From 5a634cab23652e8c60ebdba645386a3312fd3c51 Mon Sep 17 00:00:00 2001
From: orbiter <orbiter@6c8d7289-2bf4-0310-a012-ef5d649a1542>
Date: Mon, 27 Apr 2009 08:46:11 +0000
Subject: [PATCH] removed generation of anchor link sets in document types that
 describe container formats.

git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@5890 6c8d7289-2bf4-0310-a012-ef5d649a1542
---
 source/de/anomic/plasma/parser/rpm/rpmParser.java            | 2 +-
 .../plasma/parser/sevenzip/SZParserExtractCallback.java      | 5 ++---
 source/de/anomic/plasma/parser/tar/tarParser.java            | 2 +-
 source/de/anomic/plasma/parser/zip/zipParser.java            | 2 +-
 4 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/source/de/anomic/plasma/parser/rpm/rpmParser.java b/source/de/anomic/plasma/parser/rpm/rpmParser.java
index 401a67ae6..af3f15806 100644
--- a/source/de/anomic/plasma/parser/rpm/rpmParser.java
+++ b/source/de/anomic/plasma/parser/rpm/rpmParser.java
@@ -121,7 +121,7 @@ public class rpmParser extends AbstractParser implements Parser {
                 else if (headerNames[i].equalsIgnoreCase("SUMMARY")) summary = tag.toString();
                 else if (headerNames[i].equalsIgnoreCase("DESCRIPTION")) description = tag.toString();
                 else if (headerNames[i].equalsIgnoreCase("PACKAGER")) packager = tag.toString();
-                else if (headerNames[i].equalsIgnoreCase("URL")) anchors.put(new yacyURL(tag.toString(), null), tag.toString());
+                //else if (headerNames[i].equalsIgnoreCase("URL")) anchors.put(new yacyURL(tag.toString(), null), tag.toString());
             }
 
             // closing the rpm file
diff --git a/source/de/anomic/plasma/parser/sevenzip/SZParserExtractCallback.java b/source/de/anomic/plasma/parser/sevenzip/SZParserExtractCallback.java
index 1db9164cf..9897f8687 100644
--- a/source/de/anomic/plasma/parser/sevenzip/SZParserExtractCallback.java
+++ b/source/de/anomic/plasma/parser/sevenzip/SZParserExtractCallback.java
@@ -25,9 +25,6 @@ package de.anomic.plasma.parser.sevenzip;
 
 import java.io.IOException;
 import java.io.OutputStream;
-import java.util.HashMap;
-import java.util.Iterator;
-import java.util.Map;
 
 import SevenZip.ArchiveExtractCallback;
 import SevenZip.Archive.IInArchive;
@@ -105,6 +102,7 @@ public class SZParserExtractCallback extends ArchiveExtractCallback {
                     theDoc = this.parser.parseSource(url, mime, null, this.cfos.getContentBAOS());
                 }
                 
+                /*
                 // revert the above workaround
                 final Map<yacyURL, String> nanchors = new HashMap<yacyURL, String>(theDoc.getAnchors().size(), 1f);
                 final Iterator<Map.Entry<yacyURL, String>> it = theDoc.getAnchors().entrySet().iterator();
@@ -124,6 +122,7 @@ public class SZParserExtractCallback extends ArchiveExtractCallback {
                 }
                 theDoc.getAnchors().clear();
                 theDoc.getAnchors().putAll(nanchors);
+                */
                 this.doc.addSubDocument(theDoc);
             }
         } catch (final ParserException e) {
diff --git a/source/de/anomic/plasma/parser/tar/tarParser.java b/source/de/anomic/plasma/parser/tar/tarParser.java
index 96df00b32..bc0a8b284 100644
--- a/source/de/anomic/plasma/parser/tar/tarParser.java
+++ b/source/de/anomic/plasma/parser/tar/tarParser.java
@@ -173,7 +173,7 @@ public class tarParser extends AbstractParser implements Parser {
                     docTextLength += FileUtils.copy(subDoc.getText(), docText);
                 }               
                 
-                docAnchors.putAll(subDoc.getAnchors());
+                //docAnchors.putAll(subDoc.getAnchors());
                 htmlFilterContentScraper.addAllImages(docImages, subDoc.getImages());
                 
                 // release subdocument
diff --git a/source/de/anomic/plasma/parser/zip/zipParser.java b/source/de/anomic/plasma/parser/zip/zipParser.java
index 72b530f79..246d9da55 100644
--- a/source/de/anomic/plasma/parser/zip/zipParser.java
+++ b/source/de/anomic/plasma/parser/zip/zipParser.java
@@ -156,7 +156,7 @@ public class zipParser extends AbstractParser implements Parser {
                     docTextLength += FileUtils.copy(subDoc.getText(), docText);
                 }
                 
-                docAnchors.putAll(subDoc.getAnchors());
+                //docAnchors.putAll(subDoc.getAnchors());
                 htmlFilterContentScraper.addAllImages(docImages, subDoc.getImages());
                 
                 // release subdocument