1 /*
2 * Copyright (C) 2010 Company 100, 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 "TextCodecBrew.h"
28
29 #include "AEEAppGen.h"
30 #include "AEEICharsetConv.h"
31 #include "NotImplemented.h"
32 #include "PlatformString.h"
33 #include <wtf/Assertions.h>
34 #include <wtf/text/CString.h>
35
36 namespace WebCore {
37
38 // FIXME: Not sure if there are Brew MP devices which use big endian.
39 const char* WebCore::TextCodecBrew::m_internalEncodingName = "UTF-16LE";
40
newTextCodecBrew(const TextEncoding & encoding,const void *)41 static PassOwnPtr<TextCodec> newTextCodecBrew(const TextEncoding& encoding, const void*)
42 {
43 return new TextCodecBrew(encoding);
44 }
45
registerExtendedEncodingNames(EncodingNameRegistrar registrar)46 void TextCodecBrew::registerExtendedEncodingNames(EncodingNameRegistrar registrar)
47 {
48 // FIXME: Not sure how to enumerate all available encodings.
49 notImplemented();
50 }
51
registerExtendedCodecs(TextCodecRegistrar registrar)52 void TextCodecBrew::registerExtendedCodecs(TextCodecRegistrar registrar)
53 {
54 notImplemented();
55 }
56
TextCodecBrew(const TextEncoding & encoding)57 TextCodecBrew::TextCodecBrew(const TextEncoding& encoding)
58 : m_charsetConverter(0)
59 , m_encoding(encoding)
60 , m_numBufferedBytes(0)
61 {
62 String format = String::format("%s>%s", encoding.name(), m_internalEncodingName);
63
64 IShell* shell = reinterpret_cast<AEEApplet*>(GETAPPINSTANCE())->m_pIShell;
65 AEECLSID classID = ISHELL_GetHandler(shell, AEEIID_ICharsetConv, format.latin1().data());
66 ISHELL_CreateInstance(shell, classID, reinterpret_cast<void**>(&m_charsetConverter));
67
68 ASSERT(m_charsetConverter);
69 }
70
~TextCodecBrew()71 TextCodecBrew::~TextCodecBrew()
72 {
73 if (m_charsetConverter)
74 ICharsetConv_Release(m_charsetConverter);
75 }
76
decode(const char * bytes,size_t length,bool flush,bool stopOnError,bool & sawError)77 String TextCodecBrew::decode(const char* bytes, size_t length, bool flush, bool stopOnError, bool& sawError)
78 {
79 int code = ICharsetConv_Initialize(m_charsetConverter, m_encoding.name(), m_internalEncodingName, 0);
80 ASSERT(code == AEE_SUCCESS);
81
82 Vector<UChar> result;
83 Vector<unsigned char> prefixedBytes(length);
84
85 int srcSize;
86 unsigned char* srcBegin;
87
88 if (m_numBufferedBytes) {
89 srcSize = length + m_numBufferedBytes;
90 prefixedBytes.grow(srcSize);
91 memcpy(prefixedBytes.data(), m_bufferedBytes, m_numBufferedBytes);
92 memcpy(prefixedBytes.data() + m_numBufferedBytes, bytes, length);
93
94 srcBegin = prefixedBytes.data();
95
96 // all buffered bytes are consumed now
97 m_numBufferedBytes = 0;
98 } else {
99 srcSize = length;
100 srcBegin = const_cast<unsigned char*>(reinterpret_cast<const unsigned char*>(bytes));
101 }
102
103 unsigned char* src = srcBegin;
104 unsigned char* srcEnd = srcBegin + srcSize;
105
106 Vector<UChar> dstBuffer(srcSize);
107
108 while (src < srcEnd) {
109 int numCharsConverted;
110 unsigned char* dstBegin = reinterpret_cast<unsigned char*>(dstBuffer.data());
111 unsigned char* dst = dstBegin;
112 int dstSize = dstBuffer.size() * sizeof(UChar);
113
114 code = ICharsetConv_CharsetConvert(m_charsetConverter, &src, &srcSize, &dst, &dstSize, &numCharsConverted);
115 ASSERT(code != AEE_ENOSUCH);
116
117 if (code == AEE_EBUFFERTOOSMALL) {
118 // Increase the buffer and try it again.
119 dstBuffer.grow(dstBuffer.size() * 2);
120 continue;
121 }
122
123 if (code == AEE_EBADITEM) {
124 sawError = true;
125 if (stopOnError) {
126 result.append(L'?');
127 break;
128 }
129
130 src++;
131 }
132
133 if (code == AEE_EINCOMPLETEITEM) {
134 if (flush) {
135 LOG_ERROR("Partial bytes at end of input while flush requested.");
136 sawError = true;
137 return String();
138 }
139
140 m_numBufferedBytes = srcEnd - src;
141 memcpy(m_bufferedBytes, src, m_numBufferedBytes);
142 break;
143 }
144
145 int numChars = (dst - dstBegin) / sizeof(UChar);
146 if (numChars > 0)
147 result.append(dstBuffer.data(), numChars);
148 }
149
150 return String::adopt(result);
151 }
152
encode(const UChar * characters,size_t length,UnencodableHandling handling)153 CString TextCodecBrew::encode(const UChar* characters, size_t length, UnencodableHandling handling)
154 {
155 if (!length)
156 return "";
157
158 unsigned int replacementCharacter = '?';
159
160 // FIXME: Impossible to handle EntitiesForUnencodables or URLEncodedEntitiesForUnencodables with ICharsetConv.
161 int code = ICharsetConv_Initialize(m_charsetConverter, m_internalEncodingName, m_encoding.name(), replacementCharacter);
162 ASSERT(code == AEE_SUCCESS);
163
164 Vector<char> result;
165
166 int srcSize = length * sizeof(UChar);
167 unsigned char* srcBegin = const_cast<unsigned char*>(reinterpret_cast<const unsigned char*>(characters));
168 unsigned char* src = srcBegin;
169 unsigned char* srcEnd = srcBegin + srcSize;
170
171 Vector<unsigned char> dstBuffer(length * sizeof(UChar));
172
173 while (src < srcEnd) {
174 int numCharsConverted;
175 unsigned char* dstBegin = dstBuffer.data();
176 unsigned char* dst = dstBegin;
177 int dstSize = dstBuffer.size();
178
179 code = ICharsetConv_CharsetConvert(m_charsetConverter, &src, &srcSize, &dst, &dstSize, &numCharsConverted);
180 ASSERT(code != AEE_EINCOMPLETEITEM);
181
182 if (code == AEE_ENOSUCH) {
183 LOG_ERROR("Conversion error, Code=%d", code);
184 return CString();
185 }
186
187 if (code == AEE_EBUFFERTOOSMALL) {
188 // Increase the buffer and try it again.
189 dstBuffer.grow(dstBuffer.size() * 2);
190 continue;
191 }
192
193 if (code == AEE_EBADITEM)
194 src += sizeof(UChar); // Skip the invalid character
195
196 int numBytes = dst - dstBegin;
197 if (numBytes > 0)
198 result.append(dstBuffer.data(), numBytes);
199 }
200
201 return CString(result.data(), result.size());
202 }
203
204 } // namespace WebCore
205