Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 10 of 23 for Tika (0.75 sec)

  2. github.com/codelibs/fess

    src/main/resources/tika.xml 

    <?xml version="1.0" encoding="UTF-8"?>
<properties>
  <parsers>
    <parser class="org.apache.tika.parser.DefaultParser">
      <parser-exclude class="org.apache.tika.parser.ocr.TesseractOCRParser"/>
    </parser>
  </parsers>
    Registered: Sat Dec 20 09:19:18 UTC 2025
    - Last Modified: Mon Feb 24 12:59:41 UTC 2020
    - 241 bytes
    - Viewed (0)
  3. github.com/codelibs/fess-crawler

    fess-crawler/src/main/resources/org/codelibs/fess/crawler/mime/tika-mimetypes.xml 

      <!--  an OLE2 (application/x-tika-msoffice) container. -->
  <!--  The are logically subclasses of (application/x-tika-ooxml),
        but their containers are literally subclasses
        of (application/x-tika-msoffice) -->
  <mime-type type="application/x-tika-ooxml-protected">
    <sub-class-of type="application/x-tika-msoffice"/>
    <_comment>Password Protected OOXML File</_comment>
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Thu Oct 16 07:46:32 UTC 2025
    - 320.2K bytes
    - Viewed (2)
  4. github.com/codelibs/fess-crawler

    fess-crawler/src/main/java/org/codelibs/fess/crawler/entity/ExtractData.java 

    import java.util.Map;
import java.util.Set;

import org.apache.tika.metadata.ClimateForcast;
import org.apache.tika.metadata.CreativeCommons;
import org.apache.tika.metadata.Geographic;
import org.apache.tika.metadata.HttpHeaders;
import org.apache.tika.metadata.Message;
import org.apache.tika.metadata.TIFF;
import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.metadata.TikaMimeKeys;

/**
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sat Sep 06 04:15:37 UTC 2025
    - 3.8K bytes
    - Viewed (0)
  5. github.com/codelibs/fess-crawler

    fess-crawler/pom.xml 

    			<artifactId>tika-parser-html-module</artifactId>
			<version>${tika.version}</version>
		</dependency>
		<dependency>
			<groupId>org.apache.tika</groupId>
			<artifactId>tika-parser-image-module</artifactId>
			<version>${tika.version}</version>
		</dependency>
		<dependency>
			<groupId>org.apache.tika</groupId>
			<artifactId>tika-parser-mail-module</artifactId>
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sat Dec 20 06:34:36 UTC 2025
    - 12.1K bytes
    - Viewed (0)
  6. github.com/codelibs/fess-crawler

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

    import java.io.BufferedInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.util.HashMap;
import java.util.Map;

import org.apache.tika.metadata.Metadata;
import org.apache.tika.mime.MediaType;
import org.apache.tika.mime.MimeTypes;
import org.apache.tika.mime.MimeTypesFactory;
import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.crawler.entity.ExtractData;
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sun Nov 23 12:19:14 UTC 2025
    - 6.6K bytes
    - Viewed (0)
  7. github.com/codelibs/fess-crawler

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

    import org.apache.logging.log4j.Logger;
import org.apache.tika.config.TikaConfig;
import org.apache.tika.detect.Detector;
import org.apache.tika.exception.TikaException;
import org.apache.tika.extractor.EmbeddedDocumentExtractor;
import org.apache.tika.extractor.ParsingEmbeddedDocumentExtractor;
import org.apache.tika.io.TemporaryResources;
import org.apache.tika.io.TikaInputStream;
import org.apache.tika.metadata.Metadata;
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sun Nov 23 12:19:14 UTC 2025
    - 30.8K bytes
    - Viewed (0)
  8. github.com/codelibs/fess

    src/main/resources/fess_indices/fess/lv/stopwords.txt 

    vis
tak
iekams
vien
# modal verbs
būt  
biju 
biji
bija
bijām
bijāt
esmu
esi
esam
esat 
būšu     
būsi
būs
būsim
būsiet
tikt
tiku
tiki
tika
tikām
tikāt
tieku
tiec
tiek
tiekam
tiekat
tikšu
tiks
tiksim
tiksiet
tapt
tapi
tapāt
topat
tapšu
tapsi
taps
tapsim
tapsiet
kļūt
kļuvu
    Registered: Sat Dec 20 09:19:18 UTC 2025
    - Last Modified: Thu Jul 19 06:31:02 UTC 2018
    - 1.2K bytes
    - Viewed (0)
  9. github.com/codelibs/fess

    src/main/resources/fess.xml 

    		<property name="valueSeparator">"\\n"</property>
		<property name="roleSeparator">","</property>
		 -->
	</component>
	<component name="tikaConfig" class="org.apache.tika.config.TikaConfig">
		<arg>org.codelibs.fess.util.ResourceUtil.getConfOrClassesPath("tika.xml")</arg>
	</component>
    Registered: Sat Dec 20 09:19:18 UTC 2025
    - Last Modified: Sun Jul 28 09:03:48 UTC 2024
    - 5.2K bytes
    - Viewed (0)
  10. github.com/codelibs/fess

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

    import java.util.Arrays;
import java.util.Map;
import java.util.stream.Collectors;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.apache.tika.language.detect.LanguageDetector;
import org.apache.tika.language.detect.LanguageResult;
import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.mylasta.direction.FessConfig;
import org.codelibs.fess.util.ComponentUtil;
    Registered: Sat Dec 20 09:19:18 UTC 2025
    - Last Modified: Fri Nov 28 16:29:12 UTC 2025
    - 6.9K bytes
    - Viewed (0)
  11. github.com/codelibs/fess-crawler

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

    				"application/x-texinfo",
				"application/x-tika-msoffice",
				"application/x-tika-msoffice-embedded",
				"application/x-tika-msoffice-embedded;format=ole10_native",
				"application/x-tika-msoffice-embedded;format=comp_obj",
				"application/x-tika-msworks-spreadsheet",
				"application/x-tika-ooxml",
				"application/x-tika-ooxml-protected",
				"application/x-tika-staroffice",
				"application/x-uc2-compressed",
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sun Nov 23 03:46:53 UTC 2025
    - 50.1K bytes
    - Viewed (0)
Back to top