crawler_ - Code Search

fess-crawler-lasta/src/main/resources/crawler/extractor.xml

	<component name="psExtractor"
		class="org.codelibs.fess.crawler.extractor.impl.PsExtractor" />
	<component name="lhaExtractor"
		class="org.codelibs.fess.crawler.extractor.impl.LhaExtractor" />
	<component name="textExtractor"
		class="org.codelibs.fess.crawler.extractor.impl.TextExtractor" />
	<component name="htmlExtractor"
		class="org.codelibs.fess.crawler.extractor.impl.HtmlExtractor">

Created: Sun Apr 12 03:50:13 GMT 2026

- Last Modified: Wed Feb 11 01:15:55 GMT 2026

- 50.4K bytes

- Click Count (0)

github.com/codelibs/fess

src/main/java/org/codelibs/fess/helper/ProtocolHelper.java

/**
 * Helper class for managing and validating URL protocols in Fess crawling system.
 * This class handles the initialization and validation of web and file protocols
 * used by the crawler to determine which URLs can be crawled.
 */
public class ProtocolHelper {
    private static final Logger logger = LogManager.getLogger(ProtocolHelper.class);

Created: Tue Mar 31 13:07:34 GMT 2026

- Last Modified: Thu Mar 26 13:59:25 GMT 2026

- 12.4K bytes

- Click Count (1)

github.com/codelibs/fess

src/main/java/org/codelibs/fess/opensearch/config/exentity/WebAuthentication.java

import org.codelibs.fess.crawler.client.http.config.CredentialsConfig;
import org.codelibs.fess.crawler.client.http.config.CredentialsConfig.CredentialsType;
import org.codelibs.fess.crawler.client.http.config.WebAuthenticationConfig;
import org.codelibs.fess.crawler.client.http.config.WebAuthenticationConfig.AuthSchemeType;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;

Created: Tue Mar 31 13:07:34 GMT 2026

- Last Modified: Sat Jan 10 01:38:30 GMT 2026

- 5.7K bytes

- Click Count (0)

github.com/codelibs/fess

src/main/java/org/codelibs/fess/opensearch/config/exentity/CrawlingConfig.java

import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.Constants;
import org.codelibs.fess.crawler.client.CrawlerClientFactory;
import org.codelibs.fess.crawler.client.ftp.FtpClient;
import org.codelibs.fess.crawler.client.http.HcHttpClient;
import org.codelibs.fess.crawler.client.smb.SmbClient;
import org.codelibs.fess.mylasta.direction.FessConfig;
import org.codelibs.fess.util.ComponentUtil;

Created: Tue Mar 31 13:07:34 GMT 2026

- Last Modified: Sat Mar 15 06:53:53 GMT 2025

- 5.6K bytes

- Click Count (0)

github.com/codelibs/fess

src/main/java/org/codelibs/fess/crawler/interval/FessIntervalController.java

 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.interval;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.fess.crawler.interval.impl.DefaultIntervalController;
import org.codelibs.fess.helper.IntervalControlHelper;
import org.codelibs.fess.util.ComponentUtil;

/**

Created: Tue Mar 31 13:07:34 GMT 2026

- Last Modified: Wed Nov 19 07:09:17 GMT 2025

- 5.1K bytes

- Click Count (0)

github.com/codelibs/fess

src/test/java/org/codelibs/fess/app/web/admin/log/AdminLogActionTest.java

        assertTrue(AdminLogAction.isLogFilename("crawler.log"));
        assertTrue(AdminLogAction.isLogFilename("audit.log"));
        assertTrue(AdminLogAction.isLogFilename("application-2024-01-01.log"));
    }

    @Test
    public void test_isLogFilename_withLogGzExtension() {
        assertTrue(AdminLogAction.isLogFilename("fess.log.gz"));
        assertTrue(AdminLogAction.isLogFilename("crawler.log.gz"));

Created: Tue Mar 31 13:07:34 GMT 2026

- Last Modified: Sun Jan 11 08:43:05 GMT 2026

- 10.5K bytes

- Click Count (0)

github.com/codelibs/fess

src/test/java/org/codelibs/fess/helper/IntervalControlHelperTest.java

        helper.setCrawlerWaitMillis(50);

        // Test when crawler is running
        assertTrue(helper.isCrawlerRunning());
        long start = System.currentTimeMillis();
        helper.checkCrawlerStatus();
        long end = System.currentTimeMillis();
        assertTrue(end - start < 100); // Should return quickly

        // Test when crawler is not running
        helper.setCrawlerRunning(false);

Created: Tue Mar 31 13:07:34 GMT 2026

- Last Modified: Wed Jan 14 14:29:07 GMT 2026

- 13.6K bytes

- Click Count (0)

github.com/codelibs/fess

src/main/java/org/codelibs/fess/helper/PermissionHelper.java

import org.apache.logging.log4j.Logger;
import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.crawler.client.fs.FileSystemClient;
import org.codelibs.fess.crawler.client.ftp.FtpClient;
import org.codelibs.fess.crawler.client.smb.SmbClient;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;
import org.codelibs.fess.mylasta.direction.FessConfig;

Created: Tue Mar 31 13:07:34 GMT 2026

- Last Modified: Thu Nov 13 05:54:52 GMT 2025

- 15.4K bytes

- Click Count (0)

github.com/codelibs/fess-crawler

fess-crawler-lasta/src/main/resources/crawler/contentlength.xml

<!DOCTYPE components PUBLIC "-//DBFLUTE//DTD LastaDi 1.0//EN"
	"http://dbflute.org/meta/lastadi10.dtd">
<components namespace="fessCrawler">
	<include path="crawler/container.xml" />

	<component name="contentLengthHelper"
		class="org.codelibs.fess.crawler.helper.ContentLengthHelper" instance="singleton">
	</component>

Created: Sun Apr 12 03:50:13 GMT 2026

- Last Modified: Sun Oct 11 02:16:55 GMT 2015

- 375 bytes

- Click Count (0)

github.com/codelibs/fess-crawler

fess-crawler-lasta/src/main/resources/crawler/interval.xml

<!DOCTYPE components PUBLIC "-//DBFLUTE//DTD LastaDi 1.0//EN"
	"http://dbflute.org/meta/lastadi10.dtd">
<components namespace="fessCrawler">
	<include path="crawler/container.xml" />

	<component name="intervalController"
		class="org.codelibs.fess.crawler.interval.impl.DefaultIntervalController"
		instance="prototype">
	</component>

Created: Sun Apr 12 03:50:13 GMT 2026

- Last Modified: Sun Oct 11 02:16:55 GMT 2015

- 389 bytes

- Click Count (0)

Search Options