| OLD | NEW |
| (Empty) |
| 1 /* | |
| 2 * Copyright (C) 2007, 2008 Apple, Inc. All rights reserved. | |
| 3 * | |
| 4 * Redistribution and use in source and binary forms, with or without | |
| 5 * modification, are permitted provided that the following conditions | |
| 6 * are met: | |
| 7 * 1. Redistributions of source code must retain the above copyright | |
| 8 * notice, this list of conditions and the following disclaimer. | |
| 9 * 2. Redistributions in binary form must reproduce the above copyright | |
| 10 * notice, this list of conditions and the following disclaimer in the | |
| 11 * documentation and/or other materials provided with the distribution. | |
| 12 * | |
| 13 * THIS SOFTWARE IS PROVIDED BY APPLE COMPUTER, INC. ``AS IS'' AND ANY | |
| 14 * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE | |
| 15 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR | |
| 16 * PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL APPLE COMPUTER, INC. OR | |
| 17 * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, | |
| 18 * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, | |
| 19 * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR | |
| 20 * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY | |
| 21 * OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT | |
| 22 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE | |
| 23 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. | |
| 24 */ | |
| 25 | |
| 26 #include "wtf/text/TextCodecUserDefined.h" | |
| 27 | |
| 28 #include "wtf/PtrUtil.h" | |
| 29 #include "wtf/text/CString.h" | |
| 30 #include "wtf/text/StringBuffer.h" | |
| 31 #include "wtf/text/StringBuilder.h" | |
| 32 #include "wtf/text/WTFString.h" | |
| 33 #include <memory> | |
| 34 | |
| 35 namespace WTF { | |
| 36 | |
| 37 void TextCodecUserDefined::registerEncodingNames( | |
| 38 EncodingNameRegistrar registrar) { | |
| 39 registrar("x-user-defined", "x-user-defined"); | |
| 40 } | |
| 41 | |
| 42 static std::unique_ptr<TextCodec> newStreamingTextDecoderUserDefined( | |
| 43 const TextEncoding&, | |
| 44 const void*) { | |
| 45 return WTF::wrapUnique(new TextCodecUserDefined); | |
| 46 } | |
| 47 | |
| 48 void TextCodecUserDefined::registerCodecs(TextCodecRegistrar registrar) { | |
| 49 registrar("x-user-defined", newStreamingTextDecoderUserDefined, 0); | |
| 50 } | |
| 51 | |
| 52 String TextCodecUserDefined::decode(const char* bytes, | |
| 53 size_t length, | |
| 54 FlushBehavior, | |
| 55 bool, | |
| 56 bool&) { | |
| 57 StringBuilder result; | |
| 58 result.reserveCapacity(length); | |
| 59 | |
| 60 for (size_t i = 0; i < length; ++i) { | |
| 61 signed char c = bytes[i]; | |
| 62 result.append(static_cast<UChar>(c & 0xF7FF)); | |
| 63 } | |
| 64 | |
| 65 return result.toString(); | |
| 66 } | |
| 67 | |
| 68 template <typename CharType> | |
| 69 static CString encodeComplexUserDefined(const CharType* characters, | |
| 70 size_t length, | |
| 71 UnencodableHandling handling) { | |
| 72 size_t targetLength = length; | |
| 73 Vector<char> result(targetLength); | |
| 74 char* bytes = result.data(); | |
| 75 | |
| 76 size_t resultLength = 0; | |
| 77 for (size_t i = 0; i < length;) { | |
| 78 UChar32 c; | |
| 79 // TODO(jsbell): Will the input for x-user-defined ever be LChars? | |
| 80 U16_NEXT(characters, i, length, c); | |
| 81 // If the input was a surrogate pair (non-BMP character) then we | |
| 82 // overestimated the length. | |
| 83 if (c > 0xffff) | |
| 84 --targetLength; | |
| 85 signed char signedByte = static_cast<signed char>(c); | |
| 86 if ((signedByte & 0xF7FF) == c) { | |
| 87 bytes[resultLength++] = signedByte; | |
| 88 } else { | |
| 89 // No way to encode this character with x-user-defined. | |
| 90 UnencodableReplacementArray replacement; | |
| 91 int replacementLength = | |
| 92 TextCodec::getUnencodableReplacement(c, handling, replacement); | |
| 93 DCHECK_GT(replacementLength, 0); | |
| 94 // Only one char was initially reserved per input character, so grow if | |
| 95 // necessary. Note that in the case of surrogate pairs and | |
| 96 // QuestionMarksForUnencodables the result length may be shorter than | |
| 97 // the input length. | |
| 98 targetLength += replacementLength - 1; | |
| 99 if (targetLength > result.size()) { | |
| 100 result.grow(targetLength); | |
| 101 bytes = result.data(); | |
| 102 } | |
| 103 memcpy(bytes + resultLength, replacement, replacementLength); | |
| 104 resultLength += replacementLength; | |
| 105 } | |
| 106 } | |
| 107 | |
| 108 return CString(bytes, resultLength); | |
| 109 } | |
| 110 | |
| 111 template <typename CharType> | |
| 112 CString TextCodecUserDefined::encodeCommon(const CharType* characters, | |
| 113 size_t length, | |
| 114 UnencodableHandling handling) { | |
| 115 char* bytes; | |
| 116 CString result = CString::createUninitialized(length, bytes); | |
| 117 | |
| 118 // Convert the string a fast way and simultaneously do an efficient check to | |
| 119 // see if it's all ASCII. | |
| 120 UChar ored = 0; | |
| 121 for (size_t i = 0; i < length; ++i) { | |
| 122 UChar c = characters[i]; | |
| 123 bytes[i] = static_cast<char>(c); | |
| 124 ored |= c; | |
| 125 } | |
| 126 | |
| 127 if (!(ored & 0xFF80)) | |
| 128 return result; | |
| 129 | |
| 130 // If it wasn't all ASCII, call the function that handles more-complex cases. | |
| 131 return encodeComplexUserDefined(characters, length, handling); | |
| 132 } | |
| 133 | |
| 134 CString TextCodecUserDefined::encode(const UChar* characters, | |
| 135 size_t length, | |
| 136 UnencodableHandling handling) { | |
| 137 return encodeCommon(characters, length, handling); | |
| 138 } | |
| 139 | |
| 140 CString TextCodecUserDefined::encode(const LChar* characters, | |
| 141 size_t length, | |
| 142 UnencodableHandling handling) { | |
| 143 return encodeCommon(characters, length, handling); | |
| 144 } | |
| 145 | |
| 146 } // namespace WTF | |
| OLD | NEW |