[wasm] Add UTF-8 validation

src/unicode.h

 // Copyright 2011 the V8 project authors. All rights reserved.
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file.
 
 #ifndef V8_UNICODE_H_
 #define V8_UNICODE_H_
 
 #include <sys/types.h>
 #include "src/globals.h"
 #include "src/utils.h"
@@ skipping 137 matching lines @@
   static const unsigned kMaxFourByteChar  = 0x1fffff;
 
   // A single surrogate is coded as a 3 byte UTF-8 sequence, but two together
   // that match are coded as a 4 byte UTF-8 sequence.
   static const unsigned kBytesSavedByCombiningSurrogates = 2;
   static const unsigned kSizeOfUnmatchedSurrogate = 3;
   // The maximum size a single UTF-16 code unit may take up when encoded as
   // UTF-8.
   static const unsigned kMax16BitCodeUnitSize  = 3;
   static inline uchar ValueOf(const byte* str, size_t length, size_t* cursor);
+
+  // Excludes non-characters from the set of valid code points.
+  static inline bool IsValidCharacter(uchar c);
+
+  static bool Validate(const byte* str, size_t length);
 };
 
 struct Uppercase {
   static bool Is(uchar c);
 };
 struct Lowercase {
   static bool Is(uchar c);
 };
 struct Letter {
   static bool Is(uchar c);
@@ skipping 44 matching lines @@
   static const int kMaxWidth = 1;
   static int Convert(uchar c,
                      uchar n,
                      uchar* result,
                      bool* allow_caching_ptr);
 };
 
 }  // namespace unibrow
 
 #endif  // V8_UNICODE_H_