fix for bug in html scraper that appears if opening and closing tag a…

…re not both in same case

see http://forum.yacy-websuche.de/viewtopic.php?f=6&t=1173&p=7836#p7836

git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@4844 6c8d7289-2bf4-0310-a012-ef5d649a1542

source/de/anomic/htmlFilter/htmlFilterContentScraper.java

@@ -72,6 +72,7 @@ public class htmlFilterContentScraper extends htmlFilterAbstractScraper implemen
     private static final HashSet<String> linkTags0 = new HashSet<String>(9,0.99f);
     private static final HashSet<String> linkTags1 = new HashSet<String>(7,0.99f);
 
+    // all these tags must be given in lowercase, because the tags from the files are compared in lowercase
     static {
         linkTags0.add("img");
         linkTags0.add("base");

source/de/anomic/htmlFilter/htmlFilterWriter.java

@@ -231,7 +231,7 @@ private char[] filterTag(String tag, boolean opening, char[] content, char quote
         }
 
         // it's a tag! which one?
-        if ((opening) || (!(tag.equals(filterTag)))) {
+        if ((opening) || (!(tag.equalsIgnoreCase(filterTag)))) {
             // this tag is not our concern. just add it
             filterCont.append(genTag0raw(tag, opening, content));
             return new char[0];