A specialized sanitizer which outputs formatted plain text instead of HTML.
The renderer removes extra whitespace, and converts block level HTML elements to lines of plain text.
Inheritance: Sanitizer
PlainTextRenderer Class Documentation
Example #1
0
		/// <summary>
		/// Converts HTML to plain text.
		/// </summary>
		/// <remarks>
		/// Warning, the returned text may contain HTML fragments!!!
		/// For example, the original HTML code is:
		/// <code>
		/// &lt;p&gt;&amp;lt;hello&amp;lt;&gt;/p&gt;
		/// </code>
		/// Then, the converted text will be:
		/// <code>
		/// &lt;hello&gt;
		/// </code>
		/// So if you intend to output the stripped text in HTML, you need encode it first!
		/// </remarks>
		/// <param name="input">Input HTML. May be <c>null</c>.</param>
		/// <param name="newLine">The line terminator string</param>
		/// <returns>Plain text, may contain angle braces!</returns>
		public static string RenderToPlainText(string input, string newLine = "\n")
		{
			if (input == null)
			{
				return null;
			}

			var inputReader = new StringReader(input);
			var resultWriter = new StringWriter();
			resultWriter.GetStringBuilder().EnsureCapacity(input.Length);
			resultWriter.NewLine = newLine;
			var textRenderer = new PlainTextRenderer();
			textRenderer.Sanitize(inputReader, resultWriter);
			return resultWriter.ToString();
		}
Example #2
0
        /// <summary>
        /// Converts HTML to plain text.
        /// </summary>
        /// <remarks>
        /// Warning, the returned text may contain HTML fragments!!!
        /// For example, the original HTML code is:
        /// <code>
        /// &lt;p&gt;&amp;lt;hello&amp;lt;&gt;/p&gt;
        /// </code>
        /// Then, the converted text will be:
        /// <code>
        /// &lt;hello&gt;
        /// </code>
        /// So if you intend to output the stripped text in HTML, you need encode it first!
        /// </remarks>
        /// <param name="input">Input HTML. May be <c>null</c>.</param>
        /// <param name="newLine">The line terminator string</param>
        /// <returns>Plain text, may contain angle braces!</returns>
        public static string RenderToPlainText(string input, string newLine = "\n")
        {
            if (input == null)
            {
                return(null);
            }

            var inputReader  = new StringReader(input);
            var resultWriter = new StringWriter();

            resultWriter.GetStringBuilder().EnsureCapacity(input.Length);
            resultWriter.NewLine = newLine;
            var textRenderer = new PlainTextRenderer();

            textRenderer.Sanitize(inputReader, resultWriter);
            return(resultWriter.ToString());
        }