*
         * 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.

        for (char c : validChars.toCharArray()) {
            assertTrue("Character '" + c + "' should be a valid URL character", CharUtil.isUrlChar(c));
        }
    }

    public void test_isUrlChar_boundaryChars() {
        // Test boundary characters for ranges
        assertTrue(CharUtil.isUrlChar('a')); // first lowercase

/**
 * 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

    }

    /**
     * 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

        }
        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') {

        /**
         * Compiles a robots.txt path pattern into a regular expression pattern.
         * According to RFC 9309:
         * - '*' matches any sequence of characters (including the empty sequence)
         * - '$' matches the end of the URL path
         * - All other characters are matched literally
         *
         * @param pattern the robots.txt path pattern
         * @return the compiled Pattern object
         */

        // Test all special characters
        String input = "Test & < > \"quote\" 'apos'";
        String expected = "Test &amp; &lt; &gt; &quot;quote&quot; &apos;apos&apos;";
        assertEquals(expected, XmlUtil.escapeXml(input));
    }

    public void test_escapeXml_noSpecialChars() {
        // Test string without special characters
        String input = "Simple text without special characters";

        if (chars.length >= 2 && Character.isUpperCase(chars[0]) && Character.isUpperCase(chars[1])) {
            return name;
        }
        chars[0] = Character.toLowerCase(chars[0]);
        return new String(chars);
    }

    /**
     * Capitalizes a string according to JavaBeans conventions.
     * Note: If the first two characters are uppercase, the string will not be capitalized.
     * <p>

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)

            assertTrue("Error message should contain 'text content'", message.contains("text content"));
        }
    }

    /**
     * Test extraction with special characters and control characters.
     */
    public void test_getText_withSpecialCharacters_handlesCorrectly() {
        final String specialContent = "Tab\there\nNewline\rCarriage return\0Null byte";