diff --git a/crates/proof/src/lib.rs b/crates/proof/src/lib.rs index 8d0baba5..bf2cde13 100644 --- a/crates/proof/src/lib.rs +++ b/crates/proof/src/lib.rs @@ -717,7 +717,9 @@ fn spelling_issues(text: &str, lang: impl Fn(usize) -> ProofLang, opts: &Options /// The whitespace-delimited token enclosing the word at `a..b` of `text`: its byte range, and /// whether it looks like a web or e-mail address. fn enclosing_token(text: &str, a: usize, b: usize) -> (usize, usize, bool) { - let ts = text.get(..a).and_then(|t| t.rfind(char::is_whitespace)).map(|i| i + 1).unwrap_or(0); + // The token starts after the last white-space character, whatever its width (a no-break + // space is two bytes and an ideographic space is three). + let ts = text.get(..a).and_then(|t| t.char_indices().rev().find(|(_, c)| c.is_whitespace())).map(|(i, c)| i + c.len_utf8()).unwrap_or(0); let te = text.get(b..).and_then(|t| t.find(char::is_whitespace)).map(|i| b + i).unwrap_or(text.len()); (ts, te, text.get(ts..te).is_some_and(is_address)) } @@ -1507,6 +1509,18 @@ mod tests { assert_eq!(bad.last(), Some(&"wugwug"), "{bad:?}"); } + #[test] + fn address_after_a_wide_space_is_an_internet_token() { + // A web or e-mail address after a no-break space or an ideographic space is skipped, + // as it is after a plain space. + let t = "see\u{a0}https://xyzq.example/blorp and\u{3000}www.qwirpy.example or\u{a0}zxq@mail.example wugwug"; + let bad: Vec<&str> = check_spelling(t).iter().map(|i| &t[i.start..i.end]).collect(); + assert_eq!(bad, vec!["wugwug"]); + let opts = Options { ignore_internet: false, ..Options::default() }; + let bad: Vec<&str> = check_spelling_with(t, &opts).iter().map(|i| &t[i.start..i.end]).collect(); + assert!(["xyzq", "blorp", "qwirpy", "zxq", "wugwug"].iter().all(|w| bad.contains(w)), "{bad:?}"); + } + #[test] fn spelling_scales_over_one_long_token() { // #1335: thousands of punctuation-separated words inside a single