<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE components PUBLIC "-//DBFLUTE//DTD LastaDi 1.0//EN"
	"http://dbflute.org/meta/lastadi10.dtd">
<components namespace="fessCrawler">
	<include path="crawler/container.xml" />

	<component name="tikaExtractor"
		class="org.codelibs.fess.crawler.extractor.impl.TikaExtractor">
		<property name="maxCompressionRatio">1</property>
		<property name="maxUncompressionSize">10000000</property>
	</component>

h=s.call(a,"div"),s.call(a,"[s!='']:x"),r.push("!=",Q)}),q=q.length&&new RegExp(q.join("|")),r=r.length&&new RegExp(r.join("|")),b=$.test(o.compareDocumentPosition),t=b||$.test(o.contains)?function(a,b){var c=9===a.nodeType?a.documentElement:a,d=b&&b.parentNode;return a===d||!(!d||1!==d.nodeType||!(c.contains?c.contains(d):a.compareDocumentPosition&&16&a.compareDocumentPosition(d)))}:function(a,b){if(b)while(b=b.parentNode)if(b===a)return!0;return!1},B=b?function(a,b){if(a===b)return l=!0,0;var ...

        } else {
            hostUrl = url;
        }
        final String robotTxtUrl = hostUrl + "/robots.txt";

        // check url
        if (crawlerContext.getRobotsTxtUrlSet().contains(robotTxtUrl)) {
            if (logger.isDebugEnabled()) {
                logger.debug("{} is already visited.", robotTxtUrl);
            }
            return;
        }