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
taps
tapsim
tapsiet
kļūt
kļuvu
kļuvi
kļuva
kļuvām
kļuvāt
kļūstu
kļūsti
kļūst
kļūstam
kļūstat
kļūšu
kļūsi
kļūs
kļūsim
kļūsiet
# verbs

"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",...

"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>

sejam
fosse
fôssemos
fossem
for
formos
forem
serei
será
seremos
serão
seria
seríamos
seriam
tenho
tem
temos
tém
tinha
tínhamos
tinham
tive
teve
tivemos
tiveram
tivera
tivéramos
tenha
tenhamos
tenham
tivesse
tivéssemos
tivessem
tiver
tivermos
tiverem
terei
terá
teremos
terão
teria
teríamos

import java.util.Map;
import java.util.Set;

import org.apache.tika.metadata.ClimateForcast;
import org.apache.tika.metadata.CreativeCommons;
import org.apache.tika.metadata.Geographic;
import org.apache.tika.metadata.HttpHeaders;
import org.apache.tika.metadata.Message;
import org.apache.tika.metadata.TIFF;
import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.metadata.TikaMimeKeys;

/**

			<artifactId>tika-parser-html-module</artifactId>
			<version>${tika.version}</version>
		</dependency>
		<dependency>
			<groupId>org.apache.tika</groupId>
			<artifactId>tika-parser-image-module</artifactId>
			<version>${tika.version}</version>
		</dependency>
		<dependency>
			<groupId>org.apache.tika</groupId>
			<artifactId>tika-parser-mail-module</artifactId>

  <!--  an OLE2 (application/x-tika-msoffice) container. -->
  <!--  The are logically subclasses of (application/x-tika-ooxml),
        but their containers are literally subclasses
        of (application/x-tika-msoffice) -->
  <mime-type type="application/x-tika-ooxml-protected">
    <sub-class-of type="application/x-tika-msoffice"/>
    <_comment>Password Protected OOXML File</_comment>

import java.io.BufferedInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.util.HashMap;
import java.util.Map;

import org.apache.tika.metadata.Metadata;
import org.apache.tika.mime.MediaType;
import org.apache.tika.mime.MimeTypes;
import org.apache.tika.mime.MimeTypesFactory;
import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.crawler.entity.ExtractData;

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;