From 416e71af4d26e67afb715ea1d625341cdea4873d Mon Sep 17 00:00:00 2001
From: "Oscar D. Lara Yejas" <odlaraye@oscars-mbp.attlocal.net>
Date: Thu, 10 Mar 2016 17:10:23 -0800
Subject: [PATCH] [SPARK-13327][SPARKR] Added parameter validations for
colnames<-
Author: Oscar D. Lara Yejas <odlaraye@oscars-mbp.attlocal.net>
Author: Oscar D. Lara Yejas <odlaraye@oscars-mbp.usca.ibm.com>
Closes #11220 from olarayej/SPARK-13312-3.
---
R/pkg/R/DataFrame.R | 22 +++++++++++++++++++++-
R/pkg/inst/tests/testthat/test_sparkSQL.R | 11 +++++++++++
2 files changed, 32 insertions(+), 1 deletion(-)
diff --git a/R/pkg/R/DataFrame.R b/R/pkg/R/DataFrame.R
index 3b7b8250b9..50655e9382 100644
--- a/R/pkg/R/DataFrame.R
+++ b/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)
})
diff --git a/R/pkg/inst/tests/testthat/test_sparkSQL.R b/R/pkg/inst/tests/testthat/test_sparkSQL.R
index 236bae6bde..cad5766812 100644
--- a/R/pkg/inst/tests/testthat/test_sparkSQL.R
+++ b/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"))
--
GitLab