updated to include all joins, make them consistent

Author: bllchmbrs

R/pkg/R/DataFrame.R

@@ -2314,8 +2314,9 @@ setMethod("dropDuplicates",
 #' Column expression. If joinExpr is omitted, the default, inner join is attempted and an error is
 #' thrown if it would be a Cartesian Product. For Cartesian join, use crossJoin instead.
 #' @param joinType The type of join to perform. The following join types are available:
-#' 'inner', 'outer', 'full', 'fullouter', leftouter', 'left_outer', 'left',
-#' 'right_outer', 'rightouter', 'right', and 'leftsemi'. The default joinType is "inner".
+#' 'inner', 'cross', 'outer', 'full', 'full_outer', 'left', 'left_outer',
+#' 'right', 'right_outer', 'left_semi', 'left_anti', 'cross'.
+#' and 'cross'. The default joinType is "inner".
 #' @return A SparkDataFrame containing the result of the join operation.
 #' @family SparkDataFrame functions
 #' @aliases join,SparkDataFrame,SparkDataFrame-method

python/pyspark/sql/dataframe.py

@@ -730,8 +730,9 @@ def join(self, other, on=None, how=None):
             a join expression (Column), or a list of Columns.
             If `on` is a string or a list of strings indicating the name of the join column(s),
             the column(s) must exist on both sides, and this performs an equi-join.
-        :param how: str, default 'inner'.
-            One of `inner`, `outer`, `left_outer`, `right_outer`, `leftsemi`.
+        :param how: str, default 'inner'. Can be any of: `inner`, `cross`, `outer`,
+            `full`, `full_outer`, `left`, `left_outer`, `right`, `right_outer`,
+            `left_semi`, `left_anti`, `cross`.
 
         The following performs a full outer join between ``df1`` and ``df2``.
 

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

@@ -750,14 +750,17 @@ class Dataset[T] private[sql](
   }
 
   /**
-   * Equi-join with another `DataFrame` using the given columns.
+   * Equi-join with another `DataFrame` using the given columns. A cross join with a predicate
+   * is specified as an inner join. If you would explicitly like to perform a cross join use the
+   * `crossJoin` method.
    *
    * Different from other join functions, the join columns will only appear once in the output,
    * i.e. similar to SQL's `JOIN USING` syntax.
    *
    * @param right Right side of the join operation.
    * @param usingColumns Names of the columns to join on. This columns must exist on both sides.
-   * @param joinType One of: `inner`, `outer`, `left_outer`, `right_outer`, `leftsemi`.
+   * @param joinType One of: `inner`, `cross`, `outer`, `full`, `full_outer`,
+   *                 `left`, `left_outer`, `right`, `right_outer`, `left_semi`, `left_anti`.
    *
    * @note If you perform a self-join using this function without aliasing the input
    * `DataFrame`s, you will NOT be able to reference any columns after the join, since
@@ -812,7 +815,8 @@ class Dataset[T] private[sql](
    *
    * @param right Right side of the join.
    * @param joinExprs Join expression.
-   * @param joinType One of: `inner`, `outer`, `left_outer`, `right_outer`, `leftsemi`.
+   * @param joinType One of: `inner`, `cross`, `outer`, `full`, `full_outer`,
+   *                 `left`, `left_outer`, `right`, `right_outer`, `left_semi`, `left_anti`.
    *
    * @group untypedrel
    * @since 2.0.0
@@ -889,7 +893,8 @@ class Dataset[T] private[sql](
    *
    * @param other Right side of the join.
    * @param condition Join expression.
-   * @param joinType One of: `inner`, `outer`, `left_outer`, `right_outer`, `leftsemi`.
+   * @param joinType One of: `inner`, `cross`, `outer`, `full`, `full_outer`,
+   *                 `left`, `left_outer`, `right`, `right_outer`, `left_semi`, `left_anti`.
    *
    * @group typedrel
    * @since 1.6.0