Sitecore PDF Indexing

IndexPDF

public class IndexPDF : IComputedIndexField
{
    /// <inheritdoc />
    public string FieldName { get; set; }
    /// <inheritdoc />
    public string ReturnType { get; set; }

    /// <inheritdoc />
    public object ComputeFieldValue(IIndexable indexable)
    {
        Item item = indexable as SitecoreIndexableItem;

        if (item != null && item.Paths.IsMediaItem) // Only for media items
        {
            try
            {
                if (item.TemplateID == new ID("{0603F166-35B8-469F-8123-E8D87BEDC171}")) // PDF template ID
                {
                    return ParsePDF(item);
                }
            }
            catch (Exception)
            {
                return null;
            }
        }
           
        return null; // Return null if nothing to index
    }

    private string ParsePDF(MediaItem mediaItem)
    {
        PDDocument doc = null;
        string content = string.Empty;
        InputStreamWrapper wrapper = null;

        if (mediaItem != null)
        {
            try
            {
                wrapper = new InputStreamWrapper(mediaItem.GetMediaStream());
                doc = PDDocument.load(wrapper);
                content = new PDFTextStripper().getText(doc);
            }
            catch (Exception ex)
            {
                return null;
            }
            finally
            {
                if ((doc != null) && (wrapper != null))
                {
                    doc.close();
                    wrapper.close();
                }
            }
        }

        if (!string.IsNullOrEmpty(content))
        {
            // Replace all whitespace with single space
            content = Regex.Replace(content, @"\s+", " ");
        }

        return content;
    }
}

Lucene index

<fields hint="raw:AddComputedIndexField">
  <field fieldName="_content" storageType="no" indexType="tokenized"
          patch:after="field[last()]">Myproject.IndexPDF, MyProject</field>
</fields>