/**
     * The name of the web configuration associated with this failure URL.
     * Used to identify which web crawling configuration encountered the failure.
     */
    public String webConfigName;

    /**
     * The name of the file configuration associated with this failure URL.
     * Used to identify which file crawling configuration encountered the failure.
     */
    public String fileConfigName;

    /**

 */
package org.codelibs.fess.app.web.admin.wizard;

/**
 * Form class for starting crawling operations in the admin wizard.
 *
 * This form is used to collect user input and parameters needed to initiate
 * crawling operations through the administrative interface wizard workflow.
 * It serves as a data transfer object between the web layer and the crawling
 * service components.
 */
public class StartCrawlingForm {

    /**

        }
    }

    /**
     * Processes a crawling request for a specific URL.
     * Executes the full crawling pipeline including client execution, rule processing,
     * transformation, and data extraction.
     *
     * @param crawlingConfig the crawling configuration to use
     * @param crawlingInfoId the crawling session ID
     * @param url the URL to process

 * This class extends the base CrawlerThread and provides Fess-specific functionality for
 * crawling and indexing documents, including incremental crawling capabilities, content
 * modification checking, and integration with the Fess search engine backend.
 *
 * <p>Key features include:</p>
 * <ul>
 * <li>Incremental crawling support with last-modified timestamp checking</li>
 * <li>Document expiration handling</li>

labels.createdTime=Created Time
labels.depth=Depth
labels.excludedPaths=Excluded Paths for Crawling
labels.excludedUrls=Excluded URLs for Crawling
labels.excludedDocPaths=Excluded Paths for Searching
labels.excludedDocUrls=Excluded URLs for Searching
labels.hostname=Hostname
labels.id=ID
labels.includedPaths=Included Paths for Crawling
labels.includedUrls=Included URLs for Crawling
labels.includedDocPaths=Included Paths for Searching

/**
 * Parser for Google Search Appliance (GSA) configuration files.
 * This SAX-based parser reads GSA XML configuration files and converts them into
 * Fess configuration objects including web crawling configurations, file crawling
 * configurations, and label types for access control.
 *
 * <p>The parser handles the following GSA configuration elements:
 * <ul>
 * <li>Collections with good/bad URL patterns</li>

## Changelog since v1.16.11

## Changes by Kind

### API Change

- Fixed: log timestamps now include trailing zeros to maintain a fixed width ([#91207](https://github.com/kubernetes/kubernetes/pull/91207), [@iamchuckss](https://github.com/iamchuckss)) [SIG Apps and Node]

### Bug or Regression

import org.dbflute.optional.OptionalEntity;

import jakarta.annotation.Resource;

/**
 * Service class for managing failure URLs that occur during web crawling.
 * Provides functionality to store, retrieve, and manage failed crawling attempts
 * with their associated error information.
 */
public class FailureUrlService {

    /** Logger instance for this class */

        return ComponentUtil.getIngestFactory();
    }

    /**
     * Processes a result data object for web/file crawling.
     * Default implementation returns the target unchanged.
     *
     * @param target the result data to process
     * @param responseData the response data from crawling
     * @return the processed result data
     */

        final StringBuilder resultBuf = new StringBuilder();

        // purge crawling sessions
        try {
            crawlingInfoService.deleteBefore(systemHelper.getCurrentTimeAsLong());
        } catch (final Exception e) {
            logger.error("Failed to purge crawling sessions.", e);
            resultBuf.append(e.getMessage()).append("\n");
        }

        // purge search logs