xSaherElmAiApi/Providers/Extractors/XPdfFileContentExtractor.cs

using System;
using System.IO;
using System.Linq;
using System.Text;
using UglyToad.PdfPig;
using System.Threading;
using System.Threading.Tasks;
using xAiApi.Interfaces.Extractors;

namespace xAiApi.Providers
{
    /// <summary>
    /// Extracts content from PDF files using PdfPig ...
    /// </summary>    
    public class XPdfFileContentExtractor : IXPdfFileContentExtractor
    {
        /// <summary>
        /// Supported MIME Types ...
        /// </summary>
        private static readonly string[] SupportedMimeTypes =
        [
            "application/pdf"
        ];

        /// <summary>
        /// Check if this extractor supports the specified MIME type ...
        /// </summary>
        public bool CanExtract(string mimeType)
        {
            //
            return SupportedMimeTypes.Contains(
                mimeType?.ToLowerInvariant() ?? string.Empty
            );
        }

        /// <summary>
        /// Extract text content from file stream ...
        /// </summary>
        public async Task<string> ExtractAsync(
            Stream fileStream,
            string mimeType,
            CancellationToken cancellationToken = default
        )
        {
            //
            var result = await Task.Run(() =>
            {
                //
                var sb = new StringBuilder();
                using var document = PdfDocument.Open(fileStream);
                foreach (var page in document.GetPages())
                {
                    //
                    var text = page.Text;

                    //
                    sb.AppendLine(text);
                    sb.AppendLine();
                }

                //
                return sb.ToString();
            }, cancellationToken);

            //
            return result;
        }
    }
}