<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>

tieku
tiec
tiek
tiekam
tiekat
tikšu
tiks
tiksim
tiksiet
tapt
tapi
tapāt
topat
tapšu
tapsi
taps
tapsim
tapsiet
kļūt
kļuvu
kļuvi
kļuva
kļuvām
kļuvāt
kļūstu
kļūsti
kļūst
kļūstam
kļūstat
kļūšu
kļūsi
kļūs
kļūsim
kļūsiet
# verbs
varēt
varēju
varējām
varēšu
varēsim
var
varēji
varējāt

"iekšpus", "nedz", "tik", "nevis", "turpretim", "jeb", "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",...

<?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>

"iekšpus", "nedz", "tik", "nevis", "turpretim", "jeb", "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",...

biasanya
bila
bilakah
bisa
bisakah
sebisanya
boleh
bolehkah
bolehlah
buat
bukan
bukankah
bukanlah
bukannya
cuma
percuma
dahulu
dalam
dan
dapat
dari
daripada
dekat
demi
demikian
demikianlah
sedemikian
dengan
depan
di
dia
dialah
dini
diri
dirinya
terdiri
dong
dulu
enggak
enggaknya
entah
entahlah
terhadap

meter-quarter:before{content:"\f2ca"}.fa-thermometer-three-quarters:before{content:"\f2c8"}.fa-think-peaks:before{content:"\f731"}.fa-thumbs-down:before{content:"\f165"}.fa-thumbs-up:before{content:"\f164"}.fa-thumbtack:before{content:"\f08d"}.fa-ticket-alt:before{content:"\f3ff"}.fa-times:before{content:"\f00d"}.fa-times-circle:before{content:"\f057"}.fa-tint:before{content:"\f043"}.fa-tint-slash:before{content:"\f5c7"}.fa-tired:before{content:"\f5c8"}.fa-toggle-off:before{content:"\f204"}.fa-t...

meter-quarter:before{content:"\f2ca"}.fa-thermometer-three-quarters:before{content:"\f2c8"}.fa-think-peaks:before{content:"\f731"}.fa-thumbs-down:before{content:"\f165"}.fa-thumbs-up:before{content:"\f164"}.fa-thumbtack:before{content:"\f08d"}.fa-ticket-alt:before{content:"\f3ff"}.fa-times:before{content:"\f00d"}.fa-times-circle:before{content:"\f057"}.fa-tint:before{content:"\f043"}.fa-tint-slash:before{content:"\f5c7"}.fa-tired:before{content:"\f5c8"}.fa-toggle-off:before{content:"\f204"}.fa-t...

		<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;