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)

    }

    /**
     * Determines the character set for the given file.
     * Currently returns the default charset configured for this client.
     *
     * @param file The file to determine the charset for
     * @return The character set name
     */
    protected String getCharSet(final File file) {
        return charset;
    }

    /**
     * Gets the character encoding used for FTP operations.
     *

        }
        return c;
    }

    /**
     * Merges two characters, handling voiced and semi-voiced sound marks.
     * @param c1 The first character.
     * @param c2 The second character.
     * @return The merged character.
     */
    public static char mergeChar(final char c1, final char c2) {
        if (c2 == 'ﾞ') {

    }

    /**
     * Strips invalid XML characters from the input string.
     *
     * This method removes characters that are not allowed in XML documents
     * according to the XML 1.0 specification. Valid characters include:
     * - Tab (0x9)
     * - Line feed (0xA)
     * - Carriage return (0xD)
     * - Any character between 0x20 and 0xD7FF
     * - Any character between 0xE000 and 0xFFFD

 *       to extract child URLs.</li>
 *   <li><b>defaultEncoding:</b> The default character encoding to use if none is
 *       specified in the HTML content.</li>
 *   <li><b>preloadSizeForCharset:</b> The number of bytes to read from the input
 *       stream to determine the character set encoding.</li>
 *   <li><b>invalidUrlPattern:</b> A regular expression pattern used to identify
 *       invalid URLs.</li>

    }

    /**
     * Gets the character set for the given file.
     *
     * @param file the file to get the character set for
     * @return the character set
     */
    protected String getCharSet(final File file) {
        return charset;
    }

    /**
     * Gets the character encoding used for files.
     *
     * @return the character encoding
     */
    public String getCharset() {

     */
    public void setMaxDuplicatedPath(final int maxDuplicatedPath) {
        this.maxDuplicatedPath = maxDuplicatedPath;
    }

    /**
     * Gets the character set name used for encoding file paths.
     *
     * @return the character set name
     */
    public String getCharsetName() {
        return charsetName;
    }

    /**
     * Sets the charset name.

        return parse(stream, Constants.UTF_8);
    }

    /**
     * Parses a robots.txt file from the given input stream using the specified character encoding.
     * @param stream the input stream to parse
     * @param charsetName the character encoding to use
     * @return the parsed RobotsTxt object, or null if disabled
     */
    public RobotsTxt parse(final InputStream stream, final String charsetName) {

/**
 * Converts Katakana characters to their corresponding Alphabet representations.
 *
 * <p>
 * This class implements the {@link ReadingConverter} interface and provides a method to convert a given
 * Katakana string into a list of possible Alphabet readings. It uses a predefined mapping of Katakana
 * characters to their Alphabet equivalents, handling both single and double Katakana character combinations.
 * </p>
 *
 * <p>

            throw new CrawlerSystemException("The uri is empty.");
        }

        return uri;
    }

    /**
     * Returns the character set for the given SMB1 file.
     *
     * @param file the SMB1 file
     * @return the character set
     */
    protected String getCharSet(final SmbFile file) {
        return charset;
    }

    /*
     * (non-Javadoc)
     *