1 // Copyright 2011 the V8 project authors. All rights reserved.
2 // Redistribution and use in source and binary forms, with or without
3 // modification, are permitted provided that the following conditions are
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.
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.
30 #include "scanner-character-streams.h"
33 #include "unicode-inl.h"
38 // ----------------------------------------------------------------------------
39 // BufferedUtf16CharacterStreams
41 BufferedUtf16CharacterStream::BufferedUtf16CharacterStream()
42 : Utf16CharacterStream(),
43 pushback_limit_(NULL) {
44 // Initialize buffer as being empty. First read will fill the buffer.
45 buffer_cursor_ = buffer_;
46 buffer_end_ = buffer_;
49 BufferedUtf16CharacterStream::~BufferedUtf16CharacterStream() { }
51 void BufferedUtf16CharacterStream::PushBack(uc32 character) {
52 if (character == kEndOfInput) {
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);
62 SlowPushBack(static_cast<uc16>(character));
66 void BufferedUtf16CharacterStream::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.
73 if (pushback_limit_ == NULL) {
74 // Enter pushback mode.
75 pushback_limit_ = buffer_end_;
76 buffer_end_ = buffer_ + kBufferSize;
77 buffer_cursor_ = buffer_end_;
79 // Ensure that there is room for at least one pushback.
80 ASSERT(buffer_cursor_ > buffer_);
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_;
92 bool BufferedUtf16CharacterStream::ReadBlock() {
93 buffer_cursor_ = buffer_;
94 if (pushback_limit_ != NULL) {
95 // Leave pushback mode.
96 buffer_end_ = pushback_limit_;
97 pushback_limit_ = NULL;
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.
103 unsigned length = FillBuffer(pos_, kBufferSize);
104 buffer_end_ = buffer_ + length;
109 unsigned BufferedUtf16CharacterStream::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);
116 // ----------------------------------------------------------------------------
117 // GenericStringUtf16CharacterStream
120 GenericStringUtf16CharacterStream::GenericStringUtf16CharacterStream(
122 unsigned start_position,
123 unsigned end_position)
125 length_(end_position) {
126 ASSERT(end_position >= start_position);
127 buffer_cursor_ = buffer_;
128 buffer_end_ = buffer_;
129 pos_ = start_position;
133 GenericStringUtf16CharacterStream::~GenericStringUtf16CharacterStream() { }
136 unsigned GenericStringUtf16CharacterStream::BufferSeekForward(unsigned delta) {
137 unsigned old_pos = pos_;
138 pos_ = Min(pos_ + delta, length_);
140 return pos_ - old_pos;
144 unsigned GenericStringUtf16CharacterStream::FillBuffer(unsigned from_pos,
146 if (from_pos >= length_) return 0;
147 if (from_pos + length > length_) {
148 length = length_ - from_pos;
150 String::WriteToFlat<uc16>(*string_, buffer_, from_pos, from_pos + length);
155 // ----------------------------------------------------------------------------
156 // Utf8ToUtf16CharacterStream
157 Utf8ToUtf16CharacterStream::Utf8ToUtf16CharacterStream(const byte* data,
159 : BufferedUtf16CharacterStream(),
161 raw_data_length_(length),
163 raw_character_position_(0) {
168 Utf8ToUtf16CharacterStream::~Utf8ToUtf16CharacterStream() { }
171 unsigned Utf8ToUtf16CharacterStream::BufferSeekForward(unsigned delta) {
172 unsigned old_pos = pos_;
173 unsigned target_pos = pos_ + delta;
174 SetRawPosition(target_pos);
175 pos_ = raw_character_position_;
177 return pos_ - old_pos;
181 unsigned Utf8ToUtf16CharacterStream::FillBuffer(unsigned char_position,
183 static const unibrow::uchar kMaxUtf16Character = 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).
191 while (i < length - 1) {
192 if (raw_data_pos_ == raw_data_length_) break;
193 unibrow::uchar c = raw_data_[raw_data_pos_];
194 if (c <= unibrow::Utf8::kMaxOneByteChar) {
197 c = unibrow::Utf8::CalculateValue(raw_data_ + raw_data_pos_,
198 raw_data_length_ - raw_data_pos_,
201 if (c > kMaxUtf16Character) {
202 buffer_[i++] = unibrow::Utf16::LeadSurrogate(c);
203 buffer_[i++] = unibrow::Utf16::TrailSurrogate(c);
205 buffer_[i++] = static_cast<uc16>(c);
208 raw_character_position_ = char_position + i;
213 static const byte kUtf8MultiByteMask = 0xC0;
214 static const byte kUtf8MultiByteCharStart = 0xC0;
215 static const byte kUtf8MultiByteCharFollower = 0x80;
219 static bool IsUtf8MultiCharacterStart(byte first_byte) {
220 return (first_byte & kUtf8MultiByteMask) == kUtf8MultiByteCharStart;
225 static bool IsUtf8MultiCharacterFollower(byte later_byte) {
226 return (later_byte & kUtf8MultiByteMask) == kUtf8MultiByteCharFollower;
230 // Move the cursor back to point at the preceding UTF-8 character start
232 static inline void Utf8CharacterBack(const byte* buffer, unsigned* cursor) {
233 byte character = buffer[--*cursor];
234 if (character > unibrow::Utf8::kMaxOneByteChar) {
235 ASSERT(IsUtf8MultiCharacterFollower(character));
236 // Last byte of a multi-byte character encoding. Step backwards until
237 // pointing to the first byte of the encoding, recognized by having the
239 while (IsUtf8MultiCharacterFollower(buffer[--*cursor])) { }
240 ASSERT(IsUtf8MultiCharacterStart(buffer[*cursor]));
245 // Move the cursor forward to point at the next following UTF-8 character start
247 static inline void Utf8CharacterForward(const byte* buffer, unsigned* cursor) {
248 byte character = buffer[(*cursor)++];
249 if (character > unibrow::Utf8::kMaxOneByteChar) {
250 // First character of a multi-byte character encoding.
251 // The number of most-significant one-bits determines the length of the
253 // 110..... - (0xCx, 0xDx) one additional byte (minimum).
254 // 1110.... - (0xEx) two additional bytes.
255 // 11110... - (0xFx) three additional bytes (maximum).
256 ASSERT(IsUtf8MultiCharacterStart(character));
257 // Additional bytes is:
258 // 1 if value in range 0xC0 .. 0xDF.
259 // 2 if value in range 0xE0 .. 0xEF.
260 // 3 if value in range 0xF0 .. 0xF7.
261 // Encode that in a single value.
262 unsigned additional_bytes =
263 ((0x3211u) >> (((character - 0xC0) >> 2) & 0xC)) & 0x03;
264 *cursor += additional_bytes;
265 ASSERT(!IsUtf8MultiCharacterFollower(buffer[1 + additional_bytes]));
270 // This can't set a raw position between two surrogate pairs, since there
271 // is no position in the UTF8 stream that corresponds to that. This assumes
272 // that the surrogate pair is correctly coded as a 4 byte UTF-8 sequence. If
273 // it is illegally coded as two 3 byte sequences then there is no problem here.
274 void Utf8ToUtf16CharacterStream::SetRawPosition(unsigned target_position) {
275 if (raw_character_position_ > target_position) {
276 // Spool backwards in utf8 buffer.
278 int old_pos = raw_data_pos_;
279 Utf8CharacterBack(raw_data_, &raw_data_pos_);
280 raw_character_position_--;
281 ASSERT(old_pos - raw_data_pos_ <= 4);
282 // Step back over both code units for surrogate pairs.
283 if (old_pos - raw_data_pos_ == 4) raw_character_position_--;
284 } while (raw_character_position_ > target_position);
285 // No surrogate pair splitting.
286 ASSERT(raw_character_position_ == target_position);
289 // Spool forwards in the utf8 buffer.
290 while (raw_character_position_ < target_position) {
291 if (raw_data_pos_ == raw_data_length_) return;
292 int old_pos = raw_data_pos_;
293 Utf8CharacterForward(raw_data_, &raw_data_pos_);
294 raw_character_position_++;
295 ASSERT(raw_data_pos_ - old_pos <= 4);
296 if (raw_data_pos_ - old_pos == 4) raw_character_position_++;
298 // No surrogate pair splitting.
299 ASSERT(raw_character_position_ == target_position);
303 // ----------------------------------------------------------------------------
304 // ExternalTwoByteStringUtf16CharacterStream
306 ExternalTwoByteStringUtf16CharacterStream::
307 ~ExternalTwoByteStringUtf16CharacterStream() { }
310 ExternalTwoByteStringUtf16CharacterStream
311 ::ExternalTwoByteStringUtf16CharacterStream(
312 Handle<ExternalTwoByteString> data,
315 : Utf16CharacterStream(),
317 raw_data_(data->GetTwoByteData(start_position)) {
318 buffer_cursor_ = raw_data_,
319 buffer_end_ = raw_data_ + (end_position - start_position);
320 pos_ = start_position;
323 } } // namespace v8::internal