Script streaming: remove byte order marks, detect encoding based on them.

Source/core/html/parser/TextResourceDecoder.h

 /*
     Copyright (C) 1999 Lars Knoll (knoll@mpi-hd.mpg.de)
     Copyright (C) 2006 Alexey Proskuryakov (ap@nypop.com)
     Copyright (C) 2006, 2008 Apple Inc. All rights reserved.
 
     This library is free software; you can redistribute it and/or
     modify it under the terms of the GNU Library General Public
     License as published by the Free Software Foundation; either
     version 2 of the License, or (at your option) any later version.
 
@@ skipping 50 matching lines @@
     String decode(const char* data, size_t length);
     String flush();
 
     void setHintEncoding(const WTF::TextEncoding& encoding)
     {
         m_hintEncoding = encoding.name();
     }
 
     void useLenientXMLDecoding() { m_useLenientXMLDecoding = true; }
     bool sawError() const { return m_sawError; }
+    size_t checkForBOM(const char*, size_t);

[marja, 2014/11/07 13:32:35]

This is sad, but I don't see any other way :(

decode() is a public function which calls this function, but we cannot decode
the full data and try to infer whether BOM was there or not.

Also, I don't think we can try to decode less-than-full data because we don't
know how long the BOM might be, and we don't want to pass incomplete UTF-8 chars
to the decoder.

 
 private:
     TextResourceDecoder(const String& mimeType, const WTF::TextEncoding& defaultEncoding, bool usesEncodingDetector);
 
     enum ContentType { PlainTextContent, HTMLContent, XMLContent, CSSContent }; // PlainText only checks for BOM.
     static ContentType determineContentType(const String& mimeType);
     static const WTF::TextEncoding& defaultEncoding(ContentType, const WTF::TextEncoding& defaultEncoding);
 
-    size_t checkForBOM(const char*, size_t);
     bool checkForCSSCharset(const char*, size_t, bool& movedDataToBuffer);
     bool checkForXMLCharset(const char*, size_t, bool& movedDataToBuffer);
     void checkForMetaCharset(const char*, size_t);
     void detectJapaneseEncoding(const char*, size_t);
     bool shouldAutoDetect() const;
 
     ContentType m_contentType;
     WTF::TextEncoding m_encoding;
     OwnPtr<TextCodec> m_codec;
     EncodingSource m_source;
     const char* m_hintEncoding;
     Vector<char> m_buffer;
     bool m_checkedForBOM;
     bool m_checkedForCSSCharset;
     bool m_checkedForXMLCharset;
     bool m_checkedForMetaCharset;
     bool m_useLenientXMLDecoding; // Don't stop on XML decoding errors.
     bool m_sawError;
     bool m_usesEncodingDetector;
 
     OwnPtr<HTMLMetaCharsetParser> m_charsetParser;
 };
 
 }
 
 #endif