last ...

Providers/Extractors/XDocxFileContentExtractor.cs

@@ -0,0 +1,79 @@
+using System;
+using System.IO;
+using System.Linq;
+using System.Text;
+using System.Threading;
+using System.Threading.Tasks;
+using xAiApi.Interfaces.Extractors;
+using DocumentFormat.OpenXml.Drawing;
+using DocumentFormat.OpenXml.Packaging;
+
+namespace xAiApi.Providers.Extractors
+{
+    /// <summary>
+    /// Extracts text content from DOCX files using DocumentFormat.OpenXml ...
+    /// </summary>    
+    public class XDocxFileContentExtractor : IXDocxFileContentExtractor
+    {
+        /// <summary>
+        /// Supported MIME Types ...
+        /// </summary>
+        private static readonly string[] SupportedMimeTypes =
+        [
+            "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
+        ];
+
+        /// <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
+        )
+        {
+            //
+            using var memoryStream = new MemoryStream();
+            await fileStream.CopyToAsync(memoryStream, cancellationToken);
+            memoryStream.Position = 0;
+
+            //
+            var stringBuilder = new StringBuilder();
+
+            //
+            using (var wordDocument = WordprocessingDocument.Open(memoryStream, false))
+            {
+                //
+                var body = wordDocument.MainDocumentPart?.Document?.Body;
+                if (body != null)
+                {
+                    //
+                    var paragraphs = body.Elements<Paragraph>();
+                    foreach (var paragraph in paragraphs)
+                    {
+                        //
+                        var text = paragraph.InnerText?.Trim();
+                        if (!string.IsNullOrEmpty(text))
+                        {
+                            stringBuilder.AppendLine(text);
+                        }
+                    }
+                }
+            }
+
+            //
+            return stringBuilder.ToString();
+        }
+    }
+}

Providers/Extractors/XExcelFileContentExtractor.cs

@@ -0,0 +1,93 @@
+using System;
+using System.IO;
+using System.Data;
+using System.Linq;
+using System.Text;
+using ExcelDataReader;
+using System.Threading;
+using System.Threading.Tasks;
+using xAiApi.Interfaces.Extractors;
+
+namespace xAiApi.Providers.Extractors
+{
+    public class XExcelFileContentExtractor : IXExcelFileContentExtractor
+    {
+        /// <summary>
+        /// Supported MIME Types ...
+        /// </summary>
+        private static readonly string[] SupportedMimeTypes =
+        [
+            "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet", // .xlsx
+            "application/vnd.ms-excel" // .xls        
+        ];
+
+        /// <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
+        )
+        {
+            //
+            Encoding.RegisterProvider(CodePagesEncodingProvider.Instance);
+
+            //
+            using var memoryStream = new MemoryStream();
+            await fileStream.CopyToAsync(memoryStream, cancellationToken);
+            memoryStream.Position = 0;
+
+            //
+            var stringBuilder = new StringBuilder();
+
+            //
+            using (var reader = ExcelReaderFactory.CreateReader(memoryStream))
+            {
+                //
+                var result = reader.AsDataSet();
+                foreach (DataTable table in result.Tables)
+                {
+                    //
+                    stringBuilder.AppendLine($"--- Sheet: {table.TableName} ---");
+
+                    //
+                    var headers = new string[table.Columns.Count];
+                    for (int i = 0; i < table.Columns.Count; i++)
+                    {
+                        headers[i] = table.Columns[i].ColumnName;
+                    }
+                    stringBuilder.AppendLine(string.Join(" | ", headers));
+                    stringBuilder.AppendLine(new string('-', 50));
+
+                    //
+                    foreach (DataRow row in table.Rows)
+                    {
+                        //
+                        var rowValues = new string[row.ItemArray.Length];
+                        for (int i = 0; i < row.ItemArray.Length; i++)
+                        {
+                            rowValues[i] = row.ItemArray[i]?.ToString()?.Trim() ?? string.Empty;
+                        }
+                        stringBuilder.AppendLine(string.Join(" | ", rowValues));
+                    }
+                    stringBuilder.AppendLine();
+                }
+            }
+
+            //
+            return stringBuilder.ToString();
+        }
+    }
+}

Providers/Extractors/XImageFileContentExtractor.cs

@@ -0,0 +1,141 @@
+using System;
+using System.IO;
+using System.Linq;
+using System.Threading;
+using xAiModels.Models;
+using System.Threading.Tasks;
+using xAiApi.Interfaces.Extractors;
+
+namespace xAiApi.Providers.Extractors
+{
+    public class XImageFileContentExtractor : IXImageFileContentExtractor
+    {
+        /// <summary>
+        /// Supported MIME Types ...
+        /// </summary>
+        private static readonly string[] SupportedMimeTypes =
+        [
+            "image/png",
+            "image/jpeg",
+            "image/jpg",
+            "image/gif",
+            "image/webp",
+            "image/bmp"
+        ];
+
+        /// <summary>
+        /// آیا OCR فعال است (برای مدل‌های غیر Vision) ...
+        /// </summary>
+        private readonly bool _enableOcrFallback;
+
+        public XImageFileContentExtractor(bool enableOcrFallback = true)
+        {
+            _enableOcrFallback = enableOcrFallback;
+        }
+
+        /// <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,
+                "image",
+                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);
+            var imageBytes = memoryStream.ToArray();
+
+            //
+            result.Images.Add(new XExtractedImage
+            {
+                Bytes = imageBytes,
+                MimeType = mimeType,
+                Description = $"Attached image: {fileName}"
+            });
+
+            // OCR Fallback برای مدل‌های متنی
+            if (_enableOcrFallback)
+            {
+                //
+                try
+                {
+                    //
+                    var ocrText = await PerformOcrAsync(imageBytes, cancellationToken);
+                    if (!string.IsNullOrWhiteSpace(ocrText))
+                    {
+                        result.Text = ocrText;
+                    }
+                }
+                catch
+                {
+                    // OCR failed, but image is still available for Vision
+                }
+            }
+
+            //
+            return result;
+        }
+
+        /// <summary>
+        /// Do OCR on Image for Text Extraction ...
+        /// </summary>
+        private async Task<string> PerformOcrAsync(
+            byte[] imageBytes,
+            CancellationToken cancellationToken
+        )
+        {
+            //
+            // TODO:
+            // پیاده‌سازی با Tesseract یا هر کتابخانه OCR دیگر
+            // در حال حاضر یک placeholder است
+            return await Task.FromResult(string.Empty);
+        }
+    }
+}