* </pre>
 */
public class Crawler {

    /**
     * Creates a new instance of Crawler.
     */
    public Crawler() {
        // Default constructor
    }

    /** Logger instance for this class. */
    private static final Logger logger = LogManager.getLogger(Crawler.class);

    /** Thread name for web and file system crawling process. */

        // Verify that multiple components can be retrieved
        final Crawler crawler1 = crawlerContainer.getComponent("crawler");
        final Crawler crawler2 = crawlerContainer.getComponent("crawler");

        // They should be different instances (prototype scope)
        assertNotNull(crawler1);
        assertNotNull(crawler2);
    }

    @Test
    public void test_isLastaCrawlerContainer() {

{"index":{"_index":"fess_config.scheduled_job","_id":"default_crawler"}}
{"name":"Default Crawler","target":"all","cronExpression":"0 0 * * *","scriptType":"groovy","scriptData":"return container.getComponent(\"crawlJob\").logLevel(\"info\").gcLogging().execute(executor);","jobLogging":true,"crawler":true,"available":true,"sortOrder":1,"createdBy":"system","createdTime":0,"updatedBy":"system","updatedTime":0}
{"index":{"_index":"fess_config.scheduled_job","_id":"suggest_indexer"}}

            crawler1.getCrawlerContext().setMaxAccessCount(maxCount);
            crawler1.getCrawlerContext().setNumOfThread(numOfThread);

            final Crawler crawler2 = getComponent(Crawler.class);
            crawler2.setBackground(true);
            ((UrlFilterImpl) crawler2.urlFilter).setIncludeFilteringPattern("$1$2$3.*");
            crawler2.addUrl(url2);
            crawler2.getCrawlerContext().setMaxAccessCount(maxCount);

**DI Config**: `fess-crawler-lasta/src/main/resources/`
- `crawler.xml` (root), `crawler/client.xml`, `crawler/extractor.xml`, `crawler/rule.xml`, `crawler/transformer.xml`, `crawler/transformer_basic.xml`
- `crawler/mimetype.xml`, `crawler/encoding.xml`, `crawler/robotstxt.xml`, `crawler/sitemaps.xml`

            crawler1.addUrl(url1);
            crawler1.getCrawlerContext().setMaxAccessCount(maxCount);
            crawler1.getCrawlerContext().setNumOfThread(numOfThread);

            final Crawler crawler2 = crawlerContainer.getComponent("crawler");
            crawler2.setSessionId(crawler2.getSessionId() + "2");
            crawler2.setBackground(true);

        Crawler.Options options = new Crawler.Options();
        options.sessionId = "test-session";
        options.fileConfigIds = "file1";

        int result = crawler.doCrawl(options);
        assertEquals(Constants.EXIT_OK, result);
    }

    @Test
    public void test_doCrawl_withDataConfigIds() {
        Crawler.Options options = new Crawler.Options();

        assertTrue(pluginHelper.isExcludedName(ArtifactType.CRAWLER, "fess-crawler-lasta"));
        assertTrue(pluginHelper.isExcludedName(ArtifactType.CRAWLER, "fess-crawler-parent"));
        assertTrue(pluginHelper.isExcludedName(ArtifactType.CRAWLER, "fess-crawler-playwright"));
        assertTrue(pluginHelper.isExcludedName(ArtifactType.CRAWLER, "fess-crawler-webdriver"));

 */
package org.codelibs.fess.crawler;

import java.util.Set;
import java.util.concurrent.atomic.AtomicInteger;
import java.util.concurrent.atomic.AtomicLong;

import org.codelibs.core.collection.LruHashSet;
import org.codelibs.fess.crawler.filter.UrlFilter;
import org.codelibs.fess.crawler.interval.IntervalController;
import org.codelibs.fess.crawler.rule.RuleManager;

/**

* [LastaFlute](https://github.com/lastaflute/lastaflute "LastaFlute"): Web Framework
* [Lasta Job](https://github.com/lastaflute/lasta-job "Lasta Job"): Job Scheduler
* [Fess Crawler](https://github.com/codelibs/fess-crawler "Fess Crawler"): Web Crawler