[SPARK-5123] Expose only one version of the data type APIs (i.e. remove the Java-specific API).

Author: rxin

mllib/src/main/scala/org/apache/spark/ml/Pipeline.scala

@@ -21,8 +21,9 @@ import scala.collection.mutable.ListBuffer
 
 import org.apache.spark.Logging
 import org.apache.spark.annotation.AlphaComponent
-import org.apache.spark.ml.param.{Params, Param, ParamMap}
-import org.apache.spark.sql.{SchemaRDD, StructType}
+import org.apache.spark.ml.param.{Param, ParamMap}
+import org.apache.spark.sql.SchemaRDD
+import org.apache.spark.sql.types.StructType
 
 /**
  * :: AlphaComponent ::

mllib/src/main/scala/org/apache/spark/ml/Transformer.scala

@@ -26,7 +26,7 @@ import org.apache.spark.sql.SchemaRDD
 import org.apache.spark.sql.api.java.JavaSchemaRDD
 import org.apache.spark.sql.catalyst.analysis.Star
 import org.apache.spark.sql.catalyst.expressions.ScalaUdf
-import org.apache.spark.sql.catalyst.types._
+import org.apache.spark.sql.types._
 
 /**
  * :: AlphaComponent ::

mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala

@@ -26,6 +26,7 @@ import org.apache.spark.mllib.regression.LabeledPoint
 import org.apache.spark.sql._
 import org.apache.spark.sql.catalyst.analysis.Star
 import org.apache.spark.sql.catalyst.dsl._
+import org.apache.spark.sql.types.{DoubleType, StructField, StructType}
 import org.apache.spark.storage.StorageLevel
 
 /**

mllib/src/main/scala/org/apache/spark/ml/evaluation/BinaryClassificationEvaluator.scala

@@ -21,7 +21,8 @@ import org.apache.spark.annotation.AlphaComponent
 import org.apache.spark.ml._
 import org.apache.spark.ml.param._
 import org.apache.spark.mllib.evaluation.BinaryClassificationMetrics
-import org.apache.spark.sql.{DoubleType, Row, SchemaRDD}
+import org.apache.spark.sql.{Row, SchemaRDD}
+import org.apache.spark.sql.types.DoubleType
 
 /**
  * :: AlphaComponent ::

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

@@ -22,7 +22,7 @@ import org.apache.spark.ml.UnaryTransformer
 import org.apache.spark.ml.param.{IntParam, ParamMap}
 import org.apache.spark.mllib.feature
 import org.apache.spark.mllib.linalg.{VectorUDT, Vector}
-import org.apache.spark.sql.catalyst.types.DataType
+import org.apache.spark.sql.types.DataType
 
 /**
  * :: AlphaComponent ::

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

@@ -25,6 +25,7 @@ import org.apache.spark.mllib.linalg.{Vector, VectorUDT}
 import org.apache.spark.sql._
 import org.apache.spark.sql.catalyst.analysis.Star
 import org.apache.spark.sql.catalyst.dsl._
+import org.apache.spark.sql.types.{StructField, StructType}
 
 /**
  * Params for [[StandardScaler]] and [[StandardScalerModel]].

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

@@ -20,7 +20,7 @@ package org.apache.spark.ml.feature
 import org.apache.spark.annotation.AlphaComponent
 import org.apache.spark.ml.UnaryTransformer
 import org.apache.spark.ml.param.ParamMap
-import org.apache.spark.sql.{DataType, StringType, ArrayType}
+import org.apache.spark.sql.types.{DataType, StringType, ArrayType}
 
 /**
  * :: AlphaComponent ::

mllib/src/main/scala/org/apache/spark/ml/tuning/CrossValidator.scala

@@ -24,7 +24,8 @@ import org.apache.spark.annotation.AlphaComponent
 import org.apache.spark.ml._
 import org.apache.spark.ml.param.{IntParam, Param, ParamMap, Params}
 import org.apache.spark.mllib.util.MLUtils
-import org.apache.spark.sql.{SchemaRDD, StructType}
+import org.apache.spark.sql.SchemaRDD
+import org.apache.spark.sql.types.StructType
 
 /**
  * Params for [[CrossValidator]] and [[CrossValidatorModel]].

mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala

@@ -27,9 +27,8 @@ import breeze.linalg.{DenseVector => BDV, SparseVector => BSV, Vector => BV}
 
 import org.apache.spark.SparkException
 import org.apache.spark.mllib.util.NumericParser
-import org.apache.spark.sql.catalyst.annotation.SQLUserDefinedType
 import org.apache.spark.sql.catalyst.expressions.{GenericMutableRow, Row}
-import org.apache.spark.sql.catalyst.types._
+import org.apache.spark.sql.types._
 
 /**
  * Represents a numeric vector, whose index type is Int and value type is Double.

project/MimaExcludes.scala

@@ -60,6 +60,18 @@ object MimaExcludes {
             ProblemFilters.exclude[IncompatibleResultTypeProblem](
               "org.apache.spark.streaming.flume.sink.SparkAvroCallbackHandler." +
                 "removeAndGetProcessor")
+          ) ++ Seq(
+            // SPARK-5123 (SparkSQL data type change) - alpha component only
+            ProblemFilters.exclude[IncompatibleResultTypeProblem](
+              "org.apache.spark.ml.feature.HashingTF.outputDataType"),
+            ProblemFilters.exclude[IncompatibleResultTypeProblem](
+              "org.apache.spark.ml.feature.Tokenizer.outputDataType"),
+            ProblemFilters.exclude[IncompatibleMethTypeProblem](
+              "org.apache.spark.ml.feature.Tokenizer.validateInputType"),
+            ProblemFilters.exclude[IncompatibleMethTypeProblem](
+              "org.apache.spark.ml.classification.LogisticRegressionModel.validateAndTransformSchema"),
+            ProblemFilters.exclude[IncompatibleMethTypeProblem](
+              "org.apache.spark.ml.classification.LogisticRegression.validateAndTransformSchema")
           )
 
         case v if v.startsWith("1.2") =>