*) some bugfixes for UTF-8 related problems

git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@2577 6c8d7289-2bf4-0310-a012-ef5d649a1542

source/de/anomic/htmlFilter/htmlFilterContentScraper.java

@@ -214,22 +214,22 @@ public class htmlFilterContentScraper extends htmlFilterAbstractScraper implemen
         }
         String h;
         if ((tagname.equalsIgnoreCase("h1")) && (text.length < 1024)) {
-            h = cleanLine(super.stripAll(new serverByteBuffer(text)).toString());
+            h = cleanLine(super.stripAll(new serverByteBuffer(text)).toString()); // TODO: bugfix needed for UTF-8
             if (h.length() > 0) headlines[0].add(h);
         }
         if ((tagname.equalsIgnoreCase("h2")) && (text.length < 1024)) {
-            h = cleanLine(super.stripAll(new serverByteBuffer(text)).toString());
+            h = cleanLine(super.stripAll(new serverByteBuffer(text)).toString()); // TODO: bugfix needed for UTF-8
             if (h.length() > 0) headlines[1].add(h);
         }
         if ((tagname.equalsIgnoreCase("h3")) && (text.length < 1024)) {
-            h = cleanLine(super.stripAll(new serverByteBuffer(text)).toString());
+            h = cleanLine(super.stripAll(new serverByteBuffer(text)).toString()); // TODO: bugfix needed for UTF-8
             if (h.length() > 0) headlines[2].add(h);
         }
         if ((tagname.equalsIgnoreCase("h4")) && (text.length < 1024)) {
-            h = cleanLine(super.stripAll(new serverByteBuffer(text)).toString());
+            h = cleanLine(super.stripAll(new serverByteBuffer(text)).toString()); // TODO: bugfix needed for UTF-8
             if (h.length() > 0) headlines[3].add(h);
         }
-        if ((tagname.equalsIgnoreCase("title")) && (text.length < 1024)) title = cleanLine(super.stripAll(new serverByteBuffer(text)).toString());        
+        if ((tagname.equalsIgnoreCase("title")) && (text.length < 1024)) title = cleanLine(super.stripAll(new serverByteBuffer(text)).toString()); // TODO: bugfix needed for UTF-8       
     }
 
     private static String cleanLine(String s) {

source/de/anomic/htmlFilter/htmlFilterOutputStream.java

@@ -58,6 +58,7 @@ import java.io.FileOutputStream;
 import java.io.IOException;
 import java.io.InputStream;
 import java.io.OutputStream;
+import java.io.UnsupportedEncodingException;
 import java.net.MalformedURLException;
 import java.util.Enumeration;
 import java.util.Properties;
@@ -157,7 +158,13 @@ public final class htmlFilterOutputStream extends OutputStream {
         while (e.hasMoreElements()) {
             key = (String) e.nextElement();
             bb = bb.append((byte) 32).append(key.getBytes()).append((byte) '=');
-            bb = bb.append(quotechar).append(prop.getProperty(key).getBytes()).append(quotechar);
+            bb = bb.append(quotechar);
+            try {
+                bb.append(prop.getProperty(key).getBytes("UTF-8"));
+            } catch (UnsupportedEncodingException e1) {
+                bb.append(prop.getProperty(key).getBytes());
+            }
+            bb.append(quotechar); 
         }
         if (bb.length() > 0) return bb.getBytes(1);
         return bb.getBytes();

source/de/anomic/server/serverByteBuffer.java

@@ -45,6 +45,7 @@ import java.io.FileInputStream;
 import java.io.FileNotFoundException;
 import java.io.IOException;
 import java.io.OutputStream;
+import java.io.UnsupportedEncodingException;
 import java.util.Properties;
 
 public final class serverByteBuffer extends OutputStream {
@@ -379,7 +380,11 @@ public final class serverByteBuffer extends OutputStream {
                 start = pos;
                 while ((pos < length) && (buffer[pos] != doublequote)) pos++;
                 if (pos >= length) break; // this is the case if we found no parent doublequote
+                try {
+                    p.setProperty(key, new String(buffer, start, pos - start,"UTF-8").trim());
+                } catch (UnsupportedEncodingException e) {
                     p.setProperty(key, new String(buffer, start, pos - start).trim());
+                } 
                 pos++;
             } else if (buffer[pos] == singlequote) {
                 // search next singlequote