/**
 * 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>

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 */

/**
 * Circuit breaker pattern implementation for SMB operations.
 * Prevents cascading failures by temporarily blocking requests to a failing service.
 *
 * The circuit breaker has three states:
 * - CLOSED: Normal operation, requests pass through
 * - OPEN: Service is failing, requests are blocked
 * - HALF_OPEN: Testing if service has recovered
 */
public class SmbCircuitBreaker {

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

        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

---
name: Bug report
about: A reproducible problem
title: ''
labels: bug
assignees: ''

---

Good bug reports include a failing test! Writing a test helps you to isolate and describe the problem, and it helps us to fix it fast. Bug reports without a failing test or reproduction steps are likely to be closed.

Here’s an example test to get you started.

   * com.google.common.testing.junit3.TearDownTestCase} and {@code
   * com.google.common.testing.junit4.TearDownTestCase} for example.
   *
   * <p>A failing {@link TearDown} may or may not fail a tl4j test, depending on the version of
   * JUnit test case you are running under. To avoid failing in the face of an exception regardless
   * of JUnit version, implement a {@link SloppyTearDown} instead.
   *

import org.lastaflute.web.response.HtmlResponse;
import org.lastaflute.web.response.render.RenderData;
import org.lastaflute.web.ruts.process.ActionRuntime;

import jakarta.annotation.Resource;

/**
 * Admin action for Crawling Info management.
 *
 */
public class AdminCrawlinginfoAction extends FessAdminAction {

    /**
     * Default constructor.
     */
    public AdminCrawlinginfoAction() {
        super();
    }

            putResultDataBody(dataMap, fessConfig.getIndexFieldContent(), content);
        }
    }

    /**
     * Retrieves the crawling configuration for the given response data.
     *
     * @param responseData the response data from crawling
     * @return the crawling configuration
     */
    protected CrawlingConfig getCrawlingConfig(final ResponseData responseData) {