final String[] path = referenceClass.getName().split("\\.");
        String baseUrl = url.toExternalForm();
        for (final String element : path) {
            final int pos = baseUrl.lastIndexOf('/');
            baseUrl = baseUrl.substring(0, pos);
        }
        return getTraverser(URLUtil.create(baseUrl + '/'), null, null);
    }

    /**

- **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

## 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

### Installation

                stateDirectory, "*.handle")) {
            for (Path handleFile : stream) {
                try (ObjectInputStream ois = new ObjectInputStream(
                        Files.newInputStream(handleFile))) {
                    HandleInfo info = (HandleInfo) ois.readObject();
                    
                    // Only load if not expired
                    if (!info.isExpired()) {

            entity.setNewToken(form.token);
            entity.setNewSegmentation(form.segmentation);
            entity.setNewReading(form.reading);
            entity.setNewPos(form.pos);
            return entity;
        });
    }

    // ===================================================================================

labels.endTime=End Time
labels.hq=hq
labels.inputs=Inputs
labels.jobLogging=Logging
labels.jobName=Name
labels.jobStatus=Status
labels.labelTypeIds=Labels
labels.lang=Language
labels.outputs=Outputs
labels.pos=Part-of-speech
labels.purgeJobLogDay=Delete old job logs
labels.purgeUserInfoDay=Delete old user logs
labels.reading=Reading
labels.roleTypeIds=Role IDs
labels.scriptData=Script
labels.scriptResult=Result

labels.dictId=字典ID
labels.docId=文檔ID
labels.endTime=結束時間
labels.hq=hq
labels.inputs=輸入
labels.jobLogging=日誌記錄
labels.jobName=名稱
labels.jobStatus=狀態
labels.labelTypeIds=標籤
labels.lang=語言
labels.outputs=輸出
labels.pos=詞性
labels.purgeJobLogDay=刪除以前的作業日誌
labels.purgeUserInfoDay=刪除以前的使用者日誌
labels.reading=讀音
labels.roleTypeIds=角色ID
labels.scriptData=腳本
labels.scriptResult=結果
labels.scriptType=執行方法
labels.segmentation=分段

import org.apache.commons.net.ftp.FTPSClient;
import org.apache.commons.net.util.TrustManagerUtils;
import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.apache.poi.util.StringUtil;
import org.codelibs.core.io.CloseableUtil;
import org.codelibs.core.io.CopyUtil;
import org.codelibs.core.io.FileUtil;
import org.codelibs.core.io.InputStreamUtil;
import org.codelibs.core.timer.TimeoutManager;

labels.endTime=Время окончания
labels.hq=hq
labels.inputs=Входы
labels.jobLogging=Ведение журнала
labels.jobName=Имя
labels.jobStatus=Статус
labels.labelTypeIds=Метки
labels.lang=Язык
labels.outputs=Выходы
labels.pos=Часть речи
labels.purgeJobLogDay=Удалить старые журналы заданий
labels.purgeUserInfoDay=Удалить старые журналы пользователей
labels.reading=Чтение
labels.roleTypeIds=ID ролей
labels.scriptData=Скрипт

labels.endTime=Ora di fine
labels.hq=hq
labels.inputs=Input
labels.jobLogging=Logging
labels.jobName=Nome
labels.jobStatus=Stato
labels.labelTypeIds=Etichette
labels.lang=Lingua
labels.outputs=Output
labels.pos=Parte del discorso
labels.purgeJobLogDay=Elimina log di lavoro precedenti
labels.purgeUserInfoDay=Elimina log utente precedenti
labels.reading=Lettura
labels.roleTypeIds=ID ruolo
labels.scriptData=Script