From eb78388a98cdcc407ca705e5ebf84fb5f66e1f1c Mon Sep 17 00:00:00 2001 From: Michael Peter Christen Date: Sun, 21 Dec 2014 19:17:06 +0100 Subject: [PATCH] changed prefer strategy for http unique in such a way that http is preferred over https. While this is a bad idea from the standpoint of security it is more common applicable for environments where http and https mix and for some domains https is not available. Then the double-check is possible even if no postprocessing is performed. --- defaults/yacy.init | 2 +- source/net/yacy/search/Switchboard.java | 2 +- source/net/yacy/search/schema/CollectionConfiguration.java | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/defaults/yacy.init b/defaults/yacy.init index 055d0f99c..08cf1cffe 100644 --- a/defaults/yacy.init +++ b/defaults/yacy.init @@ -1033,7 +1033,7 @@ search.ranking.solr.doubledetection.quantrate=0.5f # Another attribute for double content is a 'greedy' ignoring of a http url is present for each https and vice versa # The same may be true for documents with leading 'www.' subdomain and without. # The following attributes will cause that https is preferred over http and with-www is preferred over without-www -search.ranking.uniqueheuristic.preferhttps = true +search.ranking.uniqueheuristic.preferhttps = false search.ranking.uniqueheuristic.preferwwwprefix = true #optional extern thumbnail program. diff --git a/source/net/yacy/search/Switchboard.java b/source/net/yacy/search/Switchboard.java index a9278b497..4b9f29f33 100644 --- a/source/net/yacy/search/Switchboard.java +++ b/source/net/yacy/search/Switchboard.java @@ -373,7 +373,7 @@ public final class Switchboard extends serverSwitch { SwitchboardConstants.DICTIONARY_SOURCE_PATH_DEFAULT); this.log.config("Dictionaries Path:" + this.dictionariesPath.toString()); - CollectionConfiguration.UNIQUE_HEURISTIC_PREFER_HTTPS = this.getConfigBool("search.ranking.uniqueheuristic.preferhttps", true); + CollectionConfiguration.UNIQUE_HEURISTIC_PREFER_HTTPS = this.getConfigBool("search.ranking.uniqueheuristic.preferhttps", false); CollectionConfiguration.UNIQUE_HEURISTIC_PREFER_WWWPREFIX = this.getConfigBool("search.ranking.uniqueheuristic.preferwwwprefix", true); diff --git a/source/net/yacy/search/schema/CollectionConfiguration.java b/source/net/yacy/search/schema/CollectionConfiguration.java index 092c685f2..068ac53d2 100644 --- a/source/net/yacy/search/schema/CollectionConfiguration.java +++ b/source/net/yacy/search/schema/CollectionConfiguration.java @@ -108,7 +108,7 @@ public class CollectionConfiguration extends SchemaConfiguration implements Seri private static final long serialVersionUID=-499100932212840385L; - public static boolean UNIQUE_HEURISTIC_PREFER_HTTPS = true; + public static boolean UNIQUE_HEURISTIC_PREFER_HTTPS = false; public static boolean UNIQUE_HEURISTIC_PREFER_WWWPREFIX = true; private final ArrayList rankings;