1 /*
2 * Copyright (C) 2008 Apple Inc. All Rights Reserved.
3 * Copyright (C) 2009 Torch Mobile, Inc. http://www.torchmobile.com/
4 * Copyright (C) 2010 Google, Inc. All Rights Reserved.
5 *
6 * Redistribution and use in source and binary forms, with or without
7 * modification, are permitted provided that the following conditions
8 * are met:
9 * 1. Redistributions of source code must retain the above copyright
10 * notice, this list of conditions and the following disclaimer.
11 * 2. Redistributions in binary form must reproduce the above copyright
12 * notice, this list of conditions and the following disclaimer in the
13 * documentation and/or other materials provided with the distribution.
14 *
15 * THIS SOFTWARE IS PROVIDED BY APPLE INC. ``AS IS'' AND ANY
16 * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
17 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
18 * PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL APPLE INC. OR
19 * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
20 * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
21 * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
22 * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
23 * OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
24 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
25 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
26 */
27
28 #ifndef MarkupTokenizerInlines_h
29 #define MarkupTokenizerInlines_h
30
31 #include "platform/text/SegmentedString.h"
32
33 namespace WebCore {
34
isTokenizerWhitespace(UChar cc)35 inline bool isTokenizerWhitespace(UChar cc)
36 {
37 return cc == ' ' || cc == '\x0A' || cc == '\x09' || cc == '\x0C';
38 }
39
advanceStringAndASSERTIgnoringCase(SegmentedString & source,const char * expectedCharacters)40 inline void advanceStringAndASSERTIgnoringCase(SegmentedString& source, const char* expectedCharacters)
41 {
42 while (*expectedCharacters)
43 source.advanceAndASSERTIgnoringCase(*expectedCharacters++);
44 }
45
advanceStringAndASSERT(SegmentedString & source,const char * expectedCharacters)46 inline void advanceStringAndASSERT(SegmentedString& source, const char* expectedCharacters)
47 {
48 while (*expectedCharacters)
49 source.advanceAndASSERT(*expectedCharacters++);
50 }
51
52 #if COMPILER(MSVC)
53 // We need to disable the "unreachable code" warning because we want to assert
54 // that some code points aren't reached in the state machine.
55 #pragma warning(disable: 4702)
56 #endif
57
58 #define BEGIN_STATE(prefix, stateName) case prefix::stateName: stateName:
59 #define END_STATE() ASSERT_NOT_REACHED(); break;
60
61 // We use this macro when the HTML5 spec says "reconsume the current input
62 // character in the <mumble> state."
63 #define RECONSUME_IN(prefix, stateName) \
64 do { \
65 m_state = prefix::stateName; \
66 goto stateName; \
67 } while (false)
68
69 // We use this macro when the HTML5 spec says "consume the next input
70 // character ... and switch to the <mumble> state."
71 #define ADVANCE_TO(prefix, stateName) \
72 do { \
73 m_state = prefix::stateName; \
74 if (!m_inputStreamPreprocessor.advance(source)) \
75 return haveBufferedCharacterToken(); \
76 cc = m_inputStreamPreprocessor.nextInputCharacter(); \
77 goto stateName; \
78 } while (false)
79
80 // Sometimes there's more complicated logic in the spec that separates when
81 // we consume the next input character and when we switch to a particular
82 // state. We handle those cases by advancing the source directly and using
83 // this macro to switch to the indicated state.
84 #define SWITCH_TO(prefix, stateName) \
85 do { \
86 m_state = prefix::stateName; \
87 if (source.isEmpty() || !m_inputStreamPreprocessor.peek(source)) \
88 return haveBufferedCharacterToken(); \
89 cc = m_inputStreamPreprocessor.nextInputCharacter(); \
90 goto stateName; \
91 } while (false)
92
93 }
94
95 #endif // MarkupTokenizerInlines_h
96