[SPARK-12746][ML] ArrayType(_, true) should also accept ArrayType(_, false) fix for branch-1.6

https://issues.apache.org/jira/browse/SPARK-13359

Author: Earthson Lu <[email protected]>

Closes #11237 from Earthson/SPARK-13359.

Author: Earthson

mllib/src/main/scala/org/apache/spark/ml/feature/CountVectorizer.scala

@@ -70,7 +70,8 @@ private[feature] trait CountVectorizerParams extends Params with HasInputCol wit
 
   /** Validates and transforms the input schema. */
   protected def validateAndTransformSchema(schema: StructType): StructType = {
-    SchemaUtils.checkColumnType(schema, $(inputCol), new ArrayType(StringType, true))
+    val typeCandidates = List(ArrayType(StringType, true), ArrayType(StringType, false))
+    SchemaUtils.checkColumnTypes(schema, $(inputCol), typeCandidates)
     SchemaUtils.appendColumn(schema, $(outputCol), new VectorUDT)
   }
 

mllib/src/main/scala/org/apache/spark/ml/util/SchemaUtils.scala

@@ -43,6 +43,23 @@ private[spark] object SchemaUtils {
       s"Column $colName must be of type $dataType but was actually $actualDataType.$message")
   }
 
+  /**
+    * Check whether the given schema contains a column of one of the require data types.
+    * @param colName  column name
+    * @param dataTypes  required column data types
+    */
+  def checkColumnTypes(
+      schema: StructType,
+      colName: String,
+      dataTypes: Seq[DataType],
+      msg: String = ""): Unit = {
+    val actualDataType = schema(colName).dataType
+    val message = if (msg != null && msg.trim.length > 0) " " + msg else ""
+    require(dataTypes.exists(actualDataType.equals),
+      s"Column $colName must be of type equal to one of the following types: " +
+        s"${dataTypes.mkString("[", ", ", "]")} but was actually of type $actualDataType.$message")
+  }
+
   /**
    * Appends a new column to the input schema. This fails if the given output column already exists.
    * @param schema input schema