How to display content from index instead of content field

Hi,

There are two things probably to consider here. In Kentico 13 Refresh 1 the widget's content search implementation doesn't require the hack you mentioned anymore. Please refer to this search documentation as well as Refresh 1 release notes.

For the second point, including some of the content from search index please consider using Azure Search instead. It already has highlight functionality, refer to the example in this article (search for "highlight" on the page).

As azure search was not an option, this is what we came up with. First we implemented an ISearchCrawlerContentProcessor to get rid of any unwanted content.

public class CustomContentProcessor : ISearchCrawlerContentProcessor
{
    private readonly IEventLogService eventLogService;

    public CustomContentProcessor(IEventLogService eventLogService)
    {
        this.eventLogService = eventLogService;
    }

    public string Process(string htmlContent)
    {
        try
        {
            //// Gets the body element from the HTML content, using the API of the AngleSharp library
            var parser = new HtmlParser();
            var doc = parser.ParseDocument(htmlContent);

            // Removes elements marked with the default Xperience exclusion attribute
            foreach (var element in doc.QuerySelectorAll($"*[{"data-ktc-search-exclude"}]"))
            {
                element.Remove();
            }

            htmlContent = doc.Body.InnerHtml;

            // Removes new line entities
            htmlContent = HTMLHelper.RegexHtmlToTextWhiteSpace.Replace(htmlContent, " ");

            // Removes JavaScript
            htmlContent = HTMLHelper.RegexHtmlToTextScript.Replace(htmlContent, " ");

            // Removes Styles
            htmlContent = HTMLHelper.RegexHtmlToTextStyle.Replace(htmlContent, " ");

            // Removes tags
            htmlContent = HTMLHelper.RegexHtmlToTextTags.Replace(htmlContent, " ");

            // Decodes HTML entities
            htmlContent = HTMLHelper.HTMLDecode(htmlContent);

            return htmlContent;
        }
        catch (Exception ex)
        {
            eventLogService.LogException("CustomContentProcessor", "PROCESS", ex);
            return string.Empty;
        }
    }
}

Next we created a document search event handler module to store this content into a custom page field.

public class CustomSmartSearchModule : Module
{
    private const string PREVIEW_TEXT_COLUMN_NAME = "SearchResultPreviewText";
    private const int PREVIEW_TEXT_MAX_LENGTH = 280;

    public CustomSmartSearchModule() : base("CustomSmartSearch")
    {
    }

    protected override void OnInit()
    {
        base.OnInit();
        DocumentEvents.GetContent.Execute += GetContentOnExecute;
    }

    private void GetContentOnExecute(object sender, DocumentSearchEventArgs e)
    {
        var currentNode = e.Node;
        if (!currentNode.ContainsColumn(PREVIEW_TEXT_COLUMN_NAME) || string.IsNullOrWhiteSpace(e.Content))
        {
            return;
        }

        var previewContent = e.Content.Trim().Substring(0, PREVIEW_TEXT_MAX_LENGTH);
        currentNode.SetValue(PREVIEW_TEXT_COLUMN_NAME, previewContent);
        currentNode.Update();
    }
}

Finally we used this custom field as content source within the search config of every indexed page type.