From 92d3f71b1643df8e5798e9e98c4694b26a6e0c78 Mon Sep 17 00:00:00 2001
From: reger <reger18@arcor.de>
Date: Sun, 28 Jul 2013 03:41:09 +0200
Subject: [PATCH] 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   | 5 -----
 source/net/yacy/document/parser/htmlParser.java              | 2 +-
 .../net/yacy/document/parser/rdfa/impl/RDFaTripleImpl.java   | 1 +
 3 files changed, 2 insertions(+), 6 deletions(-)

diff --git a/source/net/yacy/document/parser/augment/AugmentParser.java b/source/net/yacy/document/parser/augment/AugmentParser.java
index 46f17796b..9304c68c5 100644
--- a/source/net/yacy/document/parser/augment/AugmentParser.java
+++ b/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 */
diff --git a/source/net/yacy/document/parser/htmlParser.java b/source/net/yacy/document/parser/htmlParser.java
index a8d84a39b..3133a8f74 100644
--- a/source/net/yacy/document/parser/htmlParser.java
+++ b/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);
diff --git a/source/net/yacy/document/parser/rdfa/impl/RDFaTripleImpl.java b/source/net/yacy/document/parser/rdfa/impl/RDFaTripleImpl.java
index b651da6ec..0f7562e15 100644
--- a/source/net/yacy/document/parser/rdfa/impl/RDFaTripleImpl.java
+++ b/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();