```

## 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());

import org.opensearch.transport.client.Client;

/**
 * <p>
 * {@link ESSourceReader} reads documents from Elasticsearch using the scroll API.
 * It implements the {@link DocumentReader} interface to provide a way to iterate over documents
 * in a large index without loading all of them into memory at once.
 * </p>
 *
 * <p>
 * The reader supports limiting the number of documents read based on a percentage of the total documents

    }

    /**
     * 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

                assertTrue(urlQueue.getUrl().startsWith(url2));
            }

            dataService.iterate(sessionId1, accessResult -> {
                assertTrue(accessResult.getUrl().startsWith(url1));
                assertEquals(Constants.GET_METHOD, accessResult.getMethod());
            });
            dataService.iterate(sessionId2, accessResult -> {
                assertTrue(accessResult.getUrl().startsWith(url2));

                assertTrue(urlQueue.getUrl().startsWith(url2));
            }

            dataService.iterate(sessionId1, accessResult -> {
                assertTrue(accessResult.getUrl().startsWith(url1));
                assertEquals(Constants.GET_METHOD, accessResult.getMethod());
            });
            dataService.iterate(sessionId2, accessResult -> {
                assertTrue(accessResult.getUrl().startsWith(url2));

     * @param sessionId The new session ID.
     */
    @Override
    public void generateUrlQueues(final String previousSessionId, final String sessionId) {
        dataService.iterate(previousSessionId, accessResult -> {
            final OpenSearchUrlQueue urlQueue = new OpenSearchUrlQueue();
            urlQueue.setSessionId(sessionId);
            urlQueue.setMethod(accessResult.getMethod());

        assertEquals(content, new String(resultData.getData()));
        assertEquals(1, resultData.getChildUrlSet().size());
        assertEquals("http://hoge/test2.html", resultData.getChildUrlSet().iterator().next().getUrl());
    }

    public void test_transform_urllink() {
        String content = "<a href=\"http://fuga/test.html\">test</a>";
        final byte[] data = new String(content).getBytes();

 */
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;