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

...

In order to index documents above the document size limit you need to inherit the HawksearchService class and override the AdaptDocuments. Here we will demonstrate how to remove empty the content field entirely or take the first 500 words in it.

Info
The following code snippet demonstrates how to strip the document from it’s Content field in order to pass the document size limit check.

...

Empty content field

Code Block

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 Hawksearch122.Custom
{
    public class CustomSearchService : HawksearchService
    {
        protected override List<SubmitDocument> AdaptDocuments(IEnumerable<IDocument> documents)
        {
            var documentList = new List<IDocument>();
            var configManager = ConfigManager.GetManager();
            var hawkConfig = configManager.GetSection<HawkSearchConfig>();

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

                foreach (var field in document.Fields)
                {
                    if (field.Value != null)
                    {
                        documentSize += System.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)
            {
                fields.Remove(contentField)contentField.Value = string.Empty;
            }

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

            return modifiedDocument;
        }
    }
}

Take first 500 words

Code Block

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 Hawksearch122.Custom
{
    public class CustomSearchService : HawksearchService
    {
        protected override List<SubmitDocument> AdaptDocuments(IEnumerable<IDocument> documents)
        {
            var documentList = new List<IDocument>();
            var configManager = ConfigManager.GetManager();
            var hawkConfig = configManager.GetSection<HawkSearchConfig>();

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

                foreach (var field in document.Fields)
                {
                    if (field.Value != null)
                    {
                        documentSize += System.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 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;
        }
    }
}

...

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 2

New Version 3

Key

Goal

Empty content field

Take first 500 words