* 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;

 */
package org.codelibs.fess.suggest.index.contents.document;

import java.io.Closeable;
import java.util.Map;

/**
 * Interface for reading documents and extracting their contents into a map.
 * Implementations of this interface should provide the logic for reading
 * documents and converting them into a key-value structure.
 *

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

import java.io.IOException;
import java.io.InputStream;
import java.util.Map;

import org.apache.poi.hpbf.extractor.PublisherTextExtractor;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;

 * 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;

 * may attempt to download and install SDK components (platforms, build-tools, platform-tools) simultaneously.
 * This can cause race conditions leading to:
 * - `FileAlreadyExistsException` when extracting files
 * - Corrupted installations (e.g., "Build-tool X has corrupt source.properties")
 * - Missing SDK components after installation
 *

 * 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.util.regex.Pattern;

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

    /**
     * Creates a new XmlExtractor instance.

    <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"/>

import java.util.Arrays;

import jcifs.Decodable;
import jcifs.internal.util.SMBUtil;

/**
 * DFS (Distributed File System) referral response buffer parser.
 * Decodes server responses to DFS referral requests, extracting information about
 * available DFS targets, path consumption details, and referral flags.
 *
 * @author mbechler
 */
public class DfsReferralResponseBuffer implements Decodable {

    /**

  if (pr_match_groups.length != 2) {
    console.log(`PR Number not found in ${context.payload.head_commit.message}`);
    throw "Error extracting PR Number from commit message";
  }
  const pr_number = parseInt(pr_match_groups[1]);
  const owner = context.payload.repository.owner.name;
  const repo = context.payload.repository.name;

 * This is not correct as it should do this with the built distribution instead.
 *
 * Doing it correctly would require running a Gradle build with the full
 * distribution and extracting the generated api jar from its Gradle user home,
 * slowing down building documentation.
 *
 * All this would be so much simpler if the Kotlin extensions to the Gradle API
 * were generated at build time instead.
 *