版本:spark 2.2.0,hadoop 3.0.0,hbase 2.0.0
实现:
1)pom.xml
<dependencies>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-sql_${scala.binary.version}</artifactId>
<version>${spark.version}</version>
</dependency>
<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase-client</artifactId>
<version>${hbase.version}</version>
<exclusions>
<exclusion>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-log4j12</artifactId>
</exclusion>
</exclusions>
</dependency>
</dependencies>
2)main
public static void main(String[] args) throws StreamingQueryException {
SparkSession sparkSession = SparkSession.builder().appName("test")
.master("local[*]").getOrCreate();
Dataset<Row> source = sparkSession
.readStream()
.format("socket")
.option("host", "bigdata-pro01.wn.com")
.option("port", 9999)
.load().selectExpr("CAST(value AS STRING)");
//使用Foreach sink
StreamingQuery foreachQuery = source.writeStream()
.foreach(new HbaseSink())
.outputMode(OutputMode.Append())
.start();
foreachQuery.awaitTermination();
}
3)HbaseSink实现
public class HbaseSink extends ForeachWriter<Row> {
private Connection connection=null;//hbase连接
private static Logger logger = LoggerFactory.getLogger(HbaseSink.class);
@Override
public boolean open(long partitionId, long version) {
//hbase
try{
Configuration conf = HBaseConfiguration.create();
conf.set("hbase.zookeeper.property.clientPort", "2181");
conf.set("hbase.zookeeper.quorum","");
conf.set("hbase.master", "");
connection = ConnectionFactory.createConnection(conf);
}catch(IOException e){
logger.error(e.toString());
}
return true;
}
@Override
public void process(Row value) {
String word = value.getAs("value").toString();
String rowkey = String.valueOf(System.currentTimeMillis());//以当前时间戳作为rowkey
String columnFamily = "info";//列簇
Put put = new Put(rowkey.getBytes());
put.addColumn(columnFamily.getBytes(), ("word").getBytes(), word.getBytes());
try{
TableName tableName = TableName.valueOf("test");//表名
Table table = connection.getTable(tableName);
table.put(put);
}catch(IOException e){
e.printStackTrace();
}
}
@Override
public void close(Throwable errorOrNull) {
try{
connection.close();
}catch(IOException e){
e.printStackTrace();
}
}
}