile</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>

            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-assembly-plugin</artifactId>
                <version>3.0.0</version>
                <configuration>
                    <archive>
                        <manifest>
                            <mainClass>com.yinggu.spark.WordCount</mainClass>
                        </manifest>
                    </archive>
                    <descriptorRefs>
                        <descriptorRef>jar-with-dependencies</descriptorRef>
                    </descriptorRefs>
                </configuration>
                <executions>
                    <execution>
                        <id>make-assembly</id>
                        <phase>package</phase>
                        <goals>
                            <goal>single</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>
</project>

4、log4j.properties

log4j.rootLogger=info,stdout,R
log4j.appender.stdout=org.apache.log4j.ConsoleAppender
log4j.appender.stdout.layout=org.apache.log4j.PatternLayout
log4j.appender.stdout.layout.ConversionPattern=%d{yyyy-MM-dd HH:mm:ss,SSS}  %5p --- [%t]  %-c(line:%L) : %m%n

log4j.appender.R=org.apache.log4j.RollingFileAppender
log4j.appender.R.File=spark.log
log4j.appender.R.MaxFileSize=1024KB
log4j.appender.R.MaxBackupIndex=1

log4j.appender.R.layout=org.apache.log4j.PatternLayout
log4j.appender.R.layout.ConversionPattern=%d{yyyy-MM-dd HH:mm:ss,SSS}  %5p --- [%t]  %-c(line:%L) : %m%n

5、spark-submit

[heihouzi@hadoop102 spark]$ bin/spark-submit \
--master spark://hadoop102:7077 \
--class unit.HbaseRedTest 
SparkHbase-jar-with-dependencies.jar