<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.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;

/**

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;

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>

## 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

![trình soạn thảo hỗ trợ](https://fastapi.tiangolo.com/img/vscode-completion.png)

Ví dụ hoàn chỉnh bao gồm nhiều tính năng hơn, xem <a href="https://fastapi.tiangolo.com/tutorial/">Tutorial - User Guide</a>.


**Cảnh báo tiết lỗ**: Tutorial - User Guide:

* Định nghĩa **tham số** từ các nguồn khác nhau như: **headers**, **cookies**, **form fields** và **files**.
* Cách thiết lập **các ràng buộc cho validation** như `maximum_length` hoặc `regex`.

        final String content = extractData.getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertTrue(content.contains("テスト"));
    }

    // TODO tika needs to support pdfbox 2.0
    //    public void test_getTika_pdf() {
    //        final InputStream in = ResourceUtil
    //                .getResourceAsStream("extractor/test.pdf");

?iroy?k&ato?ihs?u&k?stawi???m&akoyr?i&hsoy?juf??uziimak???naznar?o&dakas?ihsay?jnoh?n&a&go?nim??imijuf?nah?oy??r&ihsayim?otagan??t&asim!ak??igus?omatik??zak??u&bihcihc!ihsagih??sonuok?ynah????y&ak&aw!.&a&d&ira?notimak??kadih?ma&h&arihs?im??y&a&kaw?tik??oduk???ru&ustakihcan?y??sauy?wa&g&a&dira?zok??orih??konik??yok?zok??e&banat?dawi??i&garustak?jiat?mani??naniak?o&bog?nimik?t&asim?omihs&ah?uk????ugnihs???o!.&a&jos?koasak?m&ay&ako?ust??ihsayah??r&abi?ukawaihsin??wi&aka?nam???e&gakay?kaw??i&gan?h&c...