resultFile = new File(fileTransformer.baseDir, "hoge.html_2" + File.separator + "hoge2.html");
        assertEquals(resultFile, file);
        FileUtil.writeBytes(file.getAbsolutePath(), "abc".getBytes());

        path = "hoge.html/hoge3.html";
        file = fileTransformer.createFile(path);
        resultFile = new File(fileTransformer.baseDir, "hoge.html_2" + File.separator + "hoge3.html");
        assertEquals(resultFile, file);

 * @author shinsuke
 *
 */
public class CommandExtractorTest extends PlainTestCase {

    private File createScriptTempFile(final int sleep) {
        String extention;
        String content;
        if (File.separator.equals("/")) {
            // Unix
            extention = ".sh";
            content = "#!/bin/bash\nsleep " + sleep + ";cp $1 $2";
        } else {
            // Windows
            extention = ".bat";

    /** The system property name for user dictionary path. */
    public static final String USER_DICT_PATH = "fess.user.dict.path";

    /** The text separator. */
    public static final String TEXT_SEPARATOR = " ";

    /** The default role for guest users. */
    public static final String DEFAULT_ROLE = "_guest_";

    /** The default document type. */

            final StringBuilder sb = new StringBuilder();
            for (final String line : rules) {
                sb.append(line).append(System.getProperty("line.separator"));
            }
            reader = new StringReader(sb.toString());
        } else if (settings.get("synonyms_path") != null) {
            if (settings.getAsBoolean("dynamic_reload", false)) {

 * including adding URLs to the queue, filtering URLs, managing crawler threads,
 * and handling the overall crawling lifecycle.
 *
 * <p>It implements the Runnable interface to be executed in a separate thread,
 * and the AutoCloseable interface to ensure resources are properly released after use.
 *
 * <p>The crawler uses several services and components, such as UrlQueueService, DataService,

 * processing the response, and extracting child URLs.
 *
 * <p>
 * This class implements the {@link Runnable} interface, allowing it to be executed in a separate thread.
 * It uses various services and components, such as {@link UrlQueueService}, {@link DataService},
 * {@link CrawlerContainer}, {@link LogHelper}, {@link CrawlerClientFactory}, and {@link CrawlerContext},

     * The date of last modification of the file. This date should be in W3C
     * Datetime format. This format allows you to omit the time portion, if
     * desired, and use YYYY-MM-DD.
     *
     * Note that this tag is separate from the If-Modified-Since (304) header
     * the server can return, and search engines may use the information from
     * both sources differently.
     */
    private String lastmod;

    /**

/**
 * 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
 * document and includes it in the extraction result.
 *
 * <p>Features:
 * <ul>

  <mime-type type="text/rtx"/>
  <mime-type type="text/sgml">
    <glob pattern="*.sgml"/>
    <glob pattern="*.sgm"/>
  </mime-type>
  <mime-type type="text/t140"/>
  <mime-type type="text/tab-separated-values">
    <glob pattern="*.tsv"/>
  </mime-type>

  <mime-type type="text/troff">
    <_comment>Roff/nroff/troff/groff Unformatted Manual Page (UNIX)</_comment>
    <alias type="application/x-troff"/>