/** Default encoding for Markdown files. */
    protected String encoding = Constants.UTF_8;

    /** Whether to extract front matter as metadata. */
    protected boolean extractFrontMatter = true;

    /** Whether to extract headings as metadata. */
    protected boolean extractHeadings = true;

    /** Whether to extract link URLs as metadata. */
    protected boolean extractLinks = false;

    /** Markdown parser with extensions. */

    protected String lineSeparator = "\n";

    /** Whether to extract top-level fields as metadata. */
    protected boolean extractMetadata = true;

    /** Prefix for flattened nested keys. */
    protected String nestedKeySeparator = ".";

    /** Maximum number of array elements to extract. */
    protected int maxArrayElements = 100;

    /**
     * Constructs a new JsonExtractor.

        }
        return field;
    }

    /**
     * Builds the extract data from headers and rows.
     *
     * @param headers the header row
     * @param rows the data rows
     * @return the extract data
     */
    protected ExtractData buildExtractData(final String[] headers, final List<String[]> rows) {

    assert response.json() == {
        "detail": [
            {
                "type": "model_attributes_type",
                "loc": ["body"],
                "msg": "Input should be a valid dictionary or object to extract fields from",
                "input": "name=Foo&price=50.5",
            }
        ]
    }


def test_explicit_content_type(client: TestClient):
    response = client.post(
        "/items/",

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
 * document and includes it in the extraction result.
 *

                throw new ExtractException(e);
            }
        }

        return encoding;
    }

    /**
     * Extracts text content from the given content by removing tags and processing attributes.
     * @param content The content to extract from.
     * @return The extracted text.
     */
    protected String extractString(final String content) {

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 {

     */
    public void setUserPrefix(final String userPrefix) {
        this.userPrefix = userPrefix;
    }

    /**
     * Extracts role type information from SMB (Server Message Block) response data.
     * Processes both SMB and SMB1 protocols to extract allowed and denied SIDs.
     *
     * @param responseData the response data containing SMB metadata

            assertTrue("Error message should mention TAR archive or extraction failure",
                    e.getMessage().contains("TAR") || e.getMessage().contains("extract"));
        }
    }

    /**
     * Test that ZipExtractor successfully extracts from valid archive.
     */
    public void test_ZipExtractor_validArchive_extractsSuccessfully() {

                        } catch (final Exception e) {
                            failedEntries++;
                            if (logger.isDebugEnabled()) {
                                logger.debug("Failed to extract content from archive entry: {}", filename, e);
                            }
                        }
                    }
                }
            }
        } catch (final MaxLengthExceededException e) {