1 /* 2 * Copyright (C) 2010 Adam Barth. All Rights Reserved. 3 * 4 * Redistribution and use in source and binary forms, with or without 5 * modification, are permitted provided that the following conditions 6 * are met: 7 * 1. Redistributions of source code must retain the above copyright 8 * notice, this list of conditions and the following disclaimer. 9 * 2. Redistributions in binary form must reproduce the above copyright 10 * notice, this list of conditions and the following disclaimer in the 11 * documentation and/or other materials provided with the distribution. 12 * 13 * THIS SOFTWARE IS PROVIDED BY APPLE INC. ``AS IS'' AND ANY 14 * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 15 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR 16 * PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL APPLE INC. OR 17 * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, 18 * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, 19 * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR 20 * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY 21 * OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT 22 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE 23 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. 24 */ 25 26 #include "config.h" 27 #include "core/html/parser/HTMLSourceTracker.h" 28 29 #include "core/html/parser/HTMLTokenizer.h" 30 #include "wtf/text/StringBuilder.h" 31 32 namespace WebCore { 33 34 HTMLSourceTracker::HTMLSourceTracker() 35 { 36 } 37 38 void HTMLSourceTracker::start(SegmentedString& currentInput, HTMLTokenizer* tokenizer, HTMLToken& token) 39 { 40 if (token.type() == HTMLToken::Uninitialized) { 41 m_previousSource.clear(); 42 if (tokenizer->numberOfBufferedCharacters()) 43 m_previousSource = tokenizer->bufferedCharacters(); 44 } else 45 m_previousSource.append(m_currentSource); 46 47 m_currentSource = currentInput; 48 token.setBaseOffset(m_currentSource.numberOfCharactersConsumed() - m_previousSource.length()); 49 } 50 51 void HTMLSourceTracker::end(SegmentedString& currentInput, HTMLTokenizer* tokenizer, HTMLToken& token) 52 { 53 m_cachedSourceForToken = String(); 54 55 // FIXME: This work should really be done by the HTMLTokenizer. 56 token.end(currentInput.numberOfCharactersConsumed() - tokenizer->numberOfBufferedCharacters()); 57 } 58 59 String HTMLSourceTracker::sourceForToken(const HTMLToken& token) 60 { 61 if (!m_cachedSourceForToken.isEmpty()) 62 return m_cachedSourceForToken; 63 64 size_t length; 65 if (token.type() == HTMLToken::EndOfFile) { 66 // Consume the remainder of the input, omitting the null character we use to mark the end of the file. 67 length = m_previousSource.length() + m_currentSource.length() - 1; 68 } else { 69 ASSERT(!token.startIndex()); 70 length = static_cast<size_t>(token.endIndex() - token.startIndex()); 71 } 72 73 StringBuilder source; 74 source.reserveCapacity(length); 75 76 size_t i = 0; 77 for ( ; i < length && !m_previousSource.isEmpty(); ++i) { 78 source.append(m_previousSource.currentChar()); 79 m_previousSource.advance(); 80 } 81 for ( ; i < length; ++i) { 82 ASSERT(!m_currentSource.isEmpty()); 83 source.append(m_currentSource.currentChar()); 84 m_currentSource.advance(); 85 } 86 87 m_cachedSourceForToken = source.toString(); 88 return m_cachedSourceForToken; 89 } 90 91 } 92
