HtmlLexicalAnalyzer.GetNextAtomToken C# (CSharp) Method

    internal void GetNextAtomToken()
    {
        Debug.Assert(_nextTokenType != HtmlTokenType.EOF);
        _nextToken.Length = 0;

        this.SkipWhiteSpace();

        _nextTokenType = HtmlTokenType.Atom;

        if ((this.NextCharacter == '\'' || this.NextCharacter == '"') && !this.IsNextCharacterEntity)
        {
            char startingQuote = this.NextCharacter;
            this.GetNextCharacter();

            // Consume all characters between quotes
            while (!(this.NextCharacter == startingQuote && !this.IsNextCharacterEntity) && !this.IsAtEndOfStream)
            {
                _nextToken.Append(this.NextCharacter);
                this.GetNextCharacter();
            }
            if (this.NextCharacter == startingQuote)
            {
                this.GetNextCharacter();
            }

            // complete the quoted value
            // NOTE: our recovery here is different from IE's
            // IE keeps reading until it finds a closing quote or end of file
            // if end of file, it treats current value as text
            // if it finds a closing quote at any point within the text, it eats everything between the quotes
            // TODO: Suggestion:
            // however, we could stop when we encounter end of file or an angle bracket of any kind
            // and assume there was a quote there
            // so the attribute value may be meaningless but it is never treated as text
        }
        else
        {
            while (!this.IsAtEndOfStream && !Char.IsWhiteSpace(this.NextCharacter) && this.NextCharacter != '>')
            {
                _nextToken.Append(this.NextCharacter);
                this.GetNextCharacter();
            }
        }
    }