final Document document = getDocument(data);

        ComponentUtil.setFessConfig(new FessConfig.SimpleImpl() {
            private static final long serialVersionUID = 1L;

            @Override
            public String getCrawlerDocumentHtmlPrunedTags() {
                return "noscript";
            }
        });

# XPath to extract canonical URL from HTML documents.
crawler.document.html.canonical.xpath=//LINK[@rel='canonical'][1]/@href
# HTML tags to prune (remove) during document processing.
crawler.document.html.pruned.tags=noscript,script,style,header,footer,aside,nav,a[rel=nofollow]
# Maximum length of digest extracted from HTML documents.
crawler.document.html.max.digest.length=120
# Default language for HTML documents.