Add some support for the code-point code-unit distinction.

sdk/lib/core/string.dart

Index: sdk/lib/core/string.dart
diff --git a/sdk/lib/core/string.dart b/sdk/lib/core/string.dart
index ad4aefee7e1fca8b4e591dd6fed3f8de54c22e9d..8486ce8cf2de7ac21d3207b08fe1944758434b76 100644
--- a/sdk/lib/core/string.dart
+++ b/sdk/lib/core/string.dart
@@ -4,36 +4,55 @@
 
 /**
  * The String class represents character strings. Strings are
- * immutable. A string is represented by a list of 32-bit Unicode
- * scalar character codes accessible through the [charCodeAt] or the
- * [charCodes] method.
+ * immutable. A string is represented by a list of 16-bit UTF-16
+ * code units accessible through the [codeUnitAt] or the [codeUnits]
+ * methods.  The corresponding Unicode code points are available with
+ * [charCodeAt] or the [charCodes] method.
  */
 interface String
     extends Comparable, Pattern, Sequence<String>
     default _StringImpl {
   /**
-   * Allocates a new String for the specified [charCodes].
+   * Allocates a new String for the specified 21 bit Unicode [codePoints].
    */
-  String.fromCharCodes(List<int> charCodes);
+  String.fromCharCodes(List<int> codePoints);
 
   /**
-   * Gets the character (as [String]) at the given [index].
+   * Allocates a new String for the specified 16 bit UTF-16 [codeUnits].
+   */
+  String.fromCodeUnits(List<int> codeUnits);
+
+  /**
+   * Gets the Unicode character (as [String]) at the given [index].  This
+   * routine can return a single combining character (accent) that would
+   * normally be displayed together with the character it is modifying.
+   * If the index corresponds to the first of two UTF-16 surrogate pair

[floitsch, 2012/11/08 15:28:21]

Update comment.

[erikcorry, 2012/11/15 13:28:25]

Done.

+   * code units then it will return a string containing the Unicode
+   * character corresponding to the pair.
    */
   String operator [](int index);
 
   /**
-   * Gets the scalar character code at the given [index].
+   * Gets the 21 bit Unicode code point at the given [index].  Surrogate
+   * pairs are handled as in [operator []].

[floitsch, 2012/11/08 15:28:21]

Update comment.

[erikcorry, 2012/11/15 13:28:25]

Done.

    */
   int charCodeAt(int index);
 
   /**
-   * The length of the string.
+   * Gets the 16 bit UTF-16 code unit at the given index.

[floitsch, 2012/11/08 15:28:21]

Update comment (now same as [operator []]).

[erikcorry, 2012/11/15 13:28:25]

Done.

[erikcorry, 2012/11/15 13:28:25]

Done.

+   */
+  int codeUnitAt(int index);
+
+
+  /**
+   * The length of the string, measured in UTF-16 code units.
    */
   int get length;
 
   /**
    * Returns whether the two strings are equal. This method compares
-   * each individual scalar character codes of the strings.
+   * each individual UTF-16 code unit.  No Unicode normalization is
+   * performed (accent composition/decomposition).
    */
   bool operator ==(String other);
 
@@ -110,16 +129,23 @@ interface String
   List<String> split(Pattern pattern);
 
   /**
-   * Returns a list of the characters of this string.
+   * Returns a list of the characters of this string.  No string normalization
+   * is performed so unprecomposed combining characters (accents) may be found
+   * in the list.
    */
   List<String> splitChars();
 
   /**
-   * Returns a list of the scalar character codes of this string.
+   * Returns a list of the 21 bit Unicode code points of this string.
    */
   List<int> get charCodes;
 
   /**
+   * Returns a list of the 16 bit UTF-16 code units of this string.
+   */
+  List<int> get codeUnits;
+
+  /**
    * If this string is not already all lower case, returns a new string
    * where all characters  are made lower case. Returns [:this:] otherwise.
    */
@@ -134,10 +160,14 @@ interface String
 
 class _StringImpl {
   /**
-   * Factory implementation of String.fromCharCodes:
-   * Allocates a new String for the specified [charCodes].
+   * Factory implementation of String.fromCharCodes.
+   */
+  external factory String.fromCharCodes(List<int> codePoints);
+
+  /**
+   * Factory implementation of String.fromCodeUnits.
    */
-  external factory String.fromCharCodes(List<int> charCodes);
+  external factory String.fromCodeUnits(List<int> codeUnits);
 
   /**
    * Joins all the given strings to create a new string.