te
vai
kamēr
# Particles
ar
diezin
droši
diemžēl
nebūt
ik
it
taču
nu
pat
tiklab
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

			<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>

<?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>

"tikvien", "vien", "kā", "ir", "te", "vai", "kamēr", "# Particles", "ar", "diezin", "droši", "diemžēl", "nebūt", "ik", "it", "taču", "nu", "pat", "tiklab", "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  ...

"tikvien", "vien", "kā", "ir", "te", "vai", "kamēr", "# Particles", "ar", "diezin", "droši", "diemžēl", "nebūt", "ik", "it", "taču", "nu", "pat", "tiklab", "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  ...

    /** 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.* */
    String CRAWLER_METADATA_CONTENT_EXCLUDES = "crawler.metadata.content.excludes";

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

ore{content:"\f1d3"}.fa-git-alt:before{content:"\f841"}.fa-git-square:before{content:"\f1d2"}.fa-github:before{content:"\f09b"}.fa-github-alt:before{content:"\f113"}.fa-github-square:before{content:"\f092"}.fa-gitkraken:before{content:"\f3a6"}.fa-gitlab:before{content:"\f296"}.fa-gitter:before{content:"\f426"}.fa-glass-cheers:before{content:"\f79f"}.fa-glass-martini:before{content:"\f000"}.fa-glass-martini-alt:before{content:"\f57b"}.fa-glass-whiskey:before{content:"\f7a0"}.fa-glasses:before{con...

ore{content:"\f1d3"}.fa-git-alt:before{content:"\f841"}.fa-git-square:before{content:"\f1d2"}.fa-github:before{content:"\f09b"}.fa-github-alt:before{content:"\f113"}.fa-github-square:before{content:"\f092"}.fa-gitkraken:before{content:"\f3a6"}.fa-gitlab:before{content:"\f296"}.fa-gitter:before{content:"\f426"}.fa-glass-cheers:before{content:"\f79f"}.fa-glass-martini:before{content:"\f000"}.fa-glass-martini-alt:before{content:"\f57b"}.fa-glass-whiskey:before{content:"\f7a0"}.fa-glasses:before{con...

		<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;