OLD | NEW |
1 // Copyright (c) 2013, the Dart project authors. Please see the AUTHORS file | 1 // Copyright (c) 2013, the Dart project authors. Please see the AUTHORS file |
2 // for details. All rights reserved. Use of this source code is governed by a | 2 // for details. All rights reserved. Use of this source code is governed by a |
3 // BSD-style license that can be found in the LICENSE file. | 3 // BSD-style license that can be found in the LICENSE file. |
4 | 4 |
5 part of dart.codec; | 5 part of dart.codec; |
6 | 6 |
7 /** | 7 /** |
8 * Open-ended Encoding enum. | 8 * Open-ended Encoding enum. |
9 */ | 9 */ |
10 // TODO(floitsch): dart:io already has an Encoding class. If we can't | 10 // TODO(floitsch): dart:io already has an Encoding class. If we can't |
11 // consolitate them, we need to remove `Encoding` here. | 11 // consolitate them, we need to remove `Encoding` here. |
12 abstract class Encoding extends Codec<String, List<int>> { | 12 abstract class Encoding extends Codec<String, List<int>> { |
13 const Encoding(); | 13 const Encoding(); |
14 } | 14 } |
15 | 15 |
16 // TODO(floitsch): add other encodings, like ASCII and ISO_8859_1. | 16 // TODO(floitsch): add other encodings, like ASCII and ISO_8859_1. |
17 const UTF8 = const Utf8Codec(); | 17 const UTF8 = const Utf8Codec(); |
18 | 18 |
19 /** | 19 /** |
20 * A [Utf8Codec] encodes strings to utf-8 code units (bytes) and decodes | 20 * A [Utf8Codec] encodes strings to utf-8 code units (bytes) and decodes |
21 * UTF-8 code units to strings. | 21 * UTF-8 code units to strings. |
22 */ | 22 */ |
23 // TODO(floitsch): Needs a way to specify if decoding should throw or use | |
24 // the replacement character. | |
25 class Utf8Codec extends Encoding { | 23 class Utf8Codec extends Encoding { |
26 const Utf8Codec(); | 24 final bool _allowMalformed; |
| 25 |
| 26 /** |
| 27 * Instantiates a new [Utf8Codec]. |
| 28 * |
| 29 * The optional [allowMalformed] argument defines how [decoder] (and [decode]) |
| 30 * deal with invalid or unterminated character sequences. |
| 31 * |
| 32 * If it is `true` (and not overriden at the method invocation) [decode] and |
| 33 * the [decoder] replace invalid (or unterminated) octet |
| 34 * sequences with the Unicode Replacement character `U+FFFD` (�). Otherwise |
| 35 * they throw a [FormatException]. |
| 36 */ |
| 37 const Utf8Codec({ bool allowMalformed: false }) |
| 38 : _allowMalformed = allowMalformed; |
| 39 |
| 40 /** |
| 41 * Decodes the UTF-8 [codeUnits] (a list of unsigned 8-bit integers) to the |
| 42 * corresponding string. |
| 43 * |
| 44 * If [allowMalformed] is `true` the decoder replaces invalid (or |
| 45 * unterminated) character sequences with the Unicode Replacement character |
| 46 * `U+FFFD` (�). Otherwise it throws a [FormatException]. |
| 47 * |
| 48 * If [allowMalformed] is not given, it defaults to the `allowMalformed` that |
| 49 * was used to instantiate `this`. |
| 50 */ |
| 51 String decode(List<int> codeUnits, { bool allowMalformed }) { |
| 52 if (allowMalformed == null) allowMalformed = _allowMalformed; |
| 53 return new Utf8Decoder(allowMalformed: allowMalformed).convert(codeUnits); |
| 54 } |
27 | 55 |
28 Converter<String, List<int>> get encoder => new Utf8Encoder(); | 56 Converter<String, List<int>> get encoder => new Utf8Encoder(); |
29 Converter<List<int>, String> get decoder => new Utf8Decoder(); | 57 Converter<List<int>, String> get decoder { |
| 58 return new Utf8Decoder(allowMalformed: _allowMalformed); |
| 59 } |
30 } | 60 } |
OLD | NEW |