ES6 unicode extensions, part 1.

src/scanner.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.
 
 // Features shared by parsing and pre-parsing scanners.
 
 #ifndef V8_SCANNER_H_
 #define V8_SCANNER_H_
 
 #include "src/allocation.h"
@@ skipping 440 matching lines @@
   }
   void SetHarmonyNumericLiterals(bool numeric_literals) {
     harmony_numeric_literals_ = numeric_literals;
   }
   bool HarmonyClasses() const {
     return harmony_classes_;
   }
   void SetHarmonyClasses(bool classes) {
     harmony_classes_ = classes;
   }
+  bool HarmonyUnicode() const { return harmony_unicode_; }
+  void SetHarmonyUnicode(bool unicode) { harmony_unicode_ = unicode; }
 
   // Returns true if there was a line terminator before the peek'ed token,
   // possibly inside a multi-line comment.
   bool HasAnyLineTerminatorBeforeNext() const {
     return has_line_terminator_before_next_ ||
            has_multiline_comment_before_next_;
   }
 
   // Scans the input as a regular expression pattern, previous
   // character(s) must be /(=). Returns true if a pattern is scanned.
@@ skipping 133 matching lines @@
   bool is_next_literal_one_byte() {
     DCHECK_NOT_NULL(next_.literal_chars);
     return next_.literal_chars->is_one_byte();
   }
   int next_literal_length() const {
     DCHECK_NOT_NULL(next_.literal_chars);
     return next_.literal_chars->length();
   }
 
   uc32 ScanHexNumber(int expected_length);
+  // Scan a number of any length but not bigger than max_value. For example, the
+  // number can be 000000001, so it's very long in characters but its value is
+  // small.
+  uc32 ScanUnlimitedLengthHexNumber(int max_value);
 
   // Scans a single JavaScript token.
   void Scan();
 
   bool SkipWhiteSpace();
   Token::Value SkipSingleLineComment();
   Token::Value SkipSourceURLComment();
   void TryToParseSourceURLComment();
   Token::Value SkipMultiLineComment();
   // Scans a possible HTML comment -- begins with '<!'.
   Token::Value ScanHtmlComment();
 
   void ScanDecimalDigits();
   Token::Value ScanNumber(bool seen_period);
   Token::Value ScanIdentifierOrKeyword();
   Token::Value ScanIdentifierSuffix(LiteralScope* literal);
 
   Token::Value ScanString();
 
   // Scans an escape-sequence which is part of a string and adds the
   // decoded character to the current literal. Returns true if a pattern
   // is scanned.
   bool ScanEscape();
   // Decodes a Unicode escape-sequence which is part of an identifier.
   // If the escape sequence cannot be decoded the result is kBadChar.
   uc32 ScanIdentifierUnicodeEscape();
+  // Helper for the above functions.
+  uc32 ScanUnicodeEscape();
 
   // Return the current source position.
   int source_pos() {
     return source_->pos() - kCharacterLookaheadBufferSize;
   }
 
   UnicodeCache* unicode_cache_;
 
   // Buffers collecting literal strings, numbers, etc.
   LiteralBuffer literal_buffer1_;
@@ skipping 24 matching lines @@
   // line-terminator after the current token, and before the next.
   bool has_multiline_comment_before_next_;
   // Whether we scan 'let' as a keyword for harmony block-scoped let bindings.
   bool harmony_scoping_;
   // Whether we scan 'module', 'import', 'export' as keywords.
   bool harmony_modules_;
   // Whether we scan 0o777 and 0b111 as numbers.
   bool harmony_numeric_literals_;
   // Whether we scan 'class', 'extends', 'static' and 'super' as keywords.
   bool harmony_classes_;
+  // Whether we allow \u{xxxxx}.
+  bool harmony_unicode_;
 };
 
 } }  // namespace v8::internal
 
 #endif  // V8_SCANNER_H_