Merge branch 'master' into r-regex-fixed

Author: Michael Chirico

.github/workflows/master.yml

@@ -103,12 +103,12 @@ jobs:
     - uses: actions/setup-java@v1
       with:
         java-version: '11'
-    - name: install R
+    - uses: r-lib/actions/setup-r@v1
+      with:
+        r-version: '3.6.2'
+    - name: Install lib
       run: |
-        echo 'deb https://cloud.r-project.org/bin/linux/ubuntu bionic-cran35/' | sudo tee -a /etc/apt/sources.list
-        curl -sL "https://keyserver.ubuntu.com/pks/lookup?op=get&search=0xE298A3A825C0D65DFD57CBB651716619E084DAB9" | sudo apt-key add
-        sudo apt-get update
-        sudo apt-get install -y r-base r-base-dev libcurl4-openssl-dev
+        sudo apt-get install -y libcurl4-openssl-dev
     - name: install R packages
       run: |
         sudo Rscript -e "install.packages(c('curl', 'xml2', 'httr', 'devtools', 'testthat', 'knitr', 'rmarkdown', 'roxygen2', 'e1071', 'survival'), repos='https://cloud.r-project.org/')"
@@ -139,12 +139,12 @@ jobs:
     - uses: actions/setup-ruby@v1
       with:
         ruby-version: '2.7'
-    - name: Install R
+    - uses: r-lib/actions/setup-r@v1
+      with:
+        r-version: '3.6.2'
+    - name: Install lib and pandoc
       run: |
-        echo 'deb https://cloud.r-project.org/bin/linux/ubuntu bionic-cran35/' | sudo tee -a /etc/apt/sources.list
-        curl -sL "https://keyserver.ubuntu.com/pks/lookup?op=get&search=0xE298A3A825C0D65DFD57CBB651716619E084DAB9" | sudo apt-key add
-        sudo apt-get update
-        sudo apt-get install -y r-base r-base-dev libcurl4-openssl-dev pandoc
+        sudo apt-get install -y libcurl4-openssl-dev pandoc
     - name: Install packages
       run: |
         pip install sphinx mkdocs numpy

R/pkg/R/DataFrame.R

@@ -271,7 +271,7 @@ setMethod("show", "SparkDataFrame",
                 paste(l, collapse = ":")
               })
               s <- paste(cols, collapse = ", ")
-              cat(paste(class(object), "[", s, "]\n", sep = ""))
+              cat(paste0(class(object), "[", s, "]\n"))
             }
           })
 
@@ -2755,10 +2755,10 @@ setMethod("merge",
               colY <- joinY[[i]]
 
               if (colX %in% by) {
-                colX <- paste(colX, suffixes[1], sep = "")
+                colX <- paste0(colX, suffixes[1])
               }
               if (colY %in% by) {
-                colY <- paste(colY, suffixes[2], sep = "")
+                colY <- paste0(colY, suffixes[2])
               }
 
               colX <- getColumn(xsel, colX)
@@ -2773,7 +2773,7 @@ setMethod("merge",
 
             # sorts the result by 'by' columns if sort = TRUE
             if (sort && length(by) > 0) {
-              colNameWithSuffix <- paste(by, suffixes[2], sep = "")
+              colNameWithSuffix <- paste0(by, suffixes[2])
               joinRes <- do.call("arrange", c(joinRes, colNameWithSuffix, decreasing = FALSE))
             }
 
@@ -2796,7 +2796,7 @@ genAliasesForIntersectedCols <- function(x, intersectedColNames, suffix) {
   cols <- lapply(allColNames, function(colName) {
     col <- getColumn(x, colName)
     if (colName %in% intersectedColNames) {
-      newJoin <- paste(colName, suffix, sep = "")
+      newJoin <- paste0(colName, suffix)
       if (newJoin %in% allColNames) {
         stop("The following column name: ", newJoin, " occurs more than once in the 'DataFrame'.",
           "Please use different suffixes for the intersected columns.")

R/pkg/R/RDD.R

@@ -69,7 +69,7 @@ setMethod("initialize", "RDD", function(.Object, jrdd, serializedMode,
 
 setMethod("showRDD", "RDD",
           function(object) {
-              cat(paste(callJMethod(getJRDD(object), "toString"), "\n", sep = ""))
+              cat(paste0(callJMethod(getJRDD(object), "toString"), "\n"))
           })
 
 setMethod("initialize", "PipelinedRDD", function(.Object, prev, func, jrdd_val) {

R/pkg/R/mllib_classification.R

@@ -338,7 +338,7 @@ setMethod("spark.logit", signature(data = "SparkDataFrame", formula = "formula")
               if (!is.null(lowerBoundsOnCoefficients) && (row != nrow(upperBoundsOnCoefficients)
                 || col != ncol(upperBoundsOnCoefficients))) {
                 stop(paste0("dimension of upperBoundsOnCoefficients ",
-                           "is not the same as lowerBoundsOnCoefficients", sep = ""))
+                            "is not the same as lowerBoundsOnCoefficients"))
               }
 
               if (is.null(lowerBoundsOnCoefficients)) {

R/pkg/R/schema.R

@@ -99,10 +99,9 @@ print.structType <- function(x, ...) {
   cat("StructType\n",
       sapply(x$fields(),
              function(field) {
-               paste("|-", "name = \"", field$name(),
-                     "\", type = \"", field$dataType.toString(),
-                     "\", nullable = ", field$nullable(), "\n",
-                     sep = "")
+               paste0("|-", "name = \"", field$name(),
+                      "\", type = \"", field$dataType.toString(),
+                      "\", nullable = ", field$nullable(), "\n")
              }),
       sep = "")
 }

R/pkg/R/sparkR.R

@@ -244,7 +244,7 @@ sparkR.sparkContext <- function(
     uriSep <- "////"
   }
   localJarPaths <- lapply(jars,
-                          function(j) { utils::URLencode(paste("file:", uriSep, j, sep = "")) })
+                          function(j) { utils::URLencode(paste0("file:", uriSep, j)) })
 
   # Set the start time to identify jobjs
   # Seconds resolution is good enough for this purpose, so use ints

R/pkg/R/types.R

@@ -94,27 +94,22 @@ checkSchemaInArrow <- function(schema) {
   }
 
   # Both cases below produce a corrupt value for unknown reason. It needs to be investigated.
-  if (any(sapply(schema$fields(), function(x) x$dataType.toString() == "FloatType"))) {
+  field_strings <- sapply(schema$fields(), function(x) x$dataType.toString())
+  if (any(field_strings == "FloatType")) {
     stop("Arrow optimization in R does not support float type yet.")
   }
-  if (any(sapply(schema$fields(), function(x) x$dataType.toString() == "BinaryType"))) {
+  if (any(field_strings == "BinaryType")) {
     stop("Arrow optimization in R does not support binary type yet.")
   }
-  if (any(sapply(schema$fields(),
-                 function(x) startsWith(x$dataType.toString(),
-                 "ArrayType")))) {
+  if (any(startsWith(field_strings, "ArrayType"))) {
     stop("Arrow optimization in R does not support array type yet.")
   }
 
   # Arrow optimization in Spark does not yet support both cases below.
-  if (any(sapply(schema$fields(),
-                 function(x) startsWith(x$dataType.toString(),
-                 "StructType")))) {
+  if (any(startsWith(field_strings, "StructType"))) {
     stop("Arrow optimization in R does not support nested struct type yet.")
   }
-  if (any(sapply(schema$fields(),
-                 function(x) startsWith(x$dataType.toString(),
-                 "MapType")))) {
+  if (any(startsWith(field_strings, "MapType"))) {
     stop("Arrow optimization in R does not support map type yet.")
   }
 }

R/pkg/R/utils.R

@@ -137,7 +137,7 @@ hashCode <- function(key) {
       as.integer(hashC)
     }
   } else {
-    warning(paste("Could not hash object, returning 0", sep = ""))
+    warning("Could not hash object, returning 0")
     as.integer(0)
   }
 }

R/pkg/tests/fulltests/test_sparkSQL.R

@@ -2593,8 +2593,8 @@ test_that("join(), crossJoin() and merge() on a DataFrame", {
   writeLines(mockLines3, jsonPath3)
   df3 <- read.json(jsonPath3)
   expect_error(merge(df, df3),
-               paste("The following column name: name_y occurs more than once in the 'DataFrame'.",
-                     "Please use different suffixes for the intersected columns.", sep = ""))
+               paste0("The following column name: name_y occurs more than once in the 'DataFrame'.",
+                      "Please use different suffixes for the intersected columns."))
 
   unlink(jsonPath2)
   unlink(jsonPath3)
@@ -2637,20 +2637,20 @@ test_that("toJSON() on DataFrame", {
 
 test_that("showDF()", {
   df <- read.json(jsonPath)
-  expected <- paste("+----+-------+\n",
-                    "| age|   name|\n",
-                    "+----+-------+\n",
-                    "|null|Michael|\n",
-                    "|  30|   Andy|\n",
-                    "|  19| Justin|\n",
-                    "+----+-------+\n", sep = "")
-  expected2 <- paste("+---+----+\n",
-                     "|age|name|\n",
-                     "+---+----+\n",
-                     "|nul| Mic|\n",
-                     "| 30| And|\n",
-                     "| 19| Jus|\n",
-                     "+---+----+\n", sep = "")
+  expected <- paste("+----+-------+",
+                    "| age|   name|",
+                    "+----+-------+",
+                    "|null|Michael|",
+                    "|  30|   Andy|",
+                    "|  19| Justin|",
+                    "+----+-------+\n", sep = "\n")
+  expected2 <- paste("+---+----+",
+                     "|age|name|",
+                     "+---+----+",
+                     "|nul| Mic|",
+                     "| 30| And|",
+                     "| 19| Jus|",
+                     "+---+----+\n", sep = "\n")
   expect_output(showDF(df), expected)
   expect_output(showDF(df, truncate = 3), expected2)
 })

dev/deps/spark-deps-hadoop-2.7-hive-1.2

@@ -160,9 +160,9 @@ objenesis/2.5.1//objenesis-2.5.1.jar
 okhttp/3.12.6//okhttp-3.12.6.jar
 okio/1.15.0//okio-1.15.0.jar
 opencsv/2.3//opencsv-2.3.jar
-orc-core/1.5.9/nohive/orc-core-1.5.9-nohive.jar
-orc-mapreduce/1.5.9/nohive/orc-mapreduce-1.5.9-nohive.jar
-orc-shims/1.5.9//orc-shims-1.5.9.jar
+orc-core/1.5.10/nohive/orc-core-1.5.10-nohive.jar
+orc-mapreduce/1.5.10/nohive/orc-mapreduce-1.5.10-nohive.jar
+orc-shims/1.5.10//orc-shims-1.5.10.jar
 oro/2.0.8//oro-2.0.8.jar
 osgi-resource-locator/1.0.3//osgi-resource-locator-1.0.3.jar
 paranamer/2.8//paranamer-2.8.jar