Search Options

Results per page
Sort
Preferred Languages
Advance

Results 31 - 40 of 127 for getText (0.11 sec)

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

        @Resource
        protected ArchiveStreamFactory archiveStreamFactory;
    
        protected long maxContentSize = -1;
    
        @Override
        public ExtractData getText(final InputStream in, final Map<String, String> params) {
            if (in == null) {
                throw new CrawlerSystemException("The inputstream is null.");
            }
    
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Feb 22 01:47:32 UTC 2024
    - 4.4K bytes
    - Viewed (0)
  2. fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/Extractor.java

    import java.io.InputStream;
    import java.util.Map;
    
    import org.codelibs.fess.crawler.entity.ExtractData;
    
    /**
     * @author shinsuke
     *
     */
    public interface Extractor {
    
        ExtractData getText(InputStream in, Map<String, String> params);
    
        default int getWeight() {
            return 1;
        }
    
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Tue Jun 18 05:49:13 UTC 2024
    - 960 bytes
    - Viewed (0)
  3. fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/HtmlXpathExtractor.java

                        }
                    });
        }
    
        /*
         * (non-Javadoc)
         *
         * @see org.codelibs.fess.crawler.extractor.Extractor#getText(java.io.InputStream,
         * java.util.Map)
         */
        @Override
        public ExtractData getText(final InputStream in, final Map<String, String> params) {
            if (in == null) {
                throw new CrawlerSystemException("The inputstream is null.");
            }
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Feb 22 01:47:32 UTC 2024
    - 7K bytes
    - Viewed (0)
  4. fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/FilenameExtractor.java

    import org.codelibs.fess.crawler.exception.ExtractException;
    
    /**
     * @author shinsuke
     *
     */
    public class FilenameExtractor extends AbstractExtractor {
    
        @Override
        public ExtractData getText(final InputStream in, final Map<String, String> params) {
            if (in == null) {
                throw new CrawlerSystemException("The inputstream is null.");
            }
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Feb 22 01:36:27 UTC 2024
    - 1.5K bytes
    - Viewed (0)
  5. fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/TextExtractor.java

    /**
     * @author shinsuke
     *
     */
    public class TextExtractor extends AbstractExtractor {
    
        protected String encoding = Constants.UTF_8;
    
        @Override
        public ExtractData getText(final InputStream in, final Map<String, String> params) {
            if (in == null) {
                throw new CrawlerSystemException("The inputstream is null.");
            }
            try {
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Feb 22 01:36:27 UTC 2024
    - 1.7K bytes
    - Viewed (0)
  6. src/main/java/org/codelibs/fess/helper/PopularWordHelper.java

                    try {
                        popularWordsRequestBuilder.execute().getResponse().getItems().stream().forEach(item -> wordList.add(item.getText()));
                    } catch (final SuggesterException e) {
                        logger.warn("Failed to generate popular words.", e);
                    }
    
                    return wordList;
                });
    Registered: Thu Oct 31 13:40:30 UTC 2024
    - Last Modified: Thu Feb 22 01:53:18 UTC 2024
    - 5.6K bytes
    - Viewed (0)
  7. fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/TikaExtractor.java

            }
        }
    
        @Override
        public ExtractData getText(final InputStream inputStream, final Map<String, String> params) {
            return getText(inputStream, params, null);
        }
    
        protected ExtractData getText(final InputStream inputStream, final Map<String, String> params,
                final BiConsumer<ExtractData, InputStream> postFilter) {
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Sat Oct 12 01:41:37 UTC 2024
    - 25K bytes
    - Viewed (0)
  8. fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/CommandExtractor.java

        protected boolean standardOutput = false;
    
        /*
         * (non-Javadoc)
         *
         * @see org.codelibs.fess.crawler.extractor.Extractor#getText(java.io.InputStream,
         * java.util.Map)
         */
        @Override
        public ExtractData getText(final InputStream in, final Map<String, String> params) {
            final String resourceName = params == null ? null : params.get(ExtractData.RESOURCE_NAME_KEY);
    
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Feb 22 01:36:27 UTC 2024
    - 13.6K bytes
    - Viewed (0)
  9. fess-crawler/src/main/java/org/codelibs/fess/crawler/transformer/impl/TextTransformer.java

            params.put(ExtractData.CONTENT_TYPE, responseData.getMimeType());
            String content = null;
            try (final InputStream in = responseData.getResponseBody()) {
                content = extractor.getText(in, params).getContent();
            } catch (final Exception e) {
                throw new CrawlingAccessException("Could not extract data.", e);
            }
    
            final ResultData resultData = new ResultData();
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Feb 22 01:47:32 UTC 2024
    - 5.2K bytes
    - Viewed (0)
  10. fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/ExtractorBuilder.java

                    }
                    return new ExtractData(StringUtil.EMPTY);
                } else {
                    try (InputStream is = getContentInputStream(out)) {
                        return extractor.getText(is, params);
                    }
                }
            } catch (final CrawlingAccessException e) {
                throw e;
            } catch (final Exception e) {
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Sat Oct 12 01:40:57 UTC 2024
    - 6.3K bytes
    - Viewed (0)
Back to top