From 3491ab4c38dab7ccf24e2c726503e1709eb82b1f Mon Sep 17 00:00:00 2001
From: orbiter <mc@yacy.net>
Date: Fri, 1 Aug 2014 13:21:16 +0200
Subject: [PATCH] removed unused images from webgraph edge computation
---
source/net/yacy/search/schema/CollectionConfiguration.java | 2 +-
source/net/yacy/search/schema/WebgraphConfiguration.java | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/source/net/yacy/search/schema/CollectionConfiguration.java b/source/net/yacy/search/schema/CollectionConfiguration.java
index 519bab1b9..36c7aa77e 100644
--- a/source/net/yacy/search/schema/CollectionConfiguration.java
+++ b/source/net/yacy/search/schema/CollectionConfiguration.java
@@ -898,7 +898,7 @@ public class CollectionConfiguration extends SchemaConfiguration implements Seri
Boolean canonical_equal_sku = canonical == null ? null : canonical.toNormalform(true).equals(url);
if (webgraph != null && (!containsCanonical || (canonical_equal_sku != null && (canonical_equal_sku.booleanValue())))) {
// a document with canonical tag should not get a webgraph relation, because that belongs to the canonical document
- List<SolrInputDocument> edges = webgraph.getEdges(subgraph, digestURL, responseHeader, collections, crawldepth, images, processTypes, document.getAnchors(), sourceName);
+ List<SolrInputDocument> edges = webgraph.getEdges(subgraph, digestURL, responseHeader, collections, crawldepth, processTypes, document.getAnchors(), sourceName);
// this also enriched the subgraph
doc.webgraphDocuments.addAll(edges);
} else {
diff --git a/source/net/yacy/search/schema/WebgraphConfiguration.java b/source/net/yacy/search/schema/WebgraphConfiguration.java
index 9204b95b5..dc01e6093 100644
--- a/source/net/yacy/search/schema/WebgraphConfiguration.java
+++ b/source/net/yacy/search/schema/WebgraphConfiguration.java
@@ -100,7 +100,7 @@ public class WebgraphConfiguration extends SchemaConfiguration implements Serial
public List<SolrInputDocument> getEdges(
final Subgraph subgraph,
final DigestURL source, final ResponseHeader responseHeader, Map<String, Pattern> collections, int crawldepth_source,
- final List<ImageEntry> images, final Set<ProcessType> processTypes, final Collection<AnchorURL> links,
+ final Set<ProcessType> processTypes, final Collection<AnchorURL> links,
final String sourceName) {
boolean allAttr = this.isEmpty();
boolean generalNofollow = responseHeader == null ? false : responseHeader.get("X-Robots-Tag", "").indexOf("nofollow") >= 0;