Home | History | Annotate | Download | only in text 
      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 "config.h"
     27 #include "wtf/text/TextCodecUTF16.h"
     28 
     29 #include "wtf/PassOwnPtr.h"
     30 #include "wtf/text/CString.h"
     31 #include "wtf/text/StringBuffer.h"
     32 #include "wtf/text/WTFString.h"
     33 
     34 using namespace std;
     35 
     36 namespace WTF {
     37 
     38 void TextCodecUTF16::registerEncodingNames(EncodingNameRegistrar registrar)
     39 {
     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 PassOwnPtr<TextCodec> newStreamingTextDecoderUTF16LE(const TextEncoding&, const void*)
     54 {
     55     return adoptPtr(new TextCodecUTF16(true));
     56 }
     57 
     58 static PassOwnPtr<TextCodec> newStreamingTextDecoderUTF16BE(const TextEncoding&, const void*)
     59 {
     60     return adoptPtr(new TextCodecUTF16(false));
     61 }
     62 
     63 void TextCodecUTF16::registerCodecs(TextCodecRegistrar registrar)
     64 {
     65     registrar("UTF-16LE", newStreamingTextDecoderUTF16LE, 0);
     66     registrar("UTF-16BE", newStreamingTextDecoderUTF16BE, 0);
     67 }
     68 
     69 String TextCodecUTF16::decode(const char* bytes, size_t length, bool, bool, bool&)
     70 {
     71     if (!length)
     72         return String();
     73 
     74     // FIXME: This should generate an error if there is an unpaired surrogate.
     75 
     76     const unsigned char* p = reinterpret_cast<const unsigned char*>(bytes);
     77     size_t numBytes = length + m_haveBufferedByte;
     78     size_t numChars = numBytes / 2;
     79 
     80     StringBuffer<UChar> buffer(numChars);
     81     UChar* q = buffer.characters();
     82 
     83     if (m_haveBufferedByte) {
     84         UChar c;
     85         if (m_littleEndian)
     86             c = m_bufferedByte | (p[0] << 8);
     87         else
     88             c = (m_bufferedByte << 8) | p[0];
     89         *q++ = c;
     90         m_haveBufferedByte = false;
     91         p += 1;
     92         numChars -= 1;
     93     }
     94 
     95     if (m_littleEndian) {
     96         for (size_t i = 0; i < numChars; ++i) {
     97             UChar c = p[0] | (p[1] << 8);
     98             p += 2;
     99             *q++ = c;
    100         }
    101     } else {
    102         for (size_t i = 0; i < numChars; ++i) {
    103             UChar c = (p[0] << 8) | p[1];
    104             p += 2;
    105             *q++ = c;
    106         }
    107     }
    108 
    109     if (numBytes & 1) {
    110         ASSERT(!m_haveBufferedByte);
    111         m_haveBufferedByte = true;
    112         m_bufferedByte = p[0];
    113     }
    114 
    115     buffer.shrink(q - buffer.characters());
    116 
    117     return String::adopt(buffer);
    118 }
    119 
    120 CString TextCodecUTF16::encode(const UChar* characters, size_t length, UnencodableHandling)
    121 {
    122     // We need to be sure we can double the length without overflowing.
    123     // Since the passed-in length is the length of an actual existing
    124     // character buffer, each character is two bytes, and we know
    125     // the buffer doesn't occupy the entire address space, we can
    126     // assert here that doubling the length does not overflow size_t
    127     // and there's no need for a runtime check.
    128     ASSERT(length <= numeric_limits<size_t>::max() / 2);
    129 
    130     char* bytes;
    131     CString result = CString::newUninitialized(length * 2, bytes);
    132 
    133     // FIXME: CString is not a reasonable data structure for encoded UTF-16, which will have
    134     // null characters inside it. Perhaps the result of encode should not be a CString.
    135     if (m_littleEndian) {
    136         for (size_t i = 0; i < length; ++i) {
    137             UChar c = characters[i];
    138             bytes[i * 2] = c;
    139             bytes[i * 2 + 1] = c >> 8;
    140         }
    141     } else {
    142         for (size_t i = 0; i < length; ++i) {
    143             UChar c = characters[i];
    144             bytes[i * 2] = c >> 8;
    145             bytes[i * 2 + 1] = c;
    146         }
    147     }
    148 
    149     return result;
    150 }
    151 
    152 CString TextCodecUTF16::encode(const LChar* characters, size_t length, UnencodableHandling)
    153 {
    154     // In the LChar case, we do actually need to perform this check in release.  :)
    155     RELEASE_ASSERT(length <= numeric_limits<size_t>::max() / 2);
    156 
    157     char* bytes;
    158     CString result = CString::newUninitialized(length * 2, bytes);
    159 
    160     if (m_littleEndian) {
    161         for (size_t i = 0; i < length; ++i) {
    162             bytes[i * 2] = characters[i];
    163             bytes[i * 2 + 1] = 0;
    164         }
    165     } else {
    166         for (size_t i = 0; i < length; ++i) {
    167             bytes[i * 2] = 0;
    168             bytes[i * 2 + 1] = characters[i];
    169         }
    170     }
    171 
    172     return result;
    173 }
    174 
    175 } // namespace WTF
    176