}

    /**
     * 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

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)

         *
         * This method reads characters from the reader and processes them according to the following rules:
         * - ISO control characters and space characters are treated as spaces.
         * - Alphanumeric characters (0-9, A-Z, a-z) are appended to the buffer.
         * - Symbol characters (!-/, :-@, [-`, {-~) are appended to the buffer.

        assertNotNull(urlFilter);
    }

    /**
     * Test special characters in URL patterns
     */
    public void test_specialCharactersInPatterns() {
        String sessionId = "test-session-018";
        urlFilter.init(sessionId);

        // Test patterns with special regex characters
        urlFilter.addInclude("https://example\\.com/\\?.*");
        urlFilter.addInclude(".*\\$price=\\d+.*");

    }

    /**
     * Test name with special characters
     */
    public void test_name_specialCharacters() {
        // Test with spaces
        testTransformer.setName("name with spaces");
        assertEquals("name with spaces", testTransformer.getName());

        // Test with special characters
        testTransformer.setName("name-with_special.chars#123");

    protected int initialBufferSize = 10000;

    /**
     * If true, duplicated terms are replaced.
     */
    protected boolean replaceDuplication = false;

    /**
     * Space characters. Default includes common space characters.
     */
    protected int[] spaceChars = { '\u0020', '\u00a0', '\u3000', '\ufffd' };

    /**
     * Memory size.
     */
    protected int memorySize = 1024 * 1024; //1mb

                    || PRIORITY_ELEMENT.equals(qName)) {
                buf = new StringBuilder();
            }
        }

        @Override
        public void characters(final char[] ch, final int offset, final int length) {
            if (buf != null) {
                buf.append(new String(ch, offset, length));
            }
        }

        @Override

        assertFalse(auth.matches("ftp://hostname:22/path/to/resource.txt"));
        assertFalse(auth.matches("ftp://otherhost/path/to/resource.txt"));

        // Test with special characters in path
        assertTrue(auth.matches("ftp://hostname:21/path%20with%20spaces/resource.txt"));
        assertTrue(auth.matches("ftp://hostname/path%20with%20spaces/resource.txt"));

        // Test with empty path

     */
    protected Map<String, String> fieldRuleMap = new LinkedHashMap<>();

    /** Flag to enable or disable trimming of whitespace characters. */
    protected boolean trimSpaceEnabled = true;

    /**
     * The charset name for the output.
     */
    protected String charsetName = Constants.UTF_8;

    /**

 *
 * <p>
 * This class provides methods to:
 * </p>
 * <ul>
 *   <li>Detect the MIME type based on the input stream and filename.</li>
 *   <li>Normalize the filename to handle special characters.</li>
 *   <li>Configure whether to use the filename for MIME type detection.</li>
 *   <li>Configure whether to use the filename for MIME type detection when the stream is octet-stream.</li>
 * </ul>
 *
 * <p>