small enhancements in pdf parser

source/net/yacy/document/parser/pdfParser.java

@@ -34,7 +34,6 @@ import java.io.IOException;
 import java.io.InputStream;
 
 import net.yacy.cora.document.MultiProtocolURI;
-import net.yacy.cora.document.UTF8;
 import net.yacy.document.AbstractParser;
 import net.yacy.document.Document;
 import net.yacy.document.Parser;
@@ -127,14 +126,14 @@ public class pdfParser extends AbstractParser implements Parser {
             docTitle = MultiProtocolURI.unescape(location.getFileName());
         }
         final CharBuffer writer = new CharBuffer(odtParser.MAX_DOCSIZE);
-        byte[] contentBytes = UTF8.getBytes("");
+        byte[] contentBytes = new byte[0];
         try {
             // create a writer for output
             final PDFTextStripper  stripper = new PDFTextStripper();
 
             stripper.setEndPage(3); // get first 3 pages (always)
             writer.append(stripper.getText(pdfDoc));
-            contentBytes = UTF8.getBytes(writer.toString()); // remember text in case of interrupting thread
+            contentBytes = writer.getBytes(); // remember text in case of interrupting thread
 
             stripper.setStartPage(4); // continue with page 4 (terminated, resulting in no text)
             stripper.setEndPage(Integer.MAX_VALUE); // set to default
@@ -151,7 +150,7 @@ public class pdfParser extends AbstractParser implements Parser {
             t.join(3000);
             if (t.isAlive()) t.interrupt();
             pdfDoc.close();
-            contentBytes = UTF8.getBytes(writer.toString()); // get final text before closing writer
+            contentBytes = writer.getBytes(); // get final text before closing writer
             writer.close();
         } catch (final IOException e) {
             // close the writer