Merge pull request #194 from atorus-research/189_91_max_var_length

add length check <=200 bytes

NAMESPACE

@@ -23,6 +23,7 @@ importFrom(cli,cli_alert_success)
 importFrom(cli,cli_div)
 importFrom(cli,cli_h2)
 importFrom(cli,cli_text)
+importFrom(dplyr,across)
 importFrom(dplyr,arrange)
 importFrom(dplyr,bind_cols)
 importFrom(dplyr,case_when)
@@ -61,6 +62,7 @@ importFrom(stringr,str_replace)
 importFrom(stringr,str_replace_all)
 importFrom(tidyselect,all_of)
 importFrom(tidyselect,any_of)
+importFrom(tidyselect,where)
 importFrom(tm,stemDocument)
 importFrom(utils,capture.output)
 importFrom(utils,packageVersion)

NEWS.md

@@ -5,6 +5,8 @@
 * `xportr_write()` now accepts `metadata` argument which can be used to set the dataset label to stay consistent with the other `xportr_*` functions. It is noteworthy that the dataset label set using the `xportr_df_label()` function will be retained during the `xportr_write()`.
 * Exporting a new dataset `dataset_spec` that contains the Dataset Specification for ADSL. (#179)
 
+* Added a check for character variable lengths up to 200 bytes in `xpt_validate()`(#91, #189).
+
 ## Deprecation and Breaking Changes
 
 * The `label` argument from the `xportr_write()` function is deprecated in favor of the `metadata` argument. (#179)

R/utils-xportr.R

@@ -302,6 +302,18 @@ xpt_validate <- function(data) {
       glue("{fmt_fmts(names(chk_formats))} must have a valid format.")
     )
   }
+
+  # 4.0 max length of Character variables <= 200 bytes
+  max_nchar <- data %>%
+    summarize(across(where(is.character), ~ max(nchar(., type = "bytes"))))
+  nchar_gt_200 <- max_nchar[which(max_nchar > 200)]
+  if (length(nchar_gt_200) > 0) {
+    err_cnd <- c(
+      err_cnd,
+      glue("Length of {names(nchar_gt_200)} must be 200 bytes or less.")
+    )
+  }
+
   return(err_cnd)
 }
 

R/xportr-package.R

@@ -95,11 +95,11 @@
 #' @import rlang haven
 #' @importFrom dplyr left_join bind_cols filter select rename rename_with n
 #'   everything arrange group_by summarize mutate ungroup case_when distinct
-#'   tribble if_else
+#'   tribble if_else across
 #' @importFrom glue glue glue_collapse
 #' @importFrom cli cli_alert_info cli_h2 cli_alert_success cli_div cli_text
 #'   cli_alert_danger
-#' @importFrom tidyselect all_of any_of
+#' @importFrom tidyselect all_of any_of where
 #' @importFrom utils capture.output str tail packageVersion
 #' @importFrom stringr str_detect str_extract str_replace str_replace_all
 #' @importFrom readr parse_number

tests/testthat/test-utils-xportr.R

@@ -111,3 +111,19 @@ test_that("xpt_validate: Get error message when the label contains non-ASCII, sy
     "Label 'A=fooçbar' cannot contain any non-ASCII, symbol or special characters."
   )
 })
+
+test_that("xpt_validate: Get error message when the length of a character variable is > 200 bytes ", {
+  df <- data.frame(A = paste(rep("A", 201), collapse = ""))
+  expect_equal(
+    xpt_validate(df),
+    "Length of A must be 200 bytes or less."
+  )
+})
+
+test_that("xpt_validate: Get error message when the length of a non-ASCII character variable is > 200 bytes", {
+  df <- data.frame(A = paste(rep("一", 67), collapse = ""))
+  expect_equal(
+    xpt_validate(df),
+    "Length of A must be 200 bytes or less."
+  )
+})