1/*
2 * Copyright (C) 2004-2019 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 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 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 <wtf/text/CString.h>
30#include <wtf/text/WTFString.h>
31
32namespace WebCore {
33
34inline TextCodecUTF16::TextCodecUTF16(bool littleEndian)
35 : m_littleEndian(littleEndian)
36{
37}
38
39void TextCodecUTF16::registerEncodingNames(EncodingNameRegistrar registrar)
40{
41 registrar("UTF-16LE", "UTF-16LE");
42 registrar("UTF-16BE", "UTF-16BE");
43
44 registrar("ISO-10646-UCS-2", "UTF-16LE");
45 registrar("UCS-2", "UTF-16LE");
46 registrar("UTF-16", "UTF-16LE");
47 registrar("Unicode", "UTF-16LE");
48 registrar("csUnicode", "UTF-16LE");
49 registrar("unicodeFEFF", "UTF-16LE");
50
51 registrar("unicodeFFFE", "UTF-16BE");
52}
53
54void TextCodecUTF16::registerCodecs(TextCodecRegistrar registrar)
55{
56 registrar("UTF-16LE", [] {
57 return std::make_unique<TextCodecUTF16>(true);
58 });
59 registrar("UTF-16BE", [] {
60 return std::make_unique<TextCodecUTF16>(false);
61 });
62}
63
64String TextCodecUTF16::decode(const char* bytes, size_t length, bool, bool, bool&)
65{
66 if (!length)
67 return String();
68
69 // FIXME: This should generate an error if there is an unpaired surrogate.
70
71 const unsigned char* p = reinterpret_cast<const unsigned char*>(bytes);
72 size_t numBytes = length + m_haveBufferedByte;
73 size_t numCodeUnits = numBytes / 2;
74 RELEASE_ASSERT(numCodeUnits <= std::numeric_limits<unsigned>::max());
75
76 UChar* q;
77 auto result = String::createUninitialized(numCodeUnits, q);
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 numCodeUnits -= 1;
89 }
90
91 if (m_littleEndian) {
92 for (size_t i = 0; i < numCodeUnits; ++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 < numCodeUnits; ++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 return result;
112}
113
114Vector<uint8_t> TextCodecUTF16::encode(StringView string, UnencodableHandling)
115{
116 Vector<uint8_t> result(WTF::checkedProduct<size_t>(string.length(), 2).unsafeGet());
117 auto* bytes = result.data();
118
119 if (m_littleEndian) {
120 for (auto character : string.codeUnits()) {
121 *bytes++ = character;
122 *bytes++ = character >> 8;
123 }
124 } else {
125 for (auto character : string.codeUnits()) {
126 *bytes++ = character >> 8;
127 *bytes++ = character;
128 }
129 }
130
131 return result;
132}
133
134} // namespace WebCore
135