package org.codelibs.fess.crawler.util;

/**
 * Utility class for character-related operations.
 */
public final class CharUtil {
    /**
     * Private constructor to prevent instantiation of this utility class.
     */
    private CharUtil() {
    }

    /**
     * Checks if the given character is a valid URL character.
     *
     * Valid URL characters include:
     * - Lowercase letters (a-z)

   * is guaranteed to be in the range {@code 0 <= cp <= Character#MAX_CODE_POINT}.
   *
   * <p>If an empty array is returned, this effectively strips the input character from the
   * resulting text.
   *
   * <p>If the character does not need to be escaped, this method should return {@code null}, rather
   * than an array containing the character representation of the code point. This enables the

  /**
   * Substitute: A character that may be substituted for a character which is determined to be
   * invalid or in error.
   *
   * @since 8.0
   */
  public static final byte SUB = 26;

  /**
   * Escape: A control character intended to provide code extension (supplementary characters) in
   * general information interchange. The Escape character itself is a prefix affecting the

/**
 * 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 {

    /**
     * The dictionary ID that identifies which character mapping dictionary configuration to update.

/**
 * Represents a single character mapping rule that defines how input characters are mapped to output characters
 * for text analysis and search processing. This class is used in character mapping dictionaries to transform
 * text during indexing and search operations.
 *
 * <p>Each mapping item consists of one or more input character sequences that are mapped to a single output

  /**
   * Asserts that an escaper does not escape the given character.
   *
   * @param escaper the non-null escaper to test
   * @param c the character to test
   */
  public static void assertUnescaped(CharEscaper escaper, char c) {
    Assert.assertNull(computeReplacement(escaper, c));
  }

  /**
   * Asserts that a Unicode escaper does not escape the given character.
   *
   * @param escaper the non-null escaper to test

  /**
   * Asserts that an escaper does not escape the given character.
   *
   * @param escaper the non-null escaper to test
   * @param c the character to test
   */
  public static void assertUnescaped(CharEscaper escaper, char c) {
    Assert.assertNull(computeReplacement(escaper, c));
  }

  /**
   * Asserts that a Unicode escaper does not escape the given character.
   *
   * @param escaper the non-null escaper to test

 *
 * <ul>
 *   <li>All specified safe characters remain unchanged.
 *   <li>If {@code plusForSpace} was specified, the space character " " is converted into a plus
 *       sign {@code "+"}.
 *   <li>All other characters are converted into one or more bytes using UTF-8 encoding and each
 *       byte is then represented by the 3-character string "%XX", where "XX" is the two-digit,

        }
    }

    /**
     * Sets a character as a word character.
     *
     * @param ctype2
     *            The array of character types.
     * @param val
     *            The character code.
     */
    protected static void wordChar(final byte[] ctype2, final int val) {
        ctype2[val] |= CT_ALPHA;
    }

    /**
     * Sets characters as whitespace.
     *
     * @param ctype2

   *
   * @param replacementMap a map of characters to their escaped representations
   * @param safeMin the lowest character value in the safe range
   * @param safeMax the highest character value in the safe range
   * @param unsafeReplacement the default replacement for unsafe characters or null if no default
   *     replacement is required
   */
  protected ArrayBasedUnicodeEscaper(
      Map<Character, String> replacementMap,
      int safeMin,