Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- val rddToSave = sc.parallelize(Seq(("1111123", "456456", "Name1"), ("22222234", "8987987", "Name2")))
- val columnName = ("ACCT_ID", "ACCT_NAME")
- val columnFamily = ("CF", "PP")
- val rdd = rddToSave.map(x => {
- val key = x._1
- val acct_id = x._2
- val acct_name = x._3
- val colNameAcctId = columnName._1
- val colNameAcctName = columnName._2
- val colFamily = columnFamily._1
- val kv = new KeyValue(Bytes.toBytes(key), colFamily.getBytes(), colNameAcctId.getBytes(), acct_id.getBytes())
- (new ImmutableBytesWritable(Bytes.toBytes(key)), kv)
- })
- rdd.saveAsNewAPIHadoopFile(pathToHFile, classOf[ImmutableBytesWritable], classOf[KeyValue],
- classOf[HFileOutputFormat], conf)
- val loadFfiles = new LoadIncrementalHFiles(conf)
- loadFfiles.doBulkLoad(new Path(pathToHFile), hTable)
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement