/** 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. */

        }
        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) {

    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.

    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 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 {

    /**
     * Constructs a new AbstractXmlExtractor.
     */
    public AbstractXmlExtractor() {
        // NOP
    }

    /**
     * Returns the pattern used to extract encoding information from content.
     * @return The encoding pattern.
     */
    protected abstract Pattern getEncodingPattern();

    /**
     * Returns the pattern used to identify tags in the content.

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

            assertTrue("Error message should contain the specific encoding", e.getMessage().contains(customEncoding));
            assertTrue("Error message should indicate extraction failure", e.getMessage().contains("Failed to extract"));
        } finally {
            // Reset to default encoding
            textExtractor.setEncoding("UTF-8");
        }
    }

    /**
     * Test extraction with empty input stream.
     */

import org.codelibs.jcifs.smb.SID;

import jakarta.annotation.Resource;

/**
 * Helper class for handling permission-related operations in Fess.
 * Provides functionality to encode/decode permission strings and extract
 * role type information from various file system protocols (SMB, file, FTP).
 */
public class PermissionHelper {
    /** Logger instance for this class */

            // ExtractException with improved message
            assertTrue("Error message should contain context about Word document or extraction",
                    e.getMessage().contains("Word") || e.getMessage().contains("extract"));
        } catch (final RuntimeException e) {
            // POI may throw IllegalArgumentException or other RuntimeExceptions
            // for invalid data, which is also acceptable