1 /*
2 * Copyright (C) 2007, 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 "TextCodecUserDefined.h"
28
29 #include "PlatformString.h"
30 #include <stdio.h>
31 #include <wtf/text/CString.h>
32 #include <wtf/text/StringBuffer.h>
33 #include <wtf/PassOwnPtr.h>
34
35 namespace WebCore {
36
registerEncodingNames(EncodingNameRegistrar registrar)37 void TextCodecUserDefined::registerEncodingNames(EncodingNameRegistrar registrar)
38 {
39 registrar("x-user-defined", "x-user-defined");
40 }
41
newStreamingTextDecoderUserDefined(const TextEncoding &,const void *)42 static PassOwnPtr<TextCodec> newStreamingTextDecoderUserDefined(const TextEncoding&, const void*)
43 {
44 return new TextCodecUserDefined;
45 }
46
registerCodecs(TextCodecRegistrar registrar)47 void TextCodecUserDefined::registerCodecs(TextCodecRegistrar registrar)
48 {
49 registrar("x-user-defined", newStreamingTextDecoderUserDefined, 0);
50 }
51
decode(const char * bytes,size_t length,bool,bool,bool &)52 String TextCodecUserDefined::decode(const char* bytes, size_t length, bool, bool, bool&)
53 {
54 UChar* buffer;
55 String result = String::createUninitialized(length, buffer);
56
57 for (size_t i = 0; i < length; ++i) {
58 signed char c = bytes[i];
59 buffer[i] = c & 0xF7FF;
60 }
61
62 return result;
63 }
64
encodeComplexUserDefined(const UChar * characters,size_t length,UnencodableHandling handling)65 static CString encodeComplexUserDefined(const UChar* characters, size_t length, UnencodableHandling handling)
66 {
67 Vector<char> result(length);
68 char* bytes = result.data();
69
70 size_t resultLength = 0;
71 for (size_t i = 0; i < length; ) {
72 UChar32 c;
73 U16_NEXT(characters, i, length, c);
74 signed char signedByte = c;
75 if ((signedByte & 0xF7FF) == c)
76 bytes[resultLength++] = signedByte;
77 else {
78 // No way to encode this character with x-user-defined.
79 UnencodableReplacementArray replacement;
80 int replacementLength = TextCodec::getUnencodableReplacement(c, handling, replacement);
81 result.grow(resultLength + replacementLength + length - i);
82 bytes = result.data();
83 memcpy(bytes + resultLength, replacement, replacementLength);
84 resultLength += replacementLength;
85 }
86 }
87
88 return CString(bytes, resultLength);
89 }
90
encode(const UChar * characters,size_t length,UnencodableHandling handling)91 CString TextCodecUserDefined::encode(const UChar* characters, size_t length, UnencodableHandling handling)
92 {
93 char* bytes;
94 CString string = CString::newUninitialized(length, bytes);
95
96 // Convert the string a fast way and simultaneously do an efficient check to see if it's all ASCII.
97 UChar ored = 0;
98 for (size_t i = 0; i < length; ++i) {
99 UChar c = characters[i];
100 bytes[i] = c;
101 ored |= c;
102 }
103
104 if (!(ored & 0xFF80))
105 return string;
106
107 // If it wasn't all ASCII, call the function that handles more-complex cases.
108 return encodeComplexUserDefined(characters, length, handling);
109 }
110
111 } // namespace WebCore
112