numfmt: stop a multi-byte locale decimal separator from panicking

src/uu/numfmt/src/format.rs

@@ -57,7 +57,9 @@ fn find_valid_number_with_suffix(s: &str, unit: Unit) -> Option<&str> {
     let accepts_suffix = unit != Unit::None;
     let accepts_i = [Unit::Auto, Unit::Iec(true)].contains(&unit);
 
-    let mut characters = s.chars().skip(numeric_part.len());
+    // Slice by byte length, not `.chars().skip()`: the numeric part may
+    // contain a multi-byte decimal separator (e.g. Arabic ٫).
+    let mut characters = s[numeric_part.len()..].chars();
     let potential_suffix = characters.next();
     let potential_i = characters.next();
 
@@ -66,14 +68,11 @@ fn find_valid_number_with_suffix(s: &str, unit: Unit) -> Option<&str> {
     }
 
     match (potential_suffix, potential_i) {
-        (Some(suffix), None) if RawSuffix::try_from(&suffix).is_ok() => {
-            Some(&s[..=numeric_part.len()])
-        }
         (Some(suffix), Some('i')) if accepts_i && RawSuffix::try_from(&suffix).is_ok() => {
-            Some(&s[..numeric_part.len() + 2])
+            Some(&s[..numeric_part.len() + suffix.len_utf8() + 'i'.len_utf8()])
         }
-        (Some(suffix), Some(_)) if RawSuffix::try_from(&suffix).is_ok() => {
-            Some(&s[..=numeric_part.len()])
+        (Some(suffix), _) if RawSuffix::try_from(&suffix).is_ok() => {
+            Some(&s[..numeric_part.len() + suffix.len_utf8()])
         }
         _ => Some(numeric_part),
     }

tests/by-util/test_numfmt.rs

@@ -1614,6 +1614,28 @@ fn test_locale_fr_rejects_period() {
         .stderr_contains("invalid");
 }
 
+#[test]
+#[cfg_attr(wasi_runner, ignore = "WASI: locale env vars not propagated")]
+fn test_locale_multibyte_separator_does_not_panic_on_invalid_suffix() {
+    // Regression test for #13937: under a locale whose decimal separator is
+    // multi-byte (Arabic ٫, 2 bytes), an invalid multi-byte suffix character
+    // right after the numeric part used to abort the process instead of
+    // being cleanly rejected, since the suffix search skipped by the
+    // separator's *byte* length as though it were a *character* count.
+    for arg in ["1٫€K", "1٫€Kx"] {
+        new_ucmd!()
+            .env("LC_ALL", "ar_SA.UTF-8")
+            .args(&["--from=si", arg])
+            .fails()
+            .stderr_contains("invalid suffix");
+    }
+    new_ucmd!()
+        .env("LC_ALL", "ar_SA.UTF-8")
+        .args(&["--from=auto", "1٫€Ki"])
+        .fails()
+        .stderr_contains("invalid suffix");
+}
+
 #[test]
 fn test_locale_c_uses_period() {
     // C locale should still use '.' as usual