fix file content extractor mechanism ...

2026-10-02 00:07:58 +03:30
parent f32972b55f
commit 4521a53734
13 changed files with 157 additions and 83 deletions
@@ -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();
+        }
+    }
+}