<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
	<modelVersion>4.0.0</modelVersion>
	<artifactId>fess-suggest</artifactId>
	<version>15.3.0-SNAPSHOT</version>
	<packaging>jar</packaging>
	<name>fess-suggest</name>
	<url>https://fess.codelibs.org/</url>

        }

        return filePath;
    }

    /**
     * Returns the character set used for content encoding.
     * @return the charset
     */
    public String getCharset() {
        return charset;
    }

    /**
     * Sets the character set used for content encoding.
     * @param charset the charset to set
     */
    public void setCharset(final String charset) {

            robotTxtFile.deleteOnExit();

            // sitemaps.xml
            buf = new StringBuilder();
            buf.append("<?xml version=\"1.0\" encoding=\"UTF-8\"?>").append('\n');
            buf.append("<urlset ").append("xmlns=\"http://www.sitemaps.org/schemas/sitemap/0.9\">").append('\n');
            buf.append("<url>").append('\n');

 * </p>
 * <p>
 * The class supports various XPath result types, including BOOLEAN, NUMBER, STRING, NODESET, and NODE.
 * It also provides options to trim whitespace from extracted values and to specify the character encoding for the output.
 * </p>
 * <p>
 * The {@link #getData(AccessResultData)} method allows retrieving the transformed data as a String (XML content),
 * a Map, or an instance of a specified class.
 * </p>
 *
 * <p>

## Configuration

### XML Configuration

Fess Crawler uses XML-based configuration with LastaFlute DI. Place configuration files in your classpath:

```xml
<!-- crawler.xml -->
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE components PUBLIC "-//DBFLUTE//DTD LastaDi 1.0//EN"
    "http://dbflute.org/meta/lastadi10.dtd">
<components namespace="fessCrawler">

                    buf.reset();
                } else {
                    buf.write(b);
                }
            }
        }));
    }

    /** The charset used for encoding and decoding. */
    protected String charset = Constants.UTF_8;

    /** Whether to resolve SIDs. */
    protected boolean resolveSids = true;

    /** The content length helper. */
    @Resource

 * The class uses {@link DOMParser} to parse HTML documents and {@link XPathAPI} to execute XPath queries.
 * It also provides methods to add custom features and properties to the {@link DOMParser}.
 * </p>
 * <p>
 * The encoding of the HTML document is automatically detected using a regular expression that matches the charset attribute in the meta tag.
 * </p>
 *
 */
public class HtmlXpathExtractor extends AbstractXmlExtractor {
    /**

    /** Property key for SMB owner attributes. */
    public static final String SMB_OWNER_ATTRIBUTES = "smbOwnerAttributes";

    /** Character set used for encoding SMB content. */
    protected String charset = Constants.UTF_8;

    /** Flag indicating whether to resolve SIDs to names. */
    protected boolean resolveSids = true;

    }

    @Test
    public void testCreateSuggestTextIdWithLongText() {
        // Test text that exceeds maximum length after encoding
        StringBuilder sb = new StringBuilder();
        for (int i = 0; i < 500; i++) {
            sb.append("0123456789");
        }
        String longText = sb.toString();

    /**
     * Private constructor to prevent instantiation.
     */
    private SuggestUtil() {
    }

    /**
     * Creates a unique identifier for the given text by encoding it to a Base64 string.
     * If the encoded string exceeds the maximum allowed length, it truncates the string
     * to the specified maximum length.
     *
     * @param text the input text to be encoded