add ut for 0-based loadlibsvm exception

apache · May 31, 2015 · 9956365 · 9956365
1 parent 5bd1f9a
commit 9956365
Showing 1 changed file with 18 additions and 0 deletions.
diff --git a/mllib/src/test/scala/org/apache/spark/mllib/util/MLUtilsSuite.scala b/mllib/src/test/scala/org/apache/spark/mllib/util/MLUtilsSuite.scala
@@ -27,6 +27,7 @@ import breeze.linalg.{squaredDistance => breezeSquaredDistance}
 import com.google.common.base.Charsets
 import com.google.common.io.Files
 
+import org.apache.spark.SparkException
 import org.apache.spark.mllib.linalg.{DenseVector, SparseVector, Vectors}
 import org.apache.spark.mllib.regression.LabeledPoint
 import org.apache.spark.mllib.util.MLUtils._
@@ -109,6 +110,23 @@ class MLUtilsSuite extends FunSuite with MLlibTestSparkContext {
     Utils.deleteRecursively(tempDir)
   }
 
+  test("loadLibSVMFile throws SparkException when passing a zero-based vector") {
+    val lines =
+      """
+        |0
+        |0 0:4.0 4:5.0 6:6.0
+      """.stripMargin
+    val tempDir = Utils.createTempDir()
+    val file = new File(tempDir.getPath, "part-00000")
+    Files.write(lines, file, Charsets.US_ASCII)
+    val path = tempDir.toURI.toString
+
+    intercept[SparkException] {
+      val pointsWithoutNumFeatures = loadLibSVMFile(sc, path).collect()
+    }
+    Utils.deleteRecursively(tempDir)
+  }
+
   test("saveAsLibSVMFile") {
     val examples = sc.parallelize(Seq(
       LabeledPoint(1.1, Vectors.sparse(3, Seq((0, 1.23), (2, 4.56)))),