- Sort Score
- Result 10 results
- Languages All
Results 11 - 20 of 262 for extractor (0.04 sec)
-
fess-crawler/src/main/java/org/codelibs/fess/crawler/transformer/impl/TextTransformer.java
import org.codelibs.fess.crawler.extractor.Extractor; import org.codelibs.fess.crawler.extractor.ExtractorFactory; import jakarta.annotation.Resource; /** * TextTransformer is a class that transforms a ResponseData object into a ResultData object containing the extracted text content. * It uses an Extractor to extract the text from the response body based on the MIME type.
Registered: Sun Sep 21 03:50:09 UTC 2025 - Last Modified: Sun Jul 06 02:13:03 UTC 2025 - 6.5K bytes - Viewed (0) -
fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/MsPowerPointExtractor.java
*/ package org.codelibs.fess.crawler.extractor.impl; import java.io.IOException; import java.io.InputStream; import java.util.Map; import org.apache.poi.hslf.usermodel.HSLFShape; import org.apache.poi.hslf.usermodel.HSLFSlideShow; import org.apache.poi.hslf.usermodel.HSLFTextParagraph; import org.apache.poi.sl.extractor.SlideShowExtractor; import org.codelibs.fess.crawler.entity.ExtractData;
Registered: Sun Sep 21 03:50:09 UTC 2025 - Last Modified: Sun Jul 06 02:13:03 UTC 2025 - 2.1K bytes - Viewed (0) -
fess-crawler/src/test/java/org/codelibs/fess/crawler/extractor/impl/CommandExtractorTest.java
final CommandExtractor extractor = new CommandExtractor(); extractor.executionTimeout = 1000L; extractor.command = getCommand(scriptFile); final Map<String, String> params = new HashMap<String, String>(); try { final ExtractData data = extractor.getText(new FileInputStream(contentFile), params); fail(data.toString());
Registered: Sun Sep 21 03:50:09 UTC 2025 - Last Modified: Sat Mar 15 06:52:00 UTC 2025 - 9.8K bytes - Viewed (0) -
src/main/java/org/codelibs/fess/crawler/transformer/AbstractFessFileTransformer.java
} /** * Get the extracted data. * @param extractor The extractor. * @param in The input stream. * @param params The parameters. * @return The extracted data. */ protected ExtractData getExtractData(final Extractor extractor, final InputStream in, final Map<String, String> params) { try { return extractor.getText(in, params);
Registered: Thu Sep 04 12:52:25 UTC 2025 - Last Modified: Thu Aug 07 03:06:29 UTC 2025 - 25.6K bytes - Viewed (0) -
fess-crawler/src/test/java/org/codelibs/fess/crawler/extractor/impl/ZipExtractorTest.java
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, * either express or implied. See the License for the specific language * governing permissions and limitations under the License. */ package org.codelibs.fess.crawler.extractor.impl; import java.io.IOException; import java.io.InputStream; import org.apache.commons.compress.archivers.ArchiveStreamFactory; import org.apache.commons.compress.compressors.CompressorStreamFactory;
Registered: Sun Sep 21 03:50:09 UTC 2025 - Last Modified: Thu Aug 07 02:55:08 UTC 2025 - 3.7K bytes - Viewed (0) -
fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/MsWordExtractor.java
} try { @SuppressWarnings("resource") final org.apache.poi.hwpf.extractor.WordExtractor wordExtractor = new org.apache.poi.hwpf.extractor.WordExtractor(in); return new ExtractData(wordExtractor.getText()); } catch (final IOException e) { throw new ExtractException(e); } }
Registered: Sun Sep 21 03:50:09 UTC 2025 - Last Modified: Sun Jul 06 02:13:03 UTC 2025 - 1.9K bytes - Viewed (0) -
fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/MsExcelExtractor.java
} try { @SuppressWarnings("resource") final org.apache.poi.hssf.extractor.ExcelExtractor excelExtractor = new org.apache.poi.hssf.extractor.ExcelExtractor(new HSSFWorkbook(in)); return new ExtractData(excelExtractor.getText()); } catch (final IOException e) { throw new ExtractException(e); }
Registered: Sun Sep 21 03:50:09 UTC 2025 - Last Modified: Sun Jul 06 02:13:03 UTC 2025 - 2K bytes - Viewed (0) -
fess-crawler/src/test/java/org/codelibs/fess/crawler/extractor/impl/JodExtractorTest.java
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, * either express or implied. See the License for the specific language * governing permissions and limitations under the License. */ package org.codelibs.fess.crawler.extractor.impl; import java.io.InputStream; import java.util.HashMap; import java.util.Map; import org.apache.logging.log4j.LogManager; import org.apache.logging.log4j.Logger; import org.codelibs.core.io.CloseableUtil;
Registered: Sun Sep 21 03:50:09 UTC 2025 - Last Modified: Sat Mar 15 06:52:00 UTC 2025 - 9.5K bytes - Viewed (0) -
fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/HtmlXpathExtractor.java
* It uses XPath expressions to extract text content from HTML documents. * <p> * This class provides methods to configure the XPath expressions, parser features, and properties. * It also includes caching mechanism for XPathAPI instances to improve performance. * </p> * <p>
Registered: Sun Sep 21 03:50:09 UTC 2025 - Last Modified: Sun Jul 06 02:13:03 UTC 2025 - 10.3K bytes - Viewed (0) -
fess-crawler/src/test/java/org/codelibs/fess/crawler/extractor/impl/XmlExtractorTest.java
final InputStream in = ResourceUtil.getResourceAsStream("extractor/test_sjis.xml"); final String content = xmlExtractor.getText(in, null).getContent(); CloseableUtil.closeQuietly(in); logger.info(content); assertTrue(content.contains("ใในใ")); } public void test_getXml_entity() { final InputStream in = ResourceUtil.getResourceAsStream("extractor/test_entity.xml");
Registered: Sun Sep 21 03:50:09 UTC 2025 - Last Modified: Sat Mar 15 06:52:00 UTC 2025 - 6.4K bytes - Viewed (0)