2 Copyright (C) 1999 Lars Knoll (knoll@mpi-hd.mpg.de)
3 Copyright (C) 2006 Alexey Proskuryakov (ap@nypop.com)
4 Copyright (C) 2006, 2008 Apple Inc. All rights reserved.
6 This library is free software; you can redistribute it and/or
7 modify it under the terms of the GNU Library General Public
8 License as published by the Free Software Foundation; either
9 version 2 of the License, or (at your option) any later version.
11 This library is distributed in the hope that it will be useful,
12 but WITHOUT ANY WARRANTY; without even the implied warranty of
13 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
14 Library General Public License for more details.
16 You should have received a copy of the GNU Library General Public License
17 along with this library; see the file COPYING.LIB. If not, write to
18 the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
19 Boston, MA 02110-1301, USA.
23 #ifndef TextResourceDecoder_h
24 #define TextResourceDecoder_h
26 #include "wtf/RefCounted.h"
27 #include "wtf/text/TextEncoding.h"
31 class HTMLMetaCharsetParser;
33 class TextResourceDecoder {
38 EncodingFromContentSniffing,
39 EncodingFromXMLHeader,
41 EncodingFromCSSCharset,
42 EncodingFromHTTPHeader,
44 EncodingFromParentFrame
47 static PassOwnPtr<TextResourceDecoder> create(const String& mimeType, const WTF::TextEncoding& defaultEncoding = WTF::TextEncoding(), bool usesEncodingDetector = false)
49 return adoptPtr(new TextResourceDecoder(mimeType, defaultEncoding, usesEncodingDetector));
51 ~TextResourceDecoder();
53 void setEncoding(const WTF::TextEncoding&, EncodingSource);
54 const WTF::TextEncoding& encoding() const { return m_encoding; }
55 bool encodingWasDetectedHeuristically() const
57 return m_source == AutoDetectedEncoding
58 || m_source == EncodingFromContentSniffing;
61 String decode(const char* data, size_t length);
64 void setHintEncoding(const WTF::TextEncoding& encoding)
66 m_hintEncoding = encoding.name();
69 void useLenientXMLDecoding() { m_useLenientXMLDecoding = true; }
70 bool sawError() const { return m_sawError; }
73 TextResourceDecoder(const String& mimeType, const WTF::TextEncoding& defaultEncoding, bool usesEncodingDetector);
75 enum ContentType { PlainTextContent, HTMLContent, XMLContent, CSSContent }; // PlainText only checks for BOM.
76 static ContentType determineContentType(const String& mimeType);
77 static const WTF::TextEncoding& defaultEncoding(ContentType, const WTF::TextEncoding& defaultEncoding);
79 size_t checkForBOM(const char*, size_t);
80 bool checkForCSSCharset(const char*, size_t, bool& movedDataToBuffer);
81 bool checkForXMLCharset(const char*, size_t, bool& movedDataToBuffer);
82 void checkForMetaCharset(const char*, size_t);
83 void detectJapaneseEncoding(const char*, size_t);
84 bool shouldAutoDetect() const;
86 ContentType m_contentType;
87 WTF::TextEncoding m_encoding;
88 OwnPtr<TextCodec> m_codec;
89 EncodingSource m_source;
90 const char* m_hintEncoding;
91 Vector<char> m_buffer;
93 bool m_checkedForCSSCharset;
94 bool m_checkedForXMLCharset;
95 bool m_checkedForMetaCharset;
96 bool m_useLenientXMLDecoding; // Don't stop on XML decoding errors.
98 bool m_usesEncodingDetector;
100 OwnPtr<HTMLMetaCharsetParser> m_charsetParser;