Chromium Code Reviews| 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.convert; | 5 part of dart.convert; |
| 6 | 6 |
| 7 const UTF8 = const Utf8Codec(); | |
| 8 | |
| 9 /** | |
| 10 * A [Utf8Codec] encodes strings to utf-8 code units (bytes) and decodes | |
| 11 * UTF-8 code units to strings. | |
| 12 */ | |
| 13 class Utf8Codec extends Encoding { | |
| 14 final bool _allowMalformed; | |
| 15 | |
| 16 /** | |
| 17 * Instantiates a new [Utf8Codec]. | |
| 18 * | |
| 19 * The optional [allowMalformed] argument defines how [decoder] (and [decode]) | |
| 20 * deal with invalid or unterminated character sequences. | |
| 21 * | |
| 22 * If it is `true` (and not overriden at the method invocation) [decode] and | |
| 23 * the [decoder] replace invalid (or unterminated) octet | |
| 24 * sequences with the Unicode Replacement character `U+FFFD` (�). Otherwise | |
|
Søren Gjesse
2013/07/22 12:04:42
Should it be possible to configure the replacement
floitsch
2013/07/22 12:24:58
We thought of it, but in the end decided against i
| |
| 25 * they throw a [FormatException]. | |
| 26 */ | |
| 27 const Utf8Codec({ bool allowMalformed: false }) | |
| 28 : _allowMalformed = allowMalformed; | |
| 29 | |
| 30 /** | |
| 31 * Decodes the UTF-8 [codeUnits] (a list of unsigned 8-bit integers) to the | |
| 32 * corresponding string. | |
| 33 * | |
| 34 * If [allowMalformed] is `true` the decoder replaces invalid (or | |
| 35 * unterminated) character sequences with the Unicode Replacement character | |
| 36 * `U+FFFD` (�). Otherwise it throws a [FormatException]. | |
| 37 * | |
| 38 * If [allowMalformed] is not given, it defaults to the `allowMalformed` that | |
| 39 * was used to instantiate `this`. | |
| 40 */ | |
| 41 String decode(List<int> codeUnits, { bool allowMalformed }) { | |
| 42 if (allowMalformed == null) allowMalformed = _allowMalformed; | |
| 43 return new Utf8Decoder(allowMalformed: allowMalformed).convert(codeUnits); | |
| 44 } | |
| 45 | |
| 46 Converter<String, List<int>> get encoder => new Utf8Encoder(); | |
| 47 Converter<List<int>, String> get decoder { | |
| 48 return new Utf8Decoder(allowMalformed: _allowMalformed); | |
| 49 } | |
| 50 } | |
| 51 | |
| 7 /** | 52 /** |
| 8 * A [Utf8Encoder] converts strings to their UTF-8 code units (a list of | 53 * A [Utf8Encoder] converts strings to their UTF-8 code units (a list of |
| 9 * unsigned 8-bit integers). | 54 * unsigned 8-bit integers). |
| 10 */ | 55 */ |
| 11 class Utf8Encoder extends Converter<String, List<int>> { | 56 class Utf8Encoder extends Converter<String, List<int>> { |
| 12 /** | 57 /** |
| 13 * Converts [string] to its UTF-8 code units (a list of | 58 * Converts [string] to its UTF-8 code units (a list of |
| 14 * unsigned 8-bit integers). | 59 * unsigned 8-bit integers). |
| 15 */ | 60 */ |
| 16 List<int> convert(String string) => OLD_UTF_LIB.encodeUtf8(string); | 61 List<int> convert(String string) => OLD_UTF_LIB.encodeUtf8(string); |
| (...skipping 181 matching lines...) Expand 10 before | Expand all | Expand 10 after Loading... | |
| 198 } | 243 } |
| 199 break loop; | 244 break loop; |
| 200 } | 245 } |
| 201 if (expectedUnits > 0) { | 246 if (expectedUnits > 0) { |
| 202 _value = value; | 247 _value = value; |
| 203 _expectedUnits = expectedUnits; | 248 _expectedUnits = expectedUnits; |
| 204 _extraUnits = extraUnits; | 249 _extraUnits = extraUnits; |
| 205 } | 250 } |
| 206 } | 251 } |
| 207 } | 252 } |
| OLD | NEW |