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

utils/tests/string_encoding/Utf8Tests.dart

Index: utils/tests/string_encoding/Utf8Tests.dart
diff --git a/utils/tests/string_encoding/Utf8Tests.dart b/utils/tests/string_encoding/Utf8Tests.dart
new file mode 100755
index 0000000000000000000000000000000000000000..2baeefd26b32ddfd8c859413954bebe9b4772748
--- /dev/null
+++ b/utils/tests/string_encoding/Utf8Tests.dart
@@ -0,0 +1,480 @@
+#!/usr/bin/env dart
+// Copyright (c) 2011, 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("Utf8Tests");
+#import("DUnit.dart");
+#import("../../string_encoding/Unicode.dart");
+#import("../../string_encoding/UnicodeCore.dart");
+#source("../../string_encoding/Utf8_impl.dart");
+
+void main() {
+  TestSuite suite = new TestSuite();
+  suite.registerTestClass(new Utf8Tests());
+  suite.run();
+}
+
+class Utf8Tests extends TestClass {
+  void registerTests(TestSuite suite) {
+    register("testUtf8bytesToCodepoints", testUtf8bytesToCodepoints, suite);
+    register("testUtf8BytesToString", testUtf8BytesToString, suite);
+    register("testEncodeToUtf8", testEncodeToUtf8, suite);
+  }
+
+  void testEncodeToUtf8() {
+    Expect.listEquals([
+        0x54, 0x68, 0x65, 0x20, 0x71, 0x75, 0x69, 0x63,
+        0x6b, 0x20, 0x62, 0x72, 0x6f, 0x77, 0x6e, 0x20,
+        0x66, 0x6f, 0x78, 0x20, 0x6a, 0x75, 0x6d, 0x70,
+        0x73, 0x20, 0x6f, 0x76, 0x65, 0x72, 0x20, 0x74,
+        0x68, 0x65, 0x20, 0x6c, 0x61, 0x7a, 0x79, 0x20,
+        0x64, 0x6f, 0x67, 0x2e],
+        encodeAsUtf8("The quick brown fox jumps over the lazy dog."),
+        "english to utf8");
+
+    Expect.listEquals([
+        0x51, 0x75, 0x69, 0x7a, 0x64, 0x65, 0x6c, 0x74,
+        0x61, 0x67, 0x65, 0x72, 0x6e, 0x65, 0x20, 0x73,
+        0x70, 0x69, 0x73, 0x74, 0x65, 0x20, 0x6a, 0x6f,
+        0x72, 0x64, 0x62, 0xc3, 0xa6, 0x72, 0x20, 0x6d,
+        0x65, 0x64, 0x20, 0x66, 0x6c, 0xc3, 0xb8, 0x64,
+        0x65, 0x20, 0x6d, 0x65, 0x6e, 0x73, 0x20, 0x63,
+        0x69, 0x72, 0x6b, 0x75, 0x73, 0x6b, 0x6c, 0x6f,
+        0x76, 0x6e, 0x65, 0x6e, 0x20, 0x57, 0x6f, 0x6c,
+        0x74, 0x68, 0x65, 0x72, 0x20, 0x73, 0x70, 0x69,
+        0x6c, 0x6c, 0x65, 0x64, 0x65, 0x20, 0x70, 0xc3,
+        0xa5, 0x20, 0x78, 0x79, 0x6c, 0x6f, 0x66, 0x6f,
+        0x6e, 0x2e],
+        encodeAsUtf8("Quizdeltagerne spiste jordbær med fløde mens " +
+            "cirkusklovnen Wolther spillede på xylofon."),
+        "encode danish to utf8");
+
+
+    Expect.listEquals([
+        0x3f, 0x20, 0xd7, 0x93, 0xd7, 0x92, 0x20, 0xd7,
+        0xa1, 0xd7, 0xa7, 0xd7, 0xa8, 0xd7, 0x9f, 0x20,
+        0xd7, 0xa9, 0xd7, 0x98, 0x20, 0xd7, 0x91, 0xd7,
+        0x99, 0xd7, 0x9d, 0x20, 0xd7, 0x9e, 0xd7, 0x90,
+        0xd7, 0x95, 0xd7, 0x9b, 0xd7, 0x96, 0xd7, 0x91,
+        0x20, 0xd7, 0x95, 0xd7, 0x9c, 0xd7, 0xa4, 0xd7,
+        0xaa, 0xd7, 0xa2, 0x20, 0xd7, 0x9e, 0xd7, 0xa6,
+        0xd7, 0x90, 0x20, 0xd7, 0x9c, 0xd7, 0x95, 0x20,
+        0xd7, 0x97, 0xd7, 0x91, 0xd7, 0xa8, 0xd7, 0x94,
+        0x20, 0xd7, 0x90, 0xd7, 0x99, 0xd7, 0x9a, 0x20,
+        0xd7, 0x94, 0xd7, 0xa7, 0xd7, 0x9c, 0xd7, 0x99],
+        encodeAsUtf8("? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקלי"),
+        "Hebrew to utf8");
+
+    Expect.listEquals([
+        0xd0, 0xa1, 0xd1, 0x8a, 0xd0, 0xb5, 0xd1, 0x88,
+        0xd1, 0x8c, 0x20, 0xd0, 0xb6, 0xd0, 0xb5, 0x20,
+        0xd0, 0xb5, 0xd1, 0x89, 0xd1, 0x91, 0x20, 0xd1,
+        0x8d, 0xd1, 0x82, 0xd0, 0xb8, 0xd1, 0x85, 0x20,
+        0xd0, 0xbc, 0xd1, 0x8f, 0xd0, 0xb3, 0xd0, 0xba,
+        0xd0, 0xb8, 0xd1, 0x85, 0x20, 0xd1, 0x84, 0xd1,
+        0x80, 0xd0, 0xb0, 0xd0, 0xbd, 0xd1, 0x86, 0xd1,
+        0x83, 0xd0, 0xb7, 0xd1, 0x81, 0xd0, 0xba, 0xd0,
+        0xb8, 0xd1, 0x85, 0x20, 0xd0, 0xb1, 0xd1, 0x83,
+        0xd0, 0xbb, 0xd0, 0xbe, 0xd0, 0xba, 0x20, 0xd0,
+        0xb4, 0xd0, 0xb0, 0x20, 0xd0, 0xb2, 0xd1, 0x8b,
+        0xd0, 0xbf, 0xd0, 0xb5, 0xd0, 0xb9, 0x20, 0xd1,
+        0x87, 0xd0, 0xb0, 0xd1, 0x8e],
+        encodeAsUtf8("Съешь же ещё этих мягких французских булок да выпей" +
+        " чаю"), "Russian #2 to utf8");
+
+    Expect.listEquals([
+        0xce, 0x93, 0xce, 0xb1, 0xce, 0xb6, 0xce, 0xad,
+        0xce, 0xb5, 0xcf, 0x82, 0x20, 0xce, 0xba, 0xce,
+        0xb1, 0xe1, 0xbd, 0xb6, 0x20, 0xce, 0xbc, 0xcf,
+        0x85, 0xcf, 0x81, 0xcf, 0x84, 0xce, 0xb9, 0xe1,
+        0xbd, 0xb2, 0xcf, 0x82, 0x20, 0xce, 0xb4, 0xe1,
+        0xbd, 0xb2, 0xce, 0xbd, 0x20, 0xce, 0xb8, 0xe1,
+        0xbd, 0xb0, 0x20, 0xce, 0xb2, 0xcf, 0x81, 0xe1,
+        0xbf, 0xb6, 0x20, 0xcf, 0x80, 0xce, 0xb9, 0xe1,
+        0xbd, 0xb0, 0x20, 0xcf, 0x83, 0xcf, 0x84, 0xe1,
+        0xbd, 0xb8, 0x20, 0xcf, 0x87, 0xcf, 0x81, 0xcf,
+        0x85, 0xcf, 0x83, 0xce, 0xb1, 0xcf, 0x86, 0xe1,
+        0xbd, 0xb6, 0x20, 0xce, 0xbe, 0xce, 0xad, 0xcf,
+        0x86, 0xcf, 0x89, 0xcf, 0x84, 0xce, 0xbf],
+        encodeAsUtf8("Γαζέες καὶ μυρτιὲς δὲν θὰ βρῶ πιὰ στὸ χρυσαφὶ ξέφωτο"),
+        "Greek to utf8");
+
+    Expect.listEquals([
+        0xe3, 0x82, 0xa4, 0xe3, 0x83, 0xad, 0xe3, 0x83,
+        0x8f, 0xe3, 0x83, 0x8b, 0xe3, 0x83, 0x9b, 0xe3,
+        0x83, 0x98, 0xe3, 0x83, 0x88, 0x20, 0xe3, 0x83,
+        0x81, 0xe3, 0x83, 0xaa, 0xe3, 0x83, 0x8c, 0xe3,
+        0x83, 0xab, 0xe3, 0x83, 0xb2, 0x20, 0xe3, 0x83,
+        0xaf, 0xe3, 0x82, 0xab, 0xe3, 0x83, 0xa8, 0xe3,
+        0x82, 0xbf, 0xe3, 0x83, 0xac, 0xe3, 0x82, 0xbd,
+        0x20, 0xe3, 0x83, 0x84, 0xe3, 0x83, 0x8d, 0xe3,
+        0x83, 0x8a, 0xe3, 0x83, 0xa9, 0xe3, 0x83, 0xa0,
+        0x0a, 0xe3, 0x82, 0xa6, 0xe3, 0x83, 0xb0, 0xe3,
+        0x83, 0x8e, 0xe3, 0x82, 0xaa, 0xe3, 0x82, 0xaf,
+        0xe3, 0x83, 0xa4, 0xe3, 0x83, 0x9e, 0x20, 0xe3,
+        0x82, 0xb1, 0xe3, 0x83, 0x95, 0xe3, 0x82, 0xb3,
+        0xe3, 0x82, 0xa8, 0xe3, 0x83, 0x86, 0x20, 0xe3,
+        0x82, 0xa2, 0xe3, 0x82, 0xb5, 0xe3, 0x82, 0xad,
+        0xe3, 0x83, 0xa6, 0xe3, 0x83, 0xa1, 0xe3, 0x83,
+        0x9f, 0xe3, 0x82, 0xb7, 0x20, 0xe3, 0x83, 0xb1,
+        0xe3, 0x83, 0x92, 0xe3, 0x83, 0xa2, 0xe3, 0x82,
+        0xbb, 0xe3, 0x82, 0xb9, 0xe3, 0x83, 0xb3],
+        encodeAsUtf8(  """
+イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム
+ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン"""),
+        "Katakana");
+  }
+
+  void testUtf8bytesToCodepoints() {
+    Expect.listEquals([954, 972, 963, 956, 949],
+        _utf8ToCodepoints([0xce, 0xba, 0xcf, 0x8c, 0xcf,
+        0x83, 0xce, 0xbc, 0xce, 0xb5]), "κόσμε");
+
+    // boundary conditions: First possible sequence of a certain length
+    Expect.listEquals([0x0], _utf8ToCodepoints([0x0]), "0");
+    Expect.listEquals([0x80], _utf8ToCodepoints([0xc2, 0x80]), "80");
+    Expect.listEquals([0x800],
+        _utf8ToCodepoints([0xe0, 0xa0, 0x80]), "800");
+    Expect.listEquals([0x10000],
+        _utf8ToCodepoints([0xf0, 0x90, 0x80, 0x80]), "10000");
+    Expect.listEquals([0x200000],
+        _utf8ToCodepoints([0xf8, 0x88, 0x80, 0x80, 0x80]), "200000");
+    Expect.listEquals([0x4000000],
+        _utf8ToCodepoints([0xfc, 0x84, 0x80, 0x80, 0x80, 0x80]),
+        "4000000");
+
+    // boundary conditions: Last possible sequence of a certain length
+    Expect.listEquals([0x7f], _utf8ToCodepoints([0x7f]), "7f");
+    Expect.listEquals([0x7ff], _utf8ToCodepoints([0xdf, 0xbf]), "7ff");
+    Expect.listEquals([0xffff],
+        _utf8ToCodepoints([0xef, 0xbf, 0xbf]), "ffff");
+    Expect.listEquals([0x1fffff],
+        _utf8ToCodepoints([0xf7, 0xbf, 0xbf, 0xbf]), "1fffff");
+    Expect.listEquals([0x3ffffff],
+        _utf8ToCodepoints([0xfb, 0xbf, 0xbf, 0xbf, 0xbf]), "3ffffff");
+    Expect.listEquals([0x7fffffff],
+        _utf8ToCodepoints([0xfd, 0xbf, 0xbf, 0xbf, 0xbf, 0xbf]),
+        "4000000");
+
+    // other boundary conditions
+    Expect.listEquals([0xd7ff],
+        _utf8ToCodepoints([0xed, 0x9f, 0xbf]), "d7ff");
+    Expect.listEquals([0xe000],
+        _utf8ToCodepoints([0xee, 0x80, 0x80]), "e000");
+    Expect.listEquals([0xfffd],
+        _utf8ToCodepoints([0xef, 0xbf, 0xbd]), "fffd");
+    Expect.listEquals([0x10ffff],
+        _utf8ToCodepoints([0xf4, 0x8f, 0xbf, 0xbf]), "10ffff");
+    Expect.listEquals([0x110000],
+        _utf8ToCodepoints([0xf4, 0x90, 0x80, 0x80]), "110000");
+
+    // unexpected continuation bytes
+    Expect.listEquals([0xfffd],
+        _utf8ToCodepoints([0x80]), "80 => replacement character");
+    Expect.listEquals([0xfffd],
+        _utf8ToCodepoints([0xbf]), "bf => replacement character");
+
+    List<int> allContinuationBytes = <int>[];
+    List<int> matchingReplacementChars = <int>[];
+    for (int i = 0x80; i < 0xc0; i++) {
+      allContinuationBytes.add(i);
+      matchingReplacementChars.add(0xfffd);
+    }
+    Expect.listEquals(matchingReplacementChars,
+        _utf8ToCodepoints(allContinuationBytes),
+        "80 - bf => replacement character x 64");
+
+    List<int> allFirstTwoByteSeq = <int>[];
+    matchingReplacementChars = <int>[];
+    for (int i = 0xc0; i < 0xe0; i++) {
+      allFirstTwoByteSeq.addAll([i, 0x20]);
+      matchingReplacementChars.addAll([0xfffd]);
+    }
+    Expect.listEquals(matchingReplacementChars,
+        _utf8ToCodepoints(allFirstTwoByteSeq),
+        "c0 - df + space => replacement character + space x 32");
+
+    List<int> allFirstThreeByteSeq = <int>[];
+    matchingReplacementChars = <int>[];
+    for (int i = 0xe0; i < 0xf0; i++) {
+      allFirstThreeByteSeq.addAll([i, 0x20]);
+      matchingReplacementChars.addAll([0xfffd]);
+    }
+    Expect.listEquals(matchingReplacementChars,
+        _utf8ToCodepoints(allFirstThreeByteSeq),
+        "e0 - ef + space => replacement character x 16");
+
+    List<int> allFirstFourByteSeq = <int>[];
+    matchingReplacementChars = <int>[];
+    for (int i = 0xf0; i < 0xf8; i++) {
+      allFirstFourByteSeq.addAll([i, 0x20]);
+      matchingReplacementChars.addAll([0xfffd]);
+    }
+    Expect.listEquals(matchingReplacementChars,
+        _utf8ToCodepoints(allFirstFourByteSeq),
+        "f0 - f7 + space => replacement character x 8");
+
+    List<int> allFirstFiveByteSeq = <int>[];
+    matchingReplacementChars = <int>[];
+    for (int i = 0xf8; i < 0xfc; i++) {
+      allFirstFiveByteSeq.addAll([i, 0x20]);
+      matchingReplacementChars.addAll([0xfffd]);
+    }
+    Expect.listEquals(matchingReplacementChars,
+        _utf8ToCodepoints(allFirstFiveByteSeq),
+        "f8 - fb + space => replacement character x 4");
+
+    List<int> allFirstSixByteSeq = <int>[];
+    matchingReplacementChars = <int>[];
+    for (int i = 0xfc; i < 0xfe; i++) {
+      allFirstSixByteSeq.addAll([i, 0x20]);
+      matchingReplacementChars.addAll([0xfffd]);
+    }
+    Expect.listEquals(matchingReplacementChars,
+        _utf8ToCodepoints(allFirstSixByteSeq),
+        "fc - fd + space => replacement character x 2");
+
+    // Sequences with last continuation byte missing
+    Expect.listEquals([0xfffd],
+        _utf8ToCodepoints([0xc2]),
+        "2-byte sequence with last byte missing");
+    Expect.listEquals([0xfffd],
+        _utf8ToCodepoints([0xe0, 0x80]),
+        "3-byte sequence with last byte missing");
+    Expect.listEquals([0xfffd],
+        _utf8ToCodepoints([0xf0, 0x80, 0x80]),
+        "4-byte sequence with last byte missing");
+    Expect.listEquals([0xfffd],
+        _utf8ToCodepoints([0xf8, 0x88, 0x80, 0x80]),
+        "5-byte sequence with last byte missing");
+    Expect.listEquals([0xfffd],
+        _utf8ToCodepoints([0xfc, 0x80, 0x80, 0x80, 0x80]),
+        "6-byte sequence with last byte missing");
+
+    Expect.listEquals([0xfffd],
+        _utf8ToCodepoints([0xdf]),
+        "2-byte sequence with last byte missing (hi)");
+    Expect.listEquals([0xfffd],
+        _utf8ToCodepoints([0xef, 0xbf]),
+        "3-byte sequence with last byte missing (hi)");
+    Expect.listEquals([0xfffd],
+        _utf8ToCodepoints([0xf7, 0xbf, 0xbf]),
+        "4-byte sequence with last byte missing (hi)");
+    Expect.listEquals([0xfffd],
+        _utf8ToCodepoints([0xfb, 0xbf, 0xbf, 0xbf]),
+        "5-byte sequence with last byte missing (hi)");
+    Expect.listEquals([0xfffd],
+        _utf8ToCodepoints([0xfd, 0xbf, 0xbf, 0xbf, 0xbf]),
+        "6-byte sequence with last byte missing (hi)");
+
+    // Concatenation of incomplete sequences
+    Expect.listEquals(
+        [ 0xfffd, 0xfffd, 0xfffd, 0xfffd, 0xfffd,
+          0xfffd, 0xfffd, 0xfffd, 0xfffd, 0xfffd ],
+        _utf8ToCodepoints(
+            [ 0xc2,
+              0xe0, 0x80,
+              0xf0, 0x80, 0x80,
+              0xf8, 0x88, 0x80, 0x80,
+              0xfc, 0x80, 0x80, 0x80, 0x80,
+              0xdf,
+              0xef, 0xbf,
+              0xf7, 0xbf, 0xbf,
+              0xfb, 0xbf, 0xbf, 0xbf,
+              0xfd, 0xbf, 0xbf, 0xbf, 0xbf ]),
+            "Concatenation of incomplete sequences");
+
+    // Impossible bytes
+    Expect.listEquals([0xfffd], _utf8ToCodepoints([0xfe]), "fe");
+    Expect.listEquals([0xfffd], _utf8ToCodepoints([0xff]), "ff");
+    Expect.listEquals([0xfffd, 0xfffd, 0xfffd, 0xfffd],
+        _utf8ToCodepoints([0xfe, 0xfe, 0xff, 0xff]), "fe fe ff ff");
+
+    // Overlong sequences
+    Expect.listEquals([0xfffd], _utf8ToCodepoints([0xc0, 0xaf]),
+        "c0 af");
+    Expect.listEquals([0xfffd], _utf8ToCodepoints([0xe0, 0x80, 0xaf]),
+        "e0 80 af");
+    Expect.listEquals([0xfffd], _utf8ToCodepoints([0xf0, 0x80, 0x80, 0xaf]),
+        "f0 80 80 af");
+    Expect.listEquals([0xfffd],
+        _utf8ToCodepoints([0xf8, 0x80, 0x80, 0x80, 0xaf]),
+        "f8 80 80 80 af");
+    Expect.listEquals([0xfffd],
+        _utf8ToCodepoints([0xfc, 0x80, 0x80, 0x80, 0x80, 0xaf]),
+        "fc 80 80 80 80 af");
+
+    Expect.listEquals([0xfffd], _utf8ToCodepoints([0xc1, 0xbf]),
+        "c1 bf");
+    Expect.listEquals([0xfffd], _utf8ToCodepoints([0xe0, 0x9f, 0xbf]),
+        "e0 9f bf");
+    Expect.listEquals([0xfffd], _utf8ToCodepoints([0xf0, 0x8f, 0xbf, 0xbf]),
+        "f0 8f bf bf");
+    Expect.listEquals([0xfffd],
+        _utf8ToCodepoints([0xf8, 0x87, 0xbf, 0xbf, 0xbf]),
+        "f8 87 bf bf bf");
+    Expect.listEquals([0xfffd],
+        _utf8ToCodepoints([0xfc, 0x83, 0xbf, 0xbf, 0xbf, 0xbf]),
+        "fc 83 bf bf bf bf");
+
+    Expect.listEquals([0xfffd], _utf8ToCodepoints([0xc0, 0x80]),
+        "c0 80");
+    Expect.listEquals([0xfffd], _utf8ToCodepoints([0xe0, 0x80, 0x80]),
+        "e0 80 80");
+    Expect.listEquals([0xfffd], _utf8ToCodepoints([0xf0, 0x80, 0x80, 0x80]),
+        "f0 80 80 80");
+    Expect.listEquals([0xfffd],
+        _utf8ToCodepoints([0xf8, 0x80, 0x80, 0x80, 0x80]),
+        "f8 80 80 80 80");
+    Expect.listEquals([0xfffd],
+        _utf8ToCodepoints([0xfc, 0x80, 0x80, 0x80, 0x80, 0x80]),
+        "fc 80 80 80 80 80");
+
+    // Illegal code positions
+    Expect.listEquals([0xfffd],
+        _utf8ToCodepoints([0xed, 0xa0, 0x80]), "U+D800");
+    Expect.listEquals([0xfffd],
+        _utf8ToCodepoints([0xed, 0xad, 0xbf]), "U+DB7F");
+    Expect.listEquals([0xfffd],
+        _utf8ToCodepoints([0xed, 0xae, 0x80]), "U+DB80");
+    Expect.listEquals([0xfffd],
+        _utf8ToCodepoints([0xed, 0xaf, 0xbf]), "U+DBFF");
+    Expect.listEquals([0xfffd],
+        _utf8ToCodepoints([0xed, 0xb0, 0x80]), "U+DC00");
+    Expect.listEquals([0xfffd],
+        _utf8ToCodepoints([0xed, 0xbe, 0x80]), "U+DF80");
+    Expect.listEquals([0xfffd],
+        _utf8ToCodepoints([0xed, 0xbf, 0xbf]), "U+DFFF");
+
+    // Paired UTF-16 surrogates
+    Expect.listEquals([0xfffd, 0xfffd],
+        _utf8ToCodepoints([0xed, 0xa0, 0x80, 0xed, 0xb0, 0x80]),
+        "U+D800 U+DC00");
+    Expect.listEquals([0xfffd, 0xfffd],
+        _utf8ToCodepoints([0xed, 0xa0, 0x80, 0xed, 0xbf, 0xbf]),
+        "U+D800 U+DFFF");
+    Expect.listEquals([0xfffd, 0xfffd],
+        _utf8ToCodepoints([0xed, 0xad, 0xbf, 0xed, 0xb0, 0x80]),
+        "U+DB7F U+DC00");
+    Expect.listEquals([0xfffd, 0xfffd],
+        _utf8ToCodepoints([0xed, 0xad, 0xbf, 0xed, 0xbf, 0xbf]),
+        "U+DB7F U+DFFF");
+    Expect.listEquals([0xfffd, 0xfffd],
+        _utf8ToCodepoints([0xed, 0xae, 0x80, 0xed, 0xb0, 0x80]),
+        "U+DB80 U+DC00");
+    Expect.listEquals([0xfffd, 0xfffd],
+        _utf8ToCodepoints([0xed, 0xae, 0x80, 0xed, 0xbf, 0xbf]),
+        "U+DB80 U+DFFF");
+    Expect.listEquals([0xfffd, 0xfffd],
+        _utf8ToCodepoints([0xed, 0xaf, 0xbf, 0xed, 0xb0, 0x80]),
+        "U+DBFF U+DC00");
+    Expect.listEquals([0xfffd, 0xfffd],
+        _utf8ToCodepoints([0xed, 0xaf, 0xbf, 0xed, 0xbf, 0xbf]),
+        "U+DBFF U+DFFF");
+
+    // Other illegal code positions (???)
+    Expect.listEquals([0xfffe], _utf8ToCodepoints([0xef, 0xbf, 0xbe]),
+        "U+FFFE");
+    Expect.listEquals([0xffff], _utf8ToCodepoints([0xef, 0xbf, 0xbf]),
+        "U+FFFF");
+  }
+
+  void testUtf8BytesToString() {
+
+    Expect.stringEquals("The quick brown fox jumps over the lazy dog.",
+        decodeFromUtf8([
+          0x54, 0x68, 0x65, 0x20, 0x71, 0x75, 0x69, 0x63,
+          0x6b, 0x20, 0x62, 0x72, 0x6f, 0x77, 0x6e, 0x20,
+          0x66, 0x6f, 0x78, 0x20, 0x6a, 0x75, 0x6d, 0x70,
+          0x73, 0x20, 0x6f, 0x76, 0x65, 0x72, 0x20, 0x74,
+          0x68, 0x65, 0x20, 0x6c, 0x61, 0x7a, 0x79, 0x20,
+          0x64, 0x6f, 0x67, 0x2e]), "English");
+
+    Expect.stringEquals("Quizdeltagerne spiste jordbær med fløde mens " +
+        "cirkusklovnen Wolther spillede på xylofon.",
+        decodeFromUtf8([
+          0x51, 0x75, 0x69, 0x7a, 0x64, 0x65, 0x6c, 0x74,
+          0x61, 0x67, 0x65, 0x72, 0x6e, 0x65, 0x20, 0x73,
+          0x70, 0x69, 0x73, 0x74, 0x65, 0x20, 0x6a, 0x6f,
+          0x72, 0x64, 0x62, 0xc3, 0xa6, 0x72, 0x20, 0x6d,
+          0x65, 0x64, 0x20, 0x66, 0x6c, 0xc3, 0xb8, 0x64,
+          0x65, 0x20, 0x6d, 0x65, 0x6e, 0x73, 0x20, 0x63,
+          0x69, 0x72, 0x6b, 0x75, 0x73, 0x6b, 0x6c, 0x6f,
+          0x76, 0x6e, 0x65, 0x6e, 0x20, 0x57, 0x6f, 0x6c,
+          0x74, 0x68, 0x65, 0x72, 0x20, 0x73, 0x70, 0x69,
+          0x6c, 0x6c, 0x65, 0x64, 0x65, 0x20, 0x70, 0xc3,
+          0xa5, 0x20, 0x78, 0x79, 0x6c, 0x6f, 0x66, 0x6f,
+          0x6e, 0x2e]), "Danish");
+
+    Expect.stringEquals("? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקלי",

[Dan Rice, 2012/01/31 16:01:10]

הקליטה

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

Done.

+        decodeFromUtf8([
+          0x3f, 0x20, 0xd7, 0x93, 0xd7, 0x92, 0x20, 0xd7,
+          0xa1, 0xd7, 0xa7, 0xd7, 0xa8, 0xd7, 0x9f, 0x20,
+          0xd7, 0xa9, 0xd7, 0x98, 0x20, 0xd7, 0x91, 0xd7,
+          0x99, 0xd7, 0x9d, 0x20, 0xd7, 0x9e, 0xd7, 0x90,
+          0xd7, 0x95, 0xd7, 0x9b, 0xd7, 0x96, 0xd7, 0x91,
+          0x20, 0xd7, 0x95, 0xd7, 0x9c, 0xd7, 0xa4, 0xd7,
+          0xaa, 0xd7, 0xa2, 0x20, 0xd7, 0x9e, 0xd7, 0xa6,
+          0xd7, 0x90, 0x20, 0xd7, 0x9c, 0xd7, 0x95, 0x20,
+          0xd7, 0x97, 0xd7, 0x91, 0xd7, 0xa8, 0xd7, 0x94,
+          0x20, 0xd7, 0x90, 0xd7, 0x99, 0xd7, 0x9a, 0x20,
+          0xd7, 0x94, 0xd7, 0xa7, 0xd7, 0x9c, 0xd7, 0x99]), "Hebrew");
+
+    Expect.stringEquals("Съешь же ещё этих мягких французских булок да выпей " +
+        "чаю",
+        decodeFromUtf8([
+          0xd0, 0xa1, 0xd1, 0x8a, 0xd0 ,0xb5, 0xd1, 0x88,
+          0xd1, 0x8c, 0x20, 0xd0, 0xb6, 0xd0, 0xb5, 0x20,
+          0xd0, 0xb5, 0xd1, 0x89, 0xd1, 0x91, 0x20, 0xd1,
+          0x8d, 0xd1, 0x82, 0xd0, 0xb8, 0xd1, 0x85, 0x20,
+          0xd0, 0xbc, 0xd1, 0x8f, 0xd0, 0xb3, 0xd0, 0xba,
+          0xd0, 0xb8, 0xd1, 0x85, 0x20, 0xd1, 0x84, 0xd1,
+          0x80, 0xd0, 0xb0, 0xd0, 0xbd, 0xd1, 0x86, 0xd1,
+          0x83, 0xd0, 0xb7, 0xd1, 0x81, 0xd0, 0xba, 0xd0,
+          0xb8, 0xd1, 0x85, 0x20, 0xd0, 0xb1, 0xd1, 0x83,
+          0xd0, 0xbb, 0xd0, 0xbe, 0xd0, 0xba, 0x20, 0xd0,
+          0xb4, 0xd0, 0xb0, 0x20, 0xd0, 0xb2, 0xd1, 0x8b,
+          0xd0, 0xbf, 0xd0, 0xb5, 0xd0, 0xb9, 0x20, 0xd1,
+          0x87, 0xd0, 0xb0, 0xd1, 0x8e]), "Russian #2");
+
+    Expect.stringEquals("Γαζέες καὶ μυρτιὲς δὲν θὰ βρῶ πιὰ στὸ χρυσαφὶ ξέφωτο",
+        decodeFromUtf8([
+          0xce, 0x93, 0xce, 0xb1, 0xce, 0xb6, 0xce, 0xad,
+          0xce, 0xb5, 0xcf, 0x82, 0x20, 0xce, 0xba, 0xce,
+          0xb1, 0xe1, 0xbd, 0xb6, 0x20, 0xce, 0xbc, 0xcf,
+          0x85, 0xcf, 0x81, 0xcf, 0x84, 0xce, 0xb9, 0xe1,
+          0xbd, 0xb2, 0xcf, 0x82, 0x20, 0xce, 0xb4, 0xe1,
+          0xbd, 0xb2, 0xce, 0xbd, 0x20, 0xce, 0xb8, 0xe1,
+          0xbd, 0xb0, 0x20, 0xce, 0xb2, 0xcf, 0x81, 0xe1,
+          0xbf, 0xb6, 0x20, 0xcf, 0x80, 0xce, 0xb9, 0xe1,
+          0xbd, 0xb0, 0x20, 0xcf, 0x83, 0xcf, 0x84, 0xe1,
+          0xbd, 0xb8, 0x20, 0xcf, 0x87, 0xcf, 0x81, 0xcf,
+          0x85, 0xcf, 0x83, 0xce, 0xb1, 0xcf, 0x86, 0xe1,
+          0xbd, 0xb6, 0x20, 0xce, 0xbe, 0xce, 0xad, 0xcf,
+          0x86, 0xcf, 0x89, 0xcf, 0x84, 0xce, 0xbf]), "Greek");
+    Expect.stringEquals("""
+イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム
+ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン""",
+        decodeFromUtf8([
+          0xe3, 0x82, 0xa4, 0xe3, 0x83, 0xad, 0xe3, 0x83,
+          0x8f, 0xe3, 0x83, 0x8b, 0xe3, 0x83, 0x9b, 0xe3,
+          0x83, 0x98, 0xe3, 0x83, 0x88, 0x20, 0xe3, 0x83,
+          0x81, 0xe3, 0x83, 0xaa, 0xe3, 0x83, 0x8c, 0xe3,
+          0x83, 0xab, 0xe3, 0x83, 0xb2, 0x20, 0xe3, 0x83,
+          0xaf, 0xe3, 0x82, 0xab, 0xe3, 0x83, 0xa8, 0xe3,
+          0x82, 0xbf, 0xe3, 0x83, 0xac, 0xe3, 0x82, 0xbd,
+          0x20, 0xe3, 0x83, 0x84, 0xe3, 0x83, 0x8d, 0xe3,
+          0x83, 0x8a, 0xe3, 0x83, 0xa9, 0xe3, 0x83, 0xa0,
+          0x0a, 0xe3, 0x82, 0xa6, 0xe3, 0x83, 0xb0, 0xe3,
+          0x83, 0x8e, 0xe3, 0x82, 0xaa, 0xe3, 0x82, 0xaf,
+          0xe3, 0x83, 0xa4, 0xe3, 0x83, 0x9e, 0x20, 0xe3,
+          0x82, 0xb1, 0xe3, 0x83, 0x95, 0xe3, 0x82, 0xb3,
+          0xe3, 0x82, 0xa8, 0xe3, 0x83, 0x86, 0x20, 0xe3,
+          0x82, 0xa2, 0xe3, 0x82, 0xb5, 0xe3, 0x82, 0xad,
+          0xe3, 0x83, 0xa6, 0xe3, 0x83, 0xa1, 0xe3, 0x83,
+          0x9f, 0xe3, 0x82, 0xb7, 0x20, 0xe3, 0x83, 0xb1,
+          0xe3, 0x83, 0x92, 0xe3, 0x83, 0xa2, 0xe3, 0x82,
+          0xbb, 0xe3, 0x82, 0xb9, 0xe3, 0x83, 0xb3]), "Katakana");
+  }
+}