- RTF, WordPerfect

#### PDFs and Images
- PDF documents (text and metadata extraction)
- Images (JPEG, PNG, GIF, TIFF, BMP)
- Image metadata (EXIF, IPTC, XMP)

#### Archives and Compressed Files
- ZIP, TAR, GZ archives
- LHA compression format
- Nested archive extraction

#### Web and Markup
- HTML, XHTML with XPath support
- XML documents
- JSON and structured data

#### Media Files

     *        permitted, and indicates that the cause is nonexistent or
     *        unknown.)
     */
    public CrawlerSystemException(final Throwable cause) {
        super(cause);
    }

    /**
     * Constructs a new CrawlerSystemException with the specified detail message and controls suppression and stack trace writing.
     *
     * @param message the detail message

 * Provides common functionality and properties for crawler rules.
 *
 * <p>
 * This class handles the registration of rules with the {@link RuleManager}
 * and provides getter and setter methods for common properties such as
 * {@code ruleId} and {@code responseProcessor}.
 * </p>
 *
 * <p>
 * Subclasses should extend this class and implement the abstract methods

/**
 * A factory for creating and managing pooled crawler objects.
 * This class extends {@link BasePooledObjectFactory} and provides
 * methods for creating, wrapping, and destroying crawler components
 * obtained from a {@link CrawlerContainer}.
 *
 * @param <T> the type of the pooled object
 */
public class CrawlerPooledObjectFactory<T> extends BasePooledObjectFactory<T> {
    /**
     * Constructs a new CrawlerPooledObjectFactory.

     * - Tab (0x9)
     * - Line feed (0xA)
     * - Carriage return (0xD)
     * - 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

        fileInputStream.mark(readlimit);
    }

    /**
     * Tests if this input stream supports the mark and reset methods.
     * This method delegates to {@link FileInputStream#markSupported()}.
     *
     * @return {@code true} if this stream type supports the mark and reset method; {@code false} otherwise
     */
    @Override
    public boolean markSupported() {

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

import org.codelibs.core.lang.StringUtil;

/**
 * Represents a Sitemap file entry, conforming to the Sitemap XML format.
 * This class holds information about a single Sitemap, including its location and last modification timestamp.
 * It implements the {@link Sitemap} interface.
 *

 * </p>
 * <ul>
 *   <li>Starting and finishing threads</li>
 *   <li>Starting and cleaning up crawling</li>
 *   <li>Handling unsupported URLs</li>
 *   <li>Checking last modified dates</li>
 *   <li>Getting content</li>
 *   <li>Handling redirects</li>
 *   <li>Processing responses</li>
 *   <li>Handling exceptions during crawling and child URL processing</li>

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

import java.util.ArrayList;
import java.util.List;

/**
 * Holds a list of FtpAuthentication objects and provides methods to add and retrieve them based on a given path.

 * on SMB (Server Message Block) shares using the SMB1 protocol. It extends {@link AbstractCrawlerClient} and utilizes the JCIFS library
 * to interact with SMB resources.
 *
 * <p>
 * This client supports authentication, content retrieval, and metadata extraction from SMB files.
 * It handles file access, directory listing, and access control entries (ACEs) processing.
 * </p>
 *