From ad09b786bf85d7fd1962bc4a9616afd62b99a185 Mon Sep 17 00:00:00 2001
From: Michael Peter Christen <mc@yacy.net>
Date: Tue, 3 Jul 2012 17:20:41 +0200
Subject: [PATCH] clean up parser data

---
 source/net/yacy/document/Document.java                | 11 +++++++++++
 .../net/yacy/document/parser/html/ContentScraper.java |  9 +++++++++
 source/net/yacy/document/parser/htmlParser.java       |  1 -
 3 files changed, 20 insertions(+), 1 deletion(-)

diff --git a/source/net/yacy/document/Document.java b/source/net/yacy/document/Document.java
index 42fb1f190..e10f8b44c 100644
--- a/source/net/yacy/document/Document.java
+++ b/source/net/yacy/document/Document.java
@@ -821,6 +821,17 @@ dc_rights
             ContentScraper.addAllImages(images, doc.getImages());
             if (doc.lon() != 0.0f && doc.lat() != 0.0f) { lon = doc.lon(); lat = doc.lat(); }
         }
+
+        // clean up parser data
+        for (final Document doc: docs) {
+            Object parserObject = doc.getParserObject();
+            if (parserObject instanceof ContentScraper) {
+                final ContentScraper html = (ContentScraper) parserObject;
+                html.close();
+            }
+        }
+
+        // return consolidation
         return new Document(
                 location,
                 globalMime,
diff --git a/source/net/yacy/document/parser/html/ContentScraper.java b/source/net/yacy/document/parser/html/ContentScraper.java
index e06eabaa2..8c3ec03c0 100644
--- a/source/net/yacy/document/parser/html/ContentScraper.java
+++ b/source/net/yacy/document/parser/html/ContentScraper.java
@@ -864,9 +864,18 @@ public class ContentScraper extends AbstractScraper implements Scraper {
         // free resources
         super.close();
         this.anchors.clear();
+        this.rss.clear();
+        this.css.clear();
+        this.script.clear();
+        this.frames.clear();
+        this.iframes.clear();
+        this.embeds.clear();
         this.images.clear();
+        this.metas.clear();
         this.title = null;
         this.headlines = null;
+        this.bold.clear();
+        this.italic.clear();
         this.content.clear();
         this.root = null;
     }
diff --git a/source/net/yacy/document/parser/htmlParser.java b/source/net/yacy/document/parser/htmlParser.java
index 107329178..2c22f73cf 100644
--- a/source/net/yacy/document/parser/htmlParser.java
+++ b/source/net/yacy/document/parser/htmlParser.java
@@ -143,7 +143,6 @@ public class htmlParser extends AbstractParser implements Parser {
                 scraper.getRSS(),
                 scraper.getImages(),
                 scraper.indexingDenied());
-        //scraper.close();
         ppd.setFavicon(scraper.getFavicon());
 
         return ppd;