import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Abstract base class for XML extractors.
 * Provides common functionality for extracting text content from XML-like documents.
 * It handles encoding detection, HTML entity unescaping, and tag-based content extraction.
 *
 */
public abstract class AbstractXmlExtractor extends AbstractExtractor {

    /**
     * Logger for this class.

* **Convertir des données** : depuis la requête vers les types requis.
* **Valider des données** : venant de chaque requête :
    * Générant automatiquement des **erreurs** renvoyées au client quand la donnée est invalide.
* **Documenter** l'API avec OpenAPI :
    * ce qui ensuite utilisé par les interfaces utilisateur automatiques de documentation interactive.

        urlFilter.init(sessionId);

        urlFilter.addInclude(".*\\.PDF$");

        // Test case sensitivity
        assertFalse(urlFilter.match("https://example.com/document.pdf"));
        assertTrue(urlFilter.match("https://example.com/document.PDF"));
    }

    /**
     * Test very long URL handling
     */
    public void test_veryLongUrl() {
        String sessionId = "test-session-020";

    /** The conditions. */
    public Map<String, String[]> as = new HashMap<>();

    /** The extra queries. */
    public String[] ex_q;

    /** The similar document hash. */
    public String sdh;

    @Override
    public String getQuery() {
        return q;
    }

    @Override
    public String[] getExtraQueries() {

class LinkRendererTest extends XmlSpecification {
    final DslDocModel model = Mock()
    final GenerationListener listener = Mock()
    final LinkRenderer renderer = new LinkRenderer(document, model, "groovyVersion", "javaVersion")

    def rendersLinkToApiClass() {
        when:
        def link = renderer.link(type('org.gradle.SomeClass'), listener)

        then:

------------------------------------------------------------------------------
Eclipse Distribution License 1.0
https://www.eclipse.org/org/documents/edl-v10.php

org.eclipse.jgit:org.eclipse.jgit

------------------------------------------------------------------------------
BSD-style

com.jcraft:jzlib
com.github.mwiede:jsch

		<property name="generatorList">
			["${path}/generate-thumbnail"]
		</property>
		<postConstruct name="addCondition">
			<arg>"mimetype"</arg>
			<arg>"application/vnd.openxmlformats-officedocument.wordprocessingml.document"</arg>
		</postConstruct>
		<postConstruct name="addCondition">
			<arg>"mimetype"</arg>
			<arg>"application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"</arg>
		</postConstruct>

        }
    }

    /**
     * {@link MetadataStaxReader.ContentTransformer}
     */
    public interface ContentTransformer {
        /**
         * Interpolate the value read from the xpp3 document
         *
         * @param source    The source value
         * @param fieldName A description of the field being interpolated. The implementation may use this to
         *                  log stuff.

 {{{./apidocs/org/apache/maven/cli/logging/Slf4jConfigurationFactory.html}Slf4jConfigurationFactory}} /
 {{{./apidocs/org/apache/maven/cli/logging/Slf4jConfiguration.html}Slf4jConfiguration}}.

~~ TODO document META-INF/maven/slf4j-configuration.properties

* Getting Logger Instance

 Starting with Maven 3.1.0, SLF4J Logger can be used directly. This technique can be used safely in Maven core

   *
   * <p>Some algorithms that operate on a {@code PredecessorsFunction} may produce undesired results
   * if the returned {@link Iterable} contains duplicate elements. Implementations of such
   * algorithms should document their behavior in the presence of duplicates.
   *
   * <p>The elements of the returned {@code Iterable} must each be:
   *
   * <ul>
   *   <li>Non-null