Click here to Skip to main content
15,867,568 members
Articles / Web Development / CSS3

AngleSharp

Rate me:
Please Sign up or sign in to vote.
5.00/5 (87 votes)
3 Jul 2013BSD28 min read 257.1K   4.3K   166  
Bringing the DOM to C# with a HTML5/CSS3 parser written in C#.
using System;
using System.Diagnostics;

namespace AngleSharp.Html
{
    /// <summary>
    /// The abstract base class of any token.
    /// </summary>
    [DebuggerStepThrough]
    abstract class HtmlToken
    {
        #region Factory

        /// <summary>
        /// Gets the end of file token.
        /// </summary>
        public static HtmlEndOfFileToken EOF
        {
            get { return eof ?? (eof = new HtmlEndOfFileToken()); }
        }

        static HtmlCharacterToken buffer = new HtmlCharacterToken();

        /// <summary>
        /// Creates a new HTML character token based on the given character.
        /// </summary>
        /// <param name="character">The character to contain.</param>
        /// <returns>The generated token.</returns>
        [DebuggerStepThrough]
        public static HtmlCharacterToken Character(Char character)
        {
            return new HtmlCharacterToken(character);
        }

        /// <summary>
        /// Creates a new HTML characters token based on the given characters.
        /// </summary>
        /// <param name="character1">The first character to contain.</param>
        /// <param name="character2">The second character to contain.</param>
        /// <returns>The generated token.</returns>
        [DebuggerStepThrough]
        public static HtmlCharactersToken Characters(Char character1, Char character2)
        {
            return new HtmlCharactersToken(new Char[] { character1, character2 });
        }

        /// <summary>
        /// Creates a new HTML characters token based on the given characters.
        /// </summary>
        /// <param name="characters">The characters to contain.</param>
        /// <returns>The generated token.</returns>
        [DebuggerStepThrough]
        public static HtmlCharactersToken Characters(Char[] characters)
        {
            return new HtmlCharactersToken(characters);
        }

        /// <summary>
        /// Creates a new HTML characters token based on the given characters.
        /// </summary>
        /// <param name="characters">The characters to contain.</param>
        /// <returns>The generated token.</returns>
        [DebuggerStepThrough]
        public static HtmlCharactersToken Characters(String characters)
        {
            return new HtmlCharactersToken(characters);
        }

        /// <summary>
        /// Creates a new HTML comment token based on the given string.
        /// </summary>
        /// <param name="comment">The comment to contain.</param>
        /// <returns>The generated token.</returns>
        [DebuggerStepThrough]
        public static HtmlCommentToken Comment(String comment)
        {
            return new HtmlCommentToken(comment);
        }

        /// <summary>
        /// Creates a new HTML doctype token.
        /// </summary>
        /// <param name="quirksmode">Determines if quirksmode will be forced.</param>
        /// <returns>The generated token.</returns>
        [DebuggerStepThrough]
        public static HtmlDoctypeToken Doctype(Boolean quirksmode)
        {
            return new HtmlDoctypeToken(quirksmode);
        }

        /// <summary>
        /// Creates a new opening HtmlTagToken.
        /// </summary>
        /// <returns>The new HTML tag token.</returns>
        [DebuggerStepThrough]
        public static HtmlTagToken OpenTag()
        {
            return new HtmlTagToken() { _type = HtmlTokenType.StartTag };
        }

        /// <summary>
        /// Creates a new closing HtmlTagToken.
        /// </summary>
        /// <returns>The new HTML tag token.</returns>
        [DebuggerStepThrough]
        public static HtmlTagToken CloseTag()
        {
            return new HtmlTagToken() { _type = HtmlTokenType.EndTag };
        }

        /// <summary>
        /// Creates a new opening HtmlTagToken for the given name.
        /// </summary>
        /// <param name="name">The name of the tag.</param>
        /// <returns>The new HTML tag token.</returns>
        [DebuggerStepThrough]
        public static HtmlTagToken OpenTag(String name)
        {
            return new HtmlTagToken(name) { _type = HtmlTokenType.StartTag };
        }

        /// <summary>
        /// Creates a new closing HtmlTagToken for the given name.
        /// </summary>
        /// <param name="name">The name of the tag.</param>
        /// <returns>The new HTML tag token.</returns>
        [DebuggerStepThrough]
        public static HtmlTagToken CloseTag(String name)
        {
            return new HtmlTagToken(name) { _type = HtmlTokenType.EndTag };
        }

        #endregion

        #region Members

        static HtmlEndOfFileToken eof;
        protected HtmlTokenType _type;

        #endregion

        #region Properties

        /// <summary>
        /// Gets the type of the token.
        /// </summary>
        public HtmlTokenType Type
        {
            get { return _type; }
        }

        /// <summary>
        /// Gets if the character data is NULL.
        /// </summary>
        /// <returns>True if the character token is NULL, otherwise false.</returns>
        public virtual bool IsNullChar
        {
            get { return false; }
        }

        /// <summary>
        /// Gets if the character data is a new line.
        /// </summary>
        /// <returns>True if the character token is a new line, otherwise false.</returns>
        public virtual bool IsNewLine
        {
            get { return false; }
        }

        /// <summary>
        /// Gets if the character data is actually a space character.
        /// </summary>
        /// <returns>True if the character data is a space character.</returns>
        public virtual bool IsIgnoreable
        {
            get { return false; }
        }

        #endregion

        #region Methods

        /// <summary>
        /// Finds out if the current token is a start tag token with the given name.
        /// </summary>
        /// <param name="name">The name of the tag.</param>
        /// <returns>True if the token is indeed a start tag token with the given name, otherwise false.</returns>
        public virtual Boolean IsStartTag(String name)
        {
            return false;
        }

        #endregion
    }
}

By viewing downloads associated with this article you agree to the Terms of Service and the article's licence.

If a file you wish to view isn't highlighted, and is a text file (not binary), please let us know and we'll add colourisation support for it.

License

This article, along with any associated source code and files, is licensed under The BSD License


Written By
Chief Technology Officer
Germany Germany
Florian lives in Munich, Germany. He started his programming career with Perl. After programming C/C++ for some years he discovered his favorite programming language C#. He did work at Siemens as a programmer until he decided to study Physics.

During his studies he worked as an IT consultant for various companies. After graduating with a PhD in theoretical particle Physics he is working as a senior technical consultant in the field of home automation and IoT.

Florian has been giving lectures in C#, HTML5 with CSS3 and JavaScript, software design, and other topics. He is regularly giving talks at user groups, conferences, and companies. He is actively contributing to open-source projects. Florian is the maintainer of AngleSharp, a completely managed browser engine.

Comments and Discussions