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 {

	Date               = "Date"
	ETag               = "ETag"
	ContentType        = "Content-Type"
	ContentMD5         = "Content-Md5"
	ContentEncoding    = "Content-Encoding"
	Expires            = "Expires"
	ContentLength      = "Content-Length"
	ContentLanguage    = "Content-Language"
	ContentRange       = "Content-Range"
	Connection         = "Connection"
	AcceptRanges       = "Accept-Ranges"

        final ExtractData extractData = pdfExtractor.getText(in, null);
        final String content = extractData.getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertTrue(content.contains("テスト"));
        assertEquals("Writer", extractData.getValues("Creator")[0]);
        assertEquals("OpenOffice.org 3.0", extractData.getValues("Producer")[0]);

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

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

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

def test_post(client: TestClient):
    yaml_data = """
        name: Deadpoolio
        tags:
        - x-force
        - x-men
        - x-avengers
        """
    response = client.post("/items/", content=yaml_data)
    assert response.status_code == 200, response.text
    assert response.json() == {
        "name": "Deadpoolio",
        "tags": ["x-force", "x-men", "x-avengers"],
    }

/**
 * 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>

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

client = TestClient(app)


def test_post():
    response = client.post("/items/", content=b"this is actually not validated")
    assert response.status_code == 200, response.text
    assert response.json() == {
        "size": 30,
        "content": {
            "name": "Maaaagic",
            "price": 42,
            "description": "Just kiddin', no magic here. ✨",
        },
    }