Trailer - Code Search

fess-crawler-lasta/src/main/resources/crawler/mimetype.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="mimeTypeHelper"
		class="org.codelibs.fess.crawler.helper.impl.MimeTypeHelperImpl" instance="singleton">
	</component>

Created: Sat Dec 20 11:21:39 GMT 2025

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

- 374 bytes

- Click Count (0)

github.com/codelibs/fess-crawler

fess-crawler-lasta/src/main/resources/crawler/sitemaps.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="sitemapsHelper" class="org.codelibs.fess.crawler.helper.SitemapsHelper"
		instance="singleton">
	</component>

Created: Sat Dec 20 11:21:39 GMT 2025

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

- 365 bytes

- Click Count (0)

github.com/codelibs/fess

CLAUDE.md

- **Web Framework**: LastaFlute (MVC framework)
- **DI Container**: Lasta Di
- **Data Access**: DBFlute (type-safe ORM for OpenSearch)
- **Search Engine**: OpenSearch
- **App Server**: Embedded Tomcat
- **Crawler**: fess-crawler library
- **Scheduler**: Lasta Job

## Key Directories

```
src/main/java/org/codelibs/fess/
├── FessBoot.java              # Application entry point
├── app/

Created: Sat Dec 20 09:19:18 GMT 2025

- Last Modified: Fri Nov 28 16:29:12 GMT 2025

- 4.8K bytes

- Click Count (0)

github.com/codelibs/fess-crawler

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

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

	<!-- Converts child links to normalize it. -->
	<component name="urlConvertHelper" class="org.codelibs.fess.crawler.helper.UrlConvertHelper">
	</component>

Created: Sat Dec 20 11:21:39 GMT 2025

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

- 394 bytes

- Click Count (0)

github.com/codelibs/fess-crawler

fess-crawler/src/main/java/org/codelibs/fess/crawler/transformer/impl/FileTransformer.java

import org.apache.logging.log4j.Logger;
import org.codelibs.core.io.CopyUtil;
import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.entity.AccessResultData;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.ResultData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;

/**
 * <p>

Created: Sat Dec 20 11:21:39 GMT 2025

- Last Modified: Thu Aug 07 02:55:08 GMT 2025

- 11.7K bytes

- Click Count (0)

github.com/codelibs/fess

src/main/resources/crawler/extractor+tikaExtractor.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="tikaExtractor"
		class="org.codelibs.fess.crawler.extractor.impl.TikaExtractor">
		<property name="maxCompressionRatio">2</property>
		<property name="maxUncompressionSize">10000000</property>
	</component>

Created: Sat Dec 20 09:19:18 GMT 2025

- Last Modified: Sun Aug 25 12:46:12 GMT 2019

- 461 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: Sat Dec 20 09:19:18 GMT 2025

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

- 5.1K bytes

- Click Count (0)

github.com/codelibs/fess-crawler

fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/Extractor.java

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

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

import org.codelibs.fess.crawler.entity.ExtractData;

/**
 * The Extractor interface defines methods for extracting text data from an input stream.

Created: Sat Dec 20 11:21:39 GMT 2025

- Last Modified: Sat Mar 15 06:52:00 GMT 2025

- 1.6K bytes

- Click Count (0)

github.com/codelibs/fess

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">
		<property name="defaultMaxLength">10485760</property><!-- 10M -->
		<postConstruct name="addMaxLength">
			<arg>"text/html"</arg>

Created: Sat Dec 20 09:19:18 GMT 2025

- Last Modified: Sun Oct 11 06:51:14 GMT 2015

- 561 bytes

- Click Count (0)

github.com/codelibs/fess-crawler

fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/FilenameExtractor.java

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

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

import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;

/**

Created: Sat Dec 20 11:21:39 GMT 2025

- Last Modified: Wed Nov 19 08:55:01 GMT 2025

- 2.7K bytes

- Click Count (0)

Search Options