Fix input and output to handle UTF16 surrogate pairs.

src/unicode.cc

 // Copyright 2012 the V8 project authors. 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
 //       copyright notice, this list of conditions and the following
 //       disclaimer in the documentation and/or other materials provided
@@ skipping 258 matching lines @@
       *cursor += 1;
       return kBadChar;
     }
     *cursor += 4;
     return code_point;
   }
   *cursor += 1;
   return kBadChar;
 }
 
+
 const byte* Utf8::ReadBlock(Buffer<const char*> str, byte* buffer,
     unsigned capacity, unsigned* chars_read_ptr, unsigned* offset_ptr) {
   unsigned offset = *offset_ptr;
   // Bail out early if we've reached the end of the string.
   if (offset == str.length()) {
     *chars_read_ptr = 0;
     return NULL;
   }
   const byte* data = reinterpret_cast<const byte*>(str.data());
   if (data[offset] <= kMaxOneByteChar) {
@@ skipping 42 matching lines @@
 unsigned CharacterStream::Length() {
   unsigned result = 0;
   while (has_more()) {
     result++;
     GetNext();
   }
   Rewind();
   return result;
 }
 
+unsigned CharacterStream::Utf16Length() {
+  unsigned result = 0;
+  while (has_more()) {
+    uchar c = GetNext();
+    result += c > Utf16::kMaxNonSurrogateCharCode ? 2 : 1;
+  }
+  Rewind();
+  return result;
+}
+
 void CharacterStream::Seek(unsigned position) {
   Rewind();
   for (unsigned i = 0; i < position; i++) {
     GetNext();
   }
 }
 
 // Uppercase:            point.category == 'Lu'
 
 static const uint16_t kUppercaseTable0Size = 450;
@@ skipping 1500 matching lines @@
       + kEcma262UnCanonicalizeMultiStrings0Size * sizeof(MultiCharacterSpecialCase<4>)  // NOLINT
       + kEcma262UnCanonicalizeMultiStrings1Size * sizeof(MultiCharacterSpecialCase<2>)  // NOLINT
       + kEcma262UnCanonicalizeMultiStrings5Size * sizeof(MultiCharacterSpecialCase<2>)  // NOLINT
       + kEcma262UnCanonicalizeMultiStrings7Size * sizeof(MultiCharacterSpecialCase<2>)  // NOLINT
       + kCanonicalizationRangeMultiStrings0Size * sizeof(MultiCharacterSpecialCase<1>)  // NOLINT
       + kCanonicalizationRangeMultiStrings1Size * sizeof(MultiCharacterSpecialCase<1>)  // NOLINT
       + kCanonicalizationRangeMultiStrings7Size * sizeof(MultiCharacterSpecialCase<1>); // NOLINT
 }
 
 }  // namespace unicode