Search Options

Results per page
Sort
Preferred Languages
Advance

Results 81 - 90 of 169 for Watch (0.01 sec)

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

            if (in == null) {
                throw new CrawlerSystemException("The inputstream is null.");
            }
            try {
                return new ExtractData(new String(InputStreamUtil.getBytes(in), getEncoding()));
            } catch (final Exception e) {
                throw new ExtractException(e);
            }
        }
    
        /**
         * Returns the encoding used for text extraction.
         * @return the encoding
         */
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 2K bytes
    - Viewed (0)
  2. fess-crawler/src/main/java/org/codelibs/fess/crawler/helper/impl/MimeTypeHelperImpl.java

         */
        public MimeTypeHelperImpl() {
            try {
                mimeTypes = MimeTypesFactory.create(MIME_TYPES_RESOURCE_NAME);
            } catch (final Exception e) {
                throw new CrawlerSystemException("Could not initialize MimeTypeHelper.", e);
            }
        }
    
        @Override
        public String getContentType(final InputStream is, final String filename) {
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 6.5K bytes
    - Viewed (0)
  3. fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/ExtractorBuilder.java

                    try (InputStream is = getContentInputStream(out)) {
                        return extractor.getText(is, params);
                    }
                }
            } catch (final CrawlingAccessException e) {
                throw e;
            } catch (final Exception e) {
                throw new ExtractException("Failed to extract data.", e);
            } finally {
                if (dfos != null && !dfos.isInMemory()) {
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 10.1K bytes
    - Viewed (0)
  4. fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/XmlExtractor.java

         * @return The encoding pattern.
         */
        @Override
        protected Pattern getEncodingPattern() {
            return xmlEncodingPattern;
        }
    
        /**
         * Returns the precompiled {@link Pattern} used to match XML tags within the content.
         * This pattern is utilized by the extractor to identify and process XML elements.
         *
         * @return the {@link Pattern} instance for XML tag matching
         */
        @Override
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 2.6K bytes
    - Viewed (0)
  5. src/test/java/org/codelibs/opensearch/extension/analysis/NumberConcatenationFilterFactory.java

                try (Reader reader = IOUtils.getDecodingReader(new FileInputStream(suffixWordsFile), StandardCharsets.UTF_8)) {
                    suffixWords = WordlistLoader.getWordSet(reader);
                } catch (final IOException e) {
                    throw new IllegalArgumentException("Could not load " + suffixWordsFile.getAbsolutePath(), e);
                }
            } else {
                suffixWords = new CharArraySet(0, false);
    Registered: Fri Sep 19 09:08:11 UTC 2025
    - Last Modified: Sun May 18 02:59:16 UTC 2025
    - 2.4K bytes
    - Viewed (0)
  6. fess-crawler/src/main/java/org/codelibs/fess/crawler/rule/impl/RuleManagerImpl.java

         * Gets the first rule that matches the given response data.
         * @param responseData the response data to match against
         * @return the first matching rule, or null if no rule matches
         */
        @Override
        public Rule getRule(final ResponseData responseData) {
            for (final Rule rule : ruleList) {
                if (rule.match(responseData)) {
                    return rule;
                }
            }
            return null;
        }
    
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 3.4K bytes
    - Viewed (0)
  7. fess-crawler/src/test/java/org/codelibs/fess/crawler/rule/impl/SitemapsRuleTest.java

            assertTrue(sitemapsRule.match(responseData));
            InputStream is = responseData.getResponseBody();
            assertTrue(is instanceof InputStream);
            CloseableUtil.closeQuietly(responseData);
        }
    
        private void assertMatchFalse(ResponseData responseData) {
            sitemapsRule.addRule("url", Pattern.compile(".*sitemap.*"));
            assertFalse(sitemapsRule.match(responseData));
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sat Mar 15 06:52:00 UTC 2025
    - 4.7K bytes
    - Viewed (0)
  8. fess-crawler/src/main/java/org/codelibs/fess/crawler/client/http/form/FormScheme.java

                    } else {
                        String content;
                        try {
                            content = new String(InputStreamUtil.getBytes(entity.getContent()), Constants.UTF_8_CHARSET);
                        } catch (final IOException e) {
                            content = e.getMessage();
                        }
                        logger.warn("Failed to access to {}. The http status is {}.\n{}", tokenUrl, httpStatusCode, content);
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 14.3K bytes
    - Viewed (1)
  9. fess-crawler/src/main/java/org/codelibs/fess/crawler/transformer/impl/FileTransformer.java

                    CopyUtil.copy(is, os);
                } catch (final IOException e) {
                    throw new CrawlerSystemException("Could not store " + file.getAbsolutePath(), e);
                }
            }
            try {
                resultData.setData(path.getBytes(charsetName));
            } catch (final UnsupportedEncodingException e) {
                if (logger.isInfoEnabled()) {
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Thu Aug 07 02:55:08 UTC 2025
    - 11.7K bytes
    - Viewed (0)
  10. fess-crawler/src/main/java/org/codelibs/fess/crawler/entity/RobotsTxt.java

     * </ul>
     *
     * <p>The class uses case-insensitive pattern matching for user agents and supports
     * wildcard characters (*) in user agent strings. When multiple directives match a user agent,
     * the most specific (longest) match is used.</p>
     *
     */
    public class RobotsTxt {
        private static final String ALL_BOTS = "*";
    
        /** Map of user agent patterns to their corresponding directives. */
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 10K bytes
    - Viewed (0)
Back to top