1 /* 2 * Copyright (C) 2008 Apple Inc. All Rights Reserved. 3 * Copyright (C) 2010 Google, Inc. All Rights Reserved. 4 * 5 * Redistribution and use in source and binary forms, with or without 6 * modification, are permitted provided that the following conditions 7 * are met: 8 * 1. Redistributions of source code must retain the above copyright 9 * notice, this list of conditions and the following disclaimer. 10 * 2. Redistributions in binary form must reproduce the above copyright 11 * notice, this list of conditions and the following disclaimer in the 12 * documentation and/or other materials provided with the distribution. 13 * 14 * THIS SOFTWARE IS PROVIDED BY APPLE INC. ``AS IS'' AND ANY 15 * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 16 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR 17 * PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL APPLE INC. OR 18 * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, 19 * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, 20 * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR 21 * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY 22 * OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT 23 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE 24 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. 25 */ 26 27 #ifndef HTMLEntityParser_h 28 #define HTMLEntityParser_h 29 30 #include "platform/text/SegmentedString.h" 31 32 namespace WebCore { 33 34 class DecodedHTMLEntity { 35 private: 36 // HTML entities contain at most four UTF-16 code units. 37 static const unsigned kMaxLength = 4; 38 39 public: DecodedHTMLEntity()40 DecodedHTMLEntity() : length(0) { } 41 isEmpty()42 bool isEmpty() const { return !length; } 43 append(UChar c)44 void append(UChar c) 45 { 46 RELEASE_ASSERT(length < kMaxLength); 47 data[length++] = c; 48 } 49 append(UChar32 c)50 void append(UChar32 c) 51 { 52 if (U_IS_BMP(c)) { 53 append(static_cast<UChar>(c)); 54 return; 55 } 56 append(U16_LEAD(c)); 57 append(U16_TRAIL(c)); 58 } 59 60 unsigned length; 61 UChar data[kMaxLength]; 62 }; 63 64 bool consumeHTMLEntity(SegmentedString&, DecodedHTMLEntity& decodedEntity, bool& notEnoughCharacters, UChar additionalAllowedCharacter = '\0'); 65 66 // Used by the XML parser. Not suitable for use in HTML parsing. Use consumeHTMLEntity instead. 67 size_t decodeNamedEntityToUCharArray(const char*, UChar result[4]); 68 69 } 70 71 #endif 72