OLD | NEW |
1 // Copyright 2006-2008 the V8 project authors. All rights reserved. | 1 // Copyright 2006-2008 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 31 matching lines...) Expand 10 before | Expand all | Expand 10 after Loading... |
42 unibrow::Predicate<unibrow::LineTerminator, 128> Scanner::kIsLineTerminator; | 42 unibrow::Predicate<unibrow::LineTerminator, 128> Scanner::kIsLineTerminator; |
43 unibrow::Predicate<unibrow::WhiteSpace, 128> Scanner::kIsWhiteSpace; | 43 unibrow::Predicate<unibrow::WhiteSpace, 128> Scanner::kIsWhiteSpace; |
44 | 44 |
45 | 45 |
46 StaticResource<Scanner::Utf8Decoder> Scanner::utf8_decoder_; | 46 StaticResource<Scanner::Utf8Decoder> Scanner::utf8_decoder_; |
47 | 47 |
48 | 48 |
49 // ---------------------------------------------------------------------------- | 49 // ---------------------------------------------------------------------------- |
50 // UTF8Buffer | 50 // UTF8Buffer |
51 | 51 |
52 UTF8Buffer::UTF8Buffer() { | 52 UTF8Buffer::UTF8Buffer() : data_(NULL), limit_(NULL) { } |
53 static const int kInitialCapacity = 1 * KB; | |
54 data_ = NewArray<char>(kInitialCapacity); | |
55 limit_ = ComputeLimit(data_, kInitialCapacity); | |
56 Reset(); | |
57 ASSERT(Capacity() == kInitialCapacity && pos() == 0); | |
58 } | |
59 | 53 |
60 | 54 |
61 UTF8Buffer::~UTF8Buffer() { | 55 UTF8Buffer::~UTF8Buffer() { |
62 DeleteArray(data_); | 56 DeleteArray(data_); |
63 } | 57 } |
64 | 58 |
65 | 59 |
66 void UTF8Buffer::AddCharSlow(uc32 c) { | 60 void UTF8Buffer::AddCharSlow(uc32 c) { |
67 static const int kCapacityGrowthLimit = 1 * MB; | 61 static const int kCapacityGrowthLimit = 1 * MB; |
68 if (cursor_ > limit_) { | 62 if (cursor_ > limit_) { |
69 int old_capacity = Capacity(); | 63 int old_capacity = Capacity(); |
70 int old_position = pos(); | 64 int old_position = pos(); |
71 int new_capacity = | 65 int new_capacity = |
72 Min(old_capacity * 2, old_capacity + kCapacityGrowthLimit); | 66 Min(old_capacity * 3, old_capacity + kCapacityGrowthLimit); |
73 char* new_data = NewArray<char>(new_capacity); | 67 char* new_data = NewArray<char>(new_capacity); |
74 memcpy(new_data, data_, old_position); | 68 memcpy(new_data, data_, old_position); |
75 DeleteArray(data_); | 69 DeleteArray(data_); |
76 data_ = new_data; | 70 data_ = new_data; |
77 cursor_ = new_data + old_position; | 71 cursor_ = new_data + old_position; |
78 limit_ = ComputeLimit(new_data, new_capacity); | 72 limit_ = ComputeLimit(new_data, new_capacity); |
79 ASSERT(Capacity() == new_capacity && pos() == old_position); | 73 ASSERT(Capacity() == new_capacity && pos() == old_position); |
80 } | 74 } |
81 if (static_cast<unsigned>(c) <= unibrow::Utf8::kMaxOneByteChar) { | 75 if (static_cast<unsigned>(c) <= unibrow::Utf8::kMaxOneByteChar) { |
82 *cursor_++ = c; // Common case: 7-bit ASCII. | 76 *cursor_++ = c; // Common case: 7-bit ASCII. |
(...skipping 256 matching lines...) Expand 10 before | Expand all | Expand 10 after Loading... |
339 two_byte_string_buffer_.Initialize( | 333 two_byte_string_buffer_.Initialize( |
340 Handle<ExternalTwoByteString>::cast(source)); | 334 Handle<ExternalTwoByteString>::cast(source)); |
341 source_ = &two_byte_string_buffer_; | 335 source_ = &two_byte_string_buffer_; |
342 } else { | 336 } else { |
343 char_stream_buffer_.Initialize(source, stream); | 337 char_stream_buffer_.Initialize(source, stream); |
344 source_ = &char_stream_buffer_; | 338 source_ = &char_stream_buffer_; |
345 } | 339 } |
346 | 340 |
347 position_ = position; | 341 position_ = position; |
348 | 342 |
349 // Reset literals buffer | |
350 literals_.Reset(); | |
351 | |
352 // Set c0_ (one character ahead) | 343 // Set c0_ (one character ahead) |
353 ASSERT(kCharacterLookaheadBufferSize == 1); | 344 ASSERT(kCharacterLookaheadBufferSize == 1); |
354 Advance(); | 345 Advance(); |
355 | 346 |
356 // Skip initial whitespace allowing HTML comment ends just like | 347 // Skip initial whitespace allowing HTML comment ends just like |
357 // after a newline and scan first token. | 348 // after a newline and scan first token. |
358 has_line_terminator_before_next_ = true; | 349 has_line_terminator_before_next_ = true; |
359 SkipWhiteSpace(); | 350 SkipWhiteSpace(); |
360 Scan(); | 351 Scan(); |
361 } | 352 } |
362 | 353 |
363 | 354 |
364 Handle<String> Scanner::SubString(int start, int end) { | 355 Handle<String> Scanner::SubString(int start, int end) { |
365 return source_->SubString(start - position_, end - position_); | 356 return source_->SubString(start - position_, end - position_); |
366 } | 357 } |
367 | 358 |
368 | 359 |
369 Token::Value Scanner::Next() { | 360 Token::Value Scanner::Next() { |
370 // BUG 1215673: Find a thread safe way to set a stack limit in | 361 // BUG 1215673: Find a thread safe way to set a stack limit in |
371 // pre-parse mode. Otherwise, we cannot safely pre-parse from other | 362 // pre-parse mode. Otherwise, we cannot safely pre-parse from other |
372 // threads. | 363 // threads. |
373 current_ = next_; | 364 current_ = next_; |
374 // Check for stack-overflow before returning any tokens. | 365 // Check for stack-overflow before returning any tokens. |
375 StackLimitCheck check; | 366 StackLimitCheck check; |
376 if (check.HasOverflowed()) { | 367 if (check.HasOverflowed()) { |
377 stack_overflow_ = true; | 368 stack_overflow_ = true; |
378 next_.token = Token::ILLEGAL; | 369 next_.token = Token::ILLEGAL; |
| 370 next_.literal_buffer = NULL; |
379 } else { | 371 } else { |
380 Scan(); | 372 Scan(); |
381 } | 373 } |
382 return current_.token; | 374 return current_.token; |
383 } | 375 } |
384 | 376 |
385 | 377 |
386 void Scanner::StartLiteral() { | 378 void Scanner::StartLiteral() { |
387 next_.literal_pos = literals_.pos(); | 379 // Use the first buffer, unless it's currently in use by the current_ token. |
| 380 // In most cases, we won't have two literals/identifiers in a row, so |
| 381 // the second buffer won't be used very often and is unlikely to grow much. |
| 382 UTF8Buffer* free_buffer = |
| 383 (current_.literal_buffer != &literal_buffer_1_) ? &literal_buffer_1_ |
| 384 : &literal_buffer_2_; |
| 385 next_.literal_buffer = free_buffer; |
| 386 free_buffer->Reset(); |
388 } | 387 } |
389 | 388 |
390 | 389 |
391 void Scanner::AddChar(uc32 c) { | 390 void Scanner::AddChar(uc32 c) { |
392 literals_.AddChar(c); | 391 next_.literal_buffer->AddChar(c); |
393 } | 392 } |
394 | 393 |
395 | 394 |
396 void Scanner::TerminateLiteral() { | 395 void Scanner::TerminateLiteral() { |
397 next_.literal_end = literals_.pos(); | |
398 AddChar(0); | 396 AddChar(0); |
399 } | 397 } |
400 | 398 |
401 | 399 |
402 void Scanner::AddCharAdvance() { | 400 void Scanner::AddCharAdvance() { |
403 AddChar(c0_); | 401 AddChar(c0_); |
404 Advance(); | 402 Advance(); |
405 } | 403 } |
406 | 404 |
407 | 405 |
(...skipping 681 matching lines...) Expand 10 before | Expand all | Expand 10 after Loading... |
1089 } | 1087 } |
1090 AddCharAdvance(); | 1088 AddCharAdvance(); |
1091 } | 1089 } |
1092 TerminateLiteral(); | 1090 TerminateLiteral(); |
1093 | 1091 |
1094 next_.location.end_pos = source_pos() - 1; | 1092 next_.location.end_pos = source_pos() - 1; |
1095 return true; | 1093 return true; |
1096 } | 1094 } |
1097 | 1095 |
1098 } } // namespace v8::internal | 1096 } } // namespace v8::internal |
OLD | NEW |