ant
apie
ar
arba
aš
be
bei
bet
bus
būti
būtų
buvo
dėl
gali
į
iki
ir
iš
ja
ją
jai
jais
jam
jame
jas
jei
ji
jį
jie
jiedu
jiedvi
jiedviem
jiedviese
jiems
jis
jo
jodviem
jog
joje
jomis
joms
jos
jose
jų

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;

labels.fileConfigName=Nome configurazione scansione file
labels.fileName=Nome file
labels.handlerName=Nome gestore
labels.handlerParameter=Parametro
labels.handler_script=Script
labels.popularWord=Parola popolare
labels.ignoreFailureType=Tipi di errore ignorati
labels.lastAccessTime=Data ultimo accesso
labels.notificationTo=Notifica a
labels.num=Numero
labels.pn=Numero di pagina
labels.protocolScheme=Schema
labels.purgeByBots=Elimina per Bot

ediliyor
edilmesi
ediyor
eğer
elli
en
etmesi
etti
ettiği
ettiğini
gibi
göre
halen
hangi
hatta
hem
henüz
hep
hepsi
her
herhangi
herkesin
hiç
hiçbir
için
iki
ile
ilgili
ise
işte
itibaren
itibariyle
kadar
karşın
katrilyon
kendi
kendilerine
kendini
kendisi
kendisine
kendisini
kez
ki
kim
kimden
kime
kimi

				"application/x-texinfo",
				"application/x-tika-msoffice",
				"application/x-tika-msoffice-embedded",
				"application/x-tika-msoffice-embedded;format=ole10_native",
				"application/x-tika-msoffice-embedded;format=comp_obj",
				"application/x-tika-msworks-spreadsheet",
				"application/x-tika-ooxml",
				"application/x-tika-ooxml-protected",
				"application/x-tika-staroffice",
				"application/x-uc2-compressed",

			<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>

- **Build**: Maven 3.x
- **License**: Apache 2.0
- **DI**: LastaFlute DI
- **Repo**: https://github.com/codelibs/fess-crawler

### Tech Stack

- **HTTP**: Apache HttpComponents 4.5+
- **Extraction**: Apache Tika 3.0+, POI 5.3+, PDFBox 3.0+
- **Testing**: JUnit 4, UTFlute, Mockito 5.7.0
- **Storage**: In-memory (default), OpenSearch (optional)

### Protocols

- **HTTP/HTTPS**: Full crawling, cookies, auth, robots.txt

    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

3. **Fallback**: English (from `fess_label.properties` and `fess_message.properties`)

### Document Language Detection

During crawling and indexing, Fess:

1. Detects language from document content using Apache Tika
2. Validates against `supported.languages` list
3. Creates language-specific fields (e.g., `content_ja`, `title_en`, `content_sv`)
4. Applies language-specific analyzers for better search results

## 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