crates/clawhdf5-migrate/src/validate.rs

@@ -144,7 +144,8 @@ fn truncate(s: &str) -> String {
     if s.len() <= 40 {
         s.to_string()
     } else {
-        format!("{}…", &s[..40])
+        let cut = s.char_indices().nth(40).map(|(i, _)| i).unwrap_or(s.len());
+        format!("{}…", &s[..cut])
     }
 }
 
@@ -161,3 +162,31 @@ fn sample_indices(n: usize, full: bool) -> Vec<usize> {
     idx.dedup();
     idx
 }
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn truncate_short_string_unchanged() {
+        assert_eq!(truncate("hello"), "hello");
+    }
+
+    /// A multi-byte character straddling byte offset 40 must not panic a
+    /// byte-index slice — this is arbitrary UTF-8 chunk text from an
+    /// untrusted source database, not test-only input.
+    #[test]
+    fn truncate_multibyte_char_at_boundary_does_not_panic() {
+        // 39 ASCII bytes then a 4-byte emoji straddling the byte-40 cut point.
+        let s = format!("{}{}", "a".repeat(39), "😀".repeat(5));
+        let result = truncate(&s);
+        assert!(result.ends_with('…'));
+        assert!(result.chars().count() < s.chars().count());
+    }
+
+    #[test]
+    fn truncate_exactly_at_limit_unchanged() {
+        let s = "a".repeat(40);
+        assert_eq!(truncate(&s), s);
+    }
+}