Search Options

Results per page
Sort
Preferred Languages
Advance

Results 31 - 40 of 49 for ExtractData (0.16 sec)

  2. github.com/codelibs/fess-crawler

    fess-crawler/src/test/java/org/codelibs/fess/crawler/extractor/ExtractorFactoryTest.java 

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

import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.extractor.impl.LhaExtractor;
import org.codelibs.fess.crawler.extractor.impl.PasswordBasedExtractor;
import org.codelibs.fess.crawler.extractor.impl.PdfExtractor;
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sat Mar 15 06:52:00 UTC 2025
    - 6.9K bytes
    - Viewed (0)
  3. github.com/codelibs/fess-crawler

    fess-crawler/src/test/java/org/codelibs/fess/crawler/extractor/impl/EmlExtractorTest.java 

    import org.apache.logging.log4j.Logger;
import org.codelibs.core.io.ResourceUtil;
import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;
import org.codelibs.fess.crawler.helper.impl.MimeTypeHelperImpl;
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Thu Aug 07 02:55:08 UTC 2025
    - 4.6K bytes
    - Viewed (1)
  4. github.com/codelibs/fess-crawler

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

         */
    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {
        validateInputStream(in);
        try (final HSSFWorkbook workbook = new HSSFWorkbook(in);
                final org.apache.poi.hssf.extractor.ExcelExtractor excelExtractor =
                        new org.apache.poi.hssf.extractor.ExcelExtractor(workbook)) {
            return new ExtractData(excelExtractor.getText());
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Mon Nov 24 03:59:47 UTC 2025
    - 1.9K bytes
    - Viewed (0)
  5. github.com/codelibs/fess-crawler

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

         * @return The extracted data.
     */
    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {
        validateInputStream(in);
        try (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) {
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Wed Nov 19 08:55:01 UTC 2025
    - 1.7K bytes
    - Viewed (0)
  6. github.com/codelibs/fess-crawler

    fess-crawler/src/test/java/org/codelibs/fess/crawler/extractor/impl/ArchiveExtractorErrorHandlingTest.java 

    import org.apache.logging.log4j.Logger;
import org.codelibs.core.io.ResourceUtil;
import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Mon Nov 24 03:59:47 UTC 2025
    - 12.6K bytes
    - Viewed (0)
  7. github.com/codelibs/fess-crawler

    fess-crawler/src/test/java/org/codelibs/fess/crawler/extractor/impl/ExtractorResourceManagementTest.java 

    import org.apache.logging.log4j.Logger;
import org.codelibs.core.io.ResourceUtil;
import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;
import org.dbflute.utflute.core.PlainTestCase;

/**
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Mon Nov 24 03:59:47 UTC 2025
    - 10.4K bytes
    - Viewed (0)
  8. github.com/codelibs/fess-crawler

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

    import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.crawler.container.CrawlerContainer;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;
import org.codelibs.fess.crawler.exception.UnsupportedExtractException;
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sun Nov 23 12:19:14 UTC 2025
    - 7.4K bytes
    - Viewed (0)
  9. github.com/codelibs/fess-crawler

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

                final MimeMessage message = new MimeMessage(mailSession, in);
            final String content = getBodyText(message);
            final ExtractData data = new ExtractData(content != null ? content : StringUtil.EMPTY);
            final Enumeration<Header> headers = message.getAllHeaders();
            while (headers.hasMoreElements()) {
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 12.6K bytes
    - Viewed (0)
  10. github.com/codelibs/fess-crawler

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

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

import org.apache.poi.hpbf.extractor.PublisherTextExtractor;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Gets a text from . file.
 *
 * @author shinsuke
 *
 */
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sun Nov 23 12:19:14 UTC 2025
    - 2K bytes
    - Viewed (0)
  11. github.com/codelibs/fess-crawler

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

    import org.apache.commons.compress.archivers.zip.ZipArchiveEntry;
import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.ExtractException;
import org.codelibs.fess.crawler.exception.MaxLengthExceededException;
import org.codelibs.fess.crawler.extractor.Extractor;
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Thu Dec 11 08:38:29 UTC 2025
    - 4.8K bytes
    - Viewed (0)
Back to top