PathValidator noUncValidator = new PathValidator(260, 255, false, false);
        // Due to normalization bug, UNC paths are not properly detected
        // The normalization removes all duplicate backslashes, so \\\\server becomes \server
        // This test validates that paths which should be UNC but aren't detected due to normalization
        // still pass validation (which is the current behavior, though not ideal)

import org.codelibs.core.lang.StringUtil;

/**
 * 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>

/**
 * 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 {

## Technology Stack

- **Java**: 21+ (configured via parent POM)
- **OpenSearch**: Latest (provided scope)
- **Apache Lucene**: Query parsing and text analysis
- **ICU4J**: Unicode text processing and normalization
- **JUnit 4**: Testing framework
- **Maven**: Build and dependency management

## Quick Start

### Prerequisites

- Java 21 or higher
- OpenSearch/Elasticsearch cluster (2.x+ recommended)

    void testInvalidPathCharacters(String path) {
        assertThrows(IllegalArgumentException.class, () -> InputValidator.validateSmbPath(path));
    }

    @Test
    @DisplayName("Test path normalization")
    void testPathNormalization() {
        assertEquals("\\server\\share\\file.txt", InputValidator.normalizeSmbPath("/server/share/file.txt"));

 *       the configured analyzers.</li>
 * </ul>
 *
 * <p>Protected static class:</p>
 * <ul>
 *   <li>FieldAnalyzerMapping: Holds the analyzer names for different types of analysis (reading, reading term,
 *       normalization, contents, and contents reading) for a specific field.</li>
 * </ul>
 *
 * @see SuggestAnalyzer
 * @see FieldAnalyzerMapping
 */
public class AnalyzerSettings {
    /** Analyzer name for reading. */

            assertNotNull(languages);
            if (languages.length > 0) {
                // Note: The actual order might be different due to normalization
                boolean hasEn = false, hasJa = false;
                for (String lang : languages) {
                    if ("en".equals(lang))
                        hasEn = true;

    doLast {
      for (configuration in configurations) {
        if (configuration.isCanBeResolved) {
          configuration.files
        }
      }
    }
  }

  normalization {
    runtimeClasspath {
      metaInf {
        ignoreAttribute("Bnd-LastModified")
      }
    }
  }
}

val platform = System.getProperty("okhttp.platform", "jdk9")

import jcifs.smb.SmbException;

/**
 * Path validation utility to prevent directory traversal and other path-based attacks.
 *
 * Features:
 * - Directory traversal prevention
 * - Path normalization
 * - Blacklist/whitelist support
 * - UNC path validation
 * - Special character filtering
 * - Length validation
 */
public class PathValidator {

        urlFilter.addExclude("https://example.com/.*");

        // Exclude should take precedence
        assertFalse(urlFilter.match("https://example.com/page"));
    }

    /**
     * Test URL normalization scenarios
     */
    public void test_urlNormalization() {
        String sessionId = "test-session-026";
        urlFilter.init(sessionId);

        urlFilter.addInclude("https://example.com/path/.*");