xSaherElmAiApi/Providers/Extractors/XPdfFileContentExtractor.cs

using System;
using System.IO;
using System.Linq;
using System.Text;
using PdfiumViewer;
using System.Threading;
using xAiModels.Models;
using System.Threading.Tasks;
using xAiApi.Interfaces.Extractors;

namespace xAiApi.Providers.Extractors
{
    /// <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>
        /// Minimum Length for Fallback Using Images ...
        /// </summary>
        private const int MinTextLengthThreshold = 50;

        /// <summary>
        /// Max Pages for Falling Back Using Images ...
        /// </summary>
        private const int MaxPagesForImageFallback = 10;

        /// <summary>
        /// Default DPI for Rendering Images ...
        /// </summary>
        private const int RenderDpi = 150;

        /// <summary>
        /// Max Rendered Image Width ...
        /// </summary>
        private const int MaxImageWidth = 2000;

        /// <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 ExtractRichAsync(
                fileStream,
                "document.pdf",
                mimeType,
                cancellationToken
            );

            //
            return result.Text;
        }

        /// <summary>
        /// Extract content from stream as Rich Result ...
        /// </summary>
        /// <param name="fileStream"></param>
        /// <param name="fileName"></param>
        /// <param name="mimeType"></param>
        /// <param name="cancellationToken"></param>
        /// <returns></returns>
        public async Task<XFileExtractionResult> ExtractRichAsync(
            Stream fileStream,
            string fileName,
            string mimeType,
            CancellationToken cancellationToken = default
        )
        {
            //
            var result = new XFileExtractionResult
            {
                FileName = fileName,
                MimeType = mimeType
            };

            //
            using var memoryStream = new MemoryStream();
            await fileStream.CopyToAsync(memoryStream, cancellationToken);
            memoryStream.Position = 0;

            //
            var extractedText = await ExtractTextAsync(
                memoryStream,
                cancellationToken
            );
            if (IsTextSufficient(extractedText))
            {
                // PDF متنی است
                result.Text = extractedText;
            }
            else
            {
                // PDF اسکن‌شده است - Fallback به تصویر
                memoryStream.Position = 0;
                result = await FallbackToImageExtractionAsync(
                    memoryStream,
                    fileName,
                    mimeType,
                    cancellationToken
                );
                result.UsedImageFallback = true;
            }

            //
            return result;
        }

        /// <summary>
        /// Extract Text From PDF Files using Common way ...
        /// </summary>
        /// <param name="pdfStream"></param>
        /// <param name="cancellationToken"></param>
        /// <returns></returns>
        private async Task<string> ExtractTextAsync(
            Stream pdfStream,
            CancellationToken cancellationToken
        )
        {
            //
            var result = await Task.Run(() =>
            {
                //
                var sb = new StringBuilder();
                using var document = UglyToad.PdfPig.PdfDocument.Open(pdfStream);
                foreach (var page in document.GetPages())
                {
                    //
                    var text = page.Text?.Trim();
                    if (!string.IsNullOrEmpty(text))
                    {
                        //
                        sb.AppendLine(text);
                        sb.AppendLine();
                    }
                }

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

            //
            return result;
        }

        /// <summary>
        /// Check Extracted Content is Sufficient or not ...
        /// if not try to Falling Back using Images ...
        /// </summary>
        private bool IsTextSufficient(string text)
        {
            //
            if (string.IsNullOrWhiteSpace(text))
            {
                return false;
            }

            //
            // حذف فاصله‌ها و بررسی طول
            var cleanText = new string(text.Where(c => !char.IsWhiteSpace(c)).ToArray());

            //
            return cleanText.Length >= MinTextLengthThreshold;
        }

        /// <summary>
        /// Fallback Converts PDF Pages to Images ...
        /// </summary>
        private async Task<XFileExtractionResult> FallbackToImageExtractionAsync(
            Stream pdfStream,
            string fileName,
            string mimeType,
            CancellationToken cancellationToken
        )
        {
            //
            var result = new XFileExtractionResult
            {
                FileName = fileName,
                MimeType = mimeType,
                UsedImageFallback = true
            };

            //
            await Task.Run(() =>
            {
                //
                try
                {
                    //
                    using var document = PdfDocument.Load(pdfStream);

                    // 
                    var pageCount = Math.Min(
                        document.PageCount,
                        MaxPagesForImageFallback
                    );

                    //                    
                    for (int pageIndex = 0; pageIndex < pageCount; pageIndex++)
                    {
                        //
                        if (cancellationToken.IsCancellationRequested)
                        {
                            break;
                        }

                        //
                        try
                        {
                            //
                            var pageSize = document.PageSizes[pageIndex];

                            //
                            var scaleFactor = RenderDpi / 72.0;
                            var renderWidth = (int)Math.Ceiling(pageSize.Width * scaleFactor);
                            var renderHeight = (int)Math.Ceiling(pageSize.Height * scaleFactor);

                            //
                            if (renderWidth > MaxImageWidth)
                            {
                                //
                                var ratio = (double)MaxImageWidth / renderWidth;
                                renderWidth = MaxImageWidth;
                                renderHeight = (int)(renderHeight * ratio);
                            }

                            //
                            using var bitmap = document.Render(
                                dpiX: RenderDpi,
                                dpiY: RenderDpi,
                                page: pageIndex,
                                width: renderWidth,
                                forPrinting: false,
                                height: renderHeight
                            );

                            //
                            byte[] imageBytes;
                            using (var memoryStream = new MemoryStream())
                            {
                                //
                                bitmap.Save(memoryStream, System.Drawing.Imaging.ImageFormat.Png);
                                imageBytes = memoryStream.ToArray();
                            }

                            //
                            result.Images.Add(new XExtractedImage
                            {
                                Bytes = imageBytes,
                                MimeType = "image/png",
                                PageNumber = pageIndex + 1,
                                Description = $"Page {pageIndex + 1} of {fileName} ({renderWidth}x{renderHeight})"
                            });
                        }
                        catch (Exception)
                        { }
                    }
                }
                catch (Exception ex)
                {
                    result.ErrorMessage = $"PDF image extraction failed: {ex.Message}";
                }
            }, cancellationToken);

            //
            return result;
        }
    }
}