| OLD | NEW |
| 1 // Copyright 2011 the V8 project authors. All rights reserved. | 1 // Copyright 2011 the V8 project authors. All rights reserved. |
| 2 // Redistribution and use in source and binary forms, with or without | 2 // Redistribution and use in source and binary forms, with or without |
| 3 // modification, are permitted provided that the following conditions are | 3 // modification, are permitted provided that the following conditions are |
| 4 // met: | 4 // met: |
| 5 // | 5 // |
| 6 // * Redistributions of source code must retain the above copyright | 6 // * Redistributions of source code must retain the above copyright |
| 7 // notice, this list of conditions and the following disclaimer. | 7 // notice, this list of conditions and the following disclaimer. |
| 8 // * Redistributions in binary form must reproduce the above | 8 // * Redistributions in binary form must reproduce the above |
| 9 // copyright notice, this list of conditions and the following | 9 // copyright notice, this list of conditions and the following |
| 10 // disclaimer in the documentation and/or other materials provided | 10 // disclaimer in the documentation and/or other materials provided |
| (...skipping 453 matching lines...) Expand 10 before | Expand all | Expand 10 after Loading... |
| 464 complete_ = true; | 464 complete_ = true; |
| 465 } | 465 } |
| 466 | 466 |
| 467 private: | 467 private: |
| 468 JavaScriptScanner* scanner_; | 468 JavaScriptScanner* scanner_; |
| 469 bool complete_; | 469 bool complete_; |
| 470 }; | 470 }; |
| 471 | 471 |
| 472 explicit JavaScriptScanner(UnicodeCache* scanner_contants); | 472 explicit JavaScriptScanner(UnicodeCache* scanner_contants); |
| 473 | 473 |
| 474 void Initialize(UC16CharacterStream* source); |
| 475 |
| 474 // Returns the next token. | 476 // Returns the next token. |
| 475 Token::Value Next(); | 477 Token::Value Next(); |
| 476 | 478 |
| 477 // Returns true if there was a line terminator before the peek'ed token. | 479 // Returns true if there was a line terminator before the peek'ed token, |
| 478 bool has_line_terminator_before_next() const { | 480 // possibly inside a multi-line comment. |
| 479 return has_line_terminator_before_next_; | 481 bool HasAnyLineTerminatorBeforeNext() const { |
| 482 return has_line_terminator_before_next_ || |
| 483 has_multiline_comment_before_next_; |
| 480 } | 484 } |
| 481 | 485 |
| 482 // Scans the input as a regular expression pattern, previous | 486 // Scans the input as a regular expression pattern, previous |
| 483 // character(s) must be /(=). Returns true if a pattern is scanned. | 487 // character(s) must be /(=). Returns true if a pattern is scanned. |
| 484 bool ScanRegExpPattern(bool seen_equal); | 488 bool ScanRegExpPattern(bool seen_equal); |
| 485 // Returns true if regexp flags are scanned (always since flags can | 489 // Returns true if regexp flags are scanned (always since flags can |
| 486 // be empty). | 490 // be empty). |
| 487 bool ScanRegExpFlags(); | 491 bool ScanRegExpFlags(); |
| 488 | 492 |
| 489 // Tells whether the buffer contains an identifier (no escapes). | 493 // Tells whether the buffer contains an identifier (no escapes). |
| (...skipping 32 matching lines...) Expand 10 before | Expand all | Expand 10 after Loading... |
| 522 // Scans a possible HTML comment -- begins with '<!'. | 526 // Scans a possible HTML comment -- begins with '<!'. |
| 523 Token::Value ScanHtmlComment(); | 527 Token::Value ScanHtmlComment(); |
| 524 | 528 |
| 525 // Decodes a unicode escape-sequence which is part of an identifier. | 529 // Decodes a unicode escape-sequence which is part of an identifier. |
| 526 // If the escape sequence cannot be decoded the result is kBadChar. | 530 // If the escape sequence cannot be decoded the result is kBadChar. |
| 527 uc32 ScanIdentifierUnicodeEscape(); | 531 uc32 ScanIdentifierUnicodeEscape(); |
| 528 | 532 |
| 529 // Start position of the octal literal last scanned. | 533 // Start position of the octal literal last scanned. |
| 530 Location octal_pos_; | 534 Location octal_pos_; |
| 531 | 535 |
| 536 // Whether there is a line terminator whitespace character after |
| 537 // the current token, and before the next. Does not count newlines |
| 538 // inside multiline comments. |
| 532 bool has_line_terminator_before_next_; | 539 bool has_line_terminator_before_next_; |
| 540 // Whether there is a multi-line comment that contains a |
| 541 // line-terminator after the current token, and before the next. |
| 542 bool has_multiline_comment_before_next_; |
| 533 }; | 543 }; |
| 534 | 544 |
| 535 | 545 |
| 536 // ---------------------------------------------------------------------------- | 546 // ---------------------------------------------------------------------------- |
| 537 // Keyword matching state machine. | 547 // Keyword matching state machine. |
| 538 | 548 |
| 539 class KeywordMatcher { | 549 class KeywordMatcher { |
| 540 // Incrementally recognize keywords. | 550 // Incrementally recognize keywords. |
| 541 // | 551 // |
| 542 // Recognized keywords: | 552 // We distinguish between normal future reserved words and words that are |
| 543 // break case catch const* continue debugger* default delete do else | 553 // considered to be future reserved words only in strict mode as required by |
| 544 // finally false for function if in instanceof native* new null | 554 // ECMA-262 7.6.1.2. |
| 545 // return switch this throw true try typeof var void while with | |
| 546 // | 555 // |
| 547 // *: Actually "future reserved keywords". These are the only ones we | 556 // Recognized as keywords: |
| 548 // recognize, the remaining are allowed as identifiers. | 557 // break, case, catch, const*, continue, debugger, default, delete, do, |
| 549 // In ES5 strict mode, we should disallow all reserved keywords. | 558 // else, finally, false, for, function, if, in, instanceof, new, null, |
| 559 // return, switch, this, throw, true, try, typeof, var, void, while, with. |
| 560 // |
| 561 // Recognized as Future Reserved Keywords: |
| 562 // class, enum, export, extends, import, super. |
| 563 // |
| 564 // Recognized as Future Reserved Keywords (strict mode only): |
| 565 // implements, interface, let, package, private, protected, public, |
| 566 // static, yield. |
| 567 // |
| 568 // *: Actually a "future reserved keyword". It's the only one we are |
| 569 // recognizing outside of ES5 strict mode, the remaining are allowed |
| 570 // as identifiers. |
| 571 // |
| 550 public: | 572 public: |
| 551 KeywordMatcher() | 573 KeywordMatcher() |
| 552 : state_(INITIAL), | 574 : state_(INITIAL), |
| 553 token_(Token::IDENTIFIER), | 575 token_(Token::IDENTIFIER), |
| 554 keyword_(NULL), | 576 keyword_(NULL), |
| 555 counter_(0), | 577 counter_(0), |
| 556 keyword_token_(Token::ILLEGAL) {} | 578 keyword_token_(Token::ILLEGAL) {} |
| 557 | 579 |
| 558 Token::Value token() { return token_; } | 580 Token::Value token() { return token_; } |
| 559 | 581 |
| (...skipping 101 matching lines...) Expand 10 before | Expand all | Expand 10 after Loading... |
| 661 // keyword with the current prefix). | 683 // keyword with the current prefix). |
| 662 const char* keyword_; | 684 const char* keyword_; |
| 663 int counter_; | 685 int counter_; |
| 664 Token::Value keyword_token_; | 686 Token::Value keyword_token_; |
| 665 }; | 687 }; |
| 666 | 688 |
| 667 | 689 |
| 668 } } // namespace v8::internal | 690 } } // namespace v8::internal |
| 669 | 691 |
| 670 #endif // V8_SCANNER_BASE_H_ | 692 #endif // V8_SCANNER_BASE_H_ |
| OLD | NEW |