Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 10 of 87 for URLs (0.02 sec)

  1. fess-crawler/src/main/java/org/codelibs/fess/crawler/processor/impl/DefaultResponseProcessor.java

            }
            return true;
        }
    
        /**
         * Stores child URLs found in the response data.
         *
         * @param crawlerContext the crawler context
         * @param childUrlList the set of child URLs
         * @param url the parent URL
         * @param depth the depth of the child URLs
         * @param encoding the encoding of the child URLs
         */
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Thu Aug 07 02:55:08 UTC 2025
    - 12.5K bytes
    - Viewed (0)
  2. 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)
  3. fess-crawler/src/main/java/org/codelibs/fess/crawler/Crawler.java

    import org.codelibs.fess.crawler.service.UrlQueueService;
    
    import jakarta.annotation.Resource;
    
    /**
     * The Crawler class is the main class for web crawling. It manages the crawling process,
     * including adding URLs to the queue, filtering URLs, managing crawler threads,
     * and handling the overall crawling lifecycle.
     *
     * <p>It implements the Runnable interface to be executed in a separate thread,
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 14K bytes
    - Viewed (0)
  4. 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)
  5. 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)
  6. src/main/java/org/codelibs/fess/opensearch/config/bsentity/BsWebConfig.java

            this.updatedTime = value;
        }
    
        public String getUrls() {
            checkSpecifiedProperty("urls");
            return convertEmptyToNull(urls);
        }
    
        public void setUrls(String value) {
            registerModifiedProperty("urls");
            this.urls = value;
        }
    
        public String getUserAgent() {
            checkSpecifiedProperty("userAgent");
    Registered: Thu Sep 04 12:52:25 UTC 2025
    - Last Modified: Sat Mar 15 06:53:53 UTC 2025
    - 14.1K bytes
    - Viewed (0)
  7. fess-crawler/src/main/java/org/codelibs/fess/crawler/entity/RobotsTxt.java

        public void addSitemap(final String url) {
            if (!sitemapList.contains(url)) {
                sitemapList.add(url);
            }
        }
    
        /**
         * Returns an array of sitemap URLs.
         *
         * @return an array of sitemap URLs
         */
        public String[] getSitemaps() {
            return sitemapList.toArray(new String[sitemapList.size()]);
        }
    
        /**
         * Represents a directive in a robots.txt file.
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 10K bytes
    - Viewed (0)
  8. src/test/java/org/codelibs/fess/helper/NotificationHelperTest.java

            } catch (Exception e) {
                fail("sendToSlack() should not throw an exception with blank URLs: " + e.getMessage());
            }
        }
    
        public void test_sendToSlack_withNullWebhookUrls() {
            // Setup mock configuration with null webhook URLs
            ComponentUtil.setFessConfig(new MockFessConfig() {
                @Override
                public String getSlackWebhookUrls() {
    Registered: Thu Sep 04 12:52:25 UTC 2025
    - Last Modified: Thu Jul 10 13:41:04 UTC 2025
    - 19.6K bytes
    - Viewed (0)
  9. src/main/java/org/codelibs/fess/opensearch/config/exentity/WebConfig.java

                if (StringUtil.isNotBlank(getIncludedDocUrls())) {
                    final List<Pattern> urlPatterList = new ArrayList<>();
                    final String[] urls = getIncludedDocUrls().split("[\r\n]");
                    for (final String u : urls) {
                        final String v = systemHelper.normalizeConfigPath(u);
                        if (StringUtil.isNotBlank(v)) {
    Registered: Thu Sep 04 12:52:25 UTC 2025
    - Last Modified: Sat Mar 15 06:53:53 UTC 2025
    - 9.9K bytes
    - Viewed (0)
  10. src/main/java/org/codelibs/fess/crawler/FessCrawlerThread.java

            }
        }
    
        /**
         * Extracts anchor URLs from the given object and converts them to RequestData objects.
         * The input object can be either a single string or a list of strings representing URLs.
         *
         * @param obj the object containing anchor URLs (String or List of Strings)
         * @return a set of RequestData objects for the anchor URLs, or null if no valid URLs found
         */
    Registered: Thu Sep 04 12:52:25 UTC 2025
    - Last Modified: Thu Aug 07 03:06:29 UTC 2025
    - 19.1K bytes
    - Viewed (0)
Back to top