- Sort Score
- Result 10 results
- Languages All
Results 1 - 6 of 6 for tikai (0.05 sec)
-
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: Sun Nov 10 03:50:12 UTC 2024 - Last Modified: Thu Feb 22 01:47:13 UTC 2024 - 11.3K bytes - Viewed (0) -
fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/TikaExtractor.java
import org.apache.commons.lang3.SystemUtils; 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: Sun Nov 10 03:50:12 UTC 2024 - Last Modified: Sat Oct 12 01:41:37 UTC 2024 - 25K bytes - Viewed (0) -
src/main/java/org/codelibs/fess/job/CrawlJob.java
Registered: Thu Oct 31 13:40:30 UTC 2024 - Last Modified: Sun Jun 23 04:13:47 UTC 2024 - 15.1K bytes - Viewed (0) -
fess-crawler/src/test/java/org/codelibs/fess/crawler/extractor/impl/TikaExtractorTest.java
final String content = extractData.getContent(); CloseableUtil.closeQuietly(in); logger.info(content); assertTrue(content.contains("ใในใ")); } // TODO tika needs to support pdfbox 2.0 // public void test_getTika_pdf() { // final InputStream in = ResourceUtil // .getResourceAsStream("extractor/test.pdf");
Registered: Sun Nov 10 03:50:12 UTC 2024 - Last Modified: Thu Feb 22 01:36:27 UTC 2024 - 30.5K bytes - Viewed (0) -
src/main/resources/fess_config.properties
crawler.hotthread.snapshots=10 crawler.hotthread.threads=3 crawler.hotthread.timeout=30s crawler.hotthread.type=cpu crawler.metadata.content.excludes=resourceName,X-Parsed-By,Content-Encoding.*,Content-Type.*,X-TIKA.*,X-FESS.* crawler.metadata.name.mapping=\ title=title:string\n\ Title=title:string\n\ dc:title=title:string\n\ # html crawler.document.html.content.xpath=//BODY
Registered: Thu Oct 31 13:40:30 UTC 2024 - Last Modified: Tue Oct 01 14:13:38 UTC 2024 - 30.9K bytes - Viewed (0) -
okhttp/src/main/resources/okhttp3/internal/publicsuffix/PublicSuffixDatabase.gz
tochigi.tochigi.jp tochio.niigata.jp toda.saitama.jp today toei.aichi.jp toga.toyama.jp togakushi.nagano.jp togane.chiba.jp togitsu.nagasaki.jp togliatti.su togo.aichi.jp togura.nagano.jp tohma.hokkaido.jp tohnosho.chiba.jp toho.fukuoka.jp tokai.aichi.jp tokai.ibaraki.jp tokamachi.niigata.jp tokashiki.okinawa.jp toki.gifu.jp tokigawa.saitama.jp tokke.no tokoname.aichi.jp tokorozawa.saitama.jp tokushima.jp tokushima.tokushima.jp tokuyama.yamaguchi.jp tokyo tokyo.jp tolga.no tomakomai.hokkaido.jp tomari.hokkaido.jp...
Registered: Fri Nov 01 11:42:11 UTC 2024 - Last Modified: Wed Dec 20 23:27:07 UTC 2023 - 40.4K bytes - Viewed (0)