UTF-8 detector for pages missing encoding info

third_party/WebKit/Source/platform/text/TextEncodingDetector.h

 /*
  * Copyright (C) 2009 Google Inc. All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
  * modification, are permitted provided that the following conditions are
  * met:
  *
  *     * Redistributions of source code must retain the above copyright
  * notice, this list of conditions and the following disclaimer.
  *     * Redistributions in binary form must reproduce the above
@@ skipping 29 matching lines @@
 
 namespace blink {
 
 // Given a sequence of bytes in |data| of length |len| and an optional
 // hintEncodingName, detect the most likely character encoding.
 // The way hintEncodingName is used is up to an implementation.
 // Currently, the only caller sets it to the parent frame encoding.
 PLATFORM_EXPORT bool detectTextEncoding(const char* data, size_t length,
     const char* hintEncodingName, WTF::TextEncoding* detectedEncoding);
 
+// Given a sequence of bytes in |data| of length |len|, check if
+// the content is encoded in UTF-8. Pure ASCII text is not regarded
+// as UTF-8 in order to respect the default encoding since it can be
+// of any encoding.
+PLATFORM_EXPORT bool isUTF8Encoded(const char* data, size_t length);
+
 } // namespace blink
 
 #endif