}
        };
        transformer.fessConfig = new FessConfig.SimpleImpl() {
            private static final long serialVersionUID = 1L;

            public String getCrawlerDocumentHtmlCanonicalXpath() {
                return "//LINK[@rel='canonical'][1]/@href";
            };
        };

        final ResponseData responseData = new ResponseData();
        responseData.setSessionId("test");

     * comment: XPath to extract canonical URL from HTML documents.
     * @return The value of found property. (NotNull: if not found, exception but basically no way)
     */
    String getCrawlerDocumentHtmlCanonicalXpath();

    /**
     * Get the value for the key 'crawler.document.html.pruned.tags'. <br>
     * The value is, e.g. noscript,script,style,header,footer,aside,nav,a[rel=nofollow] <br>

Shinsuke Sugaya <******@****.***> 1774681159 +0900

Shinsuke Sugaya <******@****.***> 1773442886 +0900

Shinsuke Sugaya <******@****.***> 1774491848 +0900

Shinsuke Sugaya <******@****.***> 1774681159 +0900

        String xpath = configMap.get(Config.HTML_CANONICAL_XPATH);
        if (xpath == null) {
            xpath = fessConfig.getCrawlerDocumentHtmlCanonicalXpath();
        }
        if (StringUtil.isBlank(xpath)) {
            return null;
        }
        final String canonicalUrl = getSingleNodeValue(document, xpath, node -> node);