crawlers - 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>

Registered: Sat Dec 20 11:21:39 UTC 2025

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

- 374 bytes

- Viewed (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>

Registered: Sat Dec 20 11:21:39 UTC 2025

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

- 365 bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/main/java/org/codelibs/fess/crawler/helper/MemoryDataHelper.java

 */
package org.codelibs.fess.crawler.helper;

import java.util.ArrayList;
import java.util.HashMap;
import java.util.LinkedList;
import java.util.List;
import java.util.Map;
import java.util.Queue;
import java.util.regex.Pattern;

import org.codelibs.fess.crawler.entity.AccessResultImpl;
import org.codelibs.fess.crawler.entity.UrlQueueImpl;

/**

Registered: Sat Dec 20 11:21:39 UTC 2025

- Last Modified: Sun Jul 06 02:13:03 UTC 2025

- 8.1K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/main/java/org/codelibs/fess/crawler/helper/impl/MimeTypeHelperImpl.java

import org.apache.tika.mime.MimeTypesFactory;
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.MimeTypeException;
import org.codelibs.fess.crawler.helper.MimeTypeHelper;

/**
 * MimeTypeHelperImpl is a helper class that detects the MIME type of a given input stream or filename.

Registered: Sat Dec 20 11:21:39 UTC 2025

- Last Modified: Sun Nov 23 12:19:14 UTC 2025

- 6.6K bytes

- Viewed (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>

Registered: Sat Dec 20 11:21:39 UTC 2025

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

- 394 bytes

- Viewed (0)

github.com/codelibs/fess

src/main/java/org/codelibs/fess/crawler/transformer/AbstractFessFileTransformer.java

import org.codelibs.fess.Constants;
import org.codelibs.fess.crawler.entity.AccessResultData;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.ResultData;
import org.codelibs.fess.crawler.entity.UrlQueue;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;

Registered: Sat Dec 20 09:19:18 UTC 2025

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

- 25.7K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/main/java/org/codelibs/fess/crawler/helper/SitemapsHelper.java

import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.entity.SitemapAlternateLink;
import org.codelibs.fess.crawler.entity.SitemapFile;
import org.codelibs.fess.crawler.entity.SitemapImage;
import org.codelibs.fess.crawler.entity.SitemapNews;
import org.codelibs.fess.crawler.entity.SitemapSet;
import org.codelibs.fess.crawler.entity.SitemapUrl;

Registered: Sat Dec 20 11:21:39 UTC 2025

- Last Modified: Fri Nov 14 13:19:40 UTC 2025

- 34.9K bytes

- Viewed (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>

Registered: Sat Dec 20 09:19:18 UTC 2025

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

- 461 bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler-lasta/pom.xml

	<modelVersion>4.0.0</modelVersion>
	<artifactId>fess-crawler-lasta</artifactId>
	<packaging>jar</packaging>
	<name>Fess Crawler for LastaFlute</name>
	<description>This is LastaFlute support.</description>
	<parent>
		<groupId>org.codelibs.fess</groupId>
		<artifactId>fess-crawler-parent</artifactId>
		<version>15.4.1-SNAPSHOT</version>
		<relativePath>../pom.xml</relativePath>
	</parent>

Registered: Sat Dec 20 11:21:39 UTC 2025

- Last Modified: Sat Dec 20 06:34:36 UTC 2025

- 2.9K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/test/java/org/codelibs/fess/crawler/transformer/impl/BinaryTransformerTest.java

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

import java.io.InputStream;

import org.apache.commons.io.IOUtils;
import org.codelibs.fess.crawler.entity.AccessResultDataImpl;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.ResultData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.dbflute.utflute.core.PlainTestCase;

Registered: Sat Dec 20 11:21:39 UTC 2025

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

- 3.2K bytes

- Viewed (0)

Search Options