*
 * This class provides methods to escape special characters in XML strings,
 * strip invalid XML characters, and parse XML content into a map of data.
 *
 * <p>
 * The class is final and cannot be instantiated.
 * </p>
 *
 * <h2>Methods:</h2>
 * <ul>
 *   <li>{@link #escapeXml(String)}: Escapes special characters in an XML string.</li>

 * half-width Katakana characters (Hankaku Kana) to full-width Katakana characters (Zenkaku Kana).
 * It also handles the conversion of voiced and semi-voiced sound marks.
 *
 * <p>This class provides the following functionalities:</p>
 * <ul>
 *   <li>Normalization of a string containing Hankaku Kana to Zenkaku Kana.</li>
 *   <li>Conversion of individual Hankaku Kana characters to Zenkaku Kana characters.</li>

	file *os.File // If non-nil, file descriptor to close.
}

func NewTokenizer(name string, r io.Reader, file *os.File) *Tokenizer {
	var s scanner.Scanner
	s.Init(r)
	// Newline is like a semicolon; other space characters are fine.
	s.Whitespace = 1<<'\t' | 1<<'\r' | 1<<' '
	// Don't skip comments: we need to count newlines.
	s.Mode = scanner.ScanChars |
		scanner.ScanFloats |
		scanner.ScanIdents |
		scanner.ScanInts |

import com.ibm.icu.text.Transliterator;

/**
 * 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

         *
         * 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.

     */
    private CharUtil() {
    }

    /**
     * Checks if the given character is a valid URL character.
     *
     * Valid URL characters include:
     * - Lowercase letters (a-z)
     * - Uppercase letters (A-Z)
     * - Digits (0-9)
     * - Special characters: . - * _ : / + % = & ? # [ ] @ ~ ! $ ' ( ) , ;
     *
     * @param c the character to check

    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

        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+.*");

 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.suggest.normalizer;

/**
 * Normalizes full-width alphanumeric characters to half-width alphanumeric characters.
 */
public class FullWidthToHalfWidthAlphabetNormalizer implements Normalizer {
    /**
     * Constructs a new {@link FullWidthToHalfWidthAlphabetNormalizer}.
     */

    "This change modifies Go to ___________"
  + Lowercase verb after the colon
  + No trailing period
  + Keep the title as short as possible. ideally under 76 characters or shorter
+ No Markdown
+ The first PR comment (this one) is wrapped at 76 characters, unless it's
  really needed (ASCII art, table, or long link)
+ If there is a corresponding issue, add either `Fixes #1234` or `Updates #1234`