}

        final long start = System.currentTimeMillis();
        final StringBuilder buf = new StringBuilder(searchWord.length());
        char prev = 0;
        for (final char c : searchWord.toCharArray()) {
            if (!Character.isWhitespace(c)) {
                buf.append(c);
            } else if (!Character.isWhitespace(prev)) {
                buf.append(' ');

            for (int j = i + 1; j < rules.size(); j++) {
                assertNotSame(rules.get(i).getRuleId(), rules.get(j).getRuleId());
            }
        }
    }

    /**
     * Test rule processor chain behavior
     */
    public void test_ruleProcessorChain() {
        final List<String> executionOrder = new ArrayList<>();

        // Create custom processor that tracks execution

 *   <li>Execution: Starts the crawler threads and waits for them to complete.</li>
 *   <li>Cleanup: Deletes the crawled data and clears the URL filter.</li>
 * </ol>
 *
 * <p>The crawler can be configured with various parameters, such as the number of threads,
 * the maximum depth of crawling, and URL filters.
 *
 * <p>Example usage:
 * <pre>
 *   Crawler crawler = new Crawler();

import org.codelibs.fess.crawler.helper.MimeTypeHelper;

/**
 * PdfExtractor extracts text content from PDF files using Apache PDFBox.
 * It supports password-protected PDFs and can extract embedded documents and annotations.
 *
 * <p>The extractor runs text extraction in a separate thread with a configurable timeout
 * to prevent hanging on problematic PDF files. It also extracts metadata from the PDF

        if (StringUtil.isBlank(url) || StringUtil.isBlank(enc)) {
            return url;
        }

        final StringBuilder buf = new StringBuilder(url.length() + 100);
        for (final char c : url.toCharArray()) {
            if (CharUtil.isUrlChar(c)) {
                buf.append(c);
            } else {
                try {
                    buf.append(URLEncoder.encode(String.valueOf(c), enc));

<setting id="org.eclipse.jdt.core.formatter.insert_new_line_before_finally_in_try_statement" value="do not insert"/>
<setting id="org.eclipse.jdt.core.formatter.tabulation.char" value="space"/>
<setting id="org.eclipse.jdt.core.formatter.insert_space_before_comma_in_multiple_field_declarations" value="do not insert"/>
<setting id="org.eclipse.jdt.core.formatter.blank_lines_between_import_groups" value="1"/>

<setting id="org.eclipse.wst.jsdt.core.formatter.blank_lines_before_new_chunk" value="1"/>
<setting id="org.eclipse.wst.jsdt.core.formatter.tabulation.char" value="space"/>
<setting id="org.eclipse.wst.jsdt.core.formatter.put_empty_statement_on_new_line" value="true"/>

				"application/x-bibtex-text-file",
				"application/x-bittorrent",
				"application/x-bplist",
				"application/x-bzip",
				"application/x-bzip2",
				"application/x-cdlink",
				"application/x-chat",
				"application/x-chess-pgn",
				"application/x-chrome-package",
				"application/x-compress",
				"application/x-corelpresentations",
				"application/x-cpio",
				"application/x-csh",

 *
 * <p>
 * The class uses Apache Commons Net library for FTP communication. It maintains a queue of FTPClient
 * instances to improve performance by reusing connections.
 * </p>
 *
 * <p>
 * The client can be configured with FTP-specific settings via init parameters, such as:
 * </p>
 * <ul>
 *   <li>ftpConfigSystemKey: The system key used to configure the FTPClientConfig.</li>

 * </p>
 *
 * <p>
 * The getData method returns the data extracted from AccessResultData. It can return either a String representation of the XML or a Map/Bean representation based on the configured dataClass.
 * </p>
 *
 * <p>
 * Example Usage:
 * </p>
 *
 * <pre>