Created
August 11, 2014 08:29
-
-
Save zsxwing/e4a35667c6c3d7273ec7 to your computer and use it in GitHub Desktop.
hbase-spark.scala
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import java.io.{DataOutputStream, ByteArrayOutputStream} | |
| import java.lang.String | |
| import org.apache.hadoop.hbase.client.Scan | |
| import org.apache.hadoop.hbase.HBaseConfiguration | |
| import org.apache.hadoop.hbase.io.ImmutableBytesWritable | |
| import org.apache.hadoop.hbase.client.Result | |
| import org.apache.hadoop.hbase.mapreduce.TableInputFormat | |
| import org.apache.hadoop.hbase.util.Base64 | |
| def convertScanToString(scan: Scan): String = { | |
| val out: ByteArrayOutputStream = new ByteArrayOutputStream | |
| val dos: DataOutputStream = new DataOutputStream(out) | |
| scan.write(dos) | |
| Base64.encodeBytes(out.toByteArray) | |
| } | |
| val conf = HBaseConfiguration.create() | |
| val scan = new Scan() | |
| scan.setCaching(500) | |
| scan.setCacheBlocks(false) | |
| conf.set(TableInputFormat.INPUT_TABLE, "table_name") | |
| conf.set(TableInputFormat.SCAN, convertScanToString(scan)) | |
| val rdd = sc.newAPIHadoopRDD(conf, classOf[TableInputFormat], classOf[ImmutableBytesWritable], classOf[Result]) | |
| rdd.count |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Did you do anything special to get
scan.write(dos)to work? I do not see#writedefined in the latest version of Scan.java.