### Protocols

- **HTTP/HTTPS**: Full crawling, cookies, auth, robots.txt
- **File**: Local/network file systems
- **FTP**: With authentication
- **SMB/CIFS**: Windows shares (SMB1/SMB2+)
- **Storage**: MinIO/S3-compatible

### Content Formats

Office (Word, Excel, PowerPoint), PDF, Archives (ZIP, TAR, GZ), HTML, XML, JSON, Media (audio/video metadata), Images (EXIF/IPTC/XMP)

---

import jakarta.annotation.Resource;

/**
 * The {@link SmbClient} class is a crawler client implementation for accessing files and directories
 * on SMB (Server Message Block) shares. It extends {@link AbstractCrawlerClient} and utilizes the JCIFS library
 * to interact with SMB resources.
 *
 * <p>
 * This client supports authentication, content retrieval, and metadata extraction from SMB files.

import org.codelibs.jcifs.smb1.util.LogStream;

import jakarta.annotation.Resource;

/**
 * The {@link SmbClient} class is a crawler client implementation for accessing files and directories
 * on SMB (Server Message Block) shares using the SMB1 protocol. It extends {@link AbstractCrawlerClient} and utilizes the JCIFS library
 * to interact with SMB resources.
 *
 * <p>

        assertFalse(robotsTxt.allows("/path with spaces/", "SpecialCharBot"));
        assertFalse(robotsTxt.allows("/path%20encoded/", "SpecialCharBot"));
        assertFalse(robotsTxt.allows("/path?query=value", "SpecialCharBot"));

        // Test multiple User-agents in sequence (Bot1, Bot2, Bot3 should share the same rules)
        assertFalse(robotsTxt.allows("/shared/", "Bot1"));

 */
package org.codelibs.fess.score;

import java.util.ArrayList;
import java.util.List;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;

/**
 * This class updates scores of documents.
 */
public class ScoreUpdater {
    /**
     * Constructor.
     */
    public ScoreUpdater() {
        super();
    }

    }

    /**
     * Starts a reindex operation with the specified parameters.
     *
     * @param replaceAliases whether to replace aliases after reindexing
     * @param resetDictionaries whether to reset dictionaries during reindexing
     * @param numberOfShards the number of shards for the new index

    protected Map<String, Pair<Map<String, String>, List<Pair<Pattern, String>>>> relatedContentMap = Collections.emptyMap();

    /**
     * Prefix used to identify regex patterns in related content terms.
     * When a term starts with this prefix, it is treated as a regular expression
     * pattern rather than an exact match term.
     */
    protected String regexPrefix = "regex:";

    /**

- `DefaultContentsParserTest` - Text processing pipeline

---

## Code Conventions

### Java Style

- **Formatter**: Eclipse formatter at `src/config/eclipse/formatter/java.xml`
- **Indentation**: 4 spaces (no tabs)
- **Line Length**: 140 characters max
- **License Headers**: Required (use `mvn license:format`)

### Naming Conventions

| Type | Convention | Example |
|------|-----------|---------|

            cb.query().addOrderBy_Name_Asc();
            cb.fetchFirst(fessConfig.getPageScheduledJobMaxFetchSizeAsInteger());
        });
    }

    /**
     * Stores a scheduled job.
     * @param scheduledJob The scheduled job to store.
     */
    public void store(final ScheduledJob scheduledJob) {
        scheduledJobBhv.insertOrUpdate(scheduledJob, op -> {

labels.searchlog_usersessionid=ID do usuário
labels.searchlog_requestedtime=Hora
labels.searchlog_accesstype=Tipo de acesso
labels.maintenance_title_configuration=Manutenção
labels.number_of_shards_for_doc=Número de shards
labels.auto_expand_replicas_for_doc=Número máximo de réplicas
labels.clear_crawler_index=Índice do rastreador
labels.clear_crawler_index_button=Excluir índice de rastreamento
labels.diagnostic_logs=Diagnóstico