Guillaume Nodet <******@****.***> 1725988727 +0200

	match     func(*DB) bool
	handler   func(*DB)
	processor *processor
}

func (cs *callbacks) Create() *processor {
	return cs.processors["create"]
}

func (cs *callbacks) Query() *processor {
	return cs.processors["query"]
}

func (cs *callbacks) Update() *processor {
	return cs.processors["update"]
}

func (cs *callbacks) Delete() *processor {
	return cs.processors["delete"]
}

import jakarta.annotation.PostConstruct;

/**
 * Response processor implementation for the Fess search engine.
 * This processor extends DefaultResponseProcessor to provide additional
 * processing capabilities through the ingest framework, allowing for
 * custom data transformation and enrichment during the crawling process.
 *
 * <p>It supports pluggable ingesters that can modify the result data

        }

        ModelObjectProcessor processor = ProcessorHolder.CACHED_PROCESSOR.get();
        if (processor == null) {
            processor = loadProcessor();
            ProcessorHolder.CACHED_PROCESSOR.compareAndSet(null, processor);
            processor = ProcessorHolder.CACHED_PROCESSOR.get();
        }
        return processor.process(object);
    }

    /**

     * @param query the Lucene query to be processed
     * @param boost the boost factor to apply to the query
     * @return the processed OpenSearch QueryBuilder
     */
    public QueryBuilder execute(final QueryContext context, final Query query, final float boost) {
        return filterChain.execute(context, query, boost);
    }

    /**
     * Adds a query command to the processor.
     *

	<component name="sitemapsRule" class="org.codelibs.fess.crawler.rule.impl.RegexRule" >
		<property name="ruleId">"sitemapsRule"</property>
		<property name="responseProcessor">
			<component class="org.codelibs.fess.crawler.processor.impl.SitemapsResponseProcessor">
			</component>
		</property>
		<postConstruct name="addRule">
			<arg>"url"</arg>
			<arg>"http[s]?:.*sitemap[^/]*\.xml.*|http[s]?:.*sitemap[^/]*\.gz.*|http[s]?:.*sitemap[^/]*\.txt.*"</arg>

        responseData3.setUrl("https://example.com/page3");

        // Execute multiple times - should not throw any exception
        processor.process(responseData1);
        processor.process(responseData2);
        processor.process(responseData3);

        // Verify all ResponseData objects are unchanged
        assertEquals("https://example.com/page1", responseData1.getUrl());

        processor.setNotModifiedHttpCodes(new int[] { 304 });

        ResponseData responseData = new ResponseData();
        responseData.setHttpStatusCode(200);
        assertTrue(processor.isSuccessful(responseData));

        responseData.setHttpStatusCode(100);
        assertFalse(processor.isSuccessful(responseData));
        responseData.setHttpStatusCode(304);
        assertFalse(processor.isSuccessful(responseData));

    }

    @Override
    public ResponseProcessor getResponseProcessor() {
        return responseProcessor;
    }

    /**
     * Sets the response processor for this rule.
     *
     * @param responseProcessor the response processor to set
     */
    public void setResponseProcessor(final ResponseProcessor responseProcessor) {
        this.responseProcessor = responseProcessor;
    }

import org.codelibs.fess.crawler.exception.ChildUrlsException;
import org.codelibs.fess.crawler.helper.SitemapsHelper;
import org.codelibs.fess.crawler.processor.ResponseProcessor;

import jakarta.annotation.Resource;

/**
 * A response processor implementation that handles sitemaps.
 * It parses the response body as a SitemapSet, extracts URLs from the sitemaps,
 * and adds them as child URLs to be crawled.
 *
 * <p>