"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  ...

			<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>

		<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.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)));

gsj.bz

// GitHub, Inc.
// Submitted by Patrick Toomey <******@****.***>
githubusercontent.com
githubpreview.dev
github.io

// GitLab, Inc.
// Submitted by Alex Hanselka <alex@gitlab.com>
gitlab.io

// Gitplac.si - https://gitplac.si
// Submitted by Aljaž Starc <******@****.***>
gitapp.si
gitpage.si

// Glitch, Inc : https://glitch.com

# 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>

ginan.gifu.jp
ginowan.okinawa.jp
ginoza.okinawa.jp
girlfriend.jp
girly.jp
giske.no
git-pages.rit.edu
git-repos.de
gitapp.si
github.io
githubpreview.dev
githubusercontent.com
gitlab.io
gitpage.si
gives
giving
gjemnes.no
gjerdrum.no
gjerstad.no
gjesdal.no
gjovik.no
gjøvik.no
gkp.pk
gl
gl.srv.us
glass
gle
gleeze.com
gliding.aero