**Fess Crawler** is a Java-based web crawling framework for enterprise content extraction.

### Essential Info

- **Language**: Java 21+
- **Build**: Maven 3.x
- **License**: Apache 2.0
- **DI**: LastaFlute DI
- **Repo**: https://github.com/codelibs/fess-crawler

### Tech Stack

- **HTTP**: Apache HttpComponents 4.5+ and 5.x (switchable)
- **Extraction**: Apache Tika, POI, PDFBox

        }
        return new URL(currentUrl);
    }

    /**
     * Gets child URL extraction rules from configuration.
     *
     * @param responseData the response data from crawling
     * @param resultData the result data
     * @return stream of tag-attribute pairs for URL extraction
     */
    @Override

    private static final Pattern ALLOWED_WRAPPER_VERSION =
        Pattern.compile("^[0-9.]+(-(rc|milestone|m)-[0-9]+)?$");

    // Keep the same extraction semantics as the old sed:
    //   sed 's/.*gradle-\(.*\)-[a-z]*\.[a-z]*/\1/'
    private static final Pattern WRAPPER_VERSION_EXTRACT =
        Pattern.compile(".*gradle-(.*)-[a-z]*\\.[a-z]*");

import org.junit.jupiter.api.Test;
import org.junit.jupiter.api.TestInfo;

/**
 * Unit tests for {@link AbstractFessFileTransformer}.
 * Tests file transformation logic including content extraction and metadata handling.
 */
public class AbstractFessFileTransformerTest extends UnitFessTestCase {

    private TestableAbstractFessFileTransformer transformer;

    @Override

/**
 * Helper class for document processing and manipulation in the Fess search system.
 * This class provides utilities for processing document content, titles, and digests,
 * handling text normalization, content extraction, and similar document hash encoding/decoding.
 * It also manages document processing requests and integrates with the crawler system.
 *
 */
public class DocumentHelper {

 *
 * Supported on Android 5.0+.
 *
 * Supported on OpenJDK 8 via the JettyALPN-boot library or Conscrypt.
 *
 * Supported on OpenJDK 9+ via SSLParameters and SSLSocket features.
 *
 * ### Trust Manager Extraction
 *
 * Supported on Android 2.3+ and OpenJDK 7+. There are no public APIs to recover the trust
 * manager that was used to create an [SSLSocketFactory].
 *
 * Not supported by choice on JDK9+ due to access checks.
 *

 */
package org.codelibs.fess.suggest.util;

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

/**
 * Utility class for type-safe value extraction from Map objects.
 * Centralizes map access patterns to reduce code duplication and improve type safety.
 *
 * <p>This class provides methods to safely extract typed values from Map&lt;String, Object&gt;

 *
 * <ul>
 *   <li>chaining methods which return a new {@code FluentIterable} based in some way on the
 *       contents of the current one (for example {@link #transform})
 *   <li>element extraction methods which facilitate the retrieval of certain elements (for example
 *       {@link #last})
 *   <li>query methods which answer questions about the {@code FluentIterable}'s contents (for
 *       example {@link #anyMatch})

 *
 * <ul>
 *   <li>chaining methods which return a new {@code FluentIterable} based in some way on the
 *       contents of the current one (for example {@link #transform})
 *   <li>element extraction methods which facilitate the retrieval of certain elements (for example
 *       {@link #last})
 *   <li>query methods which answer questions about the {@code FluentIterable}'s contents (for
 *       example {@link #anyMatch})

            }
            return extractJsonStringFallback(json, key);
        }
        return "";
    }

    /**
     * Fallback regex-based extraction for string values.
     *
     * @param json the JSON response
     * @param key the key to extract
     * @return the extracted string value
     */