String encoding utility methods and tests for Unicode, UTF-8, -16 and -32.

utils/string_encoding/Unicode.dart

Index: utils/string_encoding/Unicode.dart
diff --git a/utils/string_encoding/Unicode.dart b/utils/string_encoding/Unicode.dart
new file mode 100644
index 0000000000000000000000000000000000000000..8f107595e8a59ab49eb5c20f95e0c986bbdb21a7
--- /dev/null
+++ b/utils/string_encoding/Unicode.dart
@@ -0,0 +1,31 @@
+// Copyright (c) 2011, the Dart project authors.  Please see the AUTHORS file

[jat, 2012/01/31 15:19:22]

Copyright date.

[dcarlson, 2012/01/31 22:11:38]

Done.

+// 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.
+
+#library("Unicode");
+#import("UnicodeCore.dart");
+
+/**
+ * Provide Unicode codepoints for a given string.
+ */
+List<int> stringToCodepoints(String str) {
+  List<int> codepoints;
+  if (is16BitCodeUnit()) {

[ahe, 2012/01/31 14:46:53]

I think you're working around bug in frog or dartc here. I suggest that you add
a TODO and file a bug to track this.

[dcarlson, 2012/01/31 15:07:34]

Done.

[Dan Rice, 2012/01/31 15:59:55]

+1

+    codepoints = utf16CodeUnitsToCodepoints(str.charCodes());
+  } else {
+    codepoints = str.charCodes();
+  }
+  return codepoints;
+}
+
+/**
+ * Generate a string for the provided Unicode codepoints.
+ */
+String codepointsToString(List<int> codepoints) {
+  if (is16BitCodeUnit()) {
+    return (new String.fromCharCodes(

[Dan Rice, 2012/01/31 15:59:55]

No need for parens around return value

[dcarlson, 2012/01/31 22:11:38]

Done.

+        codepointsToUtf16CodeUnits(codepoints)));
+  } else {
+    return (new String.fromCharCodes(codepoints));

[Dan Rice, 2012/01/31 15:59:55]

Ditto

[dcarlson, 2012/01/31 22:11:38]

Done.

+  }
+}