OLD | NEW |
1 /* | 1 /* |
2 * Copyright (C) 2008 Apple Inc. All Rights Reserved. | 2 * Copyright (C) 2008 Apple Inc. All Rights Reserved. |
3 * Copyright (C) 2010 Google, Inc. All Rights Reserved. | 3 * Copyright (C) 2010 Google, Inc. All Rights Reserved. |
4 * | 4 * |
5 * Redistribution and use in source and binary forms, with or without | 5 * Redistribution and use in source and binary forms, with or without |
6 * modification, are permitted provided that the following conditions | 6 * modification, are permitted provided that the following conditions |
7 * are met: | 7 * are met: |
8 * 1. Redistributions of source code must retain the above copyright | 8 * 1. Redistributions of source code must retain the above copyright |
9 * notice, this list of conditions and the following disclaimer. | 9 * notice, this list of conditions and the following disclaimer. |
10 * 2. Redistributions in binary form must reproduce the above copyright | 10 * 2. Redistributions in binary form must reproduce the above copyright |
(...skipping 13 matching lines...) Expand all Loading... |
24 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. | 24 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
25 */ | 25 */ |
26 | 26 |
27 #ifndef HTMLEntityParser_h | 27 #ifndef HTMLEntityParser_h |
28 #define HTMLEntityParser_h | 28 #define HTMLEntityParser_h |
29 | 29 |
30 #include "platform/text/SegmentedString.h" | 30 #include "platform/text/SegmentedString.h" |
31 | 31 |
32 namespace blink { | 32 namespace blink { |
33 | 33 |
34 class DecodedHTMLEntity { | 34 class HTMLEntityParser { |
| 35 public: |
| 36 typedef Vector<UChar, 32> OutputBuffer; |
| 37 |
| 38 HTMLEntityParser(); |
| 39 ~HTMLEntityParser(); |
| 40 |
| 41 void reset(); |
| 42 bool parse(SegmentedString&); |
| 43 |
| 44 const OutputBuffer& result() const { return m_buffer; } |
| 45 |
35 private: | 46 private: |
36 // HTML entities contain at most four UTF-16 code units. | 47 enum EntityState { |
37 static const unsigned kMaxLength = 4; | 48 Initial, |
| 49 Numeric, |
| 50 PossiblyHex, |
| 51 Hex, |
| 52 Decimal, |
| 53 Named |
| 54 }; |
38 | 55 |
39 public: | 56 void finalizeNumericEntity(); |
40 DecodedHTMLEntity() : length(0) { } | 57 void finalizeNamedEntity(); |
41 | 58 |
42 bool isEmpty() const { return !length; } | 59 EntityState m_state; |
43 | 60 UChar32 m_result; |
44 void append(UChar c) | 61 OutputBuffer m_buffer; |
45 { | |
46 RELEASE_ASSERT(length < kMaxLength); | |
47 data[length++] = c; | |
48 } | |
49 | |
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 }; | 62 }; |
63 | 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 consumeHT
MLEntity instead. | |
67 size_t decodeNamedEntityToUCharArray(const char*, UChar result[4]); | |
68 | |
69 } | 64 } |
70 | 65 |
71 #endif | 66 #endif |
OLD | NEW |