OLD | NEW |
1 // Copyright 2011 the V8 project authors. All rights reserved. | 1 // Copyright 2011 the V8 project authors. All rights reserved. |
2 // Use of this source code is governed by a BSD-style license that can be | 2 // Use of this source code is governed by a BSD-style license that can be |
3 // found in the LICENSE file. | 3 // found in the LICENSE file. |
4 | 4 |
5 // Features shared by parsing and pre-parsing scanners. | 5 // Features shared by parsing and pre-parsing scanners. |
6 | 6 |
7 #include "src/parsing/scanner.h" | 7 #include "src/parsing/scanner.h" |
8 | 8 |
9 #include <stdint.h> | 9 #include <stdint.h> |
10 | 10 |
(...skipping 24 matching lines...) Expand all Loading... |
35 | 35 |
36 // ---------------------------------------------------------------------------- | 36 // ---------------------------------------------------------------------------- |
37 // Scanner | 37 // Scanner |
38 | 38 |
39 Scanner::Scanner(UnicodeCache* unicode_cache) | 39 Scanner::Scanner(UnicodeCache* unicode_cache) |
40 : unicode_cache_(unicode_cache), | 40 : unicode_cache_(unicode_cache), |
41 bookmark_c0_(kNoBookmark), | 41 bookmark_c0_(kNoBookmark), |
42 octal_pos_(Location::invalid()), | 42 octal_pos_(Location::invalid()), |
43 decimal_with_leading_zero_pos_(Location::invalid()), | 43 decimal_with_leading_zero_pos_(Location::invalid()), |
44 found_html_comment_(false), | 44 found_html_comment_(false), |
| 45 allow_html_comments_(true), |
45 allow_harmony_exponentiation_operator_(false) { | 46 allow_harmony_exponentiation_operator_(false) { |
46 bookmark_current_.literal_chars = &bookmark_current_literal_; | 47 bookmark_current_.literal_chars = &bookmark_current_literal_; |
47 bookmark_current_.raw_literal_chars = &bookmark_current_raw_literal_; | 48 bookmark_current_.raw_literal_chars = &bookmark_current_raw_literal_; |
48 bookmark_next_.literal_chars = &bookmark_next_literal_; | 49 bookmark_next_.literal_chars = &bookmark_next_literal_; |
49 bookmark_next_.raw_literal_chars = &bookmark_next_raw_literal_; | 50 bookmark_next_.raw_literal_chars = &bookmark_next_raw_literal_; |
50 } | 51 } |
51 | 52 |
52 | 53 void Scanner::Initialize(Utf16CharacterStream* source, |
53 void Scanner::Initialize(Utf16CharacterStream* source) { | 54 bool allow_html_comments) { |
54 source_ = source; | 55 source_ = source; |
55 // Need to capture identifiers in order to recognize "get" and "set" | 56 // Need to capture identifiers in order to recognize "get" and "set" |
56 // in object literals. | 57 // in object literals. |
57 Init(); | 58 Init(); |
58 // Skip initial whitespace allowing HTML comment ends just like | 59 // Skip initial whitespace allowing HTML comment ends just like |
59 // after a newline and scan first token. | 60 // after a newline and scan first token. |
60 has_line_terminator_before_next_ = true; | 61 has_line_terminator_before_next_ = true; |
| 62 allow_html_comments_ = allow_html_comments; |
61 SkipWhiteSpace(); | 63 SkipWhiteSpace(); |
62 Scan(); | 64 Scan(); |
63 } | 65 } |
64 | 66 |
65 template <bool capture_raw, bool unicode> | 67 template <bool capture_raw, bool unicode> |
66 uc32 Scanner::ScanHexNumber(int expected_length) { | 68 uc32 Scanner::ScanHexNumber(int expected_length) { |
67 DCHECK(expected_length <= 4); // prevent overflow | 69 DCHECK(expected_length <= 4); // prevent overflow |
68 | 70 |
69 int begin = source_pos() - 2; | 71 int begin = source_pos() - 2; |
70 uc32 x = 0; | 72 uc32 x = 0; |
(...skipping 247 matching lines...) Expand 10 before | Expand all | Expand 10 after Loading... |
318 !IsLittleEndianByteOrderMark(c0_)) { | 320 !IsLittleEndianByteOrderMark(c0_)) { |
319 break; | 321 break; |
320 } | 322 } |
321 Advance(); | 323 Advance(); |
322 } | 324 } |
323 | 325 |
324 // If there is an HTML comment end '-->' at the beginning of a | 326 // If there is an HTML comment end '-->' at the beginning of a |
325 // line (with only whitespace in front of it), we treat the rest | 327 // line (with only whitespace in front of it), we treat the rest |
326 // of the line as a comment. This is in line with the way | 328 // of the line as a comment. This is in line with the way |
327 // SpiderMonkey handles it. | 329 // SpiderMonkey handles it. |
328 if (c0_ == '-' && has_line_terminator_before_next_) { | 330 if (c0_ == '-' && has_line_terminator_before_next_ && |
| 331 allow_html_comments_) { |
329 Advance(); | 332 Advance(); |
330 if (c0_ == '-') { | 333 if (c0_ == '-') { |
331 Advance(); | 334 Advance(); |
332 if (c0_ == '>') { | 335 if (c0_ == '>') { |
333 // Treat the rest of the line as a comment. | 336 // Treat the rest of the line as a comment. |
334 SkipSingleLineComment(); | 337 SkipSingleLineComment(); |
335 // Continue skipping white space after the comment. | 338 // Continue skipping white space after the comment. |
336 continue; | 339 continue; |
337 } | 340 } |
338 PushBack('-'); // undo Advance() | 341 PushBack('-'); // undo Advance() |
(...skipping 152 matching lines...) Expand 10 before | Expand all | Expand 10 after Loading... |
491 token = ScanString(); | 494 token = ScanString(); |
492 break; | 495 break; |
493 | 496 |
494 case '<': | 497 case '<': |
495 // < <= << <<= <!-- | 498 // < <= << <<= <!-- |
496 Advance(); | 499 Advance(); |
497 if (c0_ == '=') { | 500 if (c0_ == '=') { |
498 token = Select(Token::LTE); | 501 token = Select(Token::LTE); |
499 } else if (c0_ == '<') { | 502 } else if (c0_ == '<') { |
500 token = Select('=', Token::ASSIGN_SHL, Token::SHL); | 503 token = Select('=', Token::ASSIGN_SHL, Token::SHL); |
501 } else if (c0_ == '!') { | 504 } else if (c0_ == '!' && allow_html_comments_) { |
502 token = ScanHtmlComment(); | 505 token = ScanHtmlComment(); |
503 } else { | 506 } else { |
504 token = Token::LT; | 507 token = Token::LT; |
505 } | 508 } |
506 break; | 509 break; |
507 | 510 |
508 case '>': | 511 case '>': |
509 // > >= >> >>= >>> >>>= | 512 // > >= >> >>= >>> >>>= |
510 Advance(); | 513 Advance(); |
511 if (c0_ == '=') { | 514 if (c0_ == '=') { |
(...skipping 45 matching lines...) Expand 10 before | Expand all | Expand 10 after Loading... |
557 } else { | 560 } else { |
558 token = Token::ADD; | 561 token = Token::ADD; |
559 } | 562 } |
560 break; | 563 break; |
561 | 564 |
562 case '-': | 565 case '-': |
563 // - -- --> -= | 566 // - -- --> -= |
564 Advance(); | 567 Advance(); |
565 if (c0_ == '-') { | 568 if (c0_ == '-') { |
566 Advance(); | 569 Advance(); |
567 if (c0_ == '>' && has_line_terminator_before_next_) { | 570 if (c0_ == '>' && has_line_terminator_before_next_ && |
| 571 allow_html_comments_) { |
568 // For compatibility with SpiderMonkey, we skip lines that | 572 // For compatibility with SpiderMonkey, we skip lines that |
569 // start with an HTML comment end '-->'. | 573 // start with an HTML comment end '-->'. |
570 token = SkipSingleLineComment(); | 574 token = SkipSingleLineComment(); |
571 } else { | 575 } else { |
572 token = Token::DEC; | 576 token = Token::DEC; |
573 } | 577 } |
574 } else if (c0_ == '=') { | 578 } else if (c0_ == '=') { |
575 token = Select(Token::ASSIGN_SUB); | 579 token = Select(Token::ASSIGN_SUB); |
576 } else { | 580 } else { |
577 token = Token::SUB; | 581 token = Token::SUB; |
(...skipping 1131 matching lines...) Expand 10 before | Expand all | Expand 10 after Loading... |
1709 backing_store_.Add(static_cast<uint8_t>((one_byte_length >> 7) | 0x80u)); | 1713 backing_store_.Add(static_cast<uint8_t>((one_byte_length >> 7) | 0x80u)); |
1710 } | 1714 } |
1711 backing_store_.Add(static_cast<uint8_t>(one_byte_length & 0x7f)); | 1715 backing_store_.Add(static_cast<uint8_t>(one_byte_length & 0x7f)); |
1712 | 1716 |
1713 backing_store_.AddBlock(bytes); | 1717 backing_store_.AddBlock(bytes); |
1714 return backing_store_.EndSequence().start(); | 1718 return backing_store_.EndSequence().start(); |
1715 } | 1719 } |
1716 | 1720 |
1717 } // namespace internal | 1721 } // namespace internal |
1718 } // namespace v8 | 1722 } // namespace v8 |
OLD | NEW |