WebCore/TextResourceDecoder.h

   1 /*
   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.
   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 "TextDecoder.h"
  27
  28 namespace WebCore {
  29
  30 class TextResourceDecoder : public RefCounted<TextResourceDecoder> {
  31 public:
  32     enum EncodingSource {
  33         DefaultEncoding,
  34         AutoDetectedEncoding,
  35         EncodingFromXMLHeader,
  36         EncodingFromMetaTag,
  37         EncodingFromCSSCharset,
  38         EncodingFromHTTPHeader,
  39         UserChosenEncoding
  40     };
  41
  42     static PassRefPtr<TextResourceDecoder> create(const String& mimeType, const TextEncoding& defaultEncoding = TextEncoding())
  43     {
  44         return adoptRef(new TextResourceDecoder(mimeType, defaultEncoding));
  45     }
  46     ~TextResourceDecoder();
  47
  48     void setEncoding(const TextEncoding&, EncodingSource);
  49     const TextEncoding& encoding() const { return m_decoder.encoding(); }
  50
  51     String decode(const char* data, size_t length);
  52     String flush();
  53
  54     bool sawError() const { return m_sawError; }
  55
  56 private:
  57     TextResourceDecoder(const String& mimeType, const TextEncoding& defaultEncoding);
  58
  59     enum ContentType { PlainText, HTML, XML, CSS }; // PlainText is equivalent to directly using TextDecoder.
  60     static ContentType determineContentType(const String& mimeType);
  61     static const TextEncoding& defaultEncoding(ContentType, const TextEncoding& defaultEncoding);
  62
  63     void checkForBOM(const char*, size_t);
  64     bool checkForCSSCharset(const char*, size_t, bool& movedDataToBuffer);
  65     bool checkForHeadCharset(const char*, size_t, bool& movedDataToBuffer);
  66     void detectJapaneseEncoding(const char*, size_t);
  67
  68     ContentType m_contentType;
  69     TextDecoder m_decoder;
  70     EncodingSource m_source;
  71     Vector<char> m_buffer;
  72     bool m_checkedForBOM;
  73     bool m_checkedForCSSCharset;
  74     bool m_checkedForHeadCharset;
  75     bool m_sawError;
  76 };
  77
  78 }
  79
  80 #endif