* 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;

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

    /*
     * (non-Javadoc)
     *
     * @see org.codelibs.fess.crawler.extractor.Extractor#getText(java.io.InputStream,
     * java.util.Map)
     */
    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {

 *
 * <p>
 * This class provides methods to extract text from an input stream, handling different scenarios such as:
 * </p>
 * <ul>
 *   <li>Normalizing text content</li>
 *   <li>Handling resource names and content types</li>
 *   <li>Retrying extraction without resource name or content type if the initial attempt fails</li>
 *   <li>Extracting text from metadata if the main content extraction fails</li>

- 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

 * 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.util.regex.Pattern;

/**
 * Extracts text content from XML documents.
 */
public class XmlExtractor extends AbstractXmlExtractor {

    /**
     * Creates a new XmlExtractor instance.
     */

                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]", " ");

 * 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;

    <include path="crawler/client.xml"/>
    <include path="crawler/rule.xml"/>
    <include path="crawler/filter.xml"/>
    <include path="crawler/interval.xml"/>
    <include path="crawler/extractor.xml"/>
    <include path="crawler/mimetype.xml"/>
    <include path="crawler/encoding.xml"/>
    <include path="crawler/urlconverter.xml"/>
    <include path="crawler/log.xml"/>
    <include path="crawler/sitemaps.xml"/>

    }

    /**
     * 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.
     */

     */
    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.