small fixes to getpageinfo_p.xml and htmlFilterContentScraper.java with respect to keyword extraction

git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@5185 6c8d7289-2bf4-0310-a012-ef5d649a1542

htroot/xml/util/getpageinfo_p.java

@@ -46,11 +46,18 @@ public class getpageinfo_p {
     public static serverObjects respond(final httpRequestHeader header, final serverObjects post, final serverSwitch<?> env) {
         final plasmaSwitchboard sb = (plasmaSwitchboard) env;
         final serverObjects prop = new serverObjects();
-        prop.put("sitemap", "");
-        prop.put("title", "");
-        prop.put("favicon","");
+        
+        // avoid UNRESOLVED PATTERN        
+        prop.put("title", "");        
+        prop.put("desc", "");
+        prop.put("lang", "");
         prop.put("robots-allowed", "3"); //unknown
-        String actions="title";
+        prop.put("sitemap", "");
+        prop.put("favicon","");        
+        
+        // default actions
+        String actions="title,robots";
+        
         if(post!=null && post.containsKey("url")){
             if(post.containsKey("actions"))
                 actions=post.get("actions");

source/de/anomic/htmlFilter/htmlFilterContentScraper.java

@@ -395,7 +395,8 @@ public class htmlFilterContentScraper extends htmlFilterAbstractScraper implemen
         if (s.length() == 0) {
             return getTitle().toLowerCase().split(splitrex);
         }
-        if (s.contains(",")) return s.split(",");
+        if (s.contains(",")) return s.split(" |,");
+        if (s.contains(";")) return s.split(" |;");
         return s.split("\\s");
     }