diff options
author | Bryan Newbold <bnewbold@archive.org> | 2018-05-21 18:36:43 -0700 |
---|---|---|
committer | Bryan Newbold <bnewbold@archive.org> | 2018-05-21 18:36:43 -0700 |
commit | b2c59428fec807ef4dbe4cedcec3614154334817 (patch) | |
tree | 0fc17327e95ddc7a9bf99ed26d05d5f47878d492 /scald-mvp/src/main/scala/example/SimpleHBaseSourceExample.scala | |
parent | 6f5beb13c718acb28345bb037e3c24b3f366e170 (diff) | |
download | sandcrawler-b2c59428fec807ef4dbe4cedcec3614154334817.tar.gz sandcrawler-b2c59428fec807ef4dbe4cedcec3614154334817.zip |
spyglass/hbase test examples (from upstream)
Diffstat (limited to 'scald-mvp/src/main/scala/example/SimpleHBaseSourceExample.scala')
-rw-r--r-- | scald-mvp/src/main/scala/example/SimpleHBaseSourceExample.scala | 35 |
1 files changed, 35 insertions, 0 deletions
diff --git a/scald-mvp/src/main/scala/example/SimpleHBaseSourceExample.scala b/scald-mvp/src/main/scala/example/SimpleHBaseSourceExample.scala new file mode 100644 index 0000000..697805d --- /dev/null +++ b/scald-mvp/src/main/scala/example/SimpleHBaseSourceExample.scala @@ -0,0 +1,35 @@ +package example + +import com.twitter.scalding.{Tsv, Args} +import parallelai.spyglass.base.JobBase +import org.apache.log4j.{Level, Logger} +import parallelai.spyglass.hbase.{HBasePipeConversions, HBaseSource} +import parallelai.spyglass.hbase.HBaseConstants.SourceMode +import cascading.tuple.Fields +import cascading.property.AppProps +import java.util.Properties + +/** + * Simple example of HBaseSource usage + */ +class SimpleHBaseSourceExample(args: Args) extends JobBase(args) with HBasePipeConversions { + + val isDebug: Boolean = args("debug").toBoolean + + if (isDebug) Logger.getRootLogger.setLevel(Level.DEBUG) + + val output = args("output") + + val hbs = new HBaseSource( + "table_name", + "quorum_name:2181", + new Fields("key"), + List("column_family"), + List(new Fields("column_name1", "column_name2")), + sourceMode = SourceMode.GET_LIST, keyList = List("1", "2", "3")) + .read + .debug + .fromBytesWritable(new Fields("key", "column_name1", "column_name2")) + .write(Tsv(output format "get_list")) + + } |