[SPARK-25908][SQL][FOLLOW-UP] Add back unionAll

R/pkg/NAMESPACE

@@ -169,6 +169,7 @@ exportMethods("arrange",
               "toJSON",
               "transform",
               "union",
+              "unionAll",
               "unionByName",
               "unique",
               "unpersist",

R/pkg/R/DataFrame.R

@@ -2732,6 +2732,20 @@ setMethod("union",
             dataFrame(unioned)
           })
 
+#' Return a new SparkDataFrame containing the union of rows
+#'
+#' This is an alias for `union`.
+#'
+#' @rdname union
+#' @name unionAll
+#' @aliases unionAll,SparkDataFrame,SparkDataFrame-method
+#' @note unionAll since 1.4.0
+setMethod("unionAll",
+          signature(x = "SparkDataFrame", y = "SparkDataFrame"),
+          function(x, y) {
+            union(x, y)
+          })
+
 #' Return a new SparkDataFrame containing the union of rows, matched by column names
 #'
 #' Return a new SparkDataFrame containing the union of rows in this SparkDataFrame

R/pkg/R/generics.R

@@ -631,6 +631,9 @@ setGeneric("toRDD", function(x) { standardGeneric("toRDD") })
 #' @rdname union
 setGeneric("union", function(x, y) { standardGeneric("union") })
 
+#' @rdname union
+setGeneric("unionAll", function(x, y) { standardGeneric("unionAll") })
+
 #' @rdname unionByName
 setGeneric("unionByName", function(x, y) { standardGeneric("unionByName") })
 

R/pkg/tests/fulltests/test_sparkSQL.R

@@ -2458,6 +2458,7 @@ test_that("union(), unionByName(), rbind(), except(), and intersect() on a DataF
   expect_equal(count(unioned), 6)
   expect_equal(first(unioned)$name, "Michael")
   expect_equal(count(arrange(suppressWarnings(union(df, df2)), df$age)), 6)
+  expect_equal(count(arrange(suppressWarnings(unionAll(df, df2)), df$age)), 6)
 
   df1 <- select(df2, "age", "name")
   unioned1 <- arrange(unionByName(df1, df), df1$age)

docs/sparkr.md

@@ -718,4 +718,4 @@ You can inspect the search path in R with [`search()`](https://stat.ethz.ch/R-ma
 ## Upgrading to SparkR 3.0.0
 
  - The deprecated methods `sparkR.init`, `sparkRSQL.init`, `sparkRHive.init` have been removed. Use `sparkR.session` instead.
- - The deprecated methods `parquetFile`, `saveAsParquetFile`, `jsonFile`, `registerTempTable`, `createExternalTable`, `dropTempTable`, `unionAll` have been removed. Use `read.parquet`, `write.parquet`, `read.json`, `createOrReplaceTempView`, `createTable`, `dropTempView`, `union` instead.
+ - The deprecated methods `parquetFile`, `saveAsParquetFile`, `jsonFile`, `registerTempTable`, `createExternalTable`, and `dropTempTable` have been removed. Use `read.parquet`, `write.parquet`, `read.json`, `createOrReplaceTempView`, `createTable`, `dropTempView`, `union` instead.

docs/sql-migration-guide-upgrade.md

@@ -341,8 +341,6 @@ displayTitle: Spark SQL Upgrading Guide
    APIs. Instead, `DataFrame` remains the primary programming abstraction, which is analogous to the
    single-node data frame notion in these languages.
 
- - Dataset and DataFrame API `unionAll` has been deprecated and replaced by `union`
-
  - Dataset and DataFrame API `explode` has been deprecated, alternatively, use `functions.explode()` with `select` or `flatMap`
 
  - Dataset and DataFrame API `registerTempTable` has been deprecated and replaced by `createOrReplaceTempView`

python/pyspark/sql/dataframe.py

@@ -1448,6 +1448,17 @@ def union(self, other):
         """
         return DataFrame(self._jdf.union(other._jdf), self.sql_ctx)
 
+    @since(1.3)
+    def unionAll(self, other):
+        """ Return a new :class:`DataFrame` containing union of rows in this and another frame.
+
+        This is equivalent to `UNION ALL` in SQL. To do a SQL-style set union
+        (that does deduplication of elements), use this function followed by :func:`distinct`.
+
+        Also as standard in SQL, this function resolves columns by position (not by name).
+        """
+        return self.union(other)
+
     @since(2.3)
     def unionByName(self, other):
         """ Returns a new :class:`DataFrame` containing union of rows in this and another frame.

sql/core/src/main/scala/org/apache/spark/sql/Dataset.scala

@@ -1852,6 +1852,20 @@ class Dataset[T] private[sql](
     CombineUnions(Union(logicalPlan, other.logicalPlan))
   }
 
+  /**
+   * Returns a new Dataset containing union of rows in this Dataset and another Dataset.
+   * This is an alias for `union`.
+   *
+   * This is equivalent to `UNION ALL` in SQL. To do a SQL-style set union (that does
+   * deduplication of elements), use this function followed by a [[distinct]].
+   *
+   * Also as standard in SQL, this function resolves columns by position (not by name).
+   *
+   * @group typedrel
+   * @since 2.0.0
+   */
+  def unionAll(other: Dataset[T]): Dataset[T] = union(other)
+
   /**
    * Returns a new Dataset containing union of rows in this Dataset and another Dataset.
    *

sql/core/src/test/scala/org/apache/spark/sql/DataFrameSuite.scala

@@ -97,6 +97,12 @@ class DataFrameSuite extends QueryTest with SharedSQLContext {
       unionDF.agg(avg('key), max('key), min('key), sum('key)),
       Row(50.5, 100, 1, 25250) :: Nil
     )
+
+    // unionAll is an alias of union
+    val unionAllDF = testData.unionAll(testData).unionAll(testData)
+      .unionAll(testData).unionAll(testData)
+
+    checkAnswer(unionDF, unionAllDF)
   }
 
   test("union should union DataFrames with UDTs (SPARK-13410)") {