assertEquals(10000, urlSet.size());

        // Add one more should maintain size at 10000 (LRU eviction)
        urlSet.add("http://overflow.com/robots.txt");
        assertEquals(10000, urlSet.size());
        assertTrue(urlSet.contains("http://overflow.com/robots.txt"));
        assertFalse(urlSet.contains("http://example0.com/robots.txt")); // First one should be evicted
    }

    /**
     * Test activeThreadCountLock getter

            list.add(value.toString());
            return list;
        }
        if (value instanceof List) {
            return (List<String>) value;
        }
        throw new IllegalArgumentException("The value should be String or List, but " + value.getClass());
    }

    /**
     * Deletes documents from the specified index based on the given query.
     *

    protected String encoding = Constants.UTF_8;

    /**
     * The preload size for charset detection.
     */
    protected int preloadSizeForCharset = 2048;

    /**
     * Indicates whether comment tags should be ignored during extraction.
     */
    protected boolean ignoreCommentTag = false;

    /**
     * Constructs a new AbstractXmlExtractor.
     */
    public AbstractXmlExtractor() {
        // NOP
    }

    /** Timeout for PDF extraction in milliseconds (default: 30 seconds). */
    protected long timeout = 30000; // 30sec

    /** Whether the extraction thread should be a daemon thread. */
    protected boolean isDaemonThread = false;

    /**
     * Creates a new PdfExtractor instance.
     */
    public PdfExtractor() {
        super();
    }

    /*

    }

    /**
     * Gets a list of access results for the specified URL.
     *
     * @param url the URL
     * @param hasData whether the result should have data
     * @return the list of access results
     */
    @Override
    public List<AccessResultImpl<Long>> getAccessResultList(final String url, final boolean hasData) {

    <_comment>after the length byte should be \x00 or a non-control character.</_comment>
    <magic priority="80">
      <match value="(?s)^([\\x05-\\x0F])[\\x00\\x20-\\x7E]{10}.{43}\\1\x00" type="regex" offset="0"/>
    </magic>
  </mime-type>
  <mime-type type="application/x-ms-nls">
    <_comment>Microsoft National Language Support</_comment>
    <_comment>Should take precedence over x-ms-owner</_comment>

            crawlerContext.activeThreadCount--;
        }
    }

    /**
     * Checks if the crawling process should continue.
     * @param tcCount The thread check count.
     * @return true if the crawling should continue, false otherwise.
     */
    protected boolean isContinue(final int tcCount) {
        if (!crawlerContainer.available()) {
            // system shutdown

      boilerplate notice, with the fields enclosed by brackets "[]"
      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

        for (SuggestItem.Kind kind : suggestItem.getKinds()) {
            if (kind == SuggestItem.Kind.USER) {
                hasUserKind = true;
                break;
            }
        }
        assertTrue("Should have USER kind", hasUserKind);
    }

    @Test
    public void testToSuggestItemWithEmptyReadings() {
        // Test toSuggestItem with empty readings
        String word = "no readings";

     * @return true if daemon threads, false otherwise.
     */
    public boolean isDaemon() {
        return daemon;
    }

    /**
     * Sets whether the crawler threads should be daemon threads.
     * @param daemon true to make threads daemon, false otherwise.
     */
    public void setDaemon(final boolean daemon) {
        this.daemon = daemon;
    }

    /**