"http://dbflute.org/meta/lastadi10.dtd">
<components namespace="fessCrawler">
	<include path="crawler/container.xml" />
	<component name="tikaExtractor"
		class="org.codelibs.fess.crawler.extractor.impl.TikaExtractor">
		<property name="maxCompressionRatio">2</property>
		<property name="maxUncompressionSize">10000000</property>
	</component>

	<component name="lhaExtractor"
		class="org.codelibs.fess.crawler.extractor.impl.LhaExtractor" />
	<component name="textExtractor"
		class="org.codelibs.fess.crawler.extractor.impl.TextExtractor" />
	<component name="htmlExtractor"
		class="org.codelibs.fess.crawler.extractor.impl.HtmlExtractor">
		<property name="featureMap">
			<component class="java.util.LinkedHashMap">
				<postConstruct name="put">

            throw new FessSystemException("Could not find extractorFactory.");
        }
        final Extractor extractor = extractorFactory.getExtractor(responseData.getMimeType());
        if (logger.isDebugEnabled()) {
            logger.debug("url={}, extractor={}", responseData.getUrl(), extractor);
        }
        return extractor;
    }

    }

    /**
     * Gets the appropriate extractor for the given response data.
     * Selects an extractor based on the MIME type or falls back to the Tika extractor.
     *
     * @param responseData the response data containing the document to extract
     * @return the extractor instance for processing the document
     * @throws FessSystemException if no suitable extractor can be found
     */
    @Override

    }

    /**
     * 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);

- **ResponseProcessor**: `DefaultResponseProcessor`, `SitemapsResponseProcessor`, `NullResponseProcessor`
- **Transformer**: `HtmlTransformer`, `XmlTransformer`, `FileTransformer`, etc.
- **Extractor**: Weight-based selection (tries in descending weight order)

### Key Extractors

`TikaExtractor`, `PdfExtractor`, `MsWordExtractor`, `MsExcelExtractor`, `MsPowerPointExtractor`, `ZipExtractor`, `HtmlExtractor`, `MarkdownExtractor`, `EmlExtractor`

- Audio formats (MP3, WAV, FLAC)
- Video formats (MP4, AVI, MOV)
- Metadata extraction from media files

## Architecture

### Multi-Module Structure

```
fess-crawler-parent/
├── fess-crawler/              # Core crawler framework
│   ├── client/               # Protocol clients (HTTP, FTP, SMB, etc.)
│   ├── extractor/           # Content extractors
│   ├── transformer/         # Data transformers

import org.codelibs.fess.Constants;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;
import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.mylasta.direction.FessConfig;
import org.codelibs.fess.unit.UnitFessTestCase;
import org.codelibs.fess.util.ComponentUtil;
import org.junit.jupiter.api.Test;

     */
    public static IntervalControlHelper getIntervalControlHelper() {
        return getComponent(INTERVAL_CONTROL_HELPER);
    }

    /**
     * Gets the extractor factory component.
     * @return The extractor factory.
     */
    public static ExtractorFactory getExtractorFactory() {
        return getComponent(EXTRACTOR_FACTORY);
    }

    /**
     * Gets a job executor by name.

    "path": "platforms/jvm/jacoco-workers",
    "unitTests": false,
    "functionalTests": false,
    "crossVersionTests": false
  },
  {
    "name": "java-api-extractor",
    "path": "platforms/core-configuration/java-api-extractor",
    "unitTests": true,
    "functionalTests": false,
    "crossVersionTests": false
  },
  {
    "name": "java-compiler-plugin",