Runes, a bi-directional code-point iterator/iterable.

sdk/lib/core/string.dart

 // Copyright (c) 2012, the Dart project authors.  Please see the AUTHORS file
 // for details. All rights reserved. Use of this source code is governed by a
 // BSD-style license that can be found in the LICENSE file.
 
 part of dart.core;
 
 /**
  * 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
@@ skipping 171 matching lines @@
    * where all characters  are made lower case. Returns [:this:] otherwise.
    */
   String toLowerCase();
 
   /**
    * If this string is not already all uper case, returns a new string
    * where all characters are made upper case. Returns [:this:] otherwise.
    */
   String toUpperCase();
 }
+
+class Runes implements Iterable<int> {
+  String _string;
+  Runes(this._string);
+  RuneIterator get iterator => new RuneIterator(_string);
+}
+
+/** [Iterator] for reading Unicode code points out of a Dart string. */
+class RuneIterator implements BiDirectionalIterator<int> {
+  /** String being iterated. */
+  final String _string;
+  /** Position before the current code point. */
+  int _position;
+  /** Position after the current code point. */
+  int _nextPosition;
+  /**
+   * Current code point.
+   *
+   * If the iterator has hit either end, the [_currentCodePoint] is null
+   * and [: _position == _nextPosition :].
+   */
+  int _currentCodePoint;
+
+  /** Create an iterator positioned at the beginning of the string. */
+  RuneIterator(String string)
+      : _string = string, _position = 0, _nextPosition = 0;
+
+  /**
+   * Create an iterator positioned before the [start]th code unit of the string.
+   *
+   * A [moveNext] will make the following code point the current value, and a
+   * [movePrevious] will make the preceding code pount the current value.
+   *
+   * If the [start] position is in the middle of a surrogate pair, then the
+   * first result in either direction will be an unmatched surrogate.
+   */
+  RuneIterator.at(String string, int start)
+      : _string = string, _position = start, _nextPosition = start {
+    if (start < 0 || start > string.length) {
+      throw new RangeError.range(start, 0, string.length);
+    }
+  }
+
+  int get current => _currentCodePoint;
+
+  bool moveNext() {

[erikcorry, 2013/01/30 13:26:55]

This one is factored into two functions, whereas the exactly analogous
movePrevious is monolithic.  They should be the same.

[Lasse Reichstein Nielsen, 2013/01/30 14:03:37]

ACK. I was using _readCharForward in the .at constructor too, but decided
against that.

+    _position = _nextPosition;
+    if (_position == _string.length) {
+      _currentCodePoint = null;
+      return false;
+    }
+    _readCharForward();
+    return true;
+  }
+
+  // Decodes code units at _position, updates _currentCodePoint, _nextPosition.
+  void _readCharForward() {
+    int codeUnit = _string.charCodeAt(_position);
+    int nextPosition = _position + 1;
+    if ((codeUnit & 0xFC00) == 0xD800 && nextPosition < _string.length) {
+      int nextCodeUnit = _string.charCodeAt(nextPosition);
+      if ((nextCodeUnit & 0xFC00) == 0xDC00) {
+        _nextPosition = nextPosition + 1;
+        _currentCodePoint =
+            0x10000 + ((nextCodeUnit & 0x3FF) << 10) | (codeUnit & 0x3FF);

[Lasse Reichstein Nielsen, 2013/01/30 14:03:37]

Good catch, these two are swapped (copy-n-paste bug from movePrevious).

+        return;
+      }
+    }
+    _nextPosition = nextPosition;
+    _currentCodePoint = codeUnit;
+  }
+
+  bool movePrevious() {
+    if (_position == 0) {
+      _currentCodePoint = null;
+      return false;
+    }
+    int position = _position - 1;
+    _nextPosition = _position;
+    int codeUnit = _string.charCodeAt(position);
+    if ((codeUnit & 0xFC00) == 0xDC00 && position > 0) {
+      int prevCodeUnit = _string.charCodeAt(position - 1);
+      if ((prevCodeUnit & 0xFC00) == 0xD800) {
+        _position = position - 1;
+        _currentCodePoint =
+            0x10000 + ((prevCodeUnit & 0x3FF) << 10) | (codeUnit & 0x3FF);
+        return true;
+      }
+    }
+    _position = position;
+    _currentCodePoint = codeUnit;
+    return true;
+  }
+}