*/
public interface AccessResultCallback<RESULT extends AccessResult<?>> {
    /**
     * Processes the given access result.
     *
     * @param accessResult the result of the access operation to be processed
     */
    /**
     * Processes the given access result.
     *
     * @param accessResult the result of the access operation to be processed
     */
    void iterate(RESULT accessResult);

     */
    public SitemapsResponseProcessor() {
        super();
    }

    /**
     * Processes the given response data, extracting URLs from sitemaps.
     * @param responseData The response data.
     */
    @Override
    public void process(final ResponseData responseData) {
        final SitemapsHelper sitemapsHelper = crawlerContainer.getComponent("sitemapsHelper");

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

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

/**
 * The ResponseProcessor interface defines a contract for processing response data.
 * Implementations of this interface are responsible for handling the response data
 * obtained during a crawling process.
 */
public interface ResponseProcessor {

    /**
     * Processes the given response data.
     *

```

### Monitoring

```java
// Monitor crawling progress
while (crawler.crawlerContext.getStatus() == CrawlerStatus.RUNNING) {
    int processed = dataService.getCount(sessionId);
    System.out.println("Processed: " + processed + " URLs");
    Thread.sleep(5000);
}
```

## Contributing

We welcome contributions to Fess Crawler! Please follow these guidelines:

    /**
     * Current status of the crawler.
     */
    protected volatile CrawlerStatus status = CrawlerStatus.INITIALIZING;

    /**
     * Filter for URLs to control which URLs are processed.
     */
    protected UrlFilter urlFilter;

    /**
     * Manager for crawling rules and configurations.
     */
    protected RuleManager ruleManager;

    /**

        this.extractorMap = extractorMap;
    }

    /**
     * Creates a new ExtractorBuilder instance.
     *
     * @param in      The input stream to be processed by the extractor.
     * @param params  The parameters to be used by the extractor.
     * @return A new ExtractorBuilder instance.
     */

 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.entity;

/**
 * The UrlQueue interface represents a queue of URLs to be processed by a web crawler.
 * It provides methods to get and set various properties of a URL queue entry.
 *
 * @param <IDTYPE> the type of the identifier for the URL queue entry
 */
public interface UrlQueue<IDTYPE> {

     * - Any character between 0x20 and 0xD7FF
     * - Any character between 0xE000 and 0xFFFD
     * - Any character between 0x10000 and 0x10FFFF
     *
     * @param in the input string to be processed
     * @return a new string with invalid XML characters removed, or the original
     *         string if it is empty
     */
    public static String stripInvalidXMLCharacters(final String in) {

	maxTokenSize int       // Maximum size of a token; modified by tests.
	token        []byte    // Last token returned by split.
	buf          []byte    // Buffer used as argument to split.
	start        int       // First non-processed byte in buf.
	end          int       // End of data in buf.
	err          error     // Sticky error.
	empties      int       // Count of successive empty tokens.
	scanCalled   bool      // Scan has been called; buffer is in use.

         * - The maximum size of alphanumeric and symbol terms can be limited by `maxAlphanumTermSize` and `maxSymbolTermSize` respectively.
         *
         * @return A processed string with terms and spaces, or an empty string if the reader is null or an IOException occurs.
         */
        public String execute() {
            if (reader == null) {
                return StringUtil.EMPTY;