fix file content extractor mechanism ...

Providers/Extractors/XFileContentExtractor.cs

@@ -0,0 +1,103 @@
+using System;
+using System.IO;
+using System.Linq;
+using System.Threading;
+using System.Reflection;
+using xCommons.Extensions;
+using xExceptions.Constants;
+using System.Threading.Tasks;
+using System.Collections.Generic;
+using xAiApi.Interfaces.Extractors;
+
+namespace xAiApi.Providers
+{
+    /// <summary>
+    /// Composite extractor that delegates to appropriate extractor 
+    /// based on MIME type ...
+    /// </summary>    
+    public class XFileContentExtractor : IXFileContentExtractor
+    {
+        //
+        private readonly IList<IXFileContentExtractor> extractors = [];
+
+        public XFileContentExtractor()
+        {
+            //
+            var path = Path.Combine(AppContext.BaseDirectory);
+            var files = Directory.GetFiles(path, "*.dll");
+            foreach (var dll in files)
+            {
+                //
+                // Retrieve DLL Assembly ...
+                var assembly = Assembly.LoadFrom(dll);
+
+                //
+                // Extract Registerar Types ...
+                var extractorTypes = assembly
+                    .GetExportedTypes()
+                    .Where(t =>
+                        !t.IsAbstract &&
+                        typeof(IXFileContentExtractor).IsAssignableFrom(t));
+                foreach (var extractorType in extractorTypes)
+                {
+                    //
+                    // Ignore XFileContentExtractor ...
+                    if (extractorType.FullName.Contains(nameof(XFileContentExtractor)))
+                    {
+                        continue;
+                    }
+
+                    //
+                    // Create Instance of Service ...
+                    var instance = (IXFileContentExtractor)Activator.CreateInstance(extractorType);
+                    if (!instance.IsNull())
+                    {
+                        //
+                        // Add Registerar Instance to Collection ...
+                        extractors.Add(instance);
+                    }
+                }
+            }
+        }
+
+        /// <summary>
+        /// Check if this extractor supports the specified MIME type ...
+        /// </summary>
+        public bool CanExtract(string mimeType)
+        {
+            return extractors.Any(e => e.CanExtract(mimeType));
+        }
+
+        /// <summary>
+        /// Extract text content from file stream ...
+        /// </summary>
+        public async Task<string> ExtractAsync(
+            Stream fileStream,
+            string mimeType,
+            CancellationToken cancellationToken = default
+        )
+        {
+            //
+            var extractor = extractors
+                .FirstOrDefault(e => e.CanExtract(mimeType));
+            if (extractor.IsNull())
+            {
+                //
+                XException.NotAllowed.Throw(
+                    $"Unsupported file type: {mimeType}"
+                );
+            }
+
+            //
+            var result = await extractor
+                .ExtractAsync(
+                    mimeType: mimeType,
+                    fileStream: fileStream,
+                    cancellationToken: cancellationToken
+                );
+
+            //
+            return result;
+        }
+    }
+}

Providers/Extractors/XPdfFileContentExtractor.cs

@@ -0,0 +1,69 @@
+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;
+        }
+    }
+}

Providers/Extractors/XPlainTextFileContentExtractor.cs

@@ -0,0 +1,54 @@
+using System;
+using System.IO;
+using System.Linq;
+using System.Threading;
+using System.Threading.Tasks;
+using xAiApi.Interfaces.Extractors;
+
+namespace xAiApi.Providers
+{
+    /// <summary>
+    /// Extracts content from plain text files (txt, md, csv, json, xml) ...
+    /// </summary>    
+    public class XPlainTextFileContentExtractor : IXPlainTextFileContentExtractor
+    {
+        /// <summary>
+        /// Supported MIME Types ...
+        /// </summary>
+        private static readonly string[] SupportedMimeTypes =
+        [
+            "text/plain",
+            "text/markdown",
+            "text/csv",
+            "text/html",
+            "text/xml",
+            "application/json",
+            "application/xml"
+        ];
+
+        /// <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 reader = new StreamReader(fileStream);
+            return await reader.ReadToEndAsync();
+        }
+    }
+}