在Spark中读取CSV文件，并使用创建的RDD将其插入到HBase

import org.apache.spark.{SparkConf, SparkContext}
import org.apache.spark.sql.{SQLContext, SaveMode}
import org.apache.hadoop.hbase.HBaseConfiguration
import org.apache.hadoop.hbase.client.HBaseAdmin
import org.apache.hadoop.hbase.mapreduce.TableInputFormat
import org.apache.hadoop.hbase.io.ImmutableBytesWritable
import org.apache.hadoop.hbase.client.Put
import org.apache.hadoop.hbase.util.Bytes

val conf = new SparkConf().setAppName("SparkHBaseExample")
val sc = new SparkContext(conf)

val sqlContext = new SQLContext(sc)

val csvFilePath = "path/to/csv/file.csv"
val csvDataFrame = sqlContext.read.format("com.databricks.spark.csv").option("header", "true").load(csvFilePath)

val hbaseTableName = "table_name"
val hbaseConf = HBaseConfiguration.create()
hbaseConf.set(TableInputFormat.INPUT_TABLE, hbaseTableName)
val hbaseRDD = csvDataFrame.rdd.map(row => {
  val put = new Put(Bytes.toBytes(row.getAs[String]("rowkey_column")))
  put.addColumn(Bytes.toBytes("column_family"), Bytes.toBytes("column"), Bytes.toBytes(row.getAs[String]("data_column")))
  (new ImmutableBytesWritable, put)
})

hbaseRDD.saveAsNewAPIHadoopDataset(hbaseConf)