[regexp] correctly parse non-BMP unicode escapes in atoms.

src/parsing/scanner-character-streams.cc

 // 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.
 
 #include "src/parsing/scanner-character-streams.h"
 
 #include "include/v8.h"
 #include "src/globals.h"
 #include "src/handles.h"
 #include "src/list-inl.h"  // TODO(mstarzinger): Temporary cycle breaker!
@@ skipping 175 matching lines @@
   ReadBlock();
 }
 
 
 Utf8ToUtf16CharacterStream::~Utf8ToUtf16CharacterStream() { }
 
 
 size_t Utf8ToUtf16CharacterStream::CopyChars(uint16_t* dest, size_t length,
                                              const byte* src, size_t* src_pos,
                                              size_t src_length) {
-  static const unibrow::uchar kMaxUtf16Character = 0xffff;
+  static const unibrow::uchar kMaxUtf16Character =
+      unibrow::Utf16::kMaxNonSurrogateCharCode;
   size_t i = 0;
   // Because of the UTF-16 lead and trail surrogates, we stop filling the buffer
   // one character early (in the normal case), because we need to have at least
   // two free spaces in the buffer to be sure that the next character will fit.
   while (i < length - 1) {
     if (*src_pos == src_length) break;
     unibrow::uchar c = src[*src_pos];
     if (c <= unibrow::Utf8::kMaxOneByteChar) {
       *src_pos = *src_pos + 1;
     } else {
@@ skipping 372 matching lines @@
 }
 
 
 void ExternalTwoByteStringUtf16CharacterStream::ResetToBookmark() {
   DCHECK(bookmark_ != kNoBookmark);
   pos_ = bookmark_;
   buffer_cursor_ = raw_data_ + bookmark_;
 }
 }  // namespace internal
 }  // namespace v8