* document and includes it in the extraction result.
 *
 * <p>Features:
 * <ul>
 *   <li>Text extraction from PDF pages</li>
 *   <li>Embedded document extraction</li>
 *   <li>Annotation extraction (file attachments)</li>
 *   <li>Metadata extraction</li>
 *   <li>Password-protected PDF support</li>
 *   <li>Configurable timeout for extraction process</li>
 * </ul>
 *
 * @author shinsuke
 */

 * It encapsulates the process of extracting data from an input stream using a specified or detected extractor.
 * The builder allows setting parameters such as MIME type, filename, extractor name, maximum content length,
 * and cache file size to optimize the extraction process.
 *
 * <p>
 * The main purpose of this class is to simplify the extraction process by providing a fluent interface

            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.
     */
    public void test_getText_emptyInputStream_returnsEmptyContent() {

    }

    /**
     * Test extraction with null parameters map.
     */
    public void test_getText_withNullParams() {
        final InputStream in = new ByteArrayInputStream(new byte[0]);

        final ExtractData result = filenameExtractor.getText(in, null);

        assertNotNull(result);
        assertEquals("", result.getContent());
    }

    /**
     * Test extraction with empty parameters map.
     */

 * Extracts text content and metadata from JSON files.
 * This extractor provides better structured data extraction compared to Tika's generic text extraction.
 *
 * <p>Features:
 * <ul>
 *   <li>Structured text extraction with key-value pairs</li>
 *   <li>Top-level field extraction as metadata</li>
 *   <li>Nested structure flattening with configurable depth</li>
 *   <li>Array element extraction</li>

/**
 * 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>
 *   <li>Clean text conversion from Markdown</li>

    /**
     * Default character encoding for content extraction.
     */
    protected String encoding = Constants.UTF_8;

    /**
     * The preload size for charset detection.
     */
    protected int preloadSizeForCharset = 2048;

    /**
     * Indicates whether comment tags should be ignored during extraction.
     */
    protected boolean ignoreCommentTag = false;

    /**

     */
    public void test_MsWordExtractor_closesResourcesOnSuccess() throws IOException {
        final MsWordExtractor extractor = container.getComponent("msWordExtractor");
        final AtomicBoolean streamClosed = new AtomicBoolean(false);

        try (final InputStream originalStream = ResourceUtil.getResourceAsStream("extractor/msoffice/test.doc")) {

import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;
import org.codelibs.fess.crawler.helper.MimeTypeHelper;
import org.codelibs.fess.crawler.util.IgnoreCloseInputStream;

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.

 */
package org.codelibs.fess.crawler.extractor;

import java.io.InputStream;
import java.util.Map;

import org.codelibs.fess.crawler.entity.ExtractData;

/**
 * The Extractor interface defines methods for extracting text data from an input stream.
 * Implementations of this interface should provide the logic for extracting text and
 * optionally override the default weight value.
 */