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..bc4b53bcbd158b0af0dcb3d4674208f6df2bd17b
--- /dev/null
+++ b/utils/string_encoding/Unicode.dart
@@ -0,0 +1,37 @@
+// 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.
+
+#library("Unicode");

[Søren Gjesse, 2012/02/01 11:25:25]

I think our current naming scheme for libraries is lowercase only.

[dcarlson, 2012/02/01 22:18:46]

Done.

+#import("UnicodeCore.dart");

[Søren Gjesse, 2012/02/01 11:25:25]

Same for file names. All Dart files in e.g. corelib/src uses all lowercase and
underscores.

[dcarlson, 2012/02/01 22:18:46]

Done.

+
+/**
+ * Provide Unicode codepoints for a given string.
+ */
+List<int> stringToCodepoints(String str) {
+  List<int> codepoints;
+  // TODO is16BitCodeUnit() is used to work around a bug with frog/dartc
+  // (http://code.google.com/p/dart/issues/detail?id=1357). Consider
+  // removing after this issue is resolved.
+  if (is16BitCodeUnit()) {
+    codepoints = utf16CodeUnitsToCodepoints(str.charCodes());
+  } else {
+    codepoints = str.charCodes();
+  }
+  return codepoints;
+}
+
+/**
+ * Generate a string for the provided Unicode codepoints.
+ */
+String codepointsToString(List<int> codepoints) {
+  // TODO is16BitCodeUnit() is used to work around a bug with frog/dartc
+  // (http://code.google.com/p/dart/issues/detail?id=1357). Consider
+  // removing after this issue is resolved.
+  if (is16BitCodeUnit()) {
+    return new String.fromCharCodes(
+        codepointsToUtf16CodeUnits(codepoints));
+  } else {
+    return new String.fromCharCodes(codepoints);
+  }
+}