final InputStream in = ResourceUtil.getResourceAsStream("extractor/lha/test.lzh");
        final String content = lhaExtractor.getText(in, null).getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertTrue(content.contains("テスト"));
        assertTrue(content.contains("テキスト"));
    }

    public void test_getText_maxSize() throws IOException {

 * 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 {
    /** Logger for this class. */
    private static final Logger logger = LogManager.getLogger(LhaExtractor.class);

    /** Maximum content size for extraction. -1 means no limit. */

                        "200": {
                            "description": "Successful Response",
                            "content": {"application/json": {"schema": {}}},
                        },
                        "422": {
                            "description": "Validation Error",
                            "content": {
                                "application/json": {
                                    "schema": {

     */
    public void addFieldRule(final String name, final String xpath) {
        fieldRuleMap.put(name, xpath);
    }

    /**
     * Returns data as XML content of String.
     *
     * @return XML content of String.
     */
    @Override
    public Object getData(final AccessResultData<?> accessResultData) {
        if (dataClass == null) {
            return super.getData(accessResultData);

# Disable signature checking on pacman because we cannot initialize the keyring.
RUN Add-Content -Path C:\tools\msys64\etc\pacman.d\mirrorlist.mingw32 -Value 'SigLevel = Never'
RUN Add-Content -Path C:\tools\msys64\etc\pacman.d\mirrorlist.mingw64 -Value 'SigLevel = Never'
RUN Add-Content -Path C:\tools\msys64\etc\pacman.d\mirrorlist.msys -Value 'SigLevel = Never'

# Install pacman packages.

                    }
                ],
                "responses": {
                    "200": {
                        "content": {"application/json": {"schema": {}}},
                        "description": "Successful Response",
                    },
                    "422": {
                        "content": {
                            "application/json": {
                                "schema": {

                    ],
                    "responses": {
                        "200": {
                            "content": {"application/json": {"schema": {}}},
                            "description": "Successful Response",
                        },
                        "422": {
                            "content": {
                                "application/json": {
                                    "schema": {

                            "content": {
                                "application/json": {
                                    "schema": {},
                                },
                            },
                            "description": "Successful Response",
                        },
                        "422": {
                            "content": {

                        "200": {
                            "description": "Successful Response",
                            "content": {"application/json": {"schema": {}}},
                        },
                        "422": {
                            "description": "Validation Error",
                            "content": {
                                "application/json": {
                                    "schema": {

/**
 * Extracts text content and metadata from Markdown files.
 * This extractor provides better structured data extraction compared to Tika's generic text extraction.
 *
 * <p>Features:
 * <ul>
 *   <li>YAML front matter metadata extraction</li>
 *   <li>Heading structure extraction</li>
 *   <li>Link URL extraction</li>
 *   <li>Code block content extraction</li>