C# Tokenizer.ConsumeChar方法代码示例

        public override void Read(Tokenizer t)
        {
            char? c = t.ConsumeChar();

            switch(c){
                case Chars.CHARACTER_TABULATION:
                case Chars.LINE_FEED:
                case Chars.FORM_FEED:
                case Chars.SPACE:
                    t.ChangeTokenState<BeforeAttributeNameState>();
                    return;
                case Chars.SOLIDUS:
                    t.ChangeTokenState<SelfClosingStartTagState>();
                    return;
                case Chars.GREATER_THAN_SIGN:
                    t.ChangeTokenState<DataState>();
                    t.EmitToken();
                    return;
                case null:
                    OnMessageRaised(new SuddenlyEndAtAttributeError());
                    t.UnConsume(1);
                    t.ChangeTokenState<DataState>();
                    return;
                default:
                    OnMessageRaised(new MissingSpaceAfterAttributeValueError(c));
                    t.UnConsume(1);
                    t.ChangeTokenState<BeforeAttributeNameState>();
                    return;
            }
        }

        public override void Read(Tokenizer t)
        {
            char? c = t.ConsumeChar();

            switch(c){
                case Chars.HYPHEN_MINUS:
                    t.ChangeTokenState<ScriptDataDoubleEscapedDashState>();
                    t.EmitToken(Chars.HYPHEN_MINUS);
                    return;
                case Chars.LESS_THAN_SIGN:
                    t.ChangeTokenState<ScriptDataDoubleEscapedLessThanSignState>();
                    t.EmitToken(Chars.LESS_THAN_SIGN);
                    return;
                case Chars.NULL:
                    OnMessageRaised(new NullInScriptError());
                    t.EmitToken(Chars.REPLACEMENT_CHARACTER);
                    return;
                case null:
                    OnMessageRaised(new SuddenlyEndAtScriptError());

                    t.UnConsume(1);
                    t.ChangeTokenState<DataState>();
                    return;
                default:
                    t.EmitToken(c);
                    return;
            }
        }

 // 文字参照
 // 参照されている文字を取得します。失敗したときはnullを返します。
 protected ReferencedCharacterToken ConsumeCharacterReference(Tokenizer t)
 {
     char? c = t.ConsumeChar();
     if(t.AdditionalAllowedCharacter != null && c == t.AdditionalAllowedCharacter){
         // Not a character reference. No characters are consumed, and nothing is returned. (This is not an error, either.)
         OnMessageRaised(new RawAmpersandWarning());
         t.UnConsume(1);
         return null;
     }
     switch(c){
         case Chars.AMPERSAND:
         case Chars.LINE_FEED:
         case Chars.FORM_FEED:
         case Chars.SPACE:
         case Chars.LESS_THAN_SIGN:
         case null:
             // Not a character reference. No characters are consumed, and nothing is returned. (This is not an error, either.)
             OnMessageRaised(new RawAmpersandWarning());
             t.UnConsume(1);
             return null;
         case Chars.NUMBER_SIGN:
             return ConsumeNumericCharacterReference(t);
         default:
             return ConsumeNamedCharacterReference(t);
     }
 }

        public override void Read(Tokenizer t)
        {
            char? c = t.ConsumeChar();

            if(c.IsLatinCapitalLetter()){
                t.TemporaryBuffer = "";
                t.TemporaryBuffer += c.ToLower();
                t.EmitToken(Chars.LESS_THAN_SIGN);
                t.EmitToken(c);
                t.ChangeTokenState<ScriptDataDoubleEscapeStartState>();
                return;
            } else if(c.IsLatinSmallLetter()){
                t.TemporaryBuffer = "";
                t.TemporaryBuffer += c;
                t.EmitToken(Chars.LESS_THAN_SIGN);
                t.EmitToken(c);
                t.ChangeTokenState<ScriptDataDoubleEscapeStartState>();
                return;
            }

            switch(c){
                case Chars.SOLIDUS:
                    t.TemporaryBuffer = "";
                    t.ChangeTokenState<ScriptDataEscapedEndTagOpenState>();
                    return;
                default:
                    t.EmitToken(Chars.LESS_THAN_SIGN);
                    t.UnConsume(1);
                    t.ChangeTokenState<ScriptDataEscapedState>();
                    return;
            }
        }

 public override void Read(Tokenizer t)
 {
     char? c = t.ConsumeChar();
     switch(c){
         case Chars.GREATER_THAN_SIGN:
             OnMessageRaised(new EmptyEndTagError());
             t.ChangeTokenState<DataState>();
             return;
         case null:
             OnMessageRaised(new SuddenlyEndAtTagError());
             t.EmitToken(Chars.LESS_THAN_SIGN);
             t.EmitToken(Chars.SOLIDUS);
             t.UnConsume(1);
             t.ChangeTokenState<DataState>();
             return;
     }
     if(c.IsLatinCapitalLetter()){
         t.CurrentToken = new EndTagToken(){Name = c.ToLower().ToString()};
         t.ChangeTokenState<TagNameState>();
         return;
     } else if(c.IsLatinSmallLetter()){
         t.CurrentToken = new EndTagToken(){Name = c.ToString()};
         t.ChangeTokenState<TagNameState>();
         return;
     }
     OnMessageRaised(new UnknownEndTagError());
     t.ChangeTokenState<BogusCommentState>();
     return;
 }

        public override void Read(Tokenizer t)
        {
            char? c = t.ConsumeChar();

            if(c.IsLatinCapitalLetter()){
                t.TemporaryBuffer += c.ToLower();
                t.EmitToken(c);
                return;
            } else if(c.IsLatinSmallLetter()){
                t.TemporaryBuffer += c;
                t.EmitToken(c);
                return;
            }

            switch(c){
                case Chars.CHARACTER_TABULATION:
                case Chars.LINE_FEED:
                case Chars.FORM_FEED:
                case Chars.SPACE:
                case Chars.SOLIDUS:
                case Chars.GREATER_THAN_SIGN:
                    if(t.TemporaryBuffer.Equals("script", StringComparison.InvariantCulture)){
                        t.ChangeTokenState<ScriptDataDoubleEscapedState>();
                    } else {
                        t.ChangeTokenState<ScriptDataEscapedState>();
                    }
                    t.EmitToken(c);
                    return;
                default:
                    t.UnConsume(1);
                    t.ChangeTokenState<ScriptDataEscapedState>();
                    return;
            }
        }

 public override void Read(Tokenizer t)
 {
     char? c = t.ConsumeChar();
     switch(c){
         case Chars.EXCLAMATION_MARK:
             t.ChangeTokenState<MarkupDeclarationOpenState>();
             return;
         case Chars.SOLIDUS:
             t.ChangeTokenState<EndTagOpenState>();
             return;
         case Chars.QUESTION_MARK:
             OnMessageRaised(new ProcessingInstructionError());
             t.ChangeTokenState<BogusCommentState>();
             return;
     }
     if(c.IsLatinCapitalLetter()){
         t.CurrentToken = new StartTagToken(){Name = c.ToLower().ToString()};
         t.ChangeTokenState<TagNameState>();
         return;
     } else if(c.IsLatinSmallLetter()){
         t.CurrentToken = new StartTagToken(){Name = c.ToString()};
         t.ChangeTokenState<TagNameState>();
         return;
     }
     OnMessageRaised(new UnknownMarkupError());
     t.UnConsume(1);
     t.ChangeTokenState<DataState>();
     t.EmitToken(Chars.LESS_THAN_SIGN);
     return;
 }

        public override void Read(Tokenizer t)
        {
            char? c = t.ConsumeChar();

            switch(c){
                case Chars.CHARACTER_TABULATION:
                case Chars.LINE_FEED:
                case Chars.FORM_FEED:
                case Chars.SPACE:
                    return;
                case Chars.GREATER_THAN_SIGN:{
                    t.ChangeTokenState<DataState>();
                    t.EmitToken();
                    return;
                }
                case null:
                    OnMessageRaised(new SuddenlyEndAtDoctypeError());
                    ((DoctypeToken)t.CurrentToken).ForceQuirks = true;
                    t.UnConsume(1);
                    t.ChangeTokenState<DataState>();
                    t.EmitToken();
                    return;
                default:
                    OnMessageRaised(new UnknownIdentifierAfterDoctypeError());
                    t.ChangeTokenState<BogusDoctypeState>();
                    return;
            }
        }

        public override void Read(Tokenizer t)
        {
            char? c = t.ConsumeChar();
            switch(c){
                case Chars.HYPHEN_MINUS:
                    t.ChangeTokenState<CommentEndState>();
                    return;
                case Chars.NULL:
                    OnMessageRaised(new NullInCommentError());
                    t.CurrentCommentToken.Append(Chars.HYPHEN_MINUS);
                    t.CurrentCommentToken.Append(Chars.REPLACEMENT_CHARACTER);

                    t.ChangeTokenState<CommentState>();
                    return;
                case null:
                    OnMessageRaised(new SuddenlyEndAtCommentError());
                    t.EmitToken();
                    t.UnConsume(1);
                    t.ChangeTokenState<DataState>();
                    return;
                default:
                    t.CurrentCommentToken.Append(Chars.HYPHEN_MINUS);
                    t.CurrentCommentToken.Append(c);
                    t.ChangeTokenState<CommentState>();
                    return;
            }
        }

        /*
        If the character reference is being consumed as part of an attribute, and the last character matched is not a U+003B SEMICOLON character (;), and the next character is either a U+003D EQUALS SIGN character (=) or in the range U+0030 DIGIT ZERO (0) to U+0039 DIGIT NINE (9), U+0041 LATIN CAPITAL LETTER A to U+005A LATIN CAPITAL LETTER Z, or U+0061 LATIN SMALL LETTER A to U+007A LATIN SMALL LETTER Z, then, for historical reasons, all the characters that were matched after the U+0026 AMPERSAND character (&) must be unconsumed, and nothing is returned.
        */
        // 名前による文字参照を展開します。
        protected ReferencedCharacterToken ConsumeNamedCharacterReference(Tokenizer t)
        {
            StringBuilder referenceName = new StringBuilder();
            bool semicolonFound = false;

            char? lastChar = t.CurrentInputChar;
            while(lastChar.IsNameToken()){
                referenceName.Append(lastChar);
                lastChar = t.ConsumeChar();
            }
            if(lastChar == Chars.SEMICOLON){
                referenceName.Append(lastChar);
                semicolonFound = true;
            } else {
                // CurrentInputCharをreferenceNameの末尾にそろえる
                t.UnConsume(1);
            }
            string originalString = referenceName.ToString();

            string matchResult = null;
            while(referenceName.Length > 0){
                if(Chars.ExistsNamedChar(referenceName.ToString())){
                    matchResult = Chars.GetNamedChar(referenceName.ToString());
                    break;
                }
                referenceName.Remove(referenceName.Length-1, 1);
                // CurrentInputCharをreferenceNameの末尾にそろえる
                t.UnConsume(1);
            }

            if(matchResult == null){
                if(semicolonFound){
                    // 名前がなく、セミコロンがある場合はパースエラー
                    // if the characters after the U+0026 AMPERSAND character (&) consist of a sequence of one or more characters in the range ASCII digits, lowercase ASCII letters, and uppercase ASCII letters, followed by a ";" (U+003B) character, then this is a parse error.
                    OnMessageRaised(new UnknownNamedCharacterReferenceWithSemicolonError(originalString));
                } else {
                    // 名前がなくセミコロンがない場合はパースエラーにならない
                    OnMessageRaised(new UnknownNamedCharacterReferenceWithoutSemicolonWarning(originalString));
                }
                t.UnConsume(referenceName.Length);
                return null;
            }
            if(!semicolonFound){
                // 属性値の中のセミコロンなし文字参照は無視する
                if(t.CurrentTokenState is CharacterReferenceInAttributeState && t.NextInputChar.IsSuffixOfIgnoreCharacterReferenceInAttribute()){
                    OnMessageRaised(new IgnoredCharacterReferenceInAttributeWarning(referenceName));
                    t.UnConsume(referenceName.Length);
                    return null;
                }
                // それ以外のセミコロンなし文字参照はエラー
                OnMessageRaised(new NamedCharacterReferenceWithoutSemicolonError(referenceName));
            }

            ReferencedCharacterToken resultToken = new ReferencedCharacterToken(matchResult);
            resultToken.OriginalString = referenceName.ToString();
            return resultToken;
        }

        public override void Read(Tokenizer t)
        {
            char? c = t.ConsumeChar();

            switch(c){
                case Chars.CHARACTER_TABULATION:
                case Chars.LINE_FEED:
                case Chars.FORM_FEED:
                case Chars.SPACE:
                    return;
                case Chars.SOLIDUS:
                    t.ChangeTokenState<SelfClosingStartTagState>();
                    return;
                case Chars.EQUALS_SIGN:
                    t.ChangeTokenState<BeforeAttributeValueState>();
                    return;
                case Chars.GREATER_THAN_SIGN:
                    t.ChangeTokenState<DataState>();
                    t.EmitToken();
                    return;
                case Chars.NULL:
                    if(t.CurrentTagToken.FixAttribute() == false){
                        OnMessageRaised(new DuplicateAttributeError(t.CurrentTagToken.CurrentAttribute.Name));
                        t.CurrentTagToken.CurrentAttribute = null;
                    }
                    OnMessageRaised(new NullInAttributeNameError());
                    t.CurrentTagToken.CreateAttribute(Chars.REPLACEMENT_CHARACTER, "");
                    return;
                case Chars.QUOTATION_MARK:
                case Chars.APOSTROPHE:
                case Chars.LESS_THAN_SIGN:
                    OnMessageRaised(new InvaridCharAtAfterAttributeNameError(c,  t.CurrentTagToken.CurrentAttribute.Name));
                    goto default;
                case null:
                    OnMessageRaised(new SuddenlyEndAtAttributeError());
                    t.UnConsume(1);
                    t.ChangeTokenState<DataState>();
                    return;
                default:
                    if(t.CurrentTagToken.FixAttribute() == false){
                        OnMessageRaised(new DuplicateAttributeError(t.CurrentTagToken.CurrentAttribute.Name));
                        t.CurrentTagToken.CurrentAttribute = null;
                    }
                    if(c.IsLatinCapitalLetter()){
                        t.CurrentTagToken.CreateAttribute(c.ToLower(), "");
                    } else {
                        t.CurrentTagToken.CreateAttribute(c, "");
                    }
                    t.ChangeTokenState<AttributeNameState>();
                    return;
            }
        }

 public override void Read(Tokenizer t)
 {
     char? c = t.ConsumeChar();
     if(c == Chars.SOLIDUS){
         t.TemporaryBuffer = "";
         t.ChangeTokenState<RAWTEXTEndTagOpenState>();
         return;
     }
     t.EmitToken(Chars.LESS_THAN_SIGN);
     t.UnConsume(1);
     t.ChangeTokenState<RAWTEXTState>();
     return;
 }

 public override void Read(Tokenizer t)
 {
     char? c = t.ConsumeChar();
     switch(c){
         case Chars.HYPHEN_MINUS:
             t.EmitToken(Chars.HYPHEN_MINUS);
             t.ChangeTokenState<ScriptDataEscapedDashDashState>();
             return;
         default:
             t.UnConsume(1);
             t.ChangeTokenState<ScriptDataState>();
             return;
     }
 }

        public override void Read(Tokenizer t)
        {
            char? c = t.ConsumeChar();

            switch(c){
                case Chars.SOLIDUS:
                    t.TemporaryBuffer = "";
                    t.ChangeTokenState<ScriptDataDoubleEscapeEndState>();
                    return;
                default:
                    t.UnConsume(1);
                    t.ChangeTokenState<ScriptDataDoubleEscapedState>();
                    return;
            }
        }

        public override void Read(Tokenizer t)
        {
            char? c = t.ConsumeChar();

            if(c.IsLatinCapitalLetter()){
                t.CurrentTagToken.Name += c.ToLower();
                t.TemporaryBuffer += c;
                return;
            } else if(c.IsLatinSmallLetter()){
                t.CurrentTagToken.Name += c;
                t.TemporaryBuffer += c;
                return;
            }

            switch(c){
                case Chars.CHARACTER_TABULATION:
                case Chars.LINE_FEED:
                case Chars.FORM_FEED:
                case Chars.SPACE:
                    if(t.IsAppropriateEndTagToken){
                        t.ChangeTokenState<BeforeAttributeNameState>();
                        return;
                    }
                    goto default;
                case Chars.SOLIDUS:
                    if(t.IsAppropriateEndTagToken){
                        t.ChangeTokenState<SelfClosingStartTagState>();
                        return;
                    }
                    goto default;
                case Chars.GREATER_THAN_SIGN:
                    if(t.IsAppropriateEndTagToken){
                        t.EmitToken();
                        t.ChangeTokenState<DataState>();
                        return;
                    }
                    goto default;
                default:{
                    t.EmitToken(Chars.LESS_THAN_SIGN);
                    t.EmitToken(Chars.SOLIDUS);

                    t.EmitToken(t.TemporaryBuffer);
                    t.UnConsume(1);
                    t.ChangeTokenState<ScriptDataEscapedState>();
                    return;
                }
            }
        }