*) htmlFilterContentScraper.java: using proper charset for document title

git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@2595 6c8d7289-2bf4-0310-a012-ef5d649a1542

source/de/anomic/htmlFilter/htmlFilterContentScraper.java

@@ -211,7 +211,8 @@ public class htmlFilterContentScraper extends htmlFilterAbstractScraper implemen
             h = cleanLine(super.stripAll(new serverByteBuffer(text)).toString());
             if (h.length() > 0) headlines[3].add(h);
         }
-        if ((tagname.equalsIgnoreCase("title")) && (text.length < 1024)) title = cleanLine(super.stripAll(new serverByteBuffer(text)).toString()); // TODO: bugfix needed for UTF-8       
+        if ((tagname.equalsIgnoreCase("title")) && (text.length < 1024)) 
+            title = cleanLine(super.stripAll(new serverByteBuffer(text)).toString(this.charset));        
     }
 
     private static String cleanLine(String s) {

source/de/anomic/plasma/plasmaParser.java

@@ -725,11 +725,11 @@ public final class plasmaParser {
                 serverFileUtils.write(contentBytes, contentFile);
             }
             
-            if ((args.length == 4)&&(args[2].equalsIgnoreCase("-m"))) {
+            if ((args.length >= 4)&&(args[2].equalsIgnoreCase("-m"))) {
                 contentMimeType = args[3];
             }
             
-            if ((args.length == 6)&&(args[4].equalsIgnoreCase("-c"))) {
+            if ((args.length >= 6)&&(args[4].equalsIgnoreCase("-c"))) {
                 charSet = args[5];
             }            
             
@@ -747,6 +747,9 @@ public final class plasmaParser {
 
             // printing out all parsed sentences
             if (document != null) {
+                System.out.print("Document titel: ");
+                System.out.println(document.getMainLongTitle());
+                
                 // found text
                 String[] sentences = document.getSentences();
                 if (sentences != null) {