OLD | NEW |
1 /* | 1 /* |
2 * Copyright (C) 2010 Google, Inc. All Rights Reserved. | 2 * Copyright (C) 2010 Google, Inc. All Rights Reserved. |
3 * | 3 * |
4 * Redistribution and use in source and binary forms, with or without | 4 * Redistribution and use in source and binary forms, with or without |
5 * modification, are permitted provided that the following conditions | 5 * modification, are permitted provided that the following conditions |
6 * are met: | 6 * are met: |
7 * 1. Redistributions of source code must retain the above copyright | 7 * 1. Redistributions of source code must retain the above copyright |
8 * notice, this list of conditions and the following disclaimer. | 8 * notice, this list of conditions and the following disclaimer. |
9 * 2. Redistributions in binary form must reproduce the above copyright | 9 * 2. Redistributions in binary form must reproduce the above copyright |
10 * notice, this list of conditions and the following disclaimer in the | 10 * notice, this list of conditions and the following disclaimer in the |
(...skipping 22 matching lines...) Expand all Loading... |
33 #include "wtf/text/TextEncodingRegistry.h" | 33 #include "wtf/text/TextEncodingRegistry.h" |
34 | 34 |
35 namespace WebCore { | 35 namespace WebCore { |
36 | 36 |
37 namespace { | 37 namespace { |
38 | 38 |
39 class TitleEncodingFixer { | 39 class TitleEncodingFixer { |
40 public: | 40 public: |
41 explicit TitleEncodingFixer(Document* document) | 41 explicit TitleEncodingFixer(Document* document) |
42 : m_document(document) | 42 : m_document(document) |
43 , m_firstEncoding(document->decoder()->encoding()) | 43 , m_firstEncoding(document->encoding()) |
44 { | 44 { |
45 } | 45 } |
46 | 46 |
47 // It's possible for the encoding of the document to change while we're deco
ding | 47 // It's possible for the encoding of the document to change while we're deco
ding |
48 // data. That can only occur while we're processing the <head> portion of th
e | 48 // data. That can only occur while we're processing the <head> portion of th
e |
49 // document. There isn't much user-visible content in the <head>, but there
is | 49 // document. There isn't much user-visible content in the <head>, but there
is |
50 // the <title> element. This function detects that situation and re-decodes
the | 50 // the <title> element. This function detects that situation and re-decodes
the |
51 // document's title so that the user doesn't see an incorrectly decoded titl
e | 51 // document's title so that the user doesn't see an incorrectly decoded titl
e |
52 // in the title bar. | 52 // in the title bar. |
53 inline void fixTitleEncodingIfNeeded() | 53 inline void fixTitleEncodingIfNeeded() |
54 { | 54 { |
55 if (m_firstEncoding == m_document->decoder()->encoding()) | 55 if (m_firstEncoding == m_document->encoding()) |
56 return; // In the common case, the encoding doesn't change and there
isn't any work to do. | 56 return; // In the common case, the encoding doesn't change and there
isn't any work to do. |
57 fixTitleEncoding(); | 57 fixTitleEncoding(); |
58 } | 58 } |
59 | 59 |
60 private: | 60 private: |
61 void fixTitleEncoding(); | 61 void fixTitleEncoding(); |
62 | 62 |
63 Document* m_document; | 63 Document* m_document; |
64 WTF::TextEncoding m_firstEncoding; | 64 WTF::TextEncoding m_firstEncoding; |
65 }; | 65 }; |
66 | 66 |
67 void TitleEncodingFixer::fixTitleEncoding() | 67 void TitleEncodingFixer::fixTitleEncoding() |
68 { | 68 { |
69 RefPtr<Element> titleElement = m_document->titleElement(); | 69 RefPtr<Element> titleElement = m_document->titleElement(); |
70 if (!titleElement | 70 if (!titleElement |
71 || titleElement->firstElementChild() | 71 || titleElement->firstElementChild() |
72 || m_firstEncoding != Latin1Encoding() | 72 || m_firstEncoding != Latin1Encoding() |
73 || !titleElement->textContent().containsOnlyLatin1()) | 73 || !titleElement->textContent().containsOnlyLatin1()) |
74 return; // Either we don't have a title yet or something bizzare as happ
ened and we give up. | 74 return; // Either we don't have a title yet or something bizzare as happ
ened and we give up. |
75 CString originalBytes = titleElement->textContent().latin1(); | 75 CString originalBytes = titleElement->textContent().latin1(); |
76 OwnPtr<TextCodec> codec = newTextCodec(m_document->decoder()->encoding()); | 76 OwnPtr<TextCodec> codec = newTextCodec(m_document->encoding()); |
77 String correctlyDecodedTitle = codec->decode(originalBytes.data(), originalB
ytes.length(), true); | 77 String correctlyDecodedTitle = codec->decode(originalBytes.data(), originalB
ytes.length(), true); |
78 titleElement->setTextContent(correctlyDecodedTitle, IGNORE_EXCEPTION); | 78 titleElement->setTextContent(correctlyDecodedTitle, IGNORE_EXCEPTION); |
79 } | 79 } |
80 | 80 |
81 } | 81 } |
82 | 82 |
83 DecodedDataDocumentParser::DecodedDataDocumentParser(Document* document) | 83 DecodedDataDocumentParser::DecodedDataDocumentParser(Document* document) |
84 : DocumentParser(document) | 84 : DocumentParser(document) |
85 { | 85 { |
86 } | 86 } |
87 | 87 |
88 size_t DecodedDataDocumentParser::appendBytes(const char* data, size_t length) | 88 size_t DecodedDataDocumentParser::appendBytes(const char* data, size_t length) |
89 { | 89 { |
90 if (!length) | 90 if (!length) |
91 return 0; | 91 return 0; |
92 | 92 |
93 TitleEncodingFixer encodingFixer(document()); | 93 TitleEncodingFixer encodingFixer(document()); |
94 | 94 |
95 String decoded = document()->decoder()->decode(data, length); | 95 String decoded = document()->decoder()->decode(data, length); |
| 96 document()->setEncoding(document()->decoder()->encoding()); |
96 | 97 |
97 encodingFixer.fixTitleEncodingIfNeeded(); | 98 encodingFixer.fixTitleEncodingIfNeeded(); |
98 | 99 |
99 if (decoded.isEmpty()) | 100 if (decoded.isEmpty()) |
100 return 0; | 101 return 0; |
101 | 102 |
102 size_t consumedChars = decoded.length(); | 103 size_t consumedChars = decoded.length(); |
103 append(decoded.releaseImpl()); | 104 append(decoded.releaseImpl()); |
104 | 105 |
105 return consumedChars; | 106 return consumedChars; |
106 } | 107 } |
107 | 108 |
108 size_t DecodedDataDocumentParser::flush() | 109 size_t DecodedDataDocumentParser::flush() |
109 { | 110 { |
110 // null decoder indicates there is no data received. | 111 // null decoder indicates there is no data received. |
111 // We have nothing to do in that case. | 112 // We have nothing to do in that case. |
112 TextResourceDecoder* decoder = document()->decoder(); | 113 TextResourceDecoder* decoder = document()->decoder(); |
113 if (!decoder) | 114 if (!decoder) |
114 return 0; | 115 return 0; |
115 String remainingData = decoder->flush(); | 116 String remainingData = decoder->flush(); |
| 117 document()->setEncoding(document()->decoder()->encoding()); |
116 if (remainingData.isEmpty()) | 118 if (remainingData.isEmpty()) |
117 return 0; | 119 return 0; |
118 | 120 |
119 size_t consumedChars = remainingData.length(); | 121 size_t consumedChars = remainingData.length(); |
120 append(remainingData.releaseImpl()); | 122 append(remainingData.releaseImpl()); |
121 | 123 |
122 return consumedChars; | 124 return consumedChars; |
123 } | 125 } |
124 | 126 |
125 }; | 127 }; |
OLD | NEW |