add requires_utf8 argument to tests

NEWS.md

@@ -24,6 +24,8 @@
 
 3. Vignettes are now built using `litedown` instead of `knitr`, [#6394](https://github.com/Rdatatable/data.table/issues/6394). Thanks @jangorecki for the suggestion and @ben-schwen and @aitap for the implementation.
 
+4. `test()` gains new argument `requires_utf8` to skip tests when UTF-8 support is not available, [#7336](https://github.com/Rdatatable/data.table/issues/7336). Thanks @MichaelChirico for the suggestion and @ben-schwen for the implementation.
+
 ### BUG FIXES
 
 1. `fread()` with `skip=0` and `(header=TRUE|FALSE)` no longer skips the first row when it has fewer fields than subsequent rows, [#7463](https://github.com/Rdatatable/data.table/issues/7463). Thanks @emayerhofer for the report and @ben-schwen for the fix.

R/test.data.table.R

@@ -370,10 +370,12 @@ gc_mem = function() {
   # nocov end
 }
 
+utf8_check = function(test_str) identical(test_str, enc2native(test_str))
+
 test = function(num, x, y=TRUE,
                 error=NULL, warning=NULL, message=NULL, output=NULL, notOutput=NULL, ignore.warning=NULL,
                 options=NULL, env=NULL,
-                context=NULL) {
+                context=NULL, requires_utf8=FALSE) {
   if (!is.null(env)) {
     old = Sys.getenv(names(env), names=TRUE, unset=NA)
     to_unset = !lengths(env)
@@ -387,6 +389,20 @@ test = function(num, x, y=TRUE,
       Sys.unsetenv(names(old)[!is_preset])
     }, add=TRUE)
   }
+  # Check UTF-8 requirement
+  if (!isFALSE(requires_utf8)) {
+    test_str = if (isTRUE(requires_utf8)) "\u00F1\u00FC\u3093" else requires_utf8
+    if (!utf8_check(test_str)) {
+      # nocov start
+      last_utf8_skip = get0("last_utf8_skip", parent.frame(), ifnotfound=0, inherits=TRUE)
+      if (num - last_utf8_skip >= 1) {
+        catf("Test %s skipped because required UTF-8 symbols cannot be represented in native encoding.\n", num)
+      }
+      assign("last_utf8_skip", num, parent.frame(), inherits=TRUE)
+      return(invisible(TRUE))
+      # nocov end
+    }
+  }
   # Usage:
   # i) tests that x equals y when both x and y are supplied, the most common usage
   # ii) tests that x is TRUE when y isn't supplied