protected class LangAnalyzerNormalizer implements Normalizer {
        /**
         * The language used for normalization.
         */
        protected final String lang;

        /**
         * Constructs a LangAnalyzerNormalizer with the specified language.
         *
         * @param lang the language to use for normalization
         */
        protected LangAnalyzerNormalizer(final String lang) {
            this.lang = lang;

/**
 * ICUNormalizer is a class that implements the Normalizer interface and provides
 * functionality to normalize text using ICU4J's Transliterator.
 *
 * <p>This class uses a specified Transliterator to perform text normalization.
 * The Transliterator is initialized with a given ID during the construction of
 * the ICUNormalizer instance.</p>
 *
 * <p>Example usage:</p>
 * <pre>

  testImplementation(libs.junit)
  testImplementation(libs.kotlin.test.common)
  testImplementation(libs.kotlin.test.junit)
  testImplementation(libs.assertk)

  testImplementation(libs.aqute.resolve)
}

normalization {
  runtimeClasspath {
    /*
       - The below two ignored files are generated during test execution
       by the test: okhttp/src/test/java/okhttp3/osgi/OsgiTest.java

        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.lastaflute.web.ruts.multipart.MultipartFormFile;
import org.lastaflute.web.validation.Required;

/**
 * Form for uploading character mapping files to the Fess search engine.
 * Character mapping allows for normalization and transformation of characters during text analysis.
 * This form is used in the admin interface to upload custom character mapping dictionary files.
 */
public class UploadForm {

    /**

import jakarta.annotation.PostConstruct;

/**
 * Creator for character mapping dictionary files.
 * Handles the creation and management of character mapping dictionaries used for text normalization.
 */
public class CharMappingCreator extends DictionaryCreator {
    private static final Logger logger = LogManager.getLogger(CharMappingCreator.class);

    /**

/**
 * Form class for creating mapping dictionary entries.
 * Mapping dictionaries allow administrators to define synonym mappings
 * where multiple input terms can be mapped to a single output term for search normalization.
 *
 */
public class CreateForm {

    /**
     * Creates a new CreateForm instance.
     */
    public CreateForm() {
        // Default constructor
    }

    /** Dictionary identifier */

tasks.register("downloadDependencies") {
  description = "Download all dependencies to the Gradle cache"
  doLast {
    for (configuration in resolvableConfigurations) {
      configuration.files
    }
  }
}

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

## 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)

/**
 * 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 {