// InputStream in =
    // ResourceUtil.getResourceAsStream("extractor/test_pass.pdf");
    // TikaExtractor extractor =
    // (TikaExtractor) getContainer().getComponent(
    // "tikaExtractorForPdfPassword");
    // Map<String, String> params = new HashMap<String, String>();
    // params.put(ExtractData.URL, "http://example.com/test_pass.pdf");
    // ExtractData extractData = extractor.getText(in, params);

 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.extractor.impl;

import java.io.IOException;
import java.io.InputStream;

import org.apache.commons.compress.archivers.ArchiveStreamFactory;
import org.apache.commons.compress.compressors.CompressorStreamFactory;

    private TestApiExtractorServer server;

    private ApiExtractor extractor;

    @Override
    protected void setUp() throws Exception {
        super.setUp();

        server = new TestApiExtractorServer(port);
        server.start();

        extractor = new ApiExtractor();
        extractor.setUrl("http://127.0.0.1:" + port + "/");
        extractor.init();
    }

    @Override

 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.extractor.impl;

import java.io.InputStream;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.core.io.CloseableUtil;
import org.codelibs.core.io.ResourceUtil;

        final InputStream in = new ByteArrayInputStream("test".getBytes());

        extractor.resetTestState();
        assertFalse("Should start with validate not called", extractor.isValidateCalled());

        extractor.getText(in, null);

        assertTrue("Should be called after getText", extractor.isValidateCalled());
    }

    /**
     * Test validateInputStream with edge case: empty stream.

        final String content = htmlXpathExtractor.getText(in, null).getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertTrue(content.contains("テスト"));
    }

    public void test_getHtml_sjis() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/test_sjis.html");

---
title: Sample Markdown Document
author: John Doe
date: 2025-01-15
tags:
  - crawler
  - extractor
  - markdown
---

# Introduction

This is a sample Markdown document for testing the MarkdownExtractor.

## Features

The extractor should handle:

- YAML front matter extraction
- Heading structure
- **Bold text** and *italic text*
- Lists and other formatting

### Code Examples

    /**
     * Get the extracted data.
     * @param extractor The extractor.
     * @param in The input stream.
     * @param params The parameters.
     * @return The extracted data.
     */
    protected ExtractData getExtractData(final Extractor extractor, final InputStream in, final Map<String, String> params) {
        try {
            return extractor.getText(in, params);
        } catch (final RuntimeException e) {

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

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

import org.apache.poi.hslf.usermodel.HSLFShape;
import org.apache.poi.hslf.usermodel.HSLFSlideShow;
import org.apache.poi.hslf.usermodel.HSLFTextParagraph;
import org.apache.poi.sl.extractor.SlideShowExtractor;
import org.codelibs.fess.crawler.entity.ExtractData;

            dfos = out;
            CopyUtil.copy(in, out);
            out.flush();

            Extractor extractor = StringUtil.isBlank(mimeType) ? null : extractorFactory.getExtractor(mimeType);
            if (extractor == null) {
                final String detectedMimeType = getMimeType(out);
                extractor = extractorFactory.getExtractor(detectedMimeType);