diff --git a/Interfaces/Extractors/IXDocxFileContentExtractor.cs b/Interfaces/Extractors/IXDocxFileContentExtractor.cs new file mode 100644 index 0000000..3ec8aaf --- /dev/null +++ b/Interfaces/Extractors/IXDocxFileContentExtractor.cs @@ -0,0 +1,5 @@ +namespace xAiApi.Interfaces.Extractors +{ + public interface IXDocxFileContentExtractor : IXFileContentExtractor + { } +} \ No newline at end of file diff --git a/Interfaces/Extractors/IXExcelFileContentExtractor.cs b/Interfaces/Extractors/IXExcelFileContentExtractor.cs new file mode 100644 index 0000000..9711643 --- /dev/null +++ b/Interfaces/Extractors/IXExcelFileContentExtractor.cs @@ -0,0 +1,5 @@ +namespace xAiApi.Interfaces.Extractors +{ + public interface IXExcelFileContentExtractor : IXFileContentExtractor + { } +} \ No newline at end of file diff --git a/Interfaces/Extractors/IXFileContentExtractor.cs b/Interfaces/Extractors/IXFileContentExtractor.cs index 4194aa3..ccb62db 100644 --- a/Interfaces/Extractors/IXFileContentExtractor.cs +++ b/Interfaces/Extractors/IXFileContentExtractor.cs @@ -1,6 +1,7 @@ using System.IO; using System.Threading; using System.Threading.Tasks; +using xAiModels.Models; namespace xAiApi.Interfaces.Extractors { @@ -22,5 +23,20 @@ namespace xAiApi.Interfaces.Extractors string mimeType, CancellationToken cancellationToken = default ); + + /// + /// Extract content from stream as Rich Result ... + /// + /// + /// + /// + /// + /// + Task ExtractRichAsync( + Stream fileStream, + string fileName, + string mimeType, + CancellationToken cancellationToken = default + ); } } \ No newline at end of file diff --git a/Interfaces/Extractors/IXImageFileContentExtractor.cs b/Interfaces/Extractors/IXImageFileContentExtractor.cs new file mode 100644 index 0000000..2844cea --- /dev/null +++ b/Interfaces/Extractors/IXImageFileContentExtractor.cs @@ -0,0 +1,5 @@ +namespace xAiApi.Interfaces.Extractors +{ + public interface IXImageFileContentExtractor : IXFileContentExtractor + { } +} \ No newline at end of file diff --git a/Providers/Extractors/XDocxFileContentExtractor.cs b/Providers/Extractors/XDocxFileContentExtractor.cs new file mode 100644 index 0000000..a67b138 --- /dev/null +++ b/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 +{ + /// + /// Extracts text content from DOCX files using DocumentFormat.OpenXml ... + /// + public class XDocxFileContentExtractor : IXDocxFileContentExtractor + { + /// + /// Supported MIME Types ... + /// + private static readonly string[] SupportedMimeTypes = + [ + "application/vnd.openxmlformats-officedocument.wordprocessingml.document" + ]; + + /// + /// Check if this extractor supports the specified MIME type ... + /// + public bool CanExtract(string mimeType) + { + // + return SupportedMimeTypes.Contains( + mimeType?.ToLowerInvariant() ?? string.Empty + ); + } + + /// + /// Extract text content from file stream ... + /// + public async Task 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(); + foreach (var paragraph in paragraphs) + { + // + var text = paragraph.InnerText?.Trim(); + if (!string.IsNullOrEmpty(text)) + { + stringBuilder.AppendLine(text); + } + } + } + } + + // + return stringBuilder.ToString(); + } + } +} \ No newline at end of file diff --git a/Providers/Extractors/XExcelFileContentExtractor.cs b/Providers/Extractors/XExcelFileContentExtractor.cs new file mode 100644 index 0000000..76326d4 --- /dev/null +++ b/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 + { + /// + /// Supported MIME Types ... + /// + private static readonly string[] SupportedMimeTypes = + [ + "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet", // .xlsx + "application/vnd.ms-excel" // .xls + ]; + + /// + /// Check if this extractor supports the specified MIME type ... + /// + public bool CanExtract(string mimeType) + { + // + return SupportedMimeTypes.Contains( + mimeType?.ToLowerInvariant() ?? string.Empty + ); + } + + /// + /// Extract text content from file stream ... + /// + public async Task 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(); + } + } +} \ No newline at end of file diff --git a/Providers/Extractors/XImageFileContentExtractor.cs b/Providers/Extractors/XImageFileContentExtractor.cs new file mode 100644 index 0000000..4b53475 --- /dev/null +++ b/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 + { + /// + /// Supported MIME Types ... + /// + private static readonly string[] SupportedMimeTypes = + [ + "image/png", + "image/jpeg", + "image/jpg", + "image/gif", + "image/webp", + "image/bmp" + ]; + + /// + /// آیا OCR فعال است (برای مدل‌های غیر Vision) ... + /// + private readonly bool _enableOcrFallback; + + public XImageFileContentExtractor(bool enableOcrFallback = true) + { + _enableOcrFallback = enableOcrFallback; + } + + /// + /// Check if this extractor supports the specified MIME type ... + /// + public bool CanExtract(string mimeType) + { + // + return SupportedMimeTypes.Contains( + mimeType?.ToLowerInvariant() ?? string.Empty + ); + } + + /// + /// Extract text content from file stream ... + /// + public async Task ExtractAsync( + Stream fileStream, + string mimeType, + CancellationToken cancellationToken = default + ) + { + // + var result = await ExtractRichAsync( + fileStream, + "image", + mimeType, + cancellationToken + ); + + // + return result.Text; + } + + /// + /// Extract content from stream as Rich Result ... + /// + /// + /// + /// + /// + /// + public async Task 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; + } + + /// + /// Do OCR on Image for Text Extraction ... + /// + private async Task 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); + } + } +} \ No newline at end of file diff --git a/xAiApi.csproj b/xAiApi.csproj index cd82fb1..24aa676 100644 --- a/xAiApi.csproj +++ b/xAiApi.csproj @@ -46,6 +46,9 @@ + + +