adding the canonical tag to crawl queues

htroot/solr/select.java

@@ -23,7 +23,6 @@ import java.io.OutputStream;
 import java.io.OutputStreamWriter;
 import java.io.Writer;
 import java.util.HashMap;
-import java.util.LinkedHashSet;
 import java.util.Map;
 
 import javax.servlet.ServletException;

source/net/yacy/document/Document.java

@@ -868,7 +868,9 @@ dc_rights
             if (parser instanceof ContentScraper) {
                 final ContentScraper html = (ContentScraper) parser;
                 String refresh = html.getRefreshPath();
-                if (refresh != null && refresh.length() > 0)try {result.put(new DigestURI(refresh), "refresh");} catch (MalformedURLException e) {}
+                if (refresh != null && refresh.length() > 0) try {result.put(new DigestURI(refresh), "refresh");} catch (MalformedURLException e) {}
+                DigestURI canonical = html.getCanonical();
+                if (canonical != null) result.put(canonical, "canonical");
             }
         }
         return result;

source/net/yacy/search/schema/CollectionConfiguration.java

@@ -490,9 +490,9 @@ public class CollectionConfiguration extends SchemaConfiguration implements Seri
 
         Subgraph subgraph = new Subgraph(inboundLinks.size(), outboundLinks.size());
         Map<DigestURI, Properties> alllinks = document.getAnchors();
+        Map<DigestURI, ImageEntry> images = new HashMap<DigestURI, ImageEntry>();
         int c = 0;
         final Object parser = document.getParserObject();
-        Map<DigestURI, ImageEntry> images = new HashMap<DigestURI, ImageEntry>();
         if (parser instanceof ContentScraper) {
             final ContentScraper html = (ContentScraper) parser;
             images = html.getImages();