htmlParser: closes input stream -> changed it to leave it open for a reset (used by AugmentParser - even if this is practically not used),

note: stream.close is done by caller (Textparser.parseSource)
- removed unnecessary reset in AugmentParser
- added stream.mark in tdfatripleimpl. to make stream.reset work here

source/net/yacy/document/parser/augment/AugmentParser.java

@@ -37,11 +37,6 @@ public class AugmentParser extends AbstractParser implements Parser {
     public Document[] parse(DigestURI url, String mimeType, String charset, InputStream source) throws Parser.Failure, InterruptedException {
 
         Document[] htmlDocs = this.rdfaParser.parse(url, mimeType, charset, source);
-        try {
-            source.reset();
-        } catch (final IOException e) {
-            ConcurrentLog.logException(e);
-        }
 
         for (final Document doc : htmlDocs) {
             /* analyze(doc, url, mimeType, charset);  // enrich document text */

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

@@ -206,7 +206,7 @@ public class htmlParser extends AbstractParser implements Parser {
             throw new Parser.Failure("IO error:" + e.getMessage(), location);
         } finally {
             writer.flush();
-            sourceStream.close();
+            //sourceStream.close(); keep open for multipe parsing (close done by caller)
             writer.close();
         }
         //OutputStream hfos = new htmlFilterOutputStream(null, scraper, null, false);

source/net/yacy/document/parser/rdfa/impl/RDFaTripleImpl.java

@@ -38,6 +38,7 @@ public class RDFaTripleImpl{
 			TransformerException, TransformerConfigurationException {
 
 		BufferedReader bufReader = new BufferedReader(in);
+                bufReader.mark(2048); // mark position for following reset
 		String readLine = bufReader.readLine();
 		if (!readLine.toLowerCase().contains("<!doctype")){
 			bufReader.reset();