1 /* 2 Copyright (C) 1999 Lars Knoll (knoll (at) mpi-hd.mpg.de) 3 Copyright (C) 2006 Alexey Proskuryakov (ap (at) nypop.com) 4 Copyright (C) 2006, 2008 Apple Inc. All rights reserved. 5 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. 10 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. 15 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. 20 21 */ 22 23 #ifndef TextResourceDecoder_h 24 #define TextResourceDecoder_h 25 26 #include "wtf/RefCounted.h" 27 #include "wtf/text/TextEncoding.h" 28 29 namespace WebCore { 30 31 class HTMLMetaCharsetParser; 32 33 class TextResourceDecoder : public RefCounted<TextResourceDecoder> { 34 public: 35 enum EncodingSource { 36 DefaultEncoding, 37 AutoDetectedEncoding, 38 EncodingFromContentSniffing, 39 EncodingFromXMLHeader, 40 EncodingFromMetaTag, 41 EncodingFromCSSCharset, 42 EncodingFromHTTPHeader, 43 UserChosenEncoding, 44 EncodingFromParentFrame 45 }; 46 47 static PassRefPtr<TextResourceDecoder> create(const String& mimeType, const WTF::TextEncoding& defaultEncoding = WTF::TextEncoding(), bool usesEncodingDetector = false) 48 { 49 return adoptRef(new TextResourceDecoder(mimeType, defaultEncoding, usesEncodingDetector)); 50 } 51 ~TextResourceDecoder(); 52 53 void setEncoding(const WTF::TextEncoding&, EncodingSource); 54 const WTF::TextEncoding& encoding() const { return m_encoding; } 55 56 String decode(const char* data, size_t length); 57 String flush(); 58 59 void setHintEncoding(const TextResourceDecoder* hintDecoder) 60 { 61 // hintEncoding is for use with autodetection, which should be 62 // only invoked when hintEncoding comes from auto-detection. 63 if (hintDecoder && hintDecoder->wasDetectedHueristically()) 64 m_hintEncoding = hintDecoder->encoding().name(); 65 } 66 67 void useLenientXMLDecoding() { m_useLenientXMLDecoding = true; } 68 bool sawError() const { return m_sawError; } 69 70 private: 71 TextResourceDecoder(const String& mimeType, const WTF::TextEncoding& defaultEncoding, bool usesEncodingDetector); 72 73 enum ContentType { PlainText, HTML, XML, CSS }; // PlainText only checks for BOM. 74 static ContentType determineContentType(const String& mimeType); 75 static const WTF::TextEncoding& defaultEncoding(ContentType, const WTF::TextEncoding& defaultEncoding); 76 77 bool wasDetectedHueristically() const { return m_source == AutoDetectedEncoding || m_source == EncodingFromContentSniffing; } 78 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; 85 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; 92 bool m_checkedForBOM; 93 bool m_checkedForCSSCharset; 94 bool m_checkedForXMLCharset; 95 bool m_checkedForMetaCharset; 96 bool m_useLenientXMLDecoding; // Don't stop on XML decoding errors. 97 bool m_sawError; 98 bool m_usesEncodingDetector; 99 100 OwnPtr<HTMLMetaCharsetParser> m_charsetParser; 101 }; 102 103 } 104 105 #endif 106
