NewGC: Merge bleeding edge up to 9009.

src/scanner-base.h

 // Copyright 2011 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 401 matching lines @@
   inline Token::Value Select(uc32 next, Token::Value then, Token::Value else_) {
     Advance();
     if (c0_ == next) {
       Advance();
       return then;
     } else {
       return else_;
     }
   }
 
-  uc32 ScanHexEscape(uc32 c, int length);
+  uc32 ScanHexNumber(int expected_length);
 
   // 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 67 matching lines @@
   // Returns the location of the last seen octal literal
   Location octal_position() const { return octal_pos_; }
   void clear_octal_position() { octal_pos_ = Location::invalid(); }
 
   // Seek forward to the given position.  This operation does not
   // work in general, for instance when there are pushed back
   // characters, but works for seeking forward until simple delimiter
   // tokens, which is what it is used for.
   void SeekForward(int pos);
 
+  bool HarmonyBlockScoping() const {
+    return harmony_block_scoping_;
+  }
+  void SetHarmonyBlockScoping(bool block_scoping) {
+    harmony_block_scoping_ = block_scoping;
+  }
+
+
  protected:
   bool SkipWhiteSpace();
   Token::Value SkipSingleLineComment();
   Token::Value SkipMultiLineComment();
 
   // Scans a single JavaScript token.
   void Scan();
 
   void ScanDecimalDigits();
   Token::Value ScanNumber(bool seen_period);
   Token::Value ScanIdentifierOrKeyword();
   Token::Value ScanIdentifierSuffix(LiteralScope* literal);
 
   void ScanEscape();
   Token::Value ScanString();
 
   // Scans a possible HTML comment -- begins with '<!'.
   Token::Value ScanHtmlComment();
 
   // Decodes a unicode escape-sequence which is part of an identifier.
   // If the escape sequence cannot be decoded the result is kBadChar.
   uc32 ScanIdentifierUnicodeEscape();
+  // Recognizes a uniocde escape-sequence and adds its characters,
+  // uninterpreted, to the current literal. Used for parsing RegExp
+  // flags.
+  bool ScanLiteralUnicodeEscape();
 
   // Start position of the octal literal last scanned.
   Location octal_pos_;
 
   // Whether there is a line terminator whitespace character after
   // the current token, and  before the next. Does not count newlines
   // inside multiline comments.
   bool has_line_terminator_before_next_;
   // Whether there is a multi-line comment that contains a
   // 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_block_scoping_;
 };
 
-
-// ----------------------------------------------------------------------------
-// Keyword matching state machine.
-
-class KeywordMatcher {
-//  Incrementally recognize keywords.
-//
-//  We distinguish between normal future reserved words and words that are
-//  considered to be future reserved words only in strict mode as required by
-//  ECMA-262 7.6.1.2.
-//
-//  Recognized as keywords:
-//      break, case, catch, const*, continue, debugger, default, delete, do,
-//      else, finally, false, for, function, if, in, instanceof, new, null,
-//      return, switch, this, throw, true, try, typeof, var, void, while, with.
-//
-//  Recognized as Future Reserved Keywords:
-//      class, enum, export, extends, import, super.
-//
-//  Recognized as Future Reserved Keywords (strict mode only):
-//      implements, interface, let, package, private, protected, public,
-//      static, yield.
-//
-//  *: Actually a "future reserved keyword". It's the only one we are
-//     recognizing outside of ES5 strict mode, the remaining are allowed
-//     as identifiers.
-//
- public:
-  KeywordMatcher()
-      : state_(INITIAL),
-        token_(Token::IDENTIFIER),
-        keyword_(NULL),
-        counter_(0),
-        keyword_token_(Token::ILLEGAL) {}
-
-  Token::Value token() { return token_; }
-
-  inline bool AddChar(unibrow::uchar input) {
-    if (state_ != UNMATCHABLE) {
-      Step(input);
-    }
-    return state_ != UNMATCHABLE;
-  }
-
-  void Fail() {
-    token_ = Token::IDENTIFIER;
-    state_ = UNMATCHABLE;
-  }
-
- private:
-  enum State {
-    UNMATCHABLE,
-    INITIAL,
-    KEYWORD_PREFIX,
-    KEYWORD_MATCHED,
-    C,
-    CA,
-    CO,
-    CON,
-    D,
-    DE,
-    E,
-    EX,
-    F,
-    I,
-    IM,
-    IMP,
-    IN,
-    N,
-    P,
-    PR,
-    S,
-    T,
-    TH,
-    TR,
-    V,
-    W,
-    LAST_STATE = W
-  };
-
-
-  STATIC_ASSERT(LAST_STATE <= 0xFF);
-  STATIC_ASSERT(Token::NUM_TOKENS <= 0x100);
-  struct FirstState {
-    const char* keyword;
-    State state : 8;
-    Token::Value token : 8;
-  };
-
-  // Range of possible first characters of a keyword.
-  static const unsigned int kFirstCharRangeMin = 'b';
-  static const unsigned int kFirstCharRangeMax = 'y';
-  static const unsigned int kFirstCharRangeLength =
-      kFirstCharRangeMax - kFirstCharRangeMin + 1;
-  // State map for first keyword character range.
-  static const FirstState first_states_[kFirstCharRangeLength];
-
-  // If input equals keyword's character at position, continue matching keyword
-  // from that position.
-  inline bool MatchKeywordStart(unibrow::uchar input,
-                                const char* keyword,
-                                int position,
-                                Token::Value token_if_match) {
-    if (input != static_cast<unibrow::uchar>(keyword[position])) {
-      return false;
-    }
-    state_ = KEYWORD_PREFIX;
-    this->keyword_ = keyword;
-    this->counter_ = position + 1;
-    this->keyword_token_ = token_if_match;
-    return true;
-  }
-
-  // If input equals match character, transition to new state and return true.
-  inline bool MatchState(unibrow::uchar input, char match, State new_state) {
-    if (input != static_cast<unibrow::uchar>(match)) {
-      return false;
-    }
-    state_ = new_state;
-    return true;
-  }
-
-  inline bool MatchKeyword(unibrow::uchar input,
-                           char match,
-                           State new_state,
-                           Token::Value keyword_token) {
-    if (input != static_cast<unibrow::uchar>(match)) {
-      return false;
-    }
-    state_ = new_state;
-    token_ = keyword_token;
-    return true;
-  }
-
-  void Step(unibrow::uchar input);
-
-  // Current state.
-  State state_;
-  // Token for currently added characters.
-  Token::Value token_;
-
-  // Matching a specific keyword string (there is only one possible valid
-  // keyword with the current prefix).
-  const char* keyword_;
-  int counter_;
-  Token::Value keyword_token_;
-};
-
-
 } }  // namespace v8::internal
 
 #endif  // V8_SCANNER_BASE_H_