1 /*
2 * Copyright (C) 2004, 2006, 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 "config.h"
27 #include "TextCodecUTF16.h"
28
29 #include "CString.h"
30 #include "PlatformString.h"
31 #include "StringBuffer.h"
32 #include <wtf/PassOwnPtr.h>
33
34 namespace WebCore {
35
registerEncodingNames(EncodingNameRegistrar registrar)36 void TextCodecUTF16::registerEncodingNames(EncodingNameRegistrar registrar)
37 {
38 registrar("UTF-16LE", "UTF-16LE");
39 registrar("UTF-16BE", "UTF-16BE");
40
41 registrar("ISO-10646-UCS-2", "UTF-16LE");
42 registrar("UCS-2", "UTF-16LE");
43 registrar("UTF-16", "UTF-16LE");
44 registrar("Unicode", "UTF-16LE");
45 registrar("csUnicode", "UTF-16LE");
46 registrar("unicodeFEFF", "UTF-16LE");
47
48 registrar("unicodeFFFE", "UTF-16BE");
49 }
50
newStreamingTextDecoderUTF16LE(const TextEncoding &,const void *)51 static PassOwnPtr<TextCodec> newStreamingTextDecoderUTF16LE(const TextEncoding&, const void*)
52 {
53 return new TextCodecUTF16(true);
54 }
55
newStreamingTextDecoderUTF16BE(const TextEncoding &,const void *)56 static PassOwnPtr<TextCodec> newStreamingTextDecoderUTF16BE(const TextEncoding&, const void*)
57 {
58 return new TextCodecUTF16(false);
59 }
60
registerCodecs(TextCodecRegistrar registrar)61 void TextCodecUTF16::registerCodecs(TextCodecRegistrar registrar)
62 {
63 registrar("UTF-16LE", newStreamingTextDecoderUTF16LE, 0);
64 registrar("UTF-16BE", newStreamingTextDecoderUTF16BE, 0);
65 }
66
decode(const char * bytes,size_t length,bool,bool,bool &)67 String TextCodecUTF16::decode(const char* bytes, size_t length, bool, bool, bool&)
68 {
69 if (!length)
70 return String();
71
72 const unsigned char* p = reinterpret_cast<const unsigned char*>(bytes);
73 size_t numBytes = length + m_haveBufferedByte;
74 size_t numChars = numBytes / 2;
75
76 StringBuffer buffer(numChars);
77 UChar* q = buffer.characters();
78
79 if (m_haveBufferedByte) {
80 UChar c;
81 if (m_littleEndian)
82 c = m_bufferedByte | (p[0] << 8);
83 else
84 c = (m_bufferedByte << 8) | p[0];
85 *q++ = c;
86 m_haveBufferedByte = false;
87 p += 1;
88 numChars -= 1;
89 }
90
91 if (m_littleEndian) {
92 for (size_t i = 0; i < numChars; ++i) {
93 UChar c = p[0] | (p[1] << 8);
94 p += 2;
95 *q++ = c;
96 }
97 } else {
98 for (size_t i = 0; i < numChars; ++i) {
99 UChar c = (p[0] << 8) | p[1];
100 p += 2;
101 *q++ = c;
102 }
103 }
104
105 if (numBytes & 1) {
106 ASSERT(!m_haveBufferedByte);
107 m_haveBufferedByte = true;
108 m_bufferedByte = p[0];
109 }
110
111 buffer.shrink(q - buffer.characters());
112
113 return String::adopt(buffer);
114 }
115
encode(const UChar * characters,size_t length,UnencodableHandling)116 CString TextCodecUTF16::encode(const UChar* characters, size_t length, UnencodableHandling)
117 {
118 char* bytes;
119 CString string = CString::newUninitialized(length * 2, bytes);
120
121 // FIXME: CString is not a reasonable data structure for encoded UTF-16, which will have
122 // null characters inside it. Perhaps the result of encode should not be a CString?
123 if (m_littleEndian)
124 for (size_t i = 0; i < length; ++i) {
125 UChar c = characters[i];
126 bytes[i * 2] = c;
127 bytes[i * 2 + 1] = c >> 8;
128 }
129 else
130 for (size_t i = 0; i < length; ++i) {
131 UChar c = characters[i];
132 bytes[i * 2] = c >> 8;
133 bytes[i * 2 + 1] = c;
134 }
135
136 return string;
137 }
138
139 } // namespace WebCore
140