<!--  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.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>

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 org.apache.logging.log4j.Logger;
import org.apache.tika.config.TikaConfig;
import org.apache.tika.detect.Detector;
import org.apache.tika.exception.TikaException;
import org.apache.tika.extractor.EmbeddedDocumentExtractor;
import org.apache.tika.extractor.ParsingEmbeddedDocumentExtractor;
import org.apache.tika.io.TemporaryResources;
import org.apache.tika.io.TikaInputStream;
import org.apache.tika.metadata.Metadata;

		<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;

			<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>

    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

## Technology Stack

- **Java**: 21+ (requires Java 21 or higher)
- **Build System**: Maven 3.x
- **DI Container**: LastaFlute DI
- **HTTP Client**: Apache HttpComponents
- **Content Extraction**: Apache Tika, Apache POI, PDFBox
- **Testing**: JUnit 4, UTFlute, Testcontainers
- **Storage Backends**: OpenSearch, Memory-based

## Quick Start

### Prerequisites

- Java 21 or higher
- Maven 3.6 or higher