*
     * @param responseData the response data from the crawled resource
     * @param resultData the result data to be processed
     * @return the access result containing the processed data
     */
    @Override
    protected AccessResult<?> createAccessResult(final ResponseData responseData, final ResultData resultData) {
        return super.createAccessResult(responseData, ingest(responseData, resultData));
    }

        responseData.setExecutionTime(500L);
        assertEquals(500L, responseData.getExecutionTime());
    }

    @Test
    public void test_responseData_parentUrl() {
        final ResponseData responseData = new ResponseData();

        assertNull(responseData.getParentUrl());
        responseData.setParentUrl("http://example.com/parent");

     * @param responseData The response data.
     */
    protected void checkMaxContentLength(final ResponseData responseData) {
        if (maxContentLength != null && responseData.getContentLength() > maxContentLength.longValue()) {
            throw new MaxLengthExceededException("The content length (" + responseData.getContentLength() + " byte) is over "

     *
     * @param responseData the response data containing the document to extract
     * @return the extractor instance for processing the document
     * @throws FessSystemException if no suitable extractor can be found
     */
    @Override
    protected Extractor getExtractor(final ResponseData responseData) {

     *
     * @param responseData The response data from the crawl operation.
     * @param resultData The result data from content processing.
     */
    @Override
    public void init(final ResponseData responseData, final ResultData resultData) {

        setCreateTime(System.currentTimeMillis());
        if (responseData != null) {
            BeanUtil.copyBeanToBean(responseData, this);

     * 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
     */
    public ResultData process(final ResultData target, final ResponseData responseData) {
        return target;
    }

    /**
     * Processes a document map for web/file crawling with access result.

     *
     * @param responseData the response data containing the file to extract
     * @return the extractor instance for processing the file
     * @throws FessSystemException if no suitable extractor factory can be found
     */
    @Override
    protected Extractor getExtractor(final ResponseData responseData) {

 */
package org.codelibs.fess.crawler.client;

import java.util.Map;

import org.codelibs.fess.crawler.entity.RequestData;
import org.codelibs.fess.crawler.entity.ResponseData;

/**
 * Interface representing a client for a web crawler.
 * This client is responsible for executing requests and handling responses.
 * It extends {@link AutoCloseable} to allow for resource management.
 */

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.core.lang.ThreadUtil;
import org.codelibs.fess.crawler.entity.RequestData;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.exception.MaxLengthExceededException;
import org.codelibs.fess.crawler.exception.MultipleCrawlingAccessException;

/**

Use `CrawlingParameterUtil` to set/get `CrawlerContext` and `UrlQueue` in worker threads. Always clear in finally block with `CrawlingParameterUtil.clearAll()`.

### Resource Cleanup Pattern

Always use try-with-resources for `ResponseData` - temp files are auto-deleted on close.

## Log Message Guidelines

- Format parameters as `key=value` (e.g., `sessionId={}`, `url={}`)
- Prefix with `[name]` when context identification is needed