* 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 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;

 * 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;

import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.ResultData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;
import org.codelibs.fess.crawler.extractor.impl.TikaExtractor;
import org.dbflute.utflute.core.PlainTestCase;

/**
 * @author shinsuke
 *
 */
public class TextTransformerTest extends PlainTestCase {

 * 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;

import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;
import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.extractor.impl.TikaExtractor;
import org.codelibs.fess.crawler.processor.ResponseProcessor;
import org.codelibs.fess.crawler.processor.impl.DefaultResponseProcessor;
import org.codelibs.fess.crawler.rule.Rule;

 * 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.ByteArrayInputStream;
import java.io.IOException;
import java.io.InputStream;

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

import org.apache.logging.log4j.Logger;
import org.apache.tika.config.TikaConfig;
import org.apache.tika.detect.Detector;
import org.apache.tika.exception.TikaException;
import org.apache.tika.extractor.EmbeddedDocumentExtractor;
import org.apache.tika.extractor.ParsingEmbeddedDocumentExtractor;
import org.apache.tika.io.TemporaryResources;
import org.apache.tika.io.TikaInputStream;
import org.apache.tika.metadata.Metadata;

    <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"/>

/**
 * A response processor implementation that handles sitemaps.
 * It parses the response body as a SitemapSet, extracts URLs from the sitemaps,
 * and adds them as child URLs to be crawled.
 *
 * <p>
 * This class uses a {@link SitemapsHelper} to parse the sitemap XML or text.
 * It then iterates through the sitemaps in the SitemapSet, extracts the URL
 * from each sitemap, and creates a new {@link RequestData} object for each URL.

import javax.inject.Inject;
import java.io.File;

import static com.google.common.collect.Iterables.getOnlyElement;
import static java.util.stream.Collectors.toList;

/**
 * Extracts Kotlin DSL runtime generated sources.
 *
 * Current implementation extracts these from the wrapper's API jars.
 * This is not correct as it should do this with the built distribution instead.
 *