Allow initial buffer size definition in TransformWriter, and use available() method to set it in htmlParser. In this situation a ByteArrayInputStream is used so the available() method gives a good size estimation and avoid the buffer needing to be continually grown

source/net/yacy/document/parser/html/TransformerWriter.java

@@ -81,11 +81,22 @@ public final class TransformerWriter extends Writer {
             final Scraper scraper,
             final Transformer transformer,
             final boolean passbyIfBinarySuspect
+    ) {
+    	this(outStream, charSet, scraper, transformer, passbyIfBinarySuspect, 1024);
+    }
+
+    public TransformerWriter(
+            final OutputStream outStream,
+            final Charset charSet,
+            final Scraper scraper,
+            final Transformer transformer,
+            final boolean passbyIfBinarySuspect,
+            final int initialBufferSize
     ) {
         this.outStream     = outStream;
         this.scraper       = scraper;
         this.transformer   = transformer;
-        this.buffer        = new CharBuffer(1024);
+        this.buffer        = new CharBuffer(initialBufferSize);
         this.filterTag     = null;
         this.filterOpts    = null;
         this.filterCont    = null;

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

@@ -196,7 +196,7 @@ public class htmlParser extends AbstractParser implements Parser {
 
         // parsing the content
         final ContentScraper scraper = new ContentScraper(location);
-        final TransformerWriter writer = new TransformerWriter(null,null,scraper,null,false);
+        final TransformerWriter writer = new TransformerWriter(null,null,scraper,null,false, sourceStream.available());
         try {
             FileUtils.copy(sourceStream, writer, c);
         } catch (final IOException e) {