"iekām", "iekāms", "kolīdz", "līdzko", "tiklīdz", "jebšu", "tālab", "tāpēc", "nekā", "itin", "jā", "jau", "jel", "nē", "nezin", "tad", "tikai", "vis", "tak", "iekams", "vien", "# modal verbs", "būt  ", "biju ", "biji", "bija", "bijām", "bijāt", "esmu", "esi", "esam", "esat ", "būšu     ", "būsi", "būs", "būsim", "būsiet", "tikt", "tiku", "tiki", "tika", "tikām", "tikāt", "tieku", "tiec", "tiek", "tiekam", "tiekat", "tikšu", "tiks", "tiksim", "tiksiet", "tapt", "tapi", "tapāt", "topat", "tapšu", "tapsi",...

			<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>

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;

    public Logger getLogger() {
        return logger;
    }

    /**
     * Gets the appropriate extractor for the given response data.
     * Selects an extractor based on the MIME type or falls back to the Tika extractor.
     *
     * @param responseData the response data containing the document to extract
     * @return the extractor instance for processing the document

        } 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)));

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

# Type of hot thread monitoring (e.g., cpu).
crawler.hotthread.type=cpu
# Metadata fields to exclude from document content.
crawler.metadata.content.excludes=resourceName,X-Parsed-By,Content-Encoding.*,Content-Type.*,X-TIKA.*,X-FESS.*
# Mapping for document metadata names.
crawler.metadata.name.mapping=\
title=title:string\n\
Title=title:string\n\
dc:title=title:string\n\

# html

    /** 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>

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

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