added Open Graph Metadata default fields, see http://ogp.me/ns#

defaults/solr.keys.list

@@ -374,6 +374,12 @@ host_organization_s
 ## breadcrumbs, see http://schema.org/WebPage; this is a counter how many itemprop="breadcrumb" properties in div tags appears within a page
 #schema_org_breadcrumb_i
 
+## Open Graph Metadata field, see http://ogp.me/ns#
+#opengraph_title_t
+#opengraph_type_s
+#opengraph_url_s
+#opengraph_image_s
+
 ## names of cms attributes; if several are recognized then they are listen in decreasing order of number of matching criterias
 #ext_cms_txt
 

source/net/yacy/cora/federate/solr/YaCySchema.java

@@ -164,8 +164,12 @@ public enum YaCySchema implements Schema {
     h4_i(SolrType.integer, true, true, false, "number of h4 header lines"),
     h5_i(SolrType.integer, true, true, false, "number of h5 header lines"),
     h6_i(SolrType.integer, true, true, false, "number of h6 header lines"),
-    
-    schema_org_breadcrumb_i(SolrType.integer, true, true, false, "number of itemprop=\"breadcrumb\" appearances in div tags"),    
+
+    schema_org_breadcrumb_i(SolrType.integer, true, true, false, "number of itemprop=\"breadcrumb\" appearances in div tags"),
+    opengraph_title_t(SolrType.text_general, true, true, false, "Open Graph Metadata from og:title metadata field, see http://ogp.me/ns#"),
+    opengraph_type_s(SolrType.text_general, true, true, false, "Open Graph Metadata from og:type metadata field, see http://ogp.me/ns#"),
+    opengraph_url_s(SolrType.text_general, true, true, false, "Open Graph Metadata from og:url metadata field, see http://ogp.me/ns#"),
+    opengraph_image_s(SolrType.text_general, true, true, false, "Open Graph Metadata from og:image metadata field, see http://ogp.me/ns#"),
     
     // special values; can only be used if '_val' type is defined in schema file; this is not standard
     bold_val(SolrType.integer, true, true, true, "number of occurrences of texts in bold_txt"),

source/net/yacy/document/parser/html/ContentScraper.java

@@ -363,18 +363,21 @@ public class ContentScraper extends AbstractScraper implements Scraper {
                 breadcrumbs++;
             }
         } else if (tagname.equalsIgnoreCase("meta")) {
-            String name = tagopts.getProperty("name", EMPTY_STRING);
             final String content = tagopts.getProperty("content", EMPTY_STRING);
+            String name = tagopts.getProperty("name", EMPTY_STRING);
             if (name.length() > 0) {
                 this.metas.put(name.toLowerCase(), CharacterCoding.html2unicode(content));
                 if (name.toLowerCase().equals("generator")) {
                     this.evaluationScores.match(Element.metagenerator, content);
                 }
-            } else {
-                name = tagopts.getProperty("http-equiv", EMPTY_STRING);
-                if (name.length() > 0) {
-                    this.metas.put(name.toLowerCase(), CharacterCoding.html2unicode(content));
-                }
+            }
+            name = tagopts.getProperty("http-equiv", EMPTY_STRING);
+            if (name.length() > 0) {
+                this.metas.put(name.toLowerCase(), CharacterCoding.html2unicode(content));
+            }
+            name = tagopts.getProperty("property", EMPTY_STRING);
+            if (name.length() > 0) {
+                this.metas.put(name.toLowerCase(), CharacterCoding.html2unicode(content));
             }
         } else if (tagname.equalsIgnoreCase("area")) {
             final String areatitle = cleanLine(tagopts.getProperty("title", EMPTY_STRING));

source/net/yacy/search/index/SolrConfiguration.java

@@ -451,6 +451,13 @@ public class SolrConfiguration extends ConfigurationSet implements Serializable
             add(doc, YaCySchema.htags_i, h);
             add(doc, YaCySchema.schema_org_breadcrumb_i, html.breadcrumbCount());
 
+            // meta tags: Open Graph properties
+            String og;
+            og = html.getMetas().get("og:title"); if (og != null) add(doc, YaCySchema.opengraph_title_t, og);
+            og = html.getMetas().get("og:type"); if (og != null) add(doc, YaCySchema.opengraph_type_s, og);
+            og = html.getMetas().get("og:url"); if (og != null) add(doc, YaCySchema.opengraph_url_s, og);
+            og = html.getMetas().get("og:image"); if (og != null) add(doc, YaCySchema.opengraph_image_s, og);
+
             // noindex and nofollow attributes
             // from HTML (meta-tag in HTML header: robots)
             // and HTTP header (x-robots property)