| OLD | NEW |
|---|
| (Empty) |
| 1 /* | |
| 2 * Copyright (C) 2004, 2006, 2008, 2010 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/TextCodecUTF16.h" | |
| 27 | |
| 28 #include "wtf/PtrUtil.h" | |
| 29 #include "wtf/text/CString.h" | |
| 30 #include "wtf/text/CharacterNames.h" | |
| 31 #include "wtf/text/StringBuffer.h" | |
| 32 #include "wtf/text/WTFString.h" | |
| 33 #include <memory> | |
| 34 | |
| 35 using namespace std; | |
| 36 | |
| 37 namespace WTF { | |
| 38 | |
| 39 void TextCodecUTF16::registerEncodingNames(EncodingNameRegistrar registrar) { | |
| 40 registrar("UTF-16LE", "UTF-16LE"); | |
| 41 registrar("UTF-16BE", "UTF-16BE"); | |
| 42 | |
| 43 registrar("ISO-10646-UCS-2", "UTF-16LE"); | |
| 44 registrar("UCS-2", "UTF-16LE"); | |
| 45 registrar("UTF-16", "UTF-16LE"); | |
| 46 registrar("Unicode", "UTF-16LE"); | |
| 47 registrar("csUnicode", "UTF-16LE"); | |
| 48 registrar("unicodeFEFF", "UTF-16LE"); | |
| 49 | |
| 50 registrar("unicodeFFFE", "UTF-16BE"); | |
| 51 } | |
| 52 | |
| 53 static std::unique_ptr<TextCodec> newStreamingTextDecoderUTF16LE( | |
| 54 const TextEncoding&, | |
| 55 const void*) { | |
| 56 return WTF::makeUnique<TextCodecUTF16>(true); | |
| 57 } | |
| 58 | |
| 59 static std::unique_ptr<TextCodec> newStreamingTextDecoderUTF16BE( | |
| 60 const TextEncoding&, | |
| 61 const void*) { | |
| 62 return WTF::makeUnique<TextCodecUTF16>(false); | |
| 63 } | |
| 64 | |
| 65 void TextCodecUTF16::registerCodecs(TextCodecRegistrar registrar) { | |
| 66 registrar("UTF-16LE", newStreamingTextDecoderUTF16LE, 0); | |
| 67 registrar("UTF-16BE", newStreamingTextDecoderUTF16BE, 0); | |
| 68 } | |
| 69 | |
| 70 String TextCodecUTF16::decode(const char* bytes, | |
| 71 size_t length, | |
| 72 FlushBehavior flush, | |
| 73 bool, | |
| 74 bool& sawError) { | |
| 75 // For compatibility reasons, ignore flush from fetch EOF. | |
| 76 const bool reallyFlush = flush != DoNotFlush && flush != FetchEOF; | |
| 77 | |
| 78 if (!length) { | |
| 79 if (reallyFlush && (m_haveLeadByte || m_haveLeadSurrogate)) { | |
| 80 m_haveLeadByte = m_haveLeadSurrogate = false; | |
| 81 sawError = true; | |
| 82 return String(&replacementCharacter, 1); | |
| 83 } | |
| 84 return String(); | |
| 85 } | |
| 86 | |
| 87 const unsigned char* p = reinterpret_cast<const unsigned char*>(bytes); | |
| 88 const size_t numBytes = length + m_haveLeadByte; | |
| 89 const bool willHaveExtraByte = numBytes & 1; | |
| 90 const size_t numCharsIn = numBytes / 2; | |
| 91 const size_t maxCharsOut = numCharsIn + (m_haveLeadSurrogate ? 1 : 0) + | |
| 92 (reallyFlush && willHaveExtraByte ? 1 : 0); | |
| 93 | |
| 94 StringBuffer<UChar> buffer(maxCharsOut); | |
| 95 UChar* q = buffer.characters(); | |
| 96 | |
| 97 for (size_t i = 0; i < numCharsIn; ++i) { | |
| 98 UChar c; | |
| 99 if (m_haveLeadByte) { | |
| 100 c = m_littleEndian ? (m_leadByte | (p[0] << 8)) | |
| 101 : ((m_leadByte << 8) | p[0]); | |
| 102 m_haveLeadByte = false; | |
| 103 ++p; | |
| 104 } else { | |
| 105 c = m_littleEndian ? (p[0] | (p[1] << 8)) : ((p[0] << 8) | p[1]); | |
| 106 p += 2; | |
| 107 } | |
| 108 | |
| 109 // TODO(jsbell): If necessary for performance, m_haveLeadByte handling | |
| 110 // can be pulled out and this loop split into distinct cases for | |
| 111 // big/little endian. The logic from here to the end of the loop is | |
| 112 // constant with respect to m_haveLeadByte and m_littleEndian. | |
| 113 | |
| 114 if (m_haveLeadSurrogate && U_IS_TRAIL(c)) { | |
| 115 *q++ = m_leadSurrogate; | |
| 116 m_haveLeadSurrogate = false; | |
| 117 *q++ = c; | |
| 118 } else { | |
| 119 if (m_haveLeadSurrogate) { | |
| 120 m_haveLeadSurrogate = false; | |
| 121 sawError = true; | |
| 122 *q++ = replacementCharacter; | |
| 123 } | |
| 124 | |
| 125 if (U_IS_LEAD(c)) { | |
| 126 m_haveLeadSurrogate = true; | |
| 127 m_leadSurrogate = c; | |
| 128 } else if (U_IS_TRAIL(c)) { | |
| 129 sawError = true; | |
| 130 *q++ = replacementCharacter; | |
| 131 } else { | |
| 132 *q++ = c; | |
| 133 } | |
| 134 } | |
| 135 } | |
| 136 | |
| 137 DCHECK(!m_haveLeadByte); | |
| 138 if (willHaveExtraByte) { | |
| 139 m_haveLeadByte = true; | |
| 140 m_leadByte = p[0]; | |
| 141 } | |
| 142 | |
| 143 if (reallyFlush && (m_haveLeadByte || m_haveLeadSurrogate)) { | |
| 144 m_haveLeadByte = m_haveLeadSurrogate = false; | |
| 145 sawError = true; | |
| 146 *q++ = replacementCharacter; | |
| 147 } | |
| 148 | |
| 149 buffer.shrink(q - buffer.characters()); | |
| 150 | |
| 151 return String::adopt(buffer); | |
| 152 } | |
| 153 | |
| 154 CString TextCodecUTF16::encode(const UChar* characters, | |
| 155 size_t length, | |
| 156 UnencodableHandling) { | |
| 157 // We need to be sure we can double the length without overflowing. | |
| 158 // Since the passed-in length is the length of an actual existing | |
| 159 // character buffer, each character is two bytes, and we know | |
| 160 // the buffer doesn't occupy the entire address space, we can | |
| 161 // assert here that doubling the length does not overflow size_t | |
| 162 // and there's no need for a runtime check. | |
| 163 DCHECK_LE(length, numeric_limits<size_t>::max() / 2); | |
| 164 | |
| 165 char* bytes; | |
| 166 CString result = CString::createUninitialized(length * 2, bytes); | |
| 167 | |
| 168 // FIXME: CString is not a reasonable data structure for encoded UTF-16, which | |
| 169 // will have null characters inside it. Perhaps the result of encode should | |
| 170 // not be a CString. | |
| 171 if (m_littleEndian) { | |
| 172 for (size_t i = 0; i < length; ++i) { | |
| 173 UChar c = characters[i]; | |
| 174 bytes[i * 2] = static_cast<char>(c); | |
| 175 bytes[i * 2 + 1] = c >> 8; | |
| 176 } | |
| 177 } else { | |
| 178 for (size_t i = 0; i < length; ++i) { | |
| 179 UChar c = characters[i]; | |
| 180 bytes[i * 2] = c >> 8; | |
| 181 bytes[i * 2 + 1] = static_cast<char>(c); | |
| 182 } | |
| 183 } | |
| 184 | |
| 185 return result; | |
| 186 } | |
| 187 | |
| 188 CString TextCodecUTF16::encode(const LChar* characters, | |
| 189 size_t length, | |
| 190 UnencodableHandling) { | |
| 191 // In the LChar case, we do actually need to perform this check in release. :) | |
| 192 RELEASE_ASSERT(length <= numeric_limits<size_t>::max() / 2); | |
| 193 | |
| 194 char* bytes; | |
| 195 CString result = CString::createUninitialized(length * 2, bytes); | |
| 196 | |
| 197 if (m_littleEndian) { | |
| 198 for (size_t i = 0; i < length; ++i) { | |
| 199 bytes[i * 2] = characters[i]; | |
| 200 bytes[i * 2 + 1] = 0; | |
| 201 } | |
| 202 } else { | |
| 203 for (size_t i = 0; i < length; ++i) { | |
| 204 bytes[i * 2] = 0; | |
| 205 bytes[i * 2 + 1] = characters[i]; | |
| 206 } | |
| 207 } | |
| 208 | |
| 209 return result; | |
| 210 } | |
| 211 | |
| 212 } // namespace WTF | |
| OLD | NEW |
|---|
Chromium Code Reviews
Issue 2764283002:
Move files in wtf/ to platform/wtf/ (Part 10). (Closed)
