Page Comparison

Goal

This article provides information on how to index documents which are above the document size limit.

...

Open the backend of your Sitefinity instance.
Navigate to Administartion → Settings and click Advanced (your-site-domain/Sitefinity/Administration/Settings/Advanced)
Open the Hawksearch configuration
Under document size limit enter 4000KB
Save the changes

...

Empty content field

Code Block

using System;
using System.Collections.Generic;
using System.Linq;
using Hawksearch.Search;
using Telerik.Sitefinity.Services.Search.Data;
using Telerik.Sitefinity.Configuration;
using Telerik.Sitefinity.Services.Search.Model;
using Hawksearch.Configuration;
using Hawksearch.SDK.Indexing;

namespace Hawksearch122.CustomSitefinityWebApp
{
    public class CustomSearchService : HawksearchService
    {
        private const string DcoumentContentType = "Telerik.Sitefinity.Libraries.Model.Document";

        protected override List<SubmitDocument> AdaptDocuments(IEnumerable<IDocument> documents)
        {
            var documentListdoc = new List<IDocument>();
            var configManager = ConfigManager.GetManagerdocuments.ToList().FirstOrDefault();
            var hawkConfigdocumentList = new configManager.GetSection<HawkSearchConfig>List<IDocument>(documents);

            foreachif (vardoc document in documents!= null)
            {
                var documentSizecontentTypeField = 0.0;
                var modifiedDocument = documentdoc.Fields.FirstOrDefault(f => f.Name == "ContentType");

                foreachif (varcontentTypeField field in document.Fields!= null)
                {
                    if (string.Equals(fieldcontentTypeField.Value != null.ToString(), DcoumentContentType, StringComparison.InvariantCultureIgnoreCase))
                    {
                        var documentSizeconfigManager += System.Text.Encoding.Unicode.GetByteCount(field.Value.ToString()) / 1024.0;ConfigManager.GetManager();
                      }  var hawkConfig = configManager.GetSection<HawkSearchConfig>();
           }             documentList = new List<IDocument>();

if (documentSize > hawkConfig.DocumentSizeLimit)                 {    foreach (var document in documents)
            modifiedDocument = this.ModifyDocument(document);          {
      }                  documentList.Add(modifiedDocument);    var documentSize = 0.0;
     }              return base.AdaptDocuments(documentList);        var }modifiedDocument = document;

      private IDocument ModifyDocument(IDocument document)         {            foreach (var fieldsfield = newin List<IField>(document.Fields);
            var contentField = document.Fields.FirstOrDefault(f => f.Name == "Content");         {
    if (contentField != null)             {            if (field.Value != null)
      contentField.Value = string.Empty;             }           {
  var modifiedDocument = new Document(fields, document.IdentityField.Name);              return modifiedDocument;         }     }
}

Take first 500 words

Code Block

usingdocumentSize += System.Collections.Generic;
using System.Linq;
using Hawksearch.Search;
using Telerik.Sitefinity.Services.Search.Data;
using Telerik.Sitefinity.Configuration;
using Telerik.Sitefinity.Services.Search.Model;
using Hawksearch.Configuration;
using Hawksearch.SDK.Indexing;
using Field = Telerik.Sitefinity.Services.Search.Publishing.Field;

namespace Hawksearch122.Custom
{
    public class CustomSearchService : HawksearchService
    {
        protected override List<SubmitDocument> AdaptDocuments(IEnumerable<IDocument> documents)Text.Encoding.Unicode.GetByteCount(field.Value.ToString()) / 1024.0;
                                }
                            }

                            if (documentSize > hawkConfig.DocumentSizeLimit)
                            {
                                modifiedDocument = this.ModifyDocument(document);
                            }

                            documentList.Add(modifiedDocument);
                        }
                    }
                }
            }

            return base.AdaptDocuments(documentList);
        }

        private IDocument ModifyDocument(IDocument document)
        {
            var fields = new List<IField>(document.Fields);
            var contentField = document.Fields.FirstOrDefault(f => f.Name == "Content");

            if (contentField != null)
            {
                contentField.Value = string.Empty;
            }

            var modifiedDocument = new Document(fields, document.IdentityField.Name);

            return modifiedDocument;
        }
    }
}

Take first 500 words

Code Block

language	c#

using System;
using System.Collections.Generic;
using System.Linq;
using Hawksearch.Search;
using Telerik.Sitefinity.Services.Search.Data;
using Telerik.Sitefinity.Configuration;
using Telerik.Sitefinity.Services.Search.Model;
using Hawksearch.Configuration;
using Hawksearch.SDK.Indexing;
using Field = Telerik.Sitefinity.Services.Search.Publishing.Field;

namespace SitefinityWebApp
{
    public class CustomSearchService : HawksearchService
    {
        private const string DcoumentContentType = "Telerik.Sitefinity.Libraries.Model.Document";

        protected override List<SubmitDocument> AdaptDocuments(IEnumerable<IDocument> documents)
        {
            var doc = documents.ToList().FirstOrDefault();
            var documentList = new List<IDocument>(documents);

            if (doc != null)
            {
                var contentTypeField = doc.Fields.FirstOrDefault(f => f.Name == "ContentType");

                if (contentTypeField != null)
                {
                    if (string.Equals(contentTypeField.Value.ToString(), DcoumentContentType, StringComparison.InvariantCultureIgnoreCase))
                    {
                        var configManager = ConfigManager.GetManager();
                        var hawkConfig = configManager.GetSection<HawkSearchConfig>();
                        documentList = new List<IDocument>();

                        foreach (var document in documents)
                        {
                            var documentSize = 0.0;
                            var modifiedDocument = document;

                            foreach (var field in document.Fields)
                            {
                {             var documentList = newif List<IDocument>();(field.Value != null)
               var configManager = ConfigManager.GetManager();             var hawkConfig{
= configManager.GetSection<HawkSearchConfig>();              foreach (var document in documents)             {    documentSize += System.Text.Encoding.Unicode.GetByteCount(field.Value.ToString()) / 1024.0;
        var documentSize = 0.0;                 var modifiedDocument = document; }
                foreach (var field in document.Fields)        }

       {                     if (field.Value != null)documentSize > hawkConfig.DocumentSizeLimit)
                      {      {
                  documentSize += System.Text.Encoding.Unicode.GetByteCount(field.Value.ToString()) / 1024.0;             modifiedDocument = this.ModifyDocument(document);
         }                 }  }

              if (documentSize > hawkConfig.DocumentSizeLimit)           documentList.Add(modifiedDocument);
     {                   }
 modifiedDocument = this.ModifyDocument(document);                 }
                 documentList.Add(modifiedDocument);}
            }

            return base.AdaptDocuments(documentList);
        }

        private IDocument ModifyDocument(IDocument document)
        {
            var wordLimit = 500;
            var fields = new List<IField>(document.Fields);
            var contentField = document.Fields.FirstOrDefault(f => f.Name == "Content");
            fields.Remove(contentField);
            contentField = this.ExtractFieldContent(contentField, wordLimit);
            fields.Add(contentField);

            var modifiedDocument = new Document(fields, document.IdentityField.Name);

            return modifiedDocument;
        }

        private IField ExtractFieldContent(IField contentField, int wordLimit)
        {
            var fieldValue = contentField.Value.ToString();

            if (!string.IsNullOrWhiteSpace(fieldValue))
            {
                var modifiedContent = string.Join(" ", fieldValue.Split(' ').Take(wordLimit).ToArray());

                contentField = new Field
                {
                    Name = "Content",
                    Value = modifiedContent
                };
            }

            return contentField;
        }
    }
}

Register Custom Search Service

...

Open the backend of your Sitefinity instance.
Navigate to Administration → Settings (your-site-domain/Sitefinity/Administration/Settings)
Go to Advanced (your-site-domain/Sitefinity/Administration/Settings/Advanced)
Under Search → Search services → Hawksearch enter the TypeName of you custom search service (e.g. SitefinityWebApp.CustomSearchService)
Save the changes

Versions Compared

Old Version 3

New Version 4

Key

Goal

Empty content field

Take first 500 words

Take first 500 words

Register Custom Search Service