How do you convert HTML to plain text in Acumatica for use in reports and inquiries?

Question

Is there any easy way to convert the body text from an activity, task or other HTML field in Acumatica into a readable format that shows well in a report or generic inquiry? I could create a SQL function to strip out the HTML, a SQL View containing the stripped code, and then add that object to Acumatica but I'm looking for a simpler, more native way.

Gabriel Gabriel · Accepted Answer · 2020-09-30T15:53:21

You can create a custom attribute that subscribes to the FieldSelecting event to dynamically convert the field to plain text. There are many ways to do the actual conversion, but I would recommend using HtmlAgilityPack, an open-source library that already ships with Acumatica to do the work.

Here's how I would define the attribute:

using System;
using System.IO;
using HtmlAgilityPack;

namespace PX.Data
{  
  [PXString(IsUnicode = true)]
  public class HtmlToTextAttribute : PXAggregateAttribute, IPXFieldSelectingSubscriber
  {
    protected Type _htmlField;
  
    public HtmlToTextAttribute(Type htmlField)
    {
      if (htmlField == null) {
        throw new PXArgumentException(nameof(htmlField), ErrorMessages.ArgumentNullException);
      }
      
      _htmlField = htmlField;
    }
  
    public virtual void FieldSelecting(PXCache sender, PXFieldSelectingEventArgs e)
    {
      var html = sender.GetValue(e.Row, _htmlField.Name) as string;
      if(!String.IsNullOrWhiteSpace(html))
      {
        e.ReturnValue = ConvertToPlainText(html);
      }
    }
    
    //Source: https://github.com/ceee/ReadSharp/blob/master/ReadSharp/HtmlUtilities.cs
    public static string ConvertToPlainText(string html)
    {
      HtmlDocument doc = new HtmlDocument();
      doc.LoadHtml(html);

      StringWriter sw = new StringWriter();
      ConvertTo(doc.DocumentNode, sw);
      sw.Flush();
      return sw.ToString();
    }

    private static void ConvertContentTo(HtmlNode node, TextWriter outText)
    {
      foreach (HtmlNode subnode in node.ChildNodes)
      {
        ConvertTo(subnode, outText);
      }
    }
        
    private static void ConvertTo(HtmlNode node, TextWriter outText)
    {
      string html;
      switch (node.NodeType)
      {
        case HtmlNodeType.Comment:
          // don't output comments
          break;

        case HtmlNodeType.Document:
          ConvertContentTo(node, outText);
          break;

        case HtmlNodeType.Text:
          // script and style must not be output
          string parentName = node.ParentNode.Name;
          if ((parentName == "script") || (parentName == "style"))
            break;

          // get text
          html = ((HtmlTextNode)node).Text;

          // is it in fact a special closing node output as text?
          if (HtmlNode.IsOverlappedClosingElement(html))
            break;

          // check the text is meaningful and not a bunch of whitespaces
          if (html.Trim().Length > 0)
          {
            outText.Write(HtmlEntity.DeEntitize(html));
          }
          break;

        case HtmlNodeType.Element:
          switch (node.Name)
          {
            case "p":
              // treat paragraphs as crlf
              outText.Write("\r\n");
              break;
            case "br":
              outText.Write("\r\n");
              break;
          }

          if (node.HasChildNodes)
          {
            ConvertContentTo(node, outText);
          }
          break;
      }
    }
  }
}

To use this attribute, just define a new (non-persisted) field and decorate it with the HtmlToText attribute, for example as an extension on the CRActivity table:

    #region UsrBodyText
    [HtmlToText(typeof(CRActivity.body))]
    [PXUIField(DisplayName="Body (text)")]
    public virtual string UsrBodyText { get; set; }
    public abstract class usrBodyText : PX.Data.BQL.BqlString.Field<usrBodyText> { }
    #endregion

How do you convert HTML to plain text in Acumatica for use in reports and inquiries?

1 Answers