Search Options

Results per page
Sort
Preferred Languages
Advance

Results 11 - 20 of 65 for urlset (0.03 sec)

  1. fess-crawler/src/main/java/org/codelibs/fess/crawler/CrawlerThread.java

                return;
            }
    
            // add url and filter
            final Set<String> urlSet = new HashSet<>();
            final List<UrlQueue<?>> childList = childUrlList.stream()
                    .filter(d -> StringUtil.isNotBlank(d.getUrl()) && urlSet.add(d.getUrl()) && crawlerContext.urlFilter.match(d.getUrl()))
                    .map(d -> {
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Thu Aug 07 02:55:08 UTC 2025
    - 20.4K bytes
    - Viewed (0)
  2. fess-crawler/src/main/java/org/codelibs/fess/crawler/client/CrawlerClientFactory.java

            }
        }
    
        /**
         * Retrieves a client that matches the given URL key.
         * @param urlKey The URL key to match.
         * @return The matching CrawlerClient instance, or null if no match is found.
         */
        public CrawlerClient getClient(final String urlKey) {
            if (StringUtil.isBlank(urlKey)) {
                return null;
            }
    
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 7K bytes
    - Viewed (0)
  3. fess-crawler/src/test/java/org/codelibs/fess/crawler/transformer/TransformerTest.java

            StatefulTransformer transformer = new StatefulTransformer("statefulTransformer");
    
            // Process multiple URLs
            String[] urls = { "http://example1.com", "http://example2.com", "http://example3.com" };
    
            for (String url : urls) {
                ResponseData responseData = new ResponseData();
                responseData.setUrl(url);
    
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sat Sep 06 04:15:37 UTC 2025
    - 28K bytes
    - Viewed (0)
  4. fess-crawler/src/test/java/org/codelibs/fess/crawler/client/smb/SmbClientTest.java

            } catch (final ChildUrlsException e) {
                String[] urls = e.getChildUrlList().stream().map(r -> r.getUrl()).sorted().toArray(String[]::new);
                assertEquals(3, urls.length);
                assertEquals(baseUrl + "dir1/", urls[0]);
                assertEquals(baseUrl + "dir3/", urls[1]);
                assertEquals(baseUrl + "file1.txt", urls[2]);
            }
            try {
                smbClient.doGet(baseUrl + "dir1/");
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sat Sep 06 04:15:37 UTC 2025
    - 13.7K bytes
    - Viewed (0)
  5. fess-crawler/src/main/java/org/codelibs/fess/crawler/processor/impl/SitemapsResponseProcessor.java

    import jakarta.annotation.Resource;
    
    /**
     * A response processor implementation that handles sitemaps.
     * It parses the response body as a SitemapSet, extracts URLs from the sitemaps,
     * and adds them as child URLs to be crawled.
     *
     * <p>
     * This class uses a {@link SitemapsHelper} to parse the sitemap XML or text.
     * It then iterates through the sitemaps in the SitemapSet, extracts the URL
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 3.4K bytes
    - Viewed (0)
  6. fess-crawler/src/main/java/org/codelibs/fess/crawler/util/TemporaryFileInputStream.java

         * This method delegates to {@link FileInputStream#reset()}.
         *
         * @throws IOException if an I/O error occurs.
         */
        @Override
        public synchronized void reset() throws IOException {
            fileInputStream.reset();
        }
    
        /**
         * Skips over and discards {@code n} bytes of data from this input stream.
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 4.3K bytes
    - Viewed (0)
  7. fess-crawler/src/main/java/org/codelibs/fess/crawler/util/IgnoreCloseInputStream.java

        public synchronized void mark(final int readlimit) {
            inputStream.mark(readlimit);
        }
    
        /**
         * Tests if this input stream supports the mark and reset methods.
         *
         * @return true if this stream instance supports the mark and reset methods; false otherwise
         */
        @Override
        public boolean markSupported() {
            return inputStream.markSupported();
        }
    
        /**
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 5.3K bytes
    - Viewed (0)
  8. fess-crawler/src/main/java/org/codelibs/fess/crawler/transformer/impl/HtmlTransformer.java

            }
            return null;
        }
    
        /**
         * Extracts URLs from HTML tag attributes using XPath.
         *
         * @param url the base URL for resolving relative URLs
         * @param document the document to extract URLs from
         * @param xpath the XPath expression to select elements
         * @param attr the attribute name to extract URLs from
         * @param encoding the character encoding to use
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 28.5K bytes
    - Viewed (0)
  9. fess-crawler/src/main/java/org/codelibs/fess/crawler/interval/impl/DefaultIntervalController.java

     * Default implementation of the IntervalController.
     * This class provides a default way to manage delays between crawler operations.
     * It allows setting delays before processing, after processing, when no URLs are in the queue,
     * and when waiting for new URLs.
     * The delays are configurable via constructor parameters.
     *
     */
    public class DefaultIntervalController extends AbstractIntervalController {
    
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 3.4K bytes
    - Viewed (0)
  10. fess-crawler/src/main/java/org/codelibs/fess/crawler/transformer/impl/FileTransformer.java

            this.path = path;
        }
    
        /**
         * Gets the replacement string for question marks in URLs.
         *
         * @return the question mark replacement string
         */
        public String getQuestionStr() {
            return questionStr;
        }
    
        /**
         * Sets the replacement string for question marks in URLs.
         *
         * @param questionStr the question mark replacement string to set
         */
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Thu Aug 07 02:55:08 UTC 2025
    - 11.7K bytes
    - Viewed (0)
Back to top