import java.io.Closeable;

/**
 * The {@code QueryLogReader} interface provides methods to read query logs and close the reader.
 * It extends the {@code Closeable} interface, ensuring that resources can be released when no longer needed.
 */
public interface QueryLogReader extends Closeable {
    /**
     * Reads a query log.
     * @return The query log.
     */
    QueryLog read();

    @Override
    void close();

 * It extends CrawlerSystemException and provides functionality to set and check the log level for the exception.
 *
 * <p>
 * This exception can be thrown when there are problems accessing URLs, files, or any other resources needed for crawling.
 * It includes constructors to handle messages, causes, or both.
 * </p>
 *
 * <p>

            }
        }
    }

    /**
     * Polls the next URL queue entry for the specified session.
     * This method manages local caches and fetches from OpenSearch when needed.
     *
     * @param sessionId The session ID.
     * @return The next URL queue entry, or null if none available.
     */
    @Override
    public OpenSearchUrlQueue poll(final String sessionId) {

   * Where there's a hierarchy in the types, list it via a parent
   * Highly specific magic matches get a high priority
   * General magic matches which could trigger a false-positive need
     a low one
   * The priority for containers normally need to be higher than for
     the things they contain, so they don't accidently get detected
     as what's in them
   * For logic too complex to be expressed in a magic match, do the best

     * @return true if all patterns must match, false if only one needs to match
     */
    public boolean isAllRequired() {
        return allRequired;
    }

    /**
     * Sets whether all regular expressions must match for this rule to match.
     * @param allRequired true if all patterns must match, false if only one needs to match
     */
    public void setAllRequired(final boolean allRequired) {

- PDF documents (text and metadata extraction)
- Images (JPEG, PNG, GIF, TIFF, BMP)
- Image metadata (EXIF, IPTC, XMP)

#### Archives and Compressed Files
- ZIP, TAR, GZ archives
- LHA compression format
- Nested archive extraction

#### Web and Markup
- HTML, XHTML with XPath support
- XML documents
- JSON and structured data

#### Media Files
- Audio formats (MP3, WAV, FLAC)
- Video formats (MP4, AVI, MOV)

 *
 * This class provides methods to normalize text by reading characters from a provided Reader
 * and processing them according to specific rules. The main functionality is encapsulated
 * within the nested {@link TextNormalizeContext} class.
 *
 * <p>The text normalization process includes:
 * <ul>
 *   <li>Treating ISO control characters and specified space characters as spaces.</li>

 * and manage various types of settings such as array settings, analyzer settings, bad word settings,
 * and elevate word settings.</p>
 *
 * <p>It also includes a nested TimeoutSettings class to manage various timeout configurations.</p>
 *
 * <p>Usage example:</p>
 * <pre>
 * {@code
 * Client client = ...;
 * Map<String, Object> initialSettings = ...;

        assertNotNull(queryList);
        assertEquals(2, queryList.size());
    }

    @Test
    public void testGetTermQueryListWithNestedBooleanQuery() {
        // Test with nested BooleanQuery
        BooleanQuery.Builder innerBuilder = new BooleanQuery.Builder();
        innerBuilder.add(new TermQuery(new Term("content", "inner")), BooleanClause.Occur.SHOULD);

        final String content = extractData.getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertTrue(content.contains("テスト"));
    }

    // TODO tika needs to support pdfbox 2.0
    //    public void test_getTika_pdf() {
    //        final InputStream in = ResourceUtil
    //                .getResourceAsStream("extractor/test.pdf");