[SPARK-13327][SPARKR] Added parameter validations for colnames<-

Author: Oscar D. Lara Yejas <[email protected]>
Author: Oscar D. Lara Yejas <[email protected]>

Closes #11220 from olarayej/SPARK-13312-3.

Author: Oscar D. Lara Yejas

R/pkg/R/DataFrame.R

@@ -303,8 +303,28 @@ setMethod("colnames",
 #' @rdname columns
 #' @name colnames<-
 setMethod("colnames<-",
-          signature(x = "DataFrame", value = "character"),
+          signature(x = "DataFrame"),
           function(x, value) {
+
+            # Check parameter integrity
+            if (class(value) != "character") {
+              stop("Invalid column names.")
+            }
+
+            if (length(value) != ncol(x)) {
+              stop(
+                "Column names must have the same length as the number of columns in the dataset.")
+            }
+
+            if (any(is.na(value))) {
+              stop("Column names cannot be NA.")
+            }
+
+            # Check if the column names have . in it
+            if (any(regexec(".", value, fixed=TRUE)[[1]][1] != -1)) {
+              stop("Colum names cannot contain the '.' symbol.")
+            }
+
             sdf <- callJMethod(x@sdf, "toDF", as.list(value))
             dataFrame(sdf)
           })

R/pkg/inst/tests/testthat/test_sparkSQL.R

@@ -691,6 +691,17 @@ test_that("names() colnames() set the column names", {
   colnames(df) <- c("col3", "col4")
   expect_equal(names(df)[1], "col3")
 
+  expect_error(colnames(df) <- c("sepal.length", "sepal_width"),
+               "Colum names cannot contain the '.' symbol.")
+  expect_error(colnames(df) <- c(1, 2), "Invalid column names.")
+  expect_error(colnames(df) <- c("a"),
+               "Column names must have the same length as the number of columns in the dataset.")
+  expect_error(colnames(df) <- c("1", NA), "Column names cannot be NA.")
+
+  # Note: if this test is broken, remove check for "." character on colnames<- method
+  irisDF <- suppressWarnings(createDataFrame(sqlContext, iris))
+  expect_equal(names(irisDF)[1], "Sepal_Length")
+
   # Test base::colnames base::names
   m2 <- cbind(1, 1:4)
   expect_equal(colnames(m2, do.NULL = FALSE), c("col1", "col2"))