import java.util.Arrays;
import java.util.Map;
import java.util.stream.Collectors;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.apache.tika.language.detect.LanguageDetector;
import org.apache.tika.language.detect.LanguageResult;
import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.mylasta.direction.FessConfig;
import org.codelibs.fess.util.ComponentUtil;

			<groupId>com.ibm.icu</groupId>
			<artifactId>icu4j</artifactId>
			<version>${icu4j.version}</version>
		</dependency>
		<dependency>
			<groupId>org.apache.tika</groupId>
			<artifactId>tika-langdetect-optimaize</artifactId>
			<version>${tika.version}</version>
			<exclusions>
				<exclusion>
					<groupId>javax.annotation</groupId>
					<artifactId>javax.annotation-api</artifactId>
				</exclusion>

				"application/x-texinfo",
				"application/x-tika-msoffice",
				"application/x-tika-msoffice-embedded",
				"application/x-tika-msoffice-embedded;format=ole10_native",
				"application/x-tika-msoffice-embedded;format=comp_obj",
				"application/x-tika-msworks-spreadsheet",
				"application/x-tika-ooxml",
				"application/x-tika-ooxml-protected",
				"application/x-tika-staroffice",
				"application/x-uc2-compressed",

        } else {
            cmdList.add("-Dfess.log.level=" + logLevel);
            if ("debug".equalsIgnoreCase(logLevel)) {
                cmdList.add("-Dorg.apache.tika.service.error.warn=true");
            }
        }
        stream(fessConfig.getJvmCrawlerOptionsAsArray())
                .of(stream -> stream.filter(StringUtil::isNotBlank).forEach(value -> cmdList.add(value)));

        final String content = extractData.getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertTrue(content.contains("テスト"));
    }

    // TODO tika needs to support pdfbox 2.0
    //    public void test_getTika_pdf() {
    //        final InputStream in = ResourceUtil
    //                .getResourceAsStream("extractor/test.pdf");

crawler.hotthread.snapshots=10
crawler.hotthread.threads=3
crawler.hotthread.timeout=30s
crawler.hotthread.type=cpu
crawler.metadata.content.excludes=resourceName,X-Parsed-By,Content-Encoding.*,Content-Type.*,X-TIKA.*,X-FESS.*
crawler.metadata.name.mapping=\
title=title:string\n\
Title=title:string\n\
dc:title=title:string\n\

# html
crawler.document.html.content.xpath=//BODY

tochigi.tochigi.jp tochio.niigata.jp toda.saitama.jp today toei.aichi.jp toga.toyama.jp togakushi.nagano.jp togane.chiba.jp togitsu.nagasaki.jp togliatti.su togo.aichi.jp togura.nagano.jp tohma.hokkaido.jp tohnosho.chiba.jp toho.fukuoka.jp tokai.aichi.jp tokai.ibaraki.jp tokamachi.niigata.jp tokashiki.okinawa.jp toki.gifu.jp tokigawa.saitama.jp tokke.no tokoname.aichi.jp tokorozawa.saitama.jp tokushima.jp tokushima.tokushima.jp tokuyama.yamaguchi.jp tokyo tokyo.jp tolga.no tomakomai.hokkaido.jp tomari.hokkaido.jp...

    /** The key of the configuration. e.g. cpu */
    String CRAWLER_HOTTHREAD_TYPE = "crawler.hotthread.type";

    /** The key of the configuration. e.g. resourceName,X-Parsed-By,Content-Encoding.*,Content-Type.*,X-TIKA.*,X-FESS.* */
    String CRAWLER_METADATA_CONTENT_EXCLUDES = "crawler.metadata.content.excludes";

    /** The key of the configuration. e.g. title=title:string<br>
     * Title=title:string<br>

okazaki.aichi.jp
owariasahi.aichi.jp
seto.aichi.jp
shikatsu.aichi.jp
shinshiro.aichi.jp
shitara.aichi.jp
tahara.aichi.jp
takahama.aichi.jp
tobishima.aichi.jp
toei.aichi.jp
togo.aichi.jp
tokai.aichi.jp
tokoname.aichi.jp
toyoake.aichi.jp
toyohashi.aichi.jp
toyokawa.aichi.jp
toyone.aichi.jp
toyota.aichi.jp
tsushima.aichi.jp
yatomi.aichi.jp
akita.akita.jp
daisen.akita.jp