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 <stdint.h> | 7 #include <stdint.h> |
8 | 8 |
9 #include <cmath> | 9 #include <cmath> |
10 | 10 |
(...skipping 770 matching lines...) Expand 10 before | Expand all | Expand 10 after Loading... |
781 // can be reported later (in strict mode). | 781 // can be reported later (in strict mode). |
782 // We don't report the error immediately, because the octal escape can | 782 // We don't report the error immediately, because the octal escape can |
783 // occur before the "use strict" directive. | 783 // occur before the "use strict" directive. |
784 if (c != '0' || i > 0) { | 784 if (c != '0' || i > 0) { |
785 octal_pos_ = Location(source_pos() - i - 1, source_pos() - 1); | 785 octal_pos_ = Location(source_pos() - i - 1, source_pos() - 1); |
786 } | 786 } |
787 return x; | 787 return x; |
788 } | 788 } |
789 | 789 |
790 | 790 |
| 791 const int kMaxAscii = 127; |
| 792 |
| 793 |
791 Token::Value Scanner::ScanString() { | 794 Token::Value Scanner::ScanString() { |
792 uc32 quote = c0_; | 795 uc32 quote = c0_; |
793 Advance(); // consume quote | 796 Advance<false, false>(); // consume quote |
794 | 797 |
795 LiteralScope literal(this); | 798 LiteralScope literal(this); |
| 799 while (true) { |
| 800 if (c0_ > kMaxAscii) { |
| 801 HandleLeadSurrogate(); |
| 802 break; |
| 803 } |
| 804 if (c0_ < 0 || c0_ == '\n' || c0_ == '\r') return Token::ILLEGAL; |
| 805 if (c0_ == quote) { |
| 806 literal.Complete(); |
| 807 Advance<false, false>(); |
| 808 return Token::STRING; |
| 809 } |
| 810 uc32 c = c0_; |
| 811 if (c == '\\') break; |
| 812 Advance<false, false>(); |
| 813 AddLiteralChar(c); |
| 814 } |
| 815 |
796 while (c0_ != quote && c0_ >= 0 | 816 while (c0_ != quote && c0_ >= 0 |
797 && !unicode_cache_->IsLineTerminator(c0_)) { | 817 && !unicode_cache_->IsLineTerminator(c0_)) { |
798 uc32 c = c0_; | 818 uc32 c = c0_; |
799 Advance(); | 819 Advance(); |
800 if (c == '\\') { | 820 if (c == '\\') { |
801 if (c0_ < 0 || !ScanEscape<false, false>()) return Token::ILLEGAL; | 821 if (c0_ < 0 || !ScanEscape<false, false>()) return Token::ILLEGAL; |
802 } else { | 822 } else { |
803 AddLiteralChar(c); | 823 AddLiteralChar(c); |
804 } | 824 } |
805 } | 825 } |
(...skipping 180 matching lines...) Expand 10 before | Expand all | Expand 10 after Loading... |
986 | 1006 |
987 uc32 first_char = c0_; | 1007 uc32 first_char = c0_; |
988 Advance<false, false>(); | 1008 Advance<false, false>(); |
989 AddLiteralChar(first_char); | 1009 AddLiteralChar(first_char); |
990 } | 1010 } |
991 | 1011 |
992 if (next_.literal_chars->one_byte_literal().length() < 10 && | 1012 if (next_.literal_chars->one_byte_literal().length() < 10 && |
993 c0_ != '.' && c0_ != 'e' && c0_ != 'E') { | 1013 c0_ != '.' && c0_ != 'e' && c0_ != 'E') { |
994 smi_value_ = value; | 1014 smi_value_ = value; |
995 literal.Complete(); | 1015 literal.Complete(); |
996 HandleLeadSurrugate(); | 1016 HandleLeadSurrogate(); |
997 | 1017 |
998 return Token::SMI; | 1018 return Token::SMI; |
999 } | 1019 } |
1000 HandleLeadSurrugate(); | 1020 HandleLeadSurrogate(); |
1001 } | 1021 } |
1002 | 1022 |
1003 ScanDecimalDigits(); // optional | 1023 ScanDecimalDigits(); // optional |
1004 if (c0_ == '.') { | 1024 if (c0_ == '.') { |
1005 AddLiteralCharAdvance(); | 1025 AddLiteralCharAdvance(); |
1006 ScanDecimalDigits(); // optional | 1026 ScanDecimalDigits(); // optional |
1007 } | 1027 } |
1008 } | 1028 } |
1009 } | 1029 } |
1010 | 1030 |
(...skipping 199 matching lines...) Expand 10 before | Expand all | Expand 10 after Loading... |
1210 c0_ == '$') { | 1230 c0_ == '$') { |
1211 // Identifier starting with lowercase. | 1231 // Identifier starting with lowercase. |
1212 uc32 first_char = c0_; | 1232 uc32 first_char = c0_; |
1213 Advance<false, false>(); | 1233 Advance<false, false>(); |
1214 AddLiteralChar(first_char); | 1234 AddLiteralChar(first_char); |
1215 while (IsAsciiIdentifier(c0_)) { | 1235 while (IsAsciiIdentifier(c0_)) { |
1216 uc32 first_char = c0_; | 1236 uc32 first_char = c0_; |
1217 Advance<false, false>(); | 1237 Advance<false, false>(); |
1218 AddLiteralChar(first_char); | 1238 AddLiteralChar(first_char); |
1219 } | 1239 } |
1220 if (c0_ <= 127 && c0_ != '\\') { | 1240 if (c0_ <= kMaxAscii && c0_ != '\\') { |
1221 literal.Complete(); | 1241 literal.Complete(); |
1222 return Token::IDENTIFIER; | 1242 return Token::IDENTIFIER; |
1223 } | 1243 } |
1224 } else if (c0_ <= 127 && c0_ != '\\') { | 1244 } else if (c0_ <= kMaxAscii && c0_ != '\\') { |
1225 // Only a-z+: could be a keyword or identifier. | 1245 // Only a-z+: could be a keyword or identifier. |
1226 literal.Complete(); | 1246 literal.Complete(); |
1227 Vector<const uint8_t> chars = next_.literal_chars->one_byte_literal(); | 1247 Vector<const uint8_t> chars = next_.literal_chars->one_byte_literal(); |
1228 return KeywordOrIdentifierToken(chars.start(), chars.length(), | 1248 return KeywordOrIdentifierToken(chars.start(), chars.length(), |
1229 harmony_scoping_, harmony_modules_, | 1249 harmony_scoping_, harmony_modules_, |
1230 harmony_classes_); | 1250 harmony_classes_); |
1231 } | 1251 } |
1232 | 1252 |
1233 HandleLeadSurrugate(); | 1253 HandleLeadSurrogate(); |
1234 } else if (IsInRange(c0_, 'A', 'Z') || c0_ == '_' || c0_ == '$') { | 1254 } else if (IsInRange(c0_, 'A', 'Z') || c0_ == '_' || c0_ == '$') { |
1235 do { | 1255 do { |
1236 uc32 first_char = c0_; | 1256 uc32 first_char = c0_; |
1237 Advance<false, false>(); | 1257 Advance<false, false>(); |
1238 AddLiteralChar(first_char); | 1258 AddLiteralChar(first_char); |
1239 } while (IsAsciiIdentifier(c0_)); | 1259 } while (IsAsciiIdentifier(c0_)); |
1240 | 1260 |
1241 if (c0_ <= 127 && c0_ != '\\') { | 1261 if (c0_ <= kMaxAscii && c0_ != '\\') { |
1242 literal.Complete(); | 1262 literal.Complete(); |
1243 return Token::IDENTIFIER; | 1263 return Token::IDENTIFIER; |
1244 } | 1264 } |
1245 | 1265 |
1246 HandleLeadSurrugate(); | 1266 HandleLeadSurrogate(); |
1247 } else if (c0_ == '\\') { | 1267 } else if (c0_ == '\\') { |
1248 // Scan identifier start character. | 1268 // Scan identifier start character. |
1249 uc32 c = ScanIdentifierUnicodeEscape(); | 1269 uc32 c = ScanIdentifierUnicodeEscape(); |
1250 // Only allow legal identifier start characters. | 1270 // Only allow legal identifier start characters. |
1251 if (c < 0 || | 1271 if (c < 0 || |
1252 c == '\\' || // No recursive escapes. | 1272 c == '\\' || // No recursive escapes. |
1253 !unicode_cache_->IsIdentifierStart(c)) { | 1273 !unicode_cache_->IsIdentifierStart(c)) { |
1254 return Token::ILLEGAL; | 1274 return Token::ILLEGAL; |
1255 } | 1275 } |
1256 AddLiteralChar(c); | 1276 AddLiteralChar(c); |
(...skipping 297 matching lines...) Expand 10 before | Expand all | Expand 10 after Loading... |
1554 } | 1574 } |
1555 backing_store_.Add(static_cast<uint8_t>((one_byte_length >> 7) | 0x80u)); | 1575 backing_store_.Add(static_cast<uint8_t>((one_byte_length >> 7) | 0x80u)); |
1556 } | 1576 } |
1557 backing_store_.Add(static_cast<uint8_t>(one_byte_length & 0x7f)); | 1577 backing_store_.Add(static_cast<uint8_t>(one_byte_length & 0x7f)); |
1558 | 1578 |
1559 backing_store_.AddBlock(bytes); | 1579 backing_store_.AddBlock(bytes); |
1560 return backing_store_.EndSequence().start(); | 1580 return backing_store_.EndSequence().start(); |
1561 } | 1581 } |
1562 | 1582 |
1563 } } // namespace v8::internal | 1583 } } // namespace v8::internal |
OLD | NEW |