## Overview

**Fess Crawler** is a powerful, flexible Java-based web crawling framework designed for enterprise-scale content extraction and processing. Built with a modular architecture, it supports multiple protocols (HTTP/HTTPS, File System, FTP, SMB, Cloud Storage) and provides extensive content extraction capabilities from various document formats.

### Key Features

/**
 * Tests Artifact extraction, computation, and parent resolution functionality.
 */
@DisplayName("GAVUtils")
class GAVUtilsTest {

    @BeforeEach
    void setUp() {}

    private UpgradeContext createMockContext() {
        return TestUtils.createMockContext();
    }

    @Nested
    @DisplayName("Artifact Extraction")
    class GAVExtractionTests {

        @Test

    /**
     * Get the extracted data.
     * @param extractor The extractor.
     * @param in The input stream.
     * @param params The parameters.
     * @return The extracted data.
     */
    protected ExtractData getExtractData(final Extractor extractor, final InputStream in, final Map<String, String> params) {
        try {
            return extractor.getText(in, params);
        } catch (final RuntimeException e) {

import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;
import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.extractor.impl.TikaExtractor;
import org.codelibs.fess.crawler.processor.ResponseProcessor;
import org.codelibs.fess.crawler.processor.impl.DefaultResponseProcessor;
import org.codelibs.fess.crawler.rule.Rule;

import org.codelibs.fess.mylasta.direction.FessConfig;
import org.codelibs.fess.util.ComponentUtil;

/**
 * Interface for transforming and processing crawled documents in Fess.
 * Provides utility methods for URL processing, site extraction, data mapping,
 * and field configuration handling during the document transformation process.
 */
public interface FessTransformer {

    /**
     * Synchronized LRU cache for storing parent URL encodings.

import org.junit.jupiter.api.BeforeEach;
import org.junit.jupiter.api.DisplayName;
import org.junit.jupiter.api.Test;

import jcifs.smb.SID;

/**
 * Unit tests for PacLogonInfo class.
 * Tests the parsing and data extraction from PAC Logon Info structures.
 */
class PacLogonInfoTest {

    private static final long TEST_FILETIME = 130640000000000000L;
    private static final String TEST_USERNAME = "testuser";

 */
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;

        return id;
    }

    /**
     * Parses the given query string and returns an array of keywords.
     *
     * @param q the query string to be parsed
     * @param field the field to be used for keyword extraction
     * @return an array of keywords extracted from the query string, or an empty array if the number of keywords exceeds the maximum allowed or if any keyword exceeds the maximum length
     */

 *
 * <p>Key features include:</p>
 * <ul>
 * <li>Incremental crawling support with last-modified timestamp checking</li>
 * <li>Document expiration handling</li>
 * <li>Child URL extraction and queueing</li>
 * <li>Integration with Fess configuration and permission systems</li>
 * <li>Client selection based on URL patterns</li>
 * </ul>
 *
 * @see CrawlerThread

    }

    /**
     * Key object for statistics tracking that contains an identifier and optional URL.
     * Used when tracking statistics for objects that don't have built-in URL extraction.
     */
    public static class StatsKeyObject {

        /** Unique identifier for this statistics key object. */
        private final String id;