aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorBryan Newbold <bnewbold@archive.org>2018-05-21 18:36:43 -0700
committerBryan Newbold <bnewbold@archive.org>2018-05-21 18:36:43 -0700
commitb2c59428fec807ef4dbe4cedcec3614154334817 (patch)
tree0fc17327e95ddc7a9bf99ed26d05d5f47878d492
parent6f5beb13c718acb28345bb037e3c24b3f366e170 (diff)
downloadsandcrawler-b2c59428fec807ef4dbe4cedcec3614154334817.tar.gz
sandcrawler-b2c59428fec807ef4dbe4cedcec3614154334817.zip
spyglass/hbase test examples (from upstream)
-rw-r--r--scald-mvp/src/main/scala/example/SimpleHBaseSourceExample.scala35
-rw-r--r--scald-mvp/src/test/scala/example/SimpleHBaseSourceExampleTest.scala58
2 files changed, 93 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"))
+
+ }
diff --git a/scald-mvp/src/test/scala/example/SimpleHBaseSourceExampleTest.scala b/scald-mvp/src/test/scala/example/SimpleHBaseSourceExampleTest.scala
new file mode 100644
index 0000000..d416af8
--- /dev/null
+++ b/scald-mvp/src/test/scala/example/SimpleHBaseSourceExampleTest.scala
@@ -0,0 +1,58 @@
+package example
+
+import org.junit.runner.RunWith
+import com.twitter.scalding.{JobTest, TupleConversions}
+import org.scalatest.FunSpec
+import org.scalatest.junit.JUnitRunner
+import org.slf4j.LoggerFactory
+import org.apache.hadoop.hbase.io.ImmutableBytesWritable
+import cascading.tuple.{Tuple, Fields}
+import org.apache.hadoop.hbase.util.Bytes
+import scala._
+import com.twitter.scalding.Tsv
+import parallelai.spyglass.hbase.HBaseSource
+import parallelai.spyglass.hbase.HBaseConstants.SourceMode
+
+/**
+ * Example of how to define tests for HBaseSource
+ */
+@RunWith(classOf[JUnitRunner])
+class SimpleHBaseSourceExampleTest extends FunSpec with TupleConversions {
+
+ val output = "/tmp/testOutput"
+
+ val log = LoggerFactory.getLogger(this.getClass.getName)
+
+ val sampleData = List(
+ List("1", "kk1", "pp1"),
+ List("2", "kk2", "pp2"),
+ List("3", "kk3", "pp3")
+ )
+
+ JobTest("parallelai.spyglass.hbase.example.SimpleHBaseSourceExample")
+ .arg("test", "")
+ .arg("app.conf.path", "app.conf")
+ .arg("output", output)
+ .arg("debug", "true")
+ .source[Tuple](
+ 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")),
+ sampleData.map(l => new Tuple(l.map(s => {new ImmutableBytesWritable(Bytes.toBytes(s))}):_*)))
+ .sink[Tuple](Tsv(output format "get_list")) {
+ outputBuffer =>
+ log.debug("Output => " + outputBuffer)
+
+ it("should return the test data provided.") {
+ println("outputBuffer.size => " + outputBuffer.size)
+ assert(outputBuffer.size === 3)
+ }
+ }
+ .run
+ .finish
+
+}