ager@chromium.org | a9aa5fa | 2011-04-13 08:46:07 +0000 | [diff] [blame] | 1 | // Copyright 2011 the V8 project authors. All rights reserved. |
christian.plesner.hansen | 43d26ec | 2008-07-03 15:10:15 +0000 | [diff] [blame] | 2 | // Redistribution and use in source and binary forms, with or without |
| 3 | // modification, are permitted provided that the following conditions are |
| 4 | // met: |
| 5 | // |
| 6 | // * Redistributions of source code must retain the above copyright |
| 7 | // notice, this list of conditions and the following disclaimer. |
| 8 | // * Redistributions in binary form must reproduce the above |
| 9 | // copyright notice, this list of conditions and the following |
| 10 | // disclaimer in the documentation and/or other materials provided |
| 11 | // with the distribution. |
| 12 | // * Neither the name of Google Inc. nor the names of its |
| 13 | // contributors may be used to endorse or promote products derived |
| 14 | // from this software without specific prior written permission. |
| 15 | // |
| 16 | // THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS |
| 17 | // "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT |
| 18 | // LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR |
| 19 | // A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT |
| 20 | // OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, |
| 21 | // SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT |
| 22 | // LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, |
| 23 | // DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY |
| 24 | // THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT |
| 25 | // (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE |
| 26 | // OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
| 27 | |
| 28 | #include "v8.h" |
| 29 | |
| 30 | #include "ast.h" |
ager@chromium.org | ce5e87b | 2010-03-10 10:24:18 +0000 | [diff] [blame] | 31 | #include "handles.h" |
christian.plesner.hansen | 43d26ec | 2008-07-03 15:10:15 +0000 | [diff] [blame] | 32 | #include "scanner.h" |
erik.corry@gmail.com | 4a6c327 | 2010-11-18 12:04:40 +0000 | [diff] [blame] | 33 | #include "unicode-inl.h" |
christian.plesner.hansen | 43d26ec | 2008-07-03 15:10:15 +0000 | [diff] [blame] | 34 | |
kasperl@chromium.org | 71affb5 | 2009-05-26 05:44:31 +0000 | [diff] [blame] | 35 | namespace v8 { |
| 36 | namespace internal { |
christian.plesner.hansen | 43d26ec | 2008-07-03 15:10:15 +0000 | [diff] [blame] | 37 | |
| 38 | // ---------------------------------------------------------------------------- |
ager@chromium.org | 5f0c45f | 2010-12-17 08:51:21 +0000 | [diff] [blame] | 39 | // BufferedUC16CharacterStreams |
christian.plesner.hansen | 43d26ec | 2008-07-03 15:10:15 +0000 | [diff] [blame] | 40 | |
ager@chromium.org | 5f0c45f | 2010-12-17 08:51:21 +0000 | [diff] [blame] | 41 | BufferedUC16CharacterStream::BufferedUC16CharacterStream() |
| 42 | : UC16CharacterStream(), |
| 43 | pushback_limit_(NULL) { |
| 44 | // Initialize buffer as being empty. First read will fill the buffer. |
| 45 | buffer_cursor_ = buffer_; |
| 46 | buffer_end_ = buffer_; |
| 47 | } |
sgjesse@chromium.org | 911335c | 2009-08-19 12:59:44 +0000 | [diff] [blame] | 48 | |
ager@chromium.org | 5f0c45f | 2010-12-17 08:51:21 +0000 | [diff] [blame] | 49 | BufferedUC16CharacterStream::~BufferedUC16CharacterStream() { } |
sgjesse@chromium.org | 911335c | 2009-08-19 12:59:44 +0000 | [diff] [blame] | 50 | |
sgjesse@chromium.org | c6c5718 | 2011-01-17 12:24:25 +0000 | [diff] [blame] | 51 | void BufferedUC16CharacterStream::PushBack(uc32 character) { |
| 52 | if (character == kEndOfInput) { |
ager@chromium.org | 5f0c45f | 2010-12-17 08:51:21 +0000 | [diff] [blame] | 53 | pos_--; |
| 54 | return; |
ager@chromium.org | ce5e87b | 2010-03-10 10:24:18 +0000 | [diff] [blame] | 55 | } |
sgjesse@chromium.org | c6c5718 | 2011-01-17 12:24:25 +0000 | [diff] [blame] | 56 | if (pushback_limit_ == NULL && buffer_cursor_ > buffer_) { |
| 57 | // buffer_ is writable, buffer_cursor_ is const pointer. |
| 58 | buffer_[--buffer_cursor_ - buffer_] = static_cast<uc16>(character); |
| 59 | pos_--; |
| 60 | return; |
| 61 | } |
| 62 | SlowPushBack(static_cast<uc16>(character)); |
sgjesse@chromium.org | 911335c | 2009-08-19 12:59:44 +0000 | [diff] [blame] | 63 | } |
| 64 | |
| 65 | |
ager@chromium.org | 5f0c45f | 2010-12-17 08:51:21 +0000 | [diff] [blame] | 66 | void BufferedUC16CharacterStream::SlowPushBack(uc16 character) { |
| 67 | // In pushback mode, the end of the buffer contains pushback, |
| 68 | // and the start of the buffer (from buffer start to pushback_limit_) |
| 69 | // contains valid data that comes just after the pushback. |
| 70 | // We NULL the pushback_limit_ if pushing all the way back to the |
| 71 | // start of the buffer. |
| 72 | |
| 73 | if (pushback_limit_ == NULL) { |
| 74 | // Enter pushback mode. |
| 75 | pushback_limit_ = buffer_end_; |
| 76 | buffer_end_ = buffer_ + kBufferSize; |
| 77 | buffer_cursor_ = buffer_end_; |
| 78 | } |
erik.corry@gmail.com | d91075f | 2011-02-10 07:45:38 +0000 | [diff] [blame] | 79 | // Ensure that there is room for at least one pushback. |
| 80 | ASSERT(buffer_cursor_ > buffer_); |
ager@chromium.org | 5f0c45f | 2010-12-17 08:51:21 +0000 | [diff] [blame] | 81 | ASSERT(pos_ > 0); |
| 82 | buffer_[--buffer_cursor_ - buffer_] = character; |
| 83 | if (buffer_cursor_ == buffer_) { |
| 84 | pushback_limit_ = NULL; |
| 85 | } else if (buffer_cursor_ < pushback_limit_) { |
| 86 | pushback_limit_ = buffer_cursor_; |
| 87 | } |
christian.plesner.hansen | 43d26ec | 2008-07-03 15:10:15 +0000 | [diff] [blame] | 88 | pos_--; |
| 89 | } |
| 90 | |
| 91 | |
ager@chromium.org | 5f0c45f | 2010-12-17 08:51:21 +0000 | [diff] [blame] | 92 | bool BufferedUC16CharacterStream::ReadBlock() { |
erik.corry@gmail.com | d91075f | 2011-02-10 07:45:38 +0000 | [diff] [blame] | 93 | buffer_cursor_ = buffer_; |
ager@chromium.org | 5f0c45f | 2010-12-17 08:51:21 +0000 | [diff] [blame] | 94 | if (pushback_limit_ != NULL) { |
erik.corry@gmail.com | d91075f | 2011-02-10 07:45:38 +0000 | [diff] [blame] | 95 | // Leave pushback mode. |
ager@chromium.org | 5f0c45f | 2010-12-17 08:51:21 +0000 | [diff] [blame] | 96 | buffer_end_ = pushback_limit_; |
| 97 | pushback_limit_ = NULL; |
erik.corry@gmail.com | d91075f | 2011-02-10 07:45:38 +0000 | [diff] [blame] | 98 | // If there were any valid characters left at the |
| 99 | // start of the buffer, use those. |
| 100 | if (buffer_cursor_ < buffer_end_) return true; |
| 101 | // Otherwise read a new block. |
ager@chromium.org | 5f0c45f | 2010-12-17 08:51:21 +0000 | [diff] [blame] | 102 | } |
| 103 | unsigned length = FillBuffer(pos_, kBufferSize); |
ager@chromium.org | 5f0c45f | 2010-12-17 08:51:21 +0000 | [diff] [blame] | 104 | buffer_end_ = buffer_ + length; |
| 105 | return length > 0; |
| 106 | } |
| 107 | |
| 108 | |
| 109 | unsigned BufferedUC16CharacterStream::SlowSeekForward(unsigned delta) { |
| 110 | // Leave pushback mode (i.e., ignore that there might be valid data |
| 111 | // in the buffer before the pushback_limit_ point). |
| 112 | pushback_limit_ = NULL; |
| 113 | return BufferSeekForward(delta); |
| 114 | } |
| 115 | |
| 116 | // ---------------------------------------------------------------------------- |
| 117 | // GenericStringUC16CharacterStream |
| 118 | |
| 119 | |
| 120 | GenericStringUC16CharacterStream::GenericStringUC16CharacterStream( |
| 121 | Handle<String> data, |
| 122 | unsigned start_position, |
| 123 | unsigned end_position) |
| 124 | : string_(data), |
| 125 | length_(end_position) { |
| 126 | ASSERT(end_position >= start_position); |
| 127 | buffer_cursor_ = buffer_; |
| 128 | buffer_end_ = buffer_; |
| 129 | pos_ = start_position; |
| 130 | } |
| 131 | |
| 132 | |
| 133 | GenericStringUC16CharacterStream::~GenericStringUC16CharacterStream() { } |
| 134 | |
| 135 | |
| 136 | unsigned GenericStringUC16CharacterStream::BufferSeekForward(unsigned delta) { |
| 137 | unsigned old_pos = pos_; |
| 138 | pos_ = Min(pos_ + delta, length_); |
| 139 | ReadBlock(); |
| 140 | return pos_ - old_pos; |
| 141 | } |
| 142 | |
| 143 | |
| 144 | unsigned GenericStringUC16CharacterStream::FillBuffer(unsigned from_pos, |
| 145 | unsigned length) { |
| 146 | if (from_pos >= length_) return 0; |
| 147 | if (from_pos + length > length_) { |
| 148 | length = length_ - from_pos; |
| 149 | } |
| 150 | String::WriteToFlat<uc16>(*string_, buffer_, from_pos, from_pos + length); |
| 151 | return length; |
| 152 | } |
| 153 | |
| 154 | |
| 155 | // ---------------------------------------------------------------------------- |
| 156 | // Utf8ToUC16CharacterStream |
| 157 | Utf8ToUC16CharacterStream::Utf8ToUC16CharacterStream(const byte* data, |
| 158 | unsigned length) |
| 159 | : BufferedUC16CharacterStream(), |
| 160 | raw_data_(data), |
| 161 | raw_data_length_(length), |
| 162 | raw_data_pos_(0), |
| 163 | raw_character_position_(0) { |
| 164 | ReadBlock(); |
| 165 | } |
| 166 | |
| 167 | |
| 168 | Utf8ToUC16CharacterStream::~Utf8ToUC16CharacterStream() { } |
| 169 | |
| 170 | |
| 171 | unsigned Utf8ToUC16CharacterStream::BufferSeekForward(unsigned delta) { |
| 172 | unsigned old_pos = pos_; |
| 173 | unsigned target_pos = pos_ + delta; |
| 174 | SetRawPosition(target_pos); |
| 175 | pos_ = raw_character_position_; |
| 176 | ReadBlock(); |
| 177 | return pos_ - old_pos; |
| 178 | } |
| 179 | |
| 180 | |
| 181 | unsigned Utf8ToUC16CharacterStream::FillBuffer(unsigned char_position, |
| 182 | unsigned length) { |
| 183 | static const unibrow::uchar kMaxUC16Character = 0xffff; |
| 184 | SetRawPosition(char_position); |
| 185 | if (raw_character_position_ != char_position) { |
| 186 | // char_position was not a valid position in the stream (hit the end |
| 187 | // while spooling to it). |
| 188 | return 0u; |
| 189 | } |
| 190 | unsigned i = 0; |
| 191 | while (i < length) { |
| 192 | if (raw_data_pos_ == raw_data_length_) break; |
| 193 | unibrow::uchar c = raw_data_[raw_data_pos_]; |
| 194 | if (c <= unibrow::Utf8::kMaxOneByteChar) { |
| 195 | raw_data_pos_++; |
| 196 | } else { |
| 197 | c = unibrow::Utf8::CalculateValue(raw_data_ + raw_data_pos_, |
| 198 | raw_data_length_ - raw_data_pos_, |
| 199 | &raw_data_pos_); |
| 200 | // Don't allow characters outside of the BMP. |
| 201 | if (c > kMaxUC16Character) { |
| 202 | c = unibrow::Utf8::kBadChar; |
| 203 | } |
| 204 | } |
| 205 | buffer_[i++] = static_cast<uc16>(c); |
| 206 | } |
| 207 | raw_character_position_ = char_position + i; |
| 208 | return i; |
| 209 | } |
| 210 | |
| 211 | |
| 212 | static const byte kUtf8MultiByteMask = 0xC0; |
| 213 | static const byte kUtf8MultiByteCharStart = 0xC0; |
| 214 | static const byte kUtf8MultiByteCharFollower = 0x80; |
| 215 | |
| 216 | |
| 217 | #ifdef DEBUG |
| 218 | static bool IsUtf8MultiCharacterStart(byte first_byte) { |
| 219 | return (first_byte & kUtf8MultiByteMask) == kUtf8MultiByteCharStart; |
| 220 | } |
| 221 | #endif |
| 222 | |
| 223 | |
| 224 | static bool IsUtf8MultiCharacterFollower(byte later_byte) { |
| 225 | return (later_byte & kUtf8MultiByteMask) == kUtf8MultiByteCharFollower; |
| 226 | } |
| 227 | |
| 228 | |
| 229 | // Move the cursor back to point at the preceding UTF-8 character start |
| 230 | // in the buffer. |
| 231 | static inline void Utf8CharacterBack(const byte* buffer, unsigned* cursor) { |
| 232 | byte character = buffer[--*cursor]; |
| 233 | if (character > unibrow::Utf8::kMaxOneByteChar) { |
| 234 | ASSERT(IsUtf8MultiCharacterFollower(character)); |
| 235 | // Last byte of a multi-byte character encoding. Step backwards until |
| 236 | // pointing to the first byte of the encoding, recognized by having the |
| 237 | // top two bits set. |
| 238 | while (IsUtf8MultiCharacterFollower(buffer[--*cursor])) { } |
| 239 | ASSERT(IsUtf8MultiCharacterStart(buffer[*cursor])); |
christian.plesner.hansen | 43d26ec | 2008-07-03 15:10:15 +0000 | [diff] [blame] | 240 | } |
| 241 | } |
| 242 | |
| 243 | |
ager@chromium.org | 5f0c45f | 2010-12-17 08:51:21 +0000 | [diff] [blame] | 244 | // Move the cursor forward to point at the next following UTF-8 character start |
| 245 | // in the buffer. |
| 246 | static inline void Utf8CharacterForward(const byte* buffer, unsigned* cursor) { |
| 247 | byte character = buffer[(*cursor)++]; |
| 248 | if (character > unibrow::Utf8::kMaxOneByteChar) { |
| 249 | // First character of a multi-byte character encoding. |
| 250 | // The number of most-significant one-bits determines the length of the |
| 251 | // encoding: |
| 252 | // 110..... - (0xCx, 0xDx) one additional byte (minimum). |
| 253 | // 1110.... - (0xEx) two additional bytes. |
| 254 | // 11110... - (0xFx) three additional bytes (maximum). |
| 255 | ASSERT(IsUtf8MultiCharacterStart(character)); |
| 256 | // Additional bytes is: |
| 257 | // 1 if value in range 0xC0 .. 0xDF. |
| 258 | // 2 if value in range 0xE0 .. 0xEF. |
| 259 | // 3 if value in range 0xF0 .. 0xF7. |
| 260 | // Encode that in a single value. |
| 261 | unsigned additional_bytes = |
| 262 | ((0x3211u) >> (((character - 0xC0) >> 2) & 0xC)) & 0x03; |
| 263 | *cursor += additional_bytes; |
| 264 | ASSERT(!IsUtf8MultiCharacterFollower(buffer[1 + additional_bytes])); |
| 265 | } |
| 266 | } |
| 267 | |
| 268 | |
| 269 | void Utf8ToUC16CharacterStream::SetRawPosition(unsigned target_position) { |
| 270 | if (raw_character_position_ > target_position) { |
| 271 | // Spool backwards in utf8 buffer. |
| 272 | do { |
| 273 | Utf8CharacterBack(raw_data_, &raw_data_pos_); |
| 274 | raw_character_position_--; |
| 275 | } while (raw_character_position_ > target_position); |
| 276 | return; |
| 277 | } |
| 278 | // Spool forwards in the utf8 buffer. |
| 279 | while (raw_character_position_ < target_position) { |
| 280 | if (raw_data_pos_ == raw_data_length_) return; |
| 281 | Utf8CharacterForward(raw_data_, &raw_data_pos_); |
| 282 | raw_character_position_++; |
| 283 | } |
| 284 | } |
| 285 | |
| 286 | |
| 287 | // ---------------------------------------------------------------------------- |
| 288 | // ExternalTwoByteStringUC16CharacterStream |
| 289 | |
| 290 | ExternalTwoByteStringUC16CharacterStream:: |
| 291 | ~ExternalTwoByteStringUC16CharacterStream() { } |
| 292 | |
| 293 | |
| 294 | ExternalTwoByteStringUC16CharacterStream |
| 295 | ::ExternalTwoByteStringUC16CharacterStream( |
| 296 | Handle<ExternalTwoByteString> data, |
| 297 | int start_position, |
| 298 | int end_position) |
| 299 | : UC16CharacterStream(), |
| 300 | source_(data), |
| 301 | raw_data_(data->GetTwoByteData(start_position)) { |
| 302 | buffer_cursor_ = raw_data_, |
| 303 | buffer_end_ = raw_data_ + (end_position - start_position); |
| 304 | pos_ = start_position; |
christian.plesner.hansen | 43d26ec | 2008-07-03 15:10:15 +0000 | [diff] [blame] | 305 | } |
| 306 | |
| 307 | |
ricow@chromium.org | 65fae84 | 2010-08-25 15:26:24 +0000 | [diff] [blame] | 308 | // ---------------------------------------------------------------------------- |
| 309 | // Scanner::LiteralScope |
| 310 | |
| 311 | Scanner::LiteralScope::LiteralScope(Scanner* self) |
| 312 | : scanner_(self), complete_(false) { |
| 313 | self->StartLiteral(); |
| 314 | } |
| 315 | |
| 316 | |
| 317 | Scanner::LiteralScope::~LiteralScope() { |
| 318 | if (!complete_) scanner_->DropLiteral(); |
| 319 | } |
| 320 | |
| 321 | |
| 322 | void Scanner::LiteralScope::Complete() { |
| 323 | scanner_->TerminateLiteral(); |
| 324 | complete_ = true; |
| 325 | } |
| 326 | |
christian.plesner.hansen | 43d26ec | 2008-07-03 15:10:15 +0000 | [diff] [blame] | 327 | } } // namespace v8::internal |