import org.codelibs.nekohtml.parsers.DOMParser;
import org.w3c.dom.Document;
import org.w3c.dom.Node;
import org.xml.sax.InputSource;

/**
 * {@link XpathTransformer} is a class that transforms HTML content into XML format based on XPath expressions.
 * It extracts data from an HTML document by applying XPath rules defined in {@link #fieldRuleMap}.
 * The extracted data is then formatted into an XML structure and stored in the {@link ResultData}.

      replaced with your own identifying information. (Don't include
      the brackets!)  The text should be enclosed in the appropriate
      comment syntax for the file format. We also recommend that a
      file or class name and description of purpose be included on the
      same "printed page" as the copyright notice for easier
      identification within third-party archives.

     */
    public Crawler() {
        crawlerContext = new CrawlerContext();
        final SimpleDateFormat sdf = new SimpleDateFormat("yyyyMMddHHmmssSSS", Locale.ENGLISH);
        crawlerContext.sessionId = sdf.format(new Date());
    }

    /**
     * Adds a URL to the crawling queue.
     * @param url The URL to add.
     */
    public void addUrl(final String url) {
        try {

      replaced with your own identifying information. (Don't include
      the brackets!)  The text should be enclosed in the appropriate
      comment syntax for the file format. We also recommend that a
      file or class name and description of purpose be included on the
      same "printed page" as the copyright notice for easier
      identification within third-party archives.

        assertEquals("", suggestItem.getText());
    }

    @Test
    public void testMultipleReadingsConversion() {
        // Test conversion of multiple readings to SuggestItem format
        String word = "multi reading";
        float boost = 1.0f;
        List<String> readings = Arrays.asList("reading1", "reading2", "reading3", "reading4", "reading5");

                }
            }
        }

        /**
         * Normalizes the URL string by cleaning up multiple slashes and resolving relative paths.
         * This method ensures the URL is in a consistent format for FTP operations.
         *
         * @param s The URL string to normalize
         * @return The normalized URL string
         */
        protected String normalize(final String s) {

import com.google.common.cache.LoadingCache;

import jakarta.annotation.Resource;

/**
 * <p>
 * XmlTransformer is a class that extends AbstractTransformer to transform XML documents into a specific format for indexing.
 * It uses XPath expressions to extract data from the XML and stores it in a ResultData object.
 * </p>
 *
 * <p>

        } else {
            cpuLoad = -1;
        }
        final long maxMemory = Runtime.getRuntime().maxMemory();
        final long freeMemory = Runtime.getRuntime().freeMemory();
        final String msg = String.format(
                "%d words from %d %s: {\"time\":{\"parse\":%d,\"index\":%d},\"cpu\":%f,\"mem\":{\"heap\":\"%dmb\",\"used\":\"%dmb\"}}",

        extensionMap.put("html", "txt");
        // Spreadsheet Formats
        extensionMap.put("ods", "tsv");
        extensionMap.put("ots", "tsv");
        extensionMap.put("sxc", "tsv");
        extensionMap.put("xls", "tsv");
        extensionMap.put("xlsx", "tsv");
        extensionMap.put("csv", "tsv");
        extensionMap.put("tsv", "tsv");
        // Presentation Formats
        extensionMap.put("odp", "pdf");

        if (modeSetting != null) {
            if ("search".equalsIgnoreCase(modeSetting)) {
                mode = JapaneseTokenizer.Mode.SEARCH;
            } else if ("normal".equalsIgnoreCase(modeSetting)) {
                mode = JapaneseTokenizer.Mode.NORMAL;
            } else if ("extended".equalsIgnoreCase(modeSetting)) {
                mode = JapaneseTokenizer.Mode.EXTENDED;
            }
        }
        return mode;