reimplement the url_check() function

R/readepi_helpers.R

@@ -133,36 +133,17 @@ fingertips_get_args <- function(args_list =
 #'
 #' @param base_url the URL to the HIS of interest
 #'
+#' @returns throws an error if the domain of the provided URL is not valid,
+#'    (invisibly) TRUE
+#'
 #' @keywords internal
 #'
 url_check <- function(base_url) {
   checkmate::assert_character(base_url, any.missing = FALSE, len = 1L,
                               null.ok = FALSE)
-  if (grepl("^https?://", base_url)) {
-    base_url   <- gsub("^https?://", "", base_url)
-  }
-
-  # split the URL parts
-  url_parts    <- unlist(strsplit(base_url, "/", fixed = TRUE))
-  # without the protocol, lets look for the sub-domain, second-level domain
-  # and the top-level domain
-  domain_structure_is_correct <- url_check_domain_structure(url_parts[[1L]])
-  stopifnot("Incorrect domain name in provided URL!" =
-              domain_structure_is_correct)
-  return(domain_structure_is_correct)
-}
-
-#' Check whether the domain structure of the URL is correct
-#'
-#' @param url_parts a character string with the domain from the URL
-#'
-#' @keywords internal
-url_check_domain_structure <- function(url_parts) {
-  domain_structure_is_correct   <- TRUE
-  url_domains                   <- unlist(strsplit(url_parts, ".",
-                                                   fixed = TRUE))
-  if (length(url_domains) < 2L) {
-    domain_structure_is_correct <- FALSE
-  }
-  domain_structure_is_correct
+  regex  <- "^(https?://)?(www\\.)?([a-z0-9]([a-z0-9]|(\\-[a-z0-9]))*\\.)+[a-z]+$" # nolint: line_length_linter
+  domain <- strsplit(gsub("^(https?://)?(www\\.)?", "", base_url),
+                     "/")[[c(1L, 1L)]]
+  stopifnot("Incorrect domain name in provided URL!" = grepl(regex, domain))
+  return(invisible(TRUE))
 }

tests/testthat/test-readepi_helpers.R

@@ -207,44 +207,39 @@ test_that("url_check works as expected", {
 })
 
 test_that("url_check works as expected", {
-  res <- url_check(base_url = "http://www.karim.sn")
+  res <- url_check(base_url = "stackoverflow.com")
   expect_true(res)
 })
 
 test_that("url_check works as expected", {
-  res <- url_check(base_url = "www.karim.sn")
+  res <- url_check(base_url = "stackoverflow.com/questions/ask")
   expect_true(res)
 })
 
 test_that("url_check works as expected", {
-  res <- url_check(base_url = "karim.sn")
+  res <- url_check(base_url = "https://stackoverflow.com/questions/ask")
   expect_true(res)
 })
 
-test_that("fingertips_get_args fails as expected", {
+test_that("url_check works as expected", {
+  res <- url_check(base_url = "http://www.amazon.com/Computers-Internet-Books/b/ref=bhp_bb0309A_comint2?ie=UTF8&node=5&pf_rd_m=ATVPDKIKX0DER&pf_rd_s=browse&pf_rd_r=0AH7GM29WF81Q72VPFDH&pf_rd_t=101&pf_rd_p=1273387142&pf_rd_i=283155") # nolint: line_length_linter
+  expect_true(res)
+})
+
+test_that("url_check fails as expected", {
   expect_error(
-    url_check("ftp://www.karim.sn"),
-    regexp = cat("URL must start with 'http://' or 'https://'.")
+    url_check("google"),
+    regexp = cat("URL must be in the form of 'https://test.com' or
+                 'https://www.test.com' or 'test.com'.")
   )
-
   expect_error(
-    url_check("this_should_not_work"),
+    url_check("http://www"),
+    regexp = cat("URL must be in the form of 'https://test.com' or
+                 'https://www.test.com' or 'test.com'.")
+  )
+  expect_error(
+    url_check("http://www..des"),
     regexp = cat("URL must be in the form of 'https://test.com' or
                  'https://www.test.com' or 'test.com'.")
   )
-})
-
-test_that("url_check_domain_structure works as expected", {
-  res <- url_check_domain_structure("www.karim.sn")
-  expect_true(res)
-})
-
-test_that("url_check_domain_structure works as expected", {
-  res <- url_check_domain_structure("karim.sn")
-  expect_true(res)
-})
-
-test_that("url_check_domain_structure works as expected", {
-  res <- url_check_domain_structure("this_should_not_work")
-  expect_false(res)
 })