/**
 * Helper class for parsing and validating sitemaps.
 * It supports XML sitemaps, XML sitemap indexes, and text sitemaps,
 * and can handle GZIP compressed sitemaps.
 * The class provides methods to check if an input stream is a valid sitemap,
 * and to parse an input stream into a {@link SitemapSet} object.
 * It uses SAX parser for XML sitemaps and XML sitemap indexes,
 * and handles potential exceptions during parsing.

 * into a ResultData object, and for retrieving the binary data from an AccessResultData object.
 * It extends the AbstractTransformer class.
 *
 * <p>
 * This transformer extracts the binary content from the response body of a web resource,
 * stores it as a byte array in the ResultData, and provides a method to retrieve this data
 * as a ByteArrayInputStream.
 * </p>
 *
 * <p>

/**
 * Utility class for text normalization and processing.
 *
 * This class provides methods to normalize text by reading characters from a provided Reader
 * and processing them according to specific rules. The main functionality is encapsulated
 * within the nested {@link TextNormalizeContext} class.
 *
 * <p>The text normalization process includes:
 * <ul>
 *   <li>Treating ISO control characters and specified space characters as spaces.</li>

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

/**
 * CrawlingAccessException is an exception class that represents an issue encountered while accessing a resource during the crawling process.
 * It extends CrawlerSystemException and provides functionality to set and check the log level for the exception.
 *
 * <p>

 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.exception;

/**
 * UnsupportedExtractException is thrown when the content extraction is not supported.
 * It extends ExtractException and indicates that the requested extraction operation cannot be performed.
 *
 */

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

import java.util.HashMap;
import java.util.Map;

import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;

/**
 * Helper class for managing content length limits based on MIME types.
 * It allows setting default and MIME type-specific maximum content lengths.

/**
 * An abstract base class for implementing Extractor interfaces.
 * Provides common functionality such as access to CrawlerContainer components
 * and registration with the ExtractorFactory.
 *
 * <p>
 * This class handles the retrieval of essential crawler components like
 * {@link MimeTypeHelper} and {@link ExtractorFactory} from the
 * {@link CrawlerContainer}. It also provides a convenient method for

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

import java.util.HashMap;
import java.util.Locale;
import java.util.Map;

import org.codelibs.core.lang.StringUtil;

/**
 * EncodingHelper provides utility methods for managing and normalizing character encodings.

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

import java.io.PrintStream;
import java.io.PrintWriter;

/**
 * An exception that indicates multiple crawling access exceptions occurred.
 * This exception holds an array of Throwable objects representing the individual causes.

 * represents a valid sitemap. It uses a SitemapsHelper to validate the response body as an InputStream.
 * The rule checks if the URL matches the defined regex pattern and then validates the content as a sitemap.
 * If any exception occurs during the sitemap validation, it logs the error and returns false.
 *
 */
public class SitemapsRule extends RegexRule {
    /**
     * Serial version UID for serialization.
     */