Chromium Code Reviews
chromiumcodereview-hr@appspot.gserviceaccount.com (chromiumcodereview-hr) | Please choose your nickname with Settings | Help | Chromium Project | Gerrit Changes | Sign out
(245)

Side by Side Diff: src/scanner.cc

Issue 197103002: Move most scanner buffer accesses into scanner. (Closed) Base URL: https://v8.googlecode.com/svn/branches/bleeding_edge
Patch Set: Created 6 years, 9 months ago
Use n/p to move between diff chunks; N/P to move between comments. Draft comments are only viewable by you.
Jump to:
View unified diff | Download patch | Annotate | Revision Log
« no previous file with comments | « src/scanner.h ('k') | test/cctest/test-parsing.cc » ('j') | no next file with comments »
Toggle Intra-line Diffs ('i') | Expand Comments ('e') | Collapse Comments ('c') | Show Comments Hide Comments ('s')
OLDNEW
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 17 matching lines...) Expand all
28 // Features shared by parsing and pre-parsing scanners. 28 // Features shared by parsing and pre-parsing scanners.
29 29
30 #include <cmath> 30 #include <cmath>
31 31
32 #include "scanner.h" 32 #include "scanner.h"
33 33
34 #include "../include/v8stdint.h" 34 #include "../include/v8stdint.h"
35 #include "char-predicates-inl.h" 35 #include "char-predicates-inl.h"
36 #include "conversions-inl.h" 36 #include "conversions-inl.h"
37 #include "list-inl.h" 37 #include "list-inl.h"
38 #include "v8.h"
38 39
39 namespace v8 { 40 namespace v8 {
40 namespace internal { 41 namespace internal {
41 42
42 // ---------------------------------------------------------------------------- 43 // ----------------------------------------------------------------------------
43 // Scanner 44 // Scanner
44 45
45 Scanner::Scanner(UnicodeCache* unicode_cache) 46 Scanner::Scanner(UnicodeCache* unicode_cache)
46 : unicode_cache_(unicode_cache), 47 : unicode_cache_(unicode_cache),
47 octal_pos_(Location::invalid()), 48 octal_pos_(Location::invalid()),
(...skipping 927 matching lines...) Expand 10 before | Expand all | Expand 10 after
975 Advance(); 976 Advance();
976 AddLiteralChar(next_char); 977 AddLiteralChar(next_char);
977 continue; 978 continue;
978 } 979 }
979 // Fallthrough if no longer able to complete keyword. 980 // Fallthrough if no longer able to complete keyword.
980 return ScanIdentifierSuffix(&literal); 981 return ScanIdentifierSuffix(&literal);
981 } 982 }
982 983
983 literal.Complete(); 984 literal.Complete();
984 985
985 if (next_.literal_chars->is_ascii()) { 986 if (next_.literal_chars->is_one_byte()) {
986 Vector<const char> chars = next_.literal_chars->ascii_literal(); 987 Vector<const char> chars = next_.literal_chars->one_byte_literal();
987 return KeywordOrIdentifierToken(chars.start(), 988 return KeywordOrIdentifierToken(chars.start(),
988 chars.length(), 989 chars.length(),
989 harmony_scoping_, 990 harmony_scoping_,
990 harmony_modules_); 991 harmony_modules_);
991 } 992 }
992 993
993 return Token::IDENTIFIER; 994 return Token::IDENTIFIER;
994 } 995 }
995 996
996 997
(...skipping 110 matching lines...) Expand 10 before | Expand all | Expand 10 after
1107 Advance(); 1108 Advance();
1108 } 1109 }
1109 } 1110 }
1110 literal.Complete(); 1111 literal.Complete();
1111 1112
1112 next_.location.end_pos = source_pos() - 1; 1113 next_.location.end_pos = source_pos() - 1;
1113 return true; 1114 return true;
1114 } 1115 }
1115 1116
1116 1117
1118 Handle<String> Scanner::AllocateLiteralString(Isolate* isolate,
1119 PretenureFlag tenured) {
1120 if (is_literal_one_byte()) {
1121 return isolate->factory()->NewStringFromOneByte(
1122 Vector<const uint8_t>::cast(literal_one_byte_string()), tenured);
1123 } else {
1124 return isolate->factory()->NewStringFromTwoByte(
1125 literal_utf16_string(), tenured);
1126 }
1127 }
1128
1129
1130 Handle<String> Scanner::AllocateNextLiteralString(Isolate* isolate,
1131 PretenureFlag tenured) {
1132 if (is_next_literal_one_byte()) {
1133 return isolate->factory()->NewStringFromOneByte(
1134 Vector<const uint8_t>::cast(next_literal_one_byte_string()), tenured);
1135 } else {
1136 return isolate->factory()->NewStringFromTwoByte(
1137 next_literal_utf16_string(), tenured);
1138 }
1139 }
1140
1141
1142 Handle<String> Scanner::AllocateInternalizedString(Isolate* isolate) {
1143 if (is_literal_one_byte()) {
1144 return isolate->factory()->InternalizeOneByteString(
1145 Vector<const uint8_t>::cast(literal_one_byte_string()));
1146 } else {
1147 return isolate->factory()->InternalizeTwoByteString(
1148 literal_utf16_string());
1149 }
1150 }
1151
1152
1153 double Scanner::DoubleValue() {
1154 ASSERT(is_literal_one_byte());
1155 return StringToDouble(
1156 unicode_cache_, literal_one_byte_string(),
1157 ALLOW_HEX | ALLOW_OCTAL | ALLOW_IMPLICIT_OCTAL | ALLOW_BINARY);
1158 }
1159
1160
1117 int DuplicateFinder::AddAsciiSymbol(Vector<const char> key, int value) { 1161 int DuplicateFinder::AddAsciiSymbol(Vector<const char> key, int value) {
1118 return AddSymbol(Vector<const byte>::cast(key), true, value); 1162 return AddSymbol(Vector<const byte>::cast(key), true, value);
1119 } 1163 }
1120 1164
1121 1165
1122 int DuplicateFinder::AddUtf16Symbol(Vector<const uint16_t> key, int value) { 1166 int DuplicateFinder::AddUtf16Symbol(Vector<const uint16_t> key, int value) {
1123 return AddSymbol(Vector<const byte>::cast(key), false, value); 1167 return AddSymbol(Vector<const byte>::cast(key), false, value);
1124 } 1168 }
1125 1169
1126 1170
1127 int DuplicateFinder::AddSymbol(Vector<const byte> key, 1171 int DuplicateFinder::AddSymbol(Vector<const byte> key,
1128 bool is_ascii, 1172 bool is_one_byte,
1129 int value) { 1173 int value) {
1130 uint32_t hash = Hash(key, is_ascii); 1174 uint32_t hash = Hash(key, is_one_byte);
1131 byte* encoding = BackupKey(key, is_ascii); 1175 byte* encoding = BackupKey(key, is_one_byte);
1132 HashMap::Entry* entry = map_.Lookup(encoding, hash, true); 1176 HashMap::Entry* entry = map_.Lookup(encoding, hash, true);
1133 int old_value = static_cast<int>(reinterpret_cast<intptr_t>(entry->value)); 1177 int old_value = static_cast<int>(reinterpret_cast<intptr_t>(entry->value));
1134 entry->value = 1178 entry->value =
1135 reinterpret_cast<void*>(static_cast<intptr_t>(value | old_value)); 1179 reinterpret_cast<void*>(static_cast<intptr_t>(value | old_value));
1136 return old_value; 1180 return old_value;
1137 } 1181 }
1138 1182
1139 1183
1140 int DuplicateFinder::AddNumber(Vector<const char> key, int value) { 1184 int DuplicateFinder::AddNumber(Vector<const char> key, int value) {
1141 ASSERT(key.length() > 0); 1185 ASSERT(key.length() > 0);
(...skipping 40 matching lines...) Expand 10 before | Expand all | Expand 10 after
1182 while (pos < length) { 1226 while (pos < length) {
1183 byte digit = number[pos] - '0'; 1227 byte digit = number[pos] - '0';
1184 if (digit > '9' - '0') return false; 1228 if (digit > '9' - '0') return false;
1185 invalid_last_digit = (digit == 0); 1229 invalid_last_digit = (digit == 0);
1186 pos++; 1230 pos++;
1187 } 1231 }
1188 return !invalid_last_digit; 1232 return !invalid_last_digit;
1189 } 1233 }
1190 1234
1191 1235
1192 uint32_t DuplicateFinder::Hash(Vector<const byte> key, bool is_ascii) { 1236 uint32_t DuplicateFinder::Hash(Vector<const byte> key, bool is_one_byte) {
1193 // Primitive hash function, almost identical to the one used 1237 // Primitive hash function, almost identical to the one used
1194 // for strings (except that it's seeded by the length and ASCII-ness). 1238 // for strings (except that it's seeded by the length and ASCII-ness).
1195 int length = key.length(); 1239 int length = key.length();
1196 uint32_t hash = (length << 1) | (is_ascii ? 1 : 0) ; 1240 uint32_t hash = (length << 1) | (is_one_byte ? 1 : 0) ;
1197 for (int i = 0; i < length; i++) { 1241 for (int i = 0; i < length; i++) {
1198 uint32_t c = key[i]; 1242 uint32_t c = key[i];
1199 hash = (hash + c) * 1025; 1243 hash = (hash + c) * 1025;
1200 hash ^= (hash >> 6); 1244 hash ^= (hash >> 6);
1201 } 1245 }
1202 return hash; 1246 return hash;
1203 } 1247 }
1204 1248
1205 1249
1206 bool DuplicateFinder::Match(void* first, void* second) { 1250 bool DuplicateFinder::Match(void* first, void* second) {
1207 // Decode lengths. 1251 // Decode lengths.
1208 // Length + ASCII-bit is encoded as base 128, most significant heptet first, 1252 // Length + ASCII-bit is encoded as base 128, most significant heptet first,
1209 // with a 8th bit being non-zero while there are more heptets. 1253 // with a 8th bit being non-zero while there are more heptets.
1210 // The value encodes the number of bytes following, and whether the original 1254 // The value encodes the number of bytes following, and whether the original
1211 // was ASCII. 1255 // was ASCII.
1212 byte* s1 = reinterpret_cast<byte*>(first); 1256 byte* s1 = reinterpret_cast<byte*>(first);
1213 byte* s2 = reinterpret_cast<byte*>(second); 1257 byte* s2 = reinterpret_cast<byte*>(second);
1214 uint32_t length_ascii_field = 0; 1258 uint32_t length_one_byte_field = 0;
1215 byte c1; 1259 byte c1;
1216 do { 1260 do {
1217 c1 = *s1; 1261 c1 = *s1;
1218 if (c1 != *s2) return false; 1262 if (c1 != *s2) return false;
1219 length_ascii_field = (length_ascii_field << 7) | (c1 & 0x7f); 1263 length_one_byte_field = (length_one_byte_field << 7) | (c1 & 0x7f);
1220 s1++; 1264 s1++;
1221 s2++; 1265 s2++;
1222 } while ((c1 & 0x80) != 0); 1266 } while ((c1 & 0x80) != 0);
1223 int length = static_cast<int>(length_ascii_field >> 1); 1267 int length = static_cast<int>(length_one_byte_field >> 1);
1224 return memcmp(s1, s2, length) == 0; 1268 return memcmp(s1, s2, length) == 0;
1225 } 1269 }
1226 1270
1227 1271
1228 byte* DuplicateFinder::BackupKey(Vector<const byte> bytes, 1272 byte* DuplicateFinder::BackupKey(Vector<const byte> bytes,
1229 bool is_ascii) { 1273 bool is_one_byte) {
1230 uint32_t ascii_length = (bytes.length() << 1) | (is_ascii ? 1 : 0); 1274 uint32_t one_byte_length = (bytes.length() << 1) | (is_one_byte ? 1 : 0);
1231 backing_store_.StartSequence(); 1275 backing_store_.StartSequence();
1232 // Emit ascii_length as base-128 encoded number, with the 7th bit set 1276 // Emit one_byte_length as base-128 encoded number, with the 7th bit set
1233 // on the byte of every heptet except the last, least significant, one. 1277 // on the byte of every heptet except the last, least significant, one.
1234 if (ascii_length >= (1 << 7)) { 1278 if (one_byte_length >= (1 << 7)) {
1235 if (ascii_length >= (1 << 14)) { 1279 if (one_byte_length >= (1 << 14)) {
1236 if (ascii_length >= (1 << 21)) { 1280 if (one_byte_length >= (1 << 21)) {
1237 if (ascii_length >= (1 << 28)) { 1281 if (one_byte_length >= (1 << 28)) {
1238 backing_store_.Add(static_cast<byte>((ascii_length >> 28) | 0x80)); 1282 backing_store_.Add(static_cast<byte>((one_byte_length >> 28) | 0x80));
1239 } 1283 }
1240 backing_store_.Add(static_cast<byte>((ascii_length >> 21) | 0x80u)); 1284 backing_store_.Add(static_cast<byte>((one_byte_length >> 21) | 0x80u));
1241 } 1285 }
1242 backing_store_.Add(static_cast<byte>((ascii_length >> 14) | 0x80u)); 1286 backing_store_.Add(static_cast<byte>((one_byte_length >> 14) | 0x80u));
1243 } 1287 }
1244 backing_store_.Add(static_cast<byte>((ascii_length >> 7) | 0x80u)); 1288 backing_store_.Add(static_cast<byte>((one_byte_length >> 7) | 0x80u));
1245 } 1289 }
1246 backing_store_.Add(static_cast<byte>(ascii_length & 0x7f)); 1290 backing_store_.Add(static_cast<byte>(one_byte_length & 0x7f));
1247 1291
1248 backing_store_.AddBlock(bytes); 1292 backing_store_.AddBlock(bytes);
1249 return backing_store_.EndSequence().start(); 1293 return backing_store_.EndSequence().start();
1250 } 1294 }
1251 1295
1252 } } // namespace v8::internal 1296 } } // namespace v8::internal
OLDNEW
« no previous file with comments | « src/scanner.h ('k') | test/cctest/test-parsing.cc » ('j') | no next file with comments »

Powered by Google App Engine
This is Rietveld 408576698