* <li>{@link #langFieldName} - Language field name.
 * <li>{@link #badWords} - List of bad words.
 * <li>{@link #parallel} - Flag for parallel processing.
 * <li>{@link #readingConverter} - Reading converter.
 * <li>{@link #contentsReadingConverter} - Contents reading converter.
 * <li>{@link #normalizer} - Normalizer.
 * <li>{@link #analyzer} - Suggest analyzer.
 * <li>{@link #contentsParser} - Contents parser.

     *
     * @return a SuggestItem representing this ElevateWord
     */
    public SuggestItem toSuggestItem() {
        final String[][] readingArray =
                this.getReadings().stream().map(reading -> new String[] { reading }).toArray(count -> new String[count][]);
        return new SuggestItem(new String[] { this.getElevateWord() }, readingArray, fields.toArray(new String[fields.size()]), 1, 0,

     */
    protected File baseDir;

    /**
     * Creates a file with the specified path, handling directory creation and duplicate names.
     *
     * @param path the file path to create
     * @return the created file
     * @throws CrawlerSystemException if directory creation fails
     */
    protected File createFile(final String path) {
        final String[] paths = path.split("/");

    private final File tempFile;

    private final FileInputStream fileInputStream;

    /**
     * A class that provides an input stream for reading from a temporary file.
     * This class wraps a {@link FileInputStream} to read from the specified temporary file.
     *
     * @param tempFile the temporary file to be read

        // Test that readings respect max reading limit
        TestReadingConverterWithLimit limitConverter = new TestReadingConverterWithLimit();
        limitConverter.init();

        assertEquals(5, limitConverter.getMaxReadingNum());

        String text = "test";
        String field = "content";

        // Request more languages than max reading num

/**
 * Implementation of the {@link UrlQueue} interface.
 * This class represents a URL to be crawled, storing its ID, session ID,
 * HTTP method, URL, metadata, encoding, parent URL, depth, last modified time,
 * creation time, and weight.
 *
 * @param <IDTYPE> the type of the identifier for the URL queue entry
 */
public class UrlQueueImpl<IDTYPE> implements UrlQueue<IDTYPE> {
    /** The unique identifier for the URL queue entry. */

     */
    public static final String METHOD = "method";

    /**
     * Field name for MIME type.
     */
    public static final String MIME_TYPE = "mimeType";

    /**
     * Field name for creation time.
     */
    public static final String CREATE_TIME = "createTime";

    /**
     * Field name for execution time.
     */
    public static final String EXECUTION_TIME = "executionTime";

    /**

    /** Key for elevate word boost. */
    public static final String ELEVATE_WORD_BOOST = "boost";
    /** Key for elevate word reading. */
    public static final String ELEVATE_WORD_READING = "reading";
    /** Key for elevate word fields. */
    public static final String ELEVATE_WORD_FIELDS = "fields";
    /** Key for elevate word tags. */

import java.util.ArrayList;
import java.util.LinkedList;
import java.util.List;
import java.util.Queue;

/**
 * A chain of {@link ReadingConverter} implementations that applies each converter in sequence to generate possible reading variations of a given text.
 * It maintains a list of ReadingConverter instances and iterates through them, applying each converter to the input text and accumulating the results.

     *
     * @param outputFile the converted output file
     * @param outExt the output file extension
     * @return the extracted text content
     * @throws ExtractException if an error occurs while reading the file
     */
    protected String getOutputContent(final File outputFile, final String outExt) {
        final Extractor extractor = getExtractor(outExt);
        if (extractor != null) {