* Returns the index of the first matching BMP character in a character sequence, or {@code -1} if
   * no matching character is present.
   *
   * <p>The default implementation iterates over the sequence in forward order calling {@link
   * #matches} for each character.
   *
   * @param sequence the character sequence to examine from the beginning
   * @return an index, or {@code -1} if no character matches
   */

 *
 * Percent encoding replaces a character (like `\ud83c\udf69`) with its UTF-8 hex bytes (like
 * `%F0%9F%8D%A9`). This approach works for whitespace characters, control characters, non-ASCII
 * characters, and characters that already have another meaning in a particular context.
 *
 * Percent encoding is used in every URL component except for the hostname. But the set of

     */
    public void setEncodeUrlLink(final boolean encodeUrlLink) {
        this.encodeUrlLink = encodeUrlLink;
    }

    /**
     * Sets the character encoding for URL links.
     *
     * @param urlLinkEncoding the character encoding to use
     */
    public void setUrlLinkEncoding(final String urlLinkEncoding) {
        this.urlLinkEncoding = urlLinkEncoding;
    }

    /**

    // Host names are special:
    //
    //  * Several characters are forbidden and must throw exceptions if used.
    //  * They don't use percent escaping at all.
    //  * They use punycode for internationalization.
    //  * URI is much more strict than HttpUrl or URL on what's accepted.
    //
    // HttpUrl is quite lenient with what characters it accepts. In particular, characters like '{'

		HTTPStatusCode: http.StatusBadRequest,
	},
	ErrLexerInvalidChar: {
		Code:           "LexerInvalidChar",
		Description:    "The SQL expression contains an invalid character.",
		HTTPStatusCode: http.StatusBadRequest,
	},
	ErrLexerInvalidOperator: {
		Code:           "LexerInvalidOperator",
		Description:    "The SQL expression contains an invalid literal.",

   * encounter order of the streams of values.
   *
   * <p>Example:
   *
   * {@snippet :
   * static final ListMultimap<Character, Character> FIRST_LETTER_MULTIMAP =
   *     Stream.of("banana", "apple", "carrot", "asparagus", "cherry")
   *         .collect(
   *             flatteningToMultimap(
   *                  str -> str.charAt(0),

   * encounter order of the streams of values.
   *
   * <p>Example:
   *
   * {@snippet :
   * static final ListMultimap<Character, Character> FIRST_LETTER_MULTIMAP =
   *     Stream.of("banana", "apple", "carrot", "asparagus", "cherry")
   *         .collect(
   *             flatteningToMultimap(
   *                  str -> str.charAt(0),

	// Invalid runes, including negative ones, should be written as the
	// replacement character.
	for _, r := range []rune{-1, utf8.MaxRune + 1} {
		var buf strings.Builder
		w := NewWriter(&buf)
		w.WriteRune(r)
		w.Flush()
		if s := buf.String(); s != "\uFFFD" {
			t.Errorf("WriteRune(%d) wrote %q, not replacement character", r, s)
		}
	}
}

func TestReadStringAllocs(t *testing.T) {
	if asan.Enabled {

        String[] spaces = (String[]) propMap.get(CRAWLER_DOCUMENT_SPACES);
        if (spaces == null) {
            spaces = Arrays.stream(getCrawlerDocumentSpaceCharsAsArray()).mapToObj(Character::toString).toArray(n -> new String[n]);
            propMap.put(CRAWLER_DOCUMENT_SPACES, spaces);
        }
        return spaces;
    }

     *
     * @param urlList the list to add URLs to
     * @param url the base URL for resolving relative URLs
     * @param attrValue the attribute value containing the URL
     * @param encoding the character encoding
     */
    @Override
    protected void addChildUrlFromTagAttribute(final List<String> urlList, final URL url, final String attrValue, final String encoding) {
        final String urlValue = attrValue.trim();