core: Add Char::len_utf16

Missing method to pair with len_utf8.

2 files changed, 18 insertions, 0 deletions

diff --git a/src/libcore/char.rs b/src/libcore/char.rs
index 82dc2becf28..93fa614e597 100644
--- a/src/libcore/char.rs
+++ b/src/libcore/char.rs
@@ -323,6 +323,10 @@ pub trait Char {
     /// UTF-8.
     fn len_utf8(&self) -> uint;
 
+    /// Returns the amount of bytes this character would need if encoded in
+    /// UTF-16.
+    fn len_utf16(&self) -> uint;
+
     /// Encodes this character as UTF-8 into the provided byte buffer,
     /// and then returns the number of bytes written.
     ///
@@ -364,6 +368,12 @@ impl Char for char {
     fn len_utf8(&self) -> uint { len_utf8_bytes(*self) }
 
     #[inline]
+    fn len_utf16(&self) -> uint {
+        let ch = *self as u32;
+        if (ch & 0xFFFF_u32) == ch { 1 } else { 2 }
+    }
+
+    #[inline]
     fn encode_utf8<'a>(&self, dst: &'a mut [u8]) -> Option<uint> {
         // Marked #[inline] to allow llvm optimizing it away
         let code = *self as u32;
diff --git a/src/libcoretest/char.rs b/src/libcoretest/char.rs
index 2d5ca983fec..507ddf65e55 100644
--- a/src/libcoretest/char.rs
+++ b/src/libcoretest/char.rs
@@ -198,6 +198,14 @@ fn test_encode_utf16() {
 }
 
 #[test]
+fn test_len_utf16() {
+    assert!('x'.len_utf16() == 1);
+    assert!('\u00e9'.len_utf16() == 1);
+    assert!('\ua66e'.len_utf16() == 1);
+    assert!('\U0001f4a9'.len_utf16() == 2);
+}
+
+#[test]
 fn test_width() {
     assert_eq!('\x00'.width(false),Some(0));
     assert_eq!('\x00'.width(true),Some(0));