[jvm-packages]add feature size for LabelPoint and DataBatch (#5303)

* fix type error

* Validate number of features.

* resolve comments

* add feature size for LabelPoint and DataBatch

* pass the feature size to native

* move feature size validating tests into a separate suite

* resolve comments

Co-authored-by: fis <jm.yuan@outlook.com>

jvm-packages/xgboost4j/src/main/scala/ml/dmlc/xgboost4j/LabeledPoint.scala

@@ -20,6 +20,7 @@ package ml.dmlc.xgboost4j
  * Labeled training data point.
  *
  * @param label Label of this point.
+ * @param size Feature dimensionality
  * @param indices Feature indices of this point or `null` if the data is dense.
  * @param values Feature values of this point.
  * @param weight Weight of this point.
@@ -28,6 +29,7 @@ package ml.dmlc.xgboost4j
  */
 case class LabeledPoint(
     label: Float,
+    size: Int,
     indices: Array[Int],
     values: Array[Float],
     weight: Float = 1f,
@@ -36,8 +38,11 @@ case class LabeledPoint(
   require(indices == null || indices.length == values.length,
     "indices and values must have the same number of elements")
 
-  def this(label: Float, indices: Array[Int], values: Array[Float]) = {
+  require(indices == null || size >= indices.length,
+    "feature dimensionality must be greater equal than size of indices")
+
+  def this(label: Float, size: Int, indices: Array[Int], values: Array[Float]) = {
     // [[weight]] default duplicated to disambiguate the constructor call.
-    this(label, indices, values, 1.0f)
+    this(label, size, indices, values, 1.0f)
   }
 }