*   <li>Treating ISO control characters and specified space characters as spaces.</li>
 *   <li>Appending alphanumeric characters (0-9, A-Z, a-z) to the buffer.</li>
 *   <li>Appending symbol characters (!-/, :-@, [-`, {-~) to the buffer.</li>
 *   <li>Optionally removing duplicate terms based on a flag.</li>
 *   <li>Limiting the maximum size of alphanumeric and symbol terms.</li>
 * </ul>
 *

 * 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}.
     */

    assertThrows(NullPointerException.class, () -> new PercentEscaper(null, false));
  }

  /**
   * Tests that specifying any alphanumeric characters as 'safe' causes an {@link
   * IllegalArgumentException}.
   */
  public void testBadArguments_badchars() {
    String msg = "Alphanumeric characters are always 'safe' and should not be explicitly specified";
    IllegalArgumentException expected =

    public Integer crudMode;

    /**
     * The name of the label type.
     */
    @Required
    @Size(max = 100)
    public String name;

    /**
     * The value of the label type (alphanumeric and underscore only).
     */
    @Required
    @Size(max = 100)
    @Pattern(regexp = "^[a-zA-Z0-9_]+$")
    public String value;

    /**
     * The paths to include for this label type.
     */

    assertThrows(NullPointerException.class, () -> new PercentEscaper(null, false));
  }

  /**
   * Tests that specifying any alphanumeric characters as 'safe' causes an {@link
   * IllegalArgumentException}.
   */
  public void testBadArguments_badchars() {
    String msg = "Alphanumeric characters are always 'safe' and should not be explicitly specified";
    IllegalArgumentException expected =

        } catch (final IOException e) {
            return StringUtil.EMPTY; // empty
        }
    }

    /**
     * Gets the maximum size for alphanumeric terms from configuration.
     *
     * @return the maximum alphanumeric term size
     */
    protected int getMaxAlphanumTermSize() {
        final FessConfig fessConfig = ComponentUtil.getFessConfig();

 *   <li>Output encoding</li>
 *   <li>Maximum compression ratio and uncompression size</li>
 *   <li>Initial buffer size</li>
 *   <li>Memory size for temporary file storage</li>
 *   <li>Maximum term sizes for alphanumeric and symbolic terms</li>
 *   <li>Custom Tika configuration</li>
 *   <li>Tesseract OCR configuration for image-based documents</li>
 *   <li>PDF Parser configuration for PDF documents</li>
 * </ul>
 *
 * <p>

crawler.document.use.site.encoding.on.english=false
# Whether to append data to documents.
crawler.document.append.data=true
# Whether to append filename to documents.
crawler.document.append.filename=false
# Maximum size of alphanumeric terms in documents.
crawler.document.max.alphanum.term.size=20
# Maximum size of symbol terms in documents.
crawler.document.max.symbol.term.size=10
# Whether to remove duplicate terms in documents.

    boolean isCrawlerDocumentAppendFilename();

    /**
     * Get the value for the key 'crawler.document.max.alphanum.term.size'. <br>
     * The value is, e.g. 20 <br>
     * comment: Maximum size of alphanumeric terms in documents.
     * @return The value of found property. (NotNull: if not found, exception but basically no way)
     */
    String getCrawlerDocumentMaxAlphanumTermSize();

    /**

	}
	return b
}

// isSeparator reports whether the rune could mark a word boundary.
// TODO: update when package unicode captures more of the properties.
func isSeparator(r rune) bool {
	// ASCII alphanumerics and underscore are not separators
	if r <= 0x7F {
		switch {
		case '0' <= r && r <= '9':
			return false
		case 'a' <= r && r <= 'z':
			return false
		case 'A' <= r && r <= 'Z':
			return false