* @throws MaxLengthExceededException if the extracted content size exceeds the maximum limit
     */
    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {
        if (in == null) {
            throw new CrawlerSystemException("The inputstream is null.");
        }

        final MimeTypeHelper mimeTypeHelper = getMimeTypeHelper();

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

import java.io.ByteArrayInputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.nio.file.Files;
import java.util.Map;

import org.apache.commons.io.output.DeferredFileOutputStream;
import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;

        InputStream is = responseData.getResponseBody();
        assertTrue(is instanceof InputStream);
        CloseableUtil.closeQuietly(responseData);
    }

    private void assertMatchFalse(ResponseData responseData) {
        sitemapsRule.addRule("url", Pattern.compile(".*sitemap.*"));
        assertFalse(sitemapsRule.match(responseData));
        InputStream is = responseData.getResponseBody();

     * @return An ExtractData object containing the filename as content.
     */
    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {
        if (in == null) {
            throw new CrawlerSystemException("The inputstream is null.");
        }
        final String content = params.getOrDefault(ExtractData.RESOURCE_NAME_KEY, StringUtil.EMPTY);
        try {

     * @param params The parameters.
     * @return The extracted data.
     */
    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {
        if (in == null) {
            throw new CrawlerSystemException("The inputstream is null.");
        }
        try {
            @SuppressWarnings("resource")

     */
    String getContentType(InputStream is, String filename);

    /**
     * Determines the content type of the given input stream using the provided parameters.
     * @param is the input stream to analyze
     * @param params the parameters containing additional information like filename
     * @return the detected content type
     */
    String getContentType(InputStream is, Map<String, String> params);

     * @param params The parameters.
     * @return The extracted data.
     */
    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {
        if (in == null) {
            throw new CrawlerSystemException("The inputstream is null.");
        }
        try {
            @SuppressWarnings("resource")

        }
    }

    @Override
    public String getContentType(final InputStream is, final String filename) {
        final Map<String, String> params = new HashMap<>();
        params.put(ExtractData.RESOURCE_NAME_KEY, filename);
        return getContentType(is, params);
    }

    @Override
    public String getContentType(final InputStream is, final Map<String, String> params) {

     * @param params The parameters.
     * @return The extracted data.
     */
    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {
        if (in == null) {
            throw new CrawlerSystemException("The inputstream is null.");
        }
        try {
            @SuppressWarnings("resource")
            final org.apache.poi.hssf.extractor.ExcelExtractor excelExtractor =

 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.helper.impl;

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

import org.codelibs.core.io.ResourceUtil;
import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.exception.MimeTypeException;