*/
package org.codelibs.fess.crawler.transformer.impl;

import java.io.InputStream;
import java.io.UnsupportedEncodingException;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.Iterator;
import java.util.LinkedHashMap;
import java.util.List;
import java.util.Map;
import java.util.concurrent.ExecutionException;
import java.util.concurrent.TimeUnit;
import java.util.regex.Matcher;

                }
                throw new ExtractException("PDFBox process cannot finish in " + timeout + " sec.");
            }
            if (!exceptionSet.isEmpty()) {
                throw exceptionSet.iterator().next();
            }
            writer.flush();
            final ExtractData extractData = new ExtractData(writer.toString());
            extractMetadata(document, extractData);
            return extractData;

    }

    /**
     * Iterates through all access results for a session, calling the callback for each result.
     * Uses OpenSearch scroll API for efficient iteration over large result sets.
     *
     * @param sessionId The session ID.
     * @param callback The callback to execute for each access result.
     */
    @Override

        return dataHelper.getAccessResultList(url);
    }

    /**
     * Iterates over all access results for the specified session.
     *
     * @param sessionId the session ID
     * @param accessResultCallback the callback to invoke for each access result
     */
    @Override
    public void iterate(final String sessionId, final AccessResultCallback<AccessResultImpl<Long>> accessResultCallback) {

 * authentication based on a given path.
 *
 * <p>This class manages a collection of {@link SmbAuthentication} objects, each associated
 * with a specific path prefix. When a path is provided, it iterates through the stored
 * authentications to find the one whose path prefix matches the beginning of the given path.
 * This allows for different SMB shares to use different authentication credentials.</p>
 */

     */
    /**
     * Processes the given access result.
     *
     * @param accessResult the result of the access operation to be processed
     */
    void iterate(RESULT accessResult);

```

## Data Access and Storage

### Accessing Crawled Data

```java
// Get data service
DataService dataService = container.getComponent("dataService");

// Iterate through crawled data
dataService.iterate(sessionId, accessResult -> {
    System.out.println("URL: " + accessResult.getUrl());
    System.out.println("Status: " + accessResult.getHttpStatusCode());

 * 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.
 * These RequestData objects are added to a set of child URLs, which are then

 * authentication based on a given path.
 *
 * <p>This class manages a collection of {@link SmbAuthentication} objects, each associated
 * with a specific path prefix. When a path is provided, it iterates through the stored
 * authentications to find the one whose path prefix matches the beginning of the given path.
 * This allows for different SMB shares to use different authentication credentials.</p>
 *
 */

                assertTrue(urlQueue.getUrl() + "=>" + url2, urlQueue.getUrl().startsWith(url2));
            }

            dataService.iterate(sessionId1, accessResult -> assertTrue(accessResult.getUrl().startsWith(url1)));
            dataService.iterate(sessionId2, accessResult -> assertTrue(accessResult.getUrl().startsWith(url2)));

            dataService.delete(sessionId1);
            dataService.delete(sessionId2);