import org.codelibs.fess.util.SystemUtil;

import jakarta.servlet.ServletContext;

/**
 * Job class for generating thumbnails for documents in the search engine.
 * This job executes the ThumbnailGenerator process as a separate JVM process
 * to create thumbnail images for supported document types.
 */
public class GenerateThumbnailJob extends ExecJob {
    /** Logger for this class. */

 * including adding URLs to the queue, filtering URLs, managing crawler threads,
 * and handling the overall crawling lifecycle.
 *
 * <p>It implements the Runnable interface to be executed in a separate thread,
 * and the AutoCloseable interface to ensure resources are properly released after use.
 *
 * <p>The crawler uses several services and components, such as UrlQueueService, DataService,

import org.codelibs.fess.util.SystemUtil;

import jakarta.servlet.ServletContext;

/**
 * CrawlJob is responsible for executing the crawling process in Fess.
 * This job launches a separate crawler process that can crawl web sites, file systems,
 * and data sources based on the configured crawling settings.
 *
 * <p>The job supports selective crawling by specifying configuration IDs for different

 */
public class PopularWordHelper {
    /** Logger instance for this class */
    private static final Logger logger = LogManager.getLogger(PopularWordHelper.class);

    /** Character used to separate cache key components */
    protected static final char CACHE_KEY_SPLITTER = '\n';

    /** Cache for storing popular word lists */
    protected Cache<String, List<String>> cache;

    /** Fess configuration instance */

     * The date of last modification of the file. This date should be in W3C
     * Datetime format. This format allows you to omit the time portion, if
     * desired, and use YYYY-MM-DD.
     *
     * Note that this tag is separate from the If-Modified-Since (304) header
     * the server can return, and search engines may use the information from
     * both sources differently.
     */
    private String lastmod;

    /**

/**
 * PdfExtractor extracts text content from PDF files using Apache PDFBox.
 * It supports password-protected PDFs and can extract embedded documents and annotations.
 *
 * <p>The extractor runs text extraction in a separate thread with a configurable timeout
 * to prevent hanging on problematic PDF files. It also extracts metadata from the PDF
 * document and includes it in the extraction result.
 *
 * <p>Features:
 * <ul>

### Configuração de Plugins para OpenSearch

Execute antrun:run para baixar os plugins no diretório de plugins:

    $ mvn antrun:run

### Executar o Fess

Execute ou depure `org.codelibs.fess.FessBoot` no seu IDE, e depois acesse http://localhost:8080/

### Criar Pacote

Execute o objetivo `package` e o arquivo de lançamento será criado em target/releases.

    $ mvn package

            });
            RenderDataUtil.register(data, "savedTags", tags);
        });
    }

    /**
     * Container class for path information containing separate path and name components.
     */
    public static class PathInfo {
        private final String path;
        private final String name;

        /**
         * Creates a new PathInfo instance.

        }
        load();
    }

    /**
     * Updates the processor configuration by reloading available searchers.
     * This method executes the load operation asynchronously in a separate thread.
     */
    public void update() {
        CommonPoolUtil.execute(this::load);
    }

    /**
     * Loads the available searcher names from system properties.

labels.endTime=Hora de término
labels.hq=hq
labels.inputs=Entradas
labels.jobLogging=Logging
labels.jobName=Nome
labels.jobStatus=Estado
labels.labelTypeIds=Rótulos
labels.lang=Idioma
labels.outputs=Saídas
labels.pos=Parte da fala
labels.purgeJobLogDay=Excluir logs de trabalho anteriores
labels.purgeUserInfoDay=Excluir logs de usuário anteriores
labels.reading=Leitura
labels.roleTypeIds=ID da função
labels.scriptData=Script