diff --git a/src/main/java/org/RI/P1/FileData.java b/src/main/java/org/RI/P1/FileData.java
index de9c07d..eb7464c 100644
--- a/src/main/java/org/RI/P1/FileData.java
+++ b/src/main/java/org/RI/P1/FileData.java
@@ -22,12 +22,15 @@ import org.apache.tika.langdetect.OptimaizeLangDetector;
 import org.apache.tika.language.detect.LanguageResult;
 import org.apache.tika.metadata.*;
 import org.apache.tika.parser.*;
+import org.apache.tika.parser.txt.CharsetDetector;
+import org.apache.tika.parser.txt.CharsetMatch;
 import org.apache.tika.sax.BodyContentHandler;
 import org.apache.tika.sax.LinkContentHandler;
 import org.apache.tika.sax.TeeContentHandler;
 import org.apache.tika.sax.ToHTMLContentHandler;
 import org.apache.tika.parser.html.HtmlParser;
 import org.xml.sax.SAXException;
+import org.apache.commons.compress.utils.IOUtils;
 
 public class FileData {
     private File file;
@@ -67,11 +70,20 @@ public class FileData {
         setMetadata();
     }
 
+    private String detectEncoding(InputStream inputStream) throws IOException {
+        CharsetDetector detector = new CharsetDetector();
+        byte[] data = IOUtils.toByteArray(inputStream);
+        detector.setText(data);
+        CharsetMatch match = detector.detect();
+
+        return match.getName();
+    }
+
     private void setMetadata() throws IOException, TikaException, SAXException {
         parser.parse(inputStream, contentHandler, metadata, parseContext);
         filename = metadata.get(TikaCoreProperties.TITLE);
         type = metadata.get(Metadata.CONTENT_TYPE);
-        encoding = metadata.get(Metadata.CONTENT_ENCODING);
+        encoding = detectEncoding(inputStream);
         language = langIdentifier.detect(contentHandler.toString());
     }