replaced auto-dom filter with easy-to-understand Site Link-List crawler option

- nobody understand the auto-dom filter without a lenghtly introduction about the function of a crawler
- nobody ever used the auto-dom filter other than with a crawl depth of 1
- the auto-dom filter was buggy since the filter did not survive a restart and then a search index contained waste
- the function of the auto-dom filter was in fact to just load a link list from the given start url and then start separate crawls for all these urls restricted by their domain
- the new Site Link-List option shows the target urls in real-time during input of the start url (like the robots check) and gives a transparent feed-back what it does before it can be used
- the new option also fits into the easy site-crawl start menu

git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@7213 6c8d7289-2bf4-0310-a012-ef5d649a1542

1 files changed, 18 insertions, 10 deletions

diff --git a/htroot/js/IndexCreate.js b/htroot/js/IndexCreate.js
index fdb26ba84..b411f2261 100644
--- a/htroot/js/IndexCreate.js
+++ b/htroot/js/IndexCreate.js
@@ -3,12 +3,12 @@ var AJAX_ON="/env/grafics/ajax.gif";
 var timeout="";
 
 function handleResponse(){
-    if(http.readyState == 4){
+    if (http.readyState == 4){
         var response = http.responseXML;
 
-		// getting the document title
+		// get the document title
         doctitle="";		
-        if(response.getElementsByTagName("title")[0].firstChild!=null){
+        if (response.getElementsByTagName("title")[0].firstChild!=null){
 	        doctitle=response.getElementsByTagName("title")[0].firstChild.nodeValue;
 	    }
 		// document.getElementById("title").innerHTML=doctitle;
@@ -23,43 +23,51 @@ function handleResponse(){
         if(robotsOKspan.firstChild){
 	        robotsOKspan.removeChild(robotsOKspan.firstChild);
         }
-        if(docrobotsOK==1){
+        if (docrobotsOK==1){
         	img=document.createElement("img");
         	img.setAttribute("src", "/env/grafics/ok.png");
         	img.setAttribute("width", "32px");
         	img.setAttribute("height", "32px");
         	robotsOKspan.appendChild(img);
-        }else if(docrobotsOK==0){
+        } else if(docrobotsOK==0){
 			img=document.createElement("img");
         	img.setAttribute("src", "/env/grafics/bad.png");
         	img.setAttribute("width", "32px");
         	img.setAttribute("height", "32px");
         	robotsOKspan.appendChild(img);
         	robotsOKspan.appendChild(img);
-        }else{
+        } else {
 	        robotsOKspan.appendChild(document.createTextNode(""));
 	        document.getElementById("robotsOK").innerHTML="";
         }		
 		
-		// getting the sitemap URL contained in the robots.txt
+		// get the sitemap URL contained in the robots.txt
 		if (document.getElementsByName("sitemapURL").length > 0) {
 			sitemap="";		
-	        if(response.getElementsByTagName("sitemap")[0].firstChild!=null){
+	        if (response.getElementsByTagName("sitemap")[0].firstChild!=null){
 		        sitemap=response.getElementsByTagName("sitemap")[0].firstChild.nodeValue;
 		    }		
 			document.getElementsByName("sitemapURL")[0].value=sitemap;
 			document.getElementById("sitemap").disabled=false;
 		}
+			sitelist="";		
+	        if (response.getElementsByTagName("sitelist")[0].firstChild!=null){
+		        sitelist=response.getElementsByTagName("sitelist")[0].firstChild.nodeValue;
+		    }
+			document.getElementById("sitelistURLs").innerHTML = sitelist;
+			document.getElementById("sitelist").disabled=false;
         
 		// clear the ajax image
 		document.getElementsByName("ajax")[0].setAttribute("src", AJAX_OFF);
     }
 }
-function changed(){
+
+function changed() {
 	window.clearTimeout(timeout);
 	timeout=window.setTimeout("loadInfos()", 1500);
 }
-function loadInfos(){
+
+function loadInfos() {
 	// displaying ajax image
 	document.getElementsByName("ajax")[0].setAttribute("src",AJAX_ON);