/**
     * Constructs a new IgnoreCloseInputStream that wraps the specified input stream.
     *
     * @param inputStream the input stream to wrap
     */
    public IgnoreCloseInputStream(final InputStream inputStream) {
        this.inputStream = inputStream;
    }

    /**
     * Overrides the close method to ignore the close operation.
     * The underlying input stream will not be closed.
     *

 * 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;
import org.apache.logging.log4j.LogManager;

        final InputStream in = new ByteArrayInputStream(bytes);

        try {
            sitemapsHelper.parse(in);
            fail();
        } catch (final CrawlingAccessException e) {
            // NOP
        }
    }

    public void test_parseXmlSitemaps_invalid2() {
        final byte[] bytes = "test".getBytes();
        final InputStream in = new ByteArrayInputStream(bytes);

     * @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")

     */
    public TextExtractor() {
        super();
    }

    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {
        if (in == null) {
            throw new CrawlerSystemException("The inputstream is null.");
        }
        try {
            return new ExtractData(new String(InputStreamUtil.getBytes(in), getEncoding()));

 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.rule.impl;

import java.io.InputStream;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;

 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.helper;

import java.io.InputStream;

import org.codelibs.core.io.CloseableUtil;
import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.entity.RobotsTxt;
import org.dbflute.utflute.core.PlainTestCase;

     * @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();

    public void test_getXml_sjis() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/test_sjis.xml");
        final String content = xmlExtractor.getText(in, null).getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertTrue(content.contains("テスト"));
    }

    public void test_getXml_entity() {

 * 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 java.util.HashMap;
import java.util.Map;

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