assertNotNull(orKeywords);
        assertEquals(2, orKeywords.size());

        // Test with invalid query
        List<String> invalidKeywords = SuggestUtil.getKeywords("((invalid", fields);
        assertNotNull(invalidKeywords);
        assertEquals(0, invalidKeywords.size());
    }

    @Test
    public void testGetKeywordsWithDuplicates() {

     * @param in the input stream to validate
     * @return true if the stream contains valid sitemap data, false otherwise
     */
    public boolean isValid(final InputStream in) {
        return isValid(in, true);
    }

    /**
     * Checks if the given input stream contains valid sitemap data.
     * @param in the input stream to validate

                return false;
            }
            return true;
        } catch (final Exception e) {
            // Log the exception at debug level because an invalid URI is not critical and can be ignored.
            logger.debug("Invalid URI: {}", path, e);
        }
        return false;
    }

        // check transformer name
        if (!getName().equals(accessResultData.getTransformerName())) {
            throw new CrawlerSystemException(
                    "Transformer is invalid. Use " + accessResultData.getTransformerName() + ". This transformer is " + getName() + ".");
        }
        final byte[] data = accessResultData.getData();
        if (data == null) {
            return null;
        }

     * This method delegates to {@link FileInputStream#mark(int)}.
     *
     * @param readlimit the maximum limit of bytes that can be read before the mark position becomes invalid
     */
    @Override
    public synchronized void mark(final int readlimit) {
        fileInputStream.mark(readlimit);
    }

    /**
     * Tests if this input stream supports the mark and reset methods.

        final Reader rd = new StringReader(inputStr);
        try (TokenStream stream = createTokenStream(rd)) {
            if (stream == null) {
                throw new IOException("Invalid tokenizer.");
            }
            stream.reset();

            int offset = 0;
            while (stream.incrementToken()) {

        }
        try {
            resultData.setData(path.getBytes(charsetName));
        } catch (final UnsupportedEncodingException e) {
            if (logger.isInfoEnabled()) {
                logger.info("Invalid charsetName: " + charsetName + ". Changed to " + Constants.UTF_8, e);
            }
            charsetName = Constants.UTF_8_CHARSET.name();
            resultData.setData(path.getBytes(Constants.UTF_8_CHARSET));
        }

            try (final InputStream is = responseData.getResponseBody()) {
                final SitemapsHelper sitemapsHelper = crawlerContainer.getComponent("sitemapsHelper");
                return sitemapsHelper.isValid(is);
            } catch (final CrawlingAccessException e) {
                throw e;
            } catch (final Exception e) {
                if (logger.isDebugEnabled()) {

 *
 * <p>
 * The crawling process involves the following steps:
 * </p>
 * <ol>
 *   <li>Fetching a URL from the queue using {@link UrlQueueService#poll(String)}.</li>
 *   <li>Checking if the URL is valid using {@link #isValid(UrlQueue)}.</li>
 *   <li>Accessing the content using a {@link CrawlerClient} obtained from {@link CrawlerClientFactory}.</li>
 *   <li>Processing the response using a {@link ResponseProcessor} associated with a {@link Rule}.</li>

        return inputStream.hashCode();
    }

    /**
     * Marks the current position in this input stream.
     *
     * @param readlimit the maximum limit of bytes that can be read before the mark position becomes invalid
     */
    @Override
    public synchronized void mark(final int readlimit) {
        inputStream.mark(readlimit);
    }

    /**
     * Tests if this input stream supports the mark and reset methods.
     *