fix for bug in html scraper that appears if opening and closing tag are 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
This commit is contained in:
orbiter 2008-05-24 10:47:22 +00:00
parent d8277e6af1
commit f8b015949c
2 changed files with 2 additions and 1 deletions

View File

@ -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");

View File

@ -231,7 +231,7 @@ public final class htmlFilterWriter extends Writer {
}
// 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];