Merge commit '87bd9c75df' into rk/more-merge

Author: Robert Kruszewski

.gitignore

@@ -81,7 +81,6 @@ work/
 .credentials
 dev/pr-deps
 docs/.jekyll-metadata
-*.crc
 
 # For Hive
 TempStatsStore/

R/WINDOWS.md

@@ -3,7 +3,7 @@
 To build SparkR on Windows, the following steps are required
 
 1. Install R (>= 3.1) and [Rtools](http://cran.r-project.org/bin/windows/Rtools/). Make sure to
-include Rtools and R in `PATH`.
+include Rtools and R in `PATH`. Note that support for R prior to version 3.4 is deprecated as of Spark 3.0.0.
 
 2. Install
 [JDK8](http://www.oracle.com/technetwork/java/javase/downloads/jdk8-downloads-2133151.html) and set

R/pkg/DESCRIPTION

@@ -15,7 +15,7 @@ URL: http://www.apache.org/ http://spark.apache.org/
 BugReports: http://spark.apache.org/contributing.html
 SystemRequirements: Java (== 8)
 Depends:
-    R (>= 3.0),
+    R (>= 3.1),
     methods
 Suggests:
     knitr,

R/pkg/R/DataFrame.R

@@ -767,6 +767,14 @@ setMethod("repartition",
 #'                      using \code{spark.sql.shuffle.partitions} as number of partitions.}
 #'}
 #'
+#' At least one partition-by expression must be specified.
+#' When no explicit sort order is specified, "ascending nulls first" is assumed.
+#'
+#' Note that due to performance reasons this method uses sampling to estimate the ranges.
+#' Hence, the output may not be consistent, since sampling can return different values.
+#' The sample size can be controlled by the config
+#' \code{spark.sql.execution.rangeExchange.sampleSizePerPartition}.
+#'
 #' @param x a SparkDataFrame.
 #' @param numPartitions the number of partitions to use.
 #' @param col the column by which the range partitioning will be performed.

R/pkg/R/functions.R

@@ -3370,7 +3370,7 @@ setMethod("flatten",
 #'
 #' @rdname column_collection_functions
 #' @aliases map_entries map_entries,Column-method
-#' @note map_entries since 2.4.0
+#' @note map_entries since 3.0.0
 setMethod("map_entries",
           signature(x = "Column"),
           function(x) {

R/pkg/R/stats.R

@@ -109,7 +109,7 @@ setMethod("corr",
 #'
 #' Finding frequent items for columns, possibly with false positives.
 #' Using the frequent element count algorithm described in
-#' \url{http://dx.doi.org/10.1145/762471.762473}, proposed by Karp, Schenker, and Papadimitriou.
+#' \url{https://doi.org/10.1145/762471.762473}, proposed by Karp, Schenker, and Papadimitriou.
 #'
 #' @param x A SparkDataFrame.
 #' @param cols A vector column names to search frequent items in.
@@ -143,7 +143,7 @@ setMethod("freqItems", signature(x = "SparkDataFrame", cols = "character"),
 #' *exact* rank of x is close to (p * N). More precisely,
 #'   floor((p - err) * N) <= rank(x) <= ceil((p + err) * N).
 #' This method implements a variation of the Greenwald-Khanna algorithm (with some speed
-#' optimizations). The algorithm was first present in [[http://dx.doi.org/10.1145/375663.375670
+#' optimizations). The algorithm was first present in [[https://doi.org/10.1145/375663.375670
 #' Space-efficient Online Computation of Quantile Summaries]] by Greenwald and Khanna.
 #' Note that NA values will be ignored in numerical columns before calculation. For
 #'   columns only containing NA values, an empty list is returned.

R/pkg/inst/profile/general.R

@@ -16,6 +16,10 @@
 #
 
 .First <- function() {
+  if (utils::compareVersion(paste0(R.version$major, ".", R.version$minor), "3.4.0") == -1) {
+    warning("Support for R prior to version 3.4 is deprecated since Spark 3.0.0")
+  }
+
   packageDir <- Sys.getenv("SPARKR_PACKAGE_DIR")
   dirs <- strsplit(packageDir, ",")[[1]]
   .libPaths(c(dirs, .libPaths()))

R/pkg/inst/profile/shell.R

@@ -16,6 +16,10 @@
 #
 
 .First <- function() {
+  if (utils::compareVersion(paste0(R.version$major, ".", R.version$minor), "3.4.0") == -1) {
+    warning("Support for R prior to version 3.4 is deprecated since Spark 3.0.0")
+  }
+
   home <- Sys.getenv("SPARK_HOME")
   .libPaths(c(file.path(home, "R", "lib"), .libPaths()))
   Sys.setenv(NOAWT = 1)

R/pkg/tests/fulltests/test_sparkSQL.R

@@ -1674,7 +1674,7 @@ test_that("column functions", {
 
   # check for unparseable
   df <- as.DataFrame(list(list("a" = "")))
-  expect_equal(collect(select(df, from_json(df$a, schema)))[[1]][[1]], NA)
+  expect_equal(collect(select(df, from_json(df$a, schema)))[[1]][[1]]$a, NA)
 
   # check if array type in string is correctly supported.
   jsonArr <- "[{\"name\":\"Bob\"}, {\"name\":\"Alice\"}]"

R/pkg/tests/fulltests/test_streaming.R

@@ -127,6 +127,7 @@ test_that("Specify a schema by using a DDL-formatted string when reading", {
   expect_false(awaitTermination(q, 5 * 1000))
   callJMethod(q@ssq, "processAllAvailable")
   expect_equal(head(sql("SELECT count(*) FROM people3"))[[1]], 3)
+  stopQuery(q)
 
   expect_error(read.stream(path = parquetPath, schema = "name stri"),
                "DataType stri is not supported.")