ios/third_party/blink/src/html_tokenizer.h

   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 HTMLTokenizer_h
  28 #define HTMLTokenizer_h
  29
  30 #include "ios/third_party/blink/src/html_input_stream_preprocessor.h"
  31 #include "ios/third_party/blink/src/html_token.h"
  32
  33 namespace WebCore {
  34
  35 class HTMLTokenizer {
  36     WTF_MAKE_NONCOPYABLE(HTMLTokenizer);
  37
  38 public:
  39     HTMLTokenizer();
  40     ~HTMLTokenizer();
  41
  42     void reset();
  43
  44     enum State {
  45         DataState,
  46         TagOpenState,
  47         EndTagOpenState,
  48         TagNameState,
  49         BeforeAttributeNameState,
  50         AttributeNameState,
  51         AfterAttributeNameState,
  52         BeforeAttributeValueState,
  53         AttributeValueDoubleQuotedState,
  54         AttributeValueSingleQuotedState,
  55         AttributeValueUnquotedState,
  56         AfterAttributeValueQuotedState,
  57         SelfClosingStartTagState,
  58         BogusCommentState,
  59         // The ContinueBogusCommentState is not in the HTML5 spec, but we use
  60         // it internally to keep track of whether we've started the bogus
  61         // comment token yet.
  62         ContinueBogusCommentState,
  63         MarkupDeclarationOpenState,
  64         CommentStartState,
  65         CommentStartDashState,
  66         CommentState,
  67         CommentEndDashState,
  68         CommentEndState,
  69         CommentEndBangState,
  70         DOCTYPEState,
  71         BeforeDOCTYPENameState,
  72         DOCTYPENameState,
  73         AfterDOCTYPENameState,
  74         AfterDOCTYPEPublicKeywordState,
  75         BeforeDOCTYPEPublicIdentifierState,
  76         DOCTYPEPublicIdentifierDoubleQuotedState,
  77         DOCTYPEPublicIdentifierSingleQuotedState,
  78         AfterDOCTYPEPublicIdentifierState,
  79         BetweenDOCTYPEPublicAndSystemIdentifiersState,
  80         AfterDOCTYPESystemKeywordState,
  81         BeforeDOCTYPESystemIdentifierState,
  82         DOCTYPESystemIdentifierDoubleQuotedState,
  83         DOCTYPESystemIdentifierSingleQuotedState,
  84         AfterDOCTYPESystemIdentifierState,
  85         BogusDOCTYPEState,
  86         CDATASectionState,
  87         // These CDATA states are not in the HTML5 spec, but we use them internally.
  88         CDATASectionRightSquareBracketState,
  89         CDATASectionDoubleRightSquareBracketState,
  90     };
  91
  92     // This function returns true if it emits a token. Otherwise, callers
  93     // must provide the same (in progress) token on the next call (unless
  94     // they call reset() first).
  95     bool nextToken(CharacterProvider&, HTMLToken&);
  96
  97     State state() const { return m_state; }
  98     void setState(State state) { m_state = state; }
  99
 100     inline bool shouldSkipNullCharacters() const
 101     {
 102         return m_state == HTMLTokenizer::DataState;
 103     }
 104
 105 private:
 106     inline void parseError();
 107
 108     inline bool emitAndResumeIn(CharacterProvider& source, State state)
 109     {
 110         ASSERT(m_token->type() != HTMLToken::Uninitialized);
 111         m_state = state;
 112         source.next();
 113         return true;
 114     }
 115
 116     inline bool emitAndReconsumeIn(CharacterProvider&, State state)
 117     {
 118         ASSERT(m_token->type() != HTMLToken::Uninitialized);
 119         m_state = state;
 120         return true;
 121     }
 122
 123     inline bool emitEndOfFile(CharacterProvider& source)
 124     {
 125         if (haveBufferedCharacterToken())
 126             return true;
 127         m_state = HTMLTokenizer::DataState;
 128         source.next();
 129         m_token->clear();
 130         m_token->makeEndOfFile();
 131         return true;
 132     }
 133
 134     // Return whether we need to emit a character token before dealing with
 135     // the buffered end tag.
 136     inline bool flushBufferedEndTag(CharacterProvider&);
 137
 138     inline bool haveBufferedCharacterToken()
 139     {
 140         return m_token->type() == HTMLToken::Character;
 141     }
 142
 143     State m_state;
 144
 145     // m_token is owned by the caller. If nextToken is not on the stack,
 146     // this member might be pointing to unallocated memory.
 147     HTMLToken* m_token;
 148
 149     // http://www.whatwg.org/specs/web-apps/current-work/#additional-allowed-character
 150     LChar m_additionalAllowedCharacter;
 151
 152     // http://www.whatwg.org/specs/web-apps/current-work/#preprocessing-the-input-stream
 153     InputStreamPreprocessor<HTMLTokenizer> m_inputStreamPreprocessor;
 154 };
 155 }
 156
 157 #endif