Merge pull request apache-spark-on-k8s#431 from palantir/juang/merge-easy-upstream

Author: robert3005

R/pkg/NAMESPACE

@@ -28,9 +28,8 @@ importFrom("utils", "download.file", "object.size", "packageVersion", "tail", "u
 
 # S3 methods exported
 export("sparkR.session")
-export("sparkR.init")
-export("sparkR.stop")
 export("sparkR.session.stop")
+export("sparkR.stop")
 export("sparkR.conf")
 export("sparkR.version")
 export("sparkR.uiWebUrl")
@@ -42,9 +41,6 @@ export("sparkR.callJStatic")
 
 export("install.spark")
 
-export("sparkRSQL.init",
-       "sparkRHive.init")
-
 # MLlib integration
 exportMethods("glm",
               "spark.glm",
@@ -70,7 +66,8 @@ exportMethods("glm",
               "spark.svmLinear",
               "spark.fpGrowth",
               "spark.freqItemsets",
-              "spark.associationRules")
+              "spark.associationRules",
+              "spark.findFrequentSequentialPatterns")
 
 # Job group lifecycle management methods
 export("setJobGroup",
@@ -150,15 +147,13 @@ exportMethods("arrange",
               "printSchema",
               "randomSplit",
               "rbind",
-              "registerTempTable",
               "rename",
               "repartition",
               "repartitionByRange",
               "rollup",
               "sample",
               "sample_frac",
               "sampleBy",
-              "saveAsParquetFile",
               "saveAsTable",
               "saveDF",
               "schema",
@@ -174,7 +169,6 @@ exportMethods("arrange",
               "toJSON",
               "transform",
               "union",
-              "unionAll",
               "unionByName",
               "unique",
               "unpersist",
@@ -274,6 +268,7 @@ exportMethods("%<=>%",
               "floor",
               "format_number",
               "format_string",
+              "from_csv",
               "from_json",
               "from_unixtime",
               "from_utc_timestamp",
@@ -413,18 +408,14 @@ export("as.DataFrame",
        "cacheTable",
        "clearCache",
        "createDataFrame",
-       "createExternalTable",
        "createTable",
        "currentDatabase",
-       "dropTempTable",
        "dropTempView",
-       "jsonFile",
        "listColumns",
        "listDatabases",
        "listFunctions",
        "listTables",
        "loadDF",
-       "parquetFile",
        "read.df",
        "read.jdbc",
        "read.json",

R/pkg/R/DataFrame.R

@@ -226,7 +226,9 @@ setMethod("showDF",
 
 #' show
 #'
-#' Print class and type information of a Spark object.
+#' If eager evaluation is enabled and the Spark object is a SparkDataFrame, evaluate the
+#' SparkDataFrame and print top rows of the SparkDataFrame, otherwise, print the class
+#' and type information of the Spark object.
 #'
 #' @param object a Spark object. Can be a SparkDataFrame, Column, GroupedData, WindowSpec.
 #'
@@ -244,11 +246,33 @@ setMethod("showDF",
 #' @note show(SparkDataFrame) since 1.4.0
 setMethod("show", "SparkDataFrame",
           function(object) {
-            cols <- lapply(dtypes(object), function(l) {
-              paste(l, collapse = ":")
-            })
-            s <- paste(cols, collapse = ", ")
-            cat(paste(class(object), "[", s, "]\n", sep = ""))
+            allConf <- sparkR.conf()
+            prop <- allConf[["spark.sql.repl.eagerEval.enabled"]]
+            if (!is.null(prop) && identical(prop, "true")) {
+              argsList <- list()
+              argsList$x <- object
+              prop <- allConf[["spark.sql.repl.eagerEval.maxNumRows"]]
+              if (!is.null(prop)) {
+                numRows <- as.integer(prop)
+                if (numRows > 0) {
+                  argsList$numRows <- numRows
+                }
+              }
+              prop <- allConf[["spark.sql.repl.eagerEval.truncate"]]
+              if (!is.null(prop)) {
+                truncate <- as.integer(prop)
+                if (truncate > 0) {
+                  argsList$truncate <- truncate
+                }
+              }
+              do.call(showDF, argsList)
+            } else {
+              cols <- lapply(dtypes(object), function(l) {
+                paste(l, collapse = ":")
+              })
+              s <- paste(cols, collapse = ", ")
+              cat(paste(class(object), "[", s, "]\n", sep = ""))
+            }
           })
 
 #' DataTypes
@@ -497,32 +521,6 @@ setMethod("createOrReplaceTempView",
               invisible(callJMethod(x@sdf, "createOrReplaceTempView", viewName))
           })
 
-#' (Deprecated) Register Temporary Table
-#'
-#' Registers a SparkDataFrame as a Temporary Table in the SparkSession
-#' @param x A SparkDataFrame
-#' @param tableName A character vector containing the name of the table
-#'
-#' @seealso \link{createOrReplaceTempView}
-#' @rdname registerTempTable-deprecated
-#' @name registerTempTable
-#' @aliases registerTempTable,SparkDataFrame,character-method
-#' @examples
-#'\dontrun{
-#' sparkR.session()
-#' path <- "path/to/file.json"
-#' df <- read.json(path)
-#' registerTempTable(df, "json_df")
-#' new_df <- sql("SELECT * FROM json_df")
-#'}
-#' @note registerTempTable since 1.4.0
-setMethod("registerTempTable",
-          signature(x = "SparkDataFrame", tableName = "character"),
-          function(x, tableName) {
-              .Deprecated("createOrReplaceTempView")
-              invisible(callJMethod(x@sdf, "createOrReplaceTempView", tableName))
-          })
-
 #' insertInto
 #'
 #' Insert the contents of a SparkDataFrame into a table registered in the current SparkSession.
@@ -932,7 +930,6 @@ setMethod("write.orc",
 #' path <- "path/to/file.json"
 #' df <- read.json(path)
 #' write.parquet(df, "/tmp/sparkr-tmp1/")
-#' saveAsParquetFile(df, "/tmp/sparkr-tmp2/")
 #'}
 #' @note write.parquet since 1.6.0
 setMethod("write.parquet",
@@ -943,17 +940,6 @@ setMethod("write.parquet",
             invisible(handledCallJMethod(write, "parquet", path))
           })
 
-#' @rdname write.parquet
-#' @name saveAsParquetFile
-#' @aliases saveAsParquetFile,SparkDataFrame,character-method
-#' @note saveAsParquetFile since 1.4.0
-setMethod("saveAsParquetFile",
-          signature(x = "SparkDataFrame", path = "character"),
-          function(x, path) {
-            .Deprecated("write.parquet")
-            write.parquet(x, path)
-          })
-
 #' Save the content of SparkDataFrame in a text file at the specified path.
 #'
 #' Save the content of the SparkDataFrame in a text file at the specified path.
@@ -2738,18 +2724,6 @@ setMethod("union",
             dataFrame(unioned)
           })
 
-#' unionAll is deprecated - use union instead
-#' @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) {
-            .Deprecated("union")
-            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