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.

     */
    public Set<String> getKeySet() {
        return metadata.keySet();
    }

    /**
     * Gets the extracted content.
     *
     * @return the extracted content
     */
    public String getContent() {
        return content;
    }

    /**
     * Sets the extracted content.
     *
     * @param content the content to set
     */
    public void setContent(final String content) {

 * optionally override the default weight value.
 */
public interface Extractor {

    /**
     * Extracts text data from the given input stream.
     *
     * @param in the input stream to extract text from
     * @param params a map of parameters to be used during extraction
     * @return an ExtractData object containing the extracted text
     */
    ExtractData getText(InputStream in, Map<String, String> params);

    /**

    protected int maxDepth = 10;

    /** Separator for key-value pairs in extracted text. */
    protected String fieldSeparator = ": ";

    /** Separator between different fields in extracted text. */
    protected String lineSeparator = "\n";

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

    /** Prefix for flattened nested keys. */

	}
	sr.ReturnNonDecryptable(true)

	// Debug corrupted streams.
	if false {
		sr.SkipEncrypted(true)
		return sr.DebugStream(os.Stdout)
	}
	extracted := false
	for {
		stream, err := sr.NextStream()
		if err != nil {
			if err == io.EOF {
				if extracted {
					return nil
				}
				return errors.New("no data found on stream")
			}
			if errors.Is(err, estream.ErrNoKey) {

                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) {
        String input = content.replaceAll("[\\r\\n]", " ");

import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;

import jakarta.annotation.Resource;

/**
 * TextTransformer is a class that transforms a ResponseData object into a ResultData object containing the extracted text content.
 * It uses an Extractor to extract the text from the response body based on the MIME type.

    /**
     * Creates a new MsVisioExtractor instance.
     */
    public MsVisioExtractor() {
        super();
    }

    /**
     * Extracts text from the Visio input stream.
     * @param in The input stream.
     * @param params The parameters.
     * @return The extracted data.
     */
    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {
        if (in == null) {

        assertEquals(testData.length, writtenBytes);

        byte[] extracted = new byte[testData.length];
        System.arraycopy(outputBuffer, 50, extracted, 0, testData.length);
        assertArrayEquals(testData, extracted);
    }

    @Test
    @DisplayName("Test small data handling")
    public void testSmallDataHandling() throws CIFSException {

---
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