From 4f9b8a6ef88a294d31f7ba715f0cf0ac592cb9cd Mon Sep 17 00:00:00 2001
From: apfelmaennchen <apfelmaennchen@6c8d7289-2bf4-0310-a012-ef5d649a1542>
Date: Sun, 18 May 2008 12:48:57 +0000
Subject: [PATCH] /xml/util/getpageinfo_p.java: fixed problem with empty tags
 and added recognition of compound tags e.g. "DER SPIEGEL"

git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@4823 6c8d7289-2bf4-0310-a012-ef5d649a1542
---
 htroot/xml/util/getpageinfo_p.java | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/htroot/xml/util/getpageinfo_p.java b/htroot/xml/util/getpageinfo_p.java
index 6b9e9c675..aa9841ac6 100644
--- a/htroot/xml/util/getpageinfo_p.java
+++ b/htroot/xml/util/getpageinfo_p.java
@@ -100,10 +100,19 @@ public class getpageinfo_p {
                     
                     // put keywords
                     String list[]=scraper.getKeywords();
+                    int count = 0;
                     for(int i=0;i<list.length;i++){
-                    	prop.putHTML("tags_"+i+"_tag", list[i]);
+                    	String tag = list[i];
+                    	if (!tag.equals("")) {
+                    		while (i<(list.length-1) && !list[i+1].equals("")) {
+                    			i++;
+                    			tag += " "+list[i];                    			
+                    		}                    	                 	
+                    		prop.putHTML("tags_"+count+"_tag", tag);
+                    		count++;
+                    	}
                     }
-                    prop.put("tags", list.length);
+                    prop.put("tags", count);
 
                 } catch (MalformedURLException e) { /* ignore this */
                 } catch (IOException e) { /* ignore this */