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 "TextEncoding.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         EncodingFromParentFrame

    41     };

    42 

    43     static PassRefPtr<TextResourceDecoder> create(const String& mimeType, const TextEncoding& defaultEncoding = TextEncoding(), bool usesEncodingDetector = false)

    44     {

    45         return adoptRef(new TextResourceDecoder(mimeType, defaultEncoding, usesEncodingDetector));

    46     }

    47     ~TextResourceDecoder();

    48 

    49     void setEncoding(const TextEncoding&, EncodingSource);

    50     const TextEncoding& encoding() const { return m_encoding; }

    51 

    52     String decode(const char* data, size_t length);

    53     String flush();

    54 

    55     void setHintEncoding(const TextResourceDecoder* hintDecoder)

    56     {

    57         // hintEncoding is for use with autodetection, which should be 

    58         // only invoked when hintEncoding comes from auto-detection.

    59         if (hintDecoder && hintDecoder->m_source == AutoDetectedEncoding)

    60             m_hintEncoding = hintDecoder->encoding().name();

    61     }

    62    

    63     void useLenientXMLDecoding() { m_useLenientXMLDecoding = true; }

    64     bool sawError() const { return m_sawError; }

    65 

    66 private:

    67     TextResourceDecoder(const String& mimeType, const TextEncoding& defaultEncoding,

    68                         bool usesEncodingDetector);

    69 

    70     enum ContentType { PlainText, HTML, XML, CSS }; // PlainText only checks for BOM.

    71     static ContentType determineContentType(const String& mimeType);

    72     static const TextEncoding& defaultEncoding(ContentType, const TextEncoding& defaultEncoding);

    73 

    74     size_t checkForBOM(const char*, size_t);

    75     bool checkForCSSCharset(const char*, size_t, bool& movedDataToBuffer);

    76     bool checkForHeadCharset(const char*, size_t, bool& movedDataToBuffer);

    77     void detectJapaneseEncoding(const char*, size_t);

    78     bool shouldAutoDetect() const;

    79 

    80     ContentType m_contentType;

    81     TextEncoding m_encoding;

    82     OwnPtr<TextCodec> m_codec;

    83     EncodingSource m_source;

    84     const char* m_hintEncoding;

    85     Vector<char> m_buffer;

    86     bool m_checkedForBOM;

    87     bool m_checkedForCSSCharset;

    88     bool m_checkedForHeadCharset;

    89     bool m_useLenientXMLDecoding; // Don't stop on XML decoding errors.

    90     bool m_sawError;

    91     bool m_usesEncodingDetector;

    92 };

    93 

    94 }

    95 

    96 #endif