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

<?xml version="1.0" encoding="UTF-8"?>
<properties>
  <parsers>
    <parser class="org.apache.tika.parser.DefaultParser">
      <parser-exclude class="org.apache.tika.parser.ocr.TesseractOCRParser"/>
    </parser>
  </parsers>

"iekam", "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",...

"iekam", "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",...

		<property name="valueSeparator">"\\n"</property>
		<property name="roleSeparator">","</property>
		 -->
	</component>
	<component name="tikaConfig" class="org.apache.tika.config.TikaConfig">
		<arg>org.codelibs.fess.util.ResourceUtil.getConfOrClassesPath("tika.xml")</arg>
	</component>

import java.util.stream.Collectors;

import javax.annotation.PostConstruct;

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>

        } 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)));

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.*
crawler.metadata.name.mapping=\
title=title:string\n\
Title=title:string\n\
dc:title=title:string\n\

# html
crawler.document.html.content.xpath=//BODY
crawler.document.html.lang.xpath=//HTML/@lang

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...