final Set<RequestData> requestDataSet = new HashSet<>();
                if (includeContent) {
                    final File[] files = file.listFiles();
                    if (files != null) {
                        for (final File f : files) {
                            final String childUri = f.toURI().toASCIIString();

        Files.createDirectory(testuser2Dir);

        Files.writeString(usersDir.resolve("file1.txt"), "file1");
        Path dir1 = usersDir.resolve("dir1");
        Files.createDirectory(dir1);
        Files.writeString(dir1.resolve("file2.txt"), "file2");
        Path dir2 = dir1.resolve("dir2");
        Files.createDirectory(dir2);
        Files.writeString(dir2.resolve("file3.txt"), "file3");
        Path dir3 = usersDir.resolve("dir3");

        }
        return new File(baseDir, filePath);
    }

    /**
     * Gets the base path for storing files.
     *
     * @return the base path
     */
    public String getPath() {
        return path;
    }

    /**
     * Sets the base path for storing files.
     *
     * @param path the base path to set
     */
    public void setPath(final String path) {

     */
    public PasswordBasedExtractor() {
        super();
    }

    /**
     * Adds a password for files matching the given regular expression pattern.
     * @param regex the regular expression pattern to match against URLs or resource names
     * @param password the password to use for matching files
     */
    public void addPassword(final String regex, final String password) {

#### Archives and Compressed Files
- ZIP, TAR, GZ archives
- LHA compression format
- Nested archive extraction

#### Web and Markup
- HTML, XHTML with XPath support
- XML documents
- JSON and structured data

#### Media Files
- Audio formats (MP3, WAV, FLAC)
- Video formats (MP4, AVI, MOV)
- Metadata extraction from media files

## Architecture

### Multi-Module Structure

                }
                final Set<RequestData> requestDataSet = new HashSet<>(100);
                if (includeContent) {
                    final SmbFile[] files = file.listFiles();
                    if (files != null) {
                        for (final SmbFile f : files) {
                            final String chileUri = f.toString();

import jp.gr.java_conf.dangan.util.lha.LhaFile;
import jp.gr.java_conf.dangan.util.lha.LhaHeader;

/**
 * Extractor implementation for LHA (LZH) archive files.
 * This extractor can extract text content from files within LHA archives
 * by using appropriate extractors for each contained file type.
 *
 * @author shinsuke
 */
public class LhaExtractor extends AbstractExtractor {

        // Without any patterns, all URLs should match
        assertTrue(urlFilter.match("https://example.com/"));
        assertTrue(urlFilter.match("https://test.com/page"));
        assertTrue(urlFilter.match("ftp://files.com/document.pdf"));
        assertTrue(urlFilter.match("file:///home/user/file.txt"));
    }

    /**
     * Test match with complex URL patterns
     */
    public void test_match_complexUrls() {

                }
                final Set<RequestData> requestDataSet = new HashSet<>(100);
                if (includeContent) {
                    final SmbFile[] files = file.listFiles();
                    if (files != null) {
                        for (final SmbFile f : files) {
                            final String childUri = f.getURL().toExternalForm();

/**
 * 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.
 *