proof: drop U+FE0F from FORBIDDENWORD and NOSUGGEST flags too

Review follow-up: the directives that name one flag read the same emoji
form, so they now skip the variation selector like PFX/SFX and stem flags.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
dmim2502-commits
2026-10-21 16:21:24 -05:00
co-authored by Claude Opus 5.5
parent fd91a78e71
commit 40ae6ac08c
+10 -1
View File
@@ -295,7 +295,7 @@ fn parse_aff(aff: &str) -> Result<Rules, String> {
}
}
directive @ ("FORBIDDENWORD" | "NOSUGGEST") => {
let mut it = at(1).chars();
let mut it = at(1).chars().filter(|&c| c != EMOJI_SELECTOR);
match (it.next(), it.next()) {
(Some(c), None) if !c.is_whitespace() => {
if directive == "FORBIDDENWORD" {
@@ -1098,6 +1098,15 @@ pub(crate) mod tests {
assert!(!d.flag_chars.contains(&EMOJI_SELECTOR), "the selector is not a flag");
}
#[test]
fn emoji_forbiddenword_and_nosuggest_flags_load() {
// The same selector after the flag of the directives that name one flag.
let aff = "SET UTF-8\nFLAG UTF-8\nFORBIDDENWORD \u{260e}\u{fe0f}\nNOSUGGEST \u{1f6ab}\u{fe0f}\n";
let d = AffixDict::from_hunspell(aff, "3\nbanco\nbanko/\u{260e}\u{fe0f}\nbancu/\u{1f6ab}\u{fe0f}\n", &[]).unwrap();
assert!(d.contains("banco") && d.contains("bancu"));
assert!(!d.contains("banko"), "a stem with the FORBIDDENWORD flag is not a word");
}
#[test]
fn more_than_64_distinct_flags_load() {
// VERO pt_BR uses 106 distinct flags (FLAG UTF-8). Build one with every basic Latin