Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 10 of 82 for Crawl (0.03 sec)

  1. src/test/java/org/codelibs/fess/helper/DataIndexHelperTest.java

            assertTrue("Configuration should be fast", true);
        }
    
        public void test_empty_session_handling() {
            try {
                dataIndexHelper.crawl("");
                dataIndexHelper.crawl(null);
                assertTrue("Empty session handling should be fast", true);
            } catch (Exception e) {
                assertTrue("Exception handling should be fast", true);
            }
        }
    
    Registered: Thu Sep 04 12:52:25 UTC 2025
    - Last Modified: Sat Jul 12 05:35:01 UTC 2025
    - 12.7K bytes
    - Viewed (0)
  2. fess-crawler/src/main/java/org/codelibs/fess/crawler/helper/RobotsTxtHelper.java

    import org.codelibs.fess.crawler.exception.RobotsTxtException;
    
    /**
     * Robots.txt Specifications:
     * <ul>
     * <li><a href=
     * "https://developers.google.com/webmasters/control-crawl-index/docs/robots_txt"
     * >https://developers.google.com/webmasters/control-crawl-index/docs/robots_txt
     * </a></li>
     * </ul>
     *
     * @author bowez
     * @author shinsuke
     *
     */
    public class RobotsTxtHelper {
    
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 7.7K bytes
    - Viewed (0)
  3. src/main/java/org/codelibs/fess/helper/WebFsIndexHelper.java

         *
         * @param sessionId The session ID for this crawling operation
         * @param webConfigIdList List of web configuration IDs to crawl, null for all
         * @param fileConfigIdList List of file configuration IDs to crawl, null for all
         */
        public void crawl(final String sessionId, final List<String> webConfigIdList, final List<String> fileConfigIdList) {
    Registered: Thu Sep 04 12:52:25 UTC 2025
    - Last Modified: Thu Jul 17 08:28:31 UTC 2025
    - 24.9K bytes
    - Viewed (0)
  4. fess-crawler/src/main/java/org/codelibs/fess/crawler/entity/RobotsTxt.java

        }
    
        /**
         * Gets the crawl delay value for the specified user agent from robots.txt.
         * The crawl delay specifies the time (in seconds) to wait between successive requests.
         *
         * @param userAgent The user agent string to match against robots.txt directives
         * @return The crawl delay value in seconds. Returns 0 if no matching directive is found
         *         or no crawl delay is specified for the matching directive.
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 10K bytes
    - Viewed (0)
  5. src/main/resources/fess_label_de.properties

    labels.crawling_info_WebFsCrawlExecTime=Crawl-Ausführungszeit (Web/Datei)
    labels.crawling_info_WebFsCrawlStartTime=Crawl-Startzeit (Web/Datei)
    labels.crawling_info_WebFsCrawlEndTime=Crawl-Endzeit (Web/Datei)
    labels.crawling_info_WebFsIndexExecTime=Indizierungs-Ausführungszeit (Web/Datei)
    labels.crawling_info_WebFsIndexSize=Indexgröße (Web/Datei)
    labels.crawling_info_DataCrawlExecTime=Crawl-Ausführungszeit (Datenspeicher)
    Registered: Thu Sep 04 12:52:25 UTC 2025
    - Last Modified: Thu Jul 10 04:56:21 UTC 2025
    - 43.5K bytes
    - Viewed (1)
  6. src/main/java/org/codelibs/fess/exec/Crawler.java

            public String name;
    
            /** Comma-separated list of web configuration IDs to crawl. */
            @Option(name = "-w", aliases = "--webConfigIds", metaVar = "webConfigIds", usage = "Web Config IDs")
            public String webConfigIds;
    
            /** Comma-separated list of file system configuration IDs to crawl. */
            @Option(name = "-f", aliases = "--fileConfigIds", metaVar = "fileConfigIds", usage = "File Config IDs")
    Registered: Thu Sep 04 12:52:25 UTC 2025
    - Last Modified: Thu Aug 07 03:06:29 UTC 2025
    - 31K bytes
    - Viewed (0)
  7. fess-crawler/src/test/resources/org/codelibs/fess/crawler/helper/robots.txt

    User-agent: FessCrawler
    Disallow:           # allows all 
    
    User-agent: BruteBot
    Disallow: /
    Allow: /foo/bar/
    Crawl-delay: 1314000
    
    # welcome!
    User-agent: Googlebot
    Crawl-delay: 1
    
    User-agent: *
    Disallow: /private/
    Disallow: /help        # disallows /help.html, /help/index.html, etc.
    Allow: /help/faq.html
    Crawl-delay: 3
    
    User-agent: Crawler
    Disallow: /aaa
    
    User-agent: Crawler/1.0
    Disallow: /bbb
    
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Oct 11 02:16:55 UTC 2015
    - 566 bytes
    - Viewed (0)
  8. src/test/java/org/codelibs/fess/helper/WebFsIndexHelperTest.java

        public void test_crawl_withNullParameters() {
            try {
                webFsIndexHelper.crawl("sessionId", null, null);
                assertTrue(true);
            } catch (Exception e) {
                assertTrue(true);
            }
        }
    
        public void test_crawl_withEmptyLists() {
            try {
                webFsIndexHelper.crawl("sessionId", Collections.emptyList(), Collections.emptyList());
                assertTrue(true);
    Registered: Thu Sep 04 12:52:25 UTC 2025
    - Last Modified: Thu Jul 10 13:41:04 UTC 2025
    - 15.2K bytes
    - Viewed (0)
  9. src/main/resources/fess_label_en.properties

    labels.crawling_info_WebFsCrawlExecTime=Crawl Execution Time (Web/File)
    labels.crawling_info_WebFsCrawlStartTime=Crawl Start Time (Web/File)
    labels.crawling_info_WebFsCrawlEndTime=Crawl End Time (Web/File)
    labels.crawling_info_WebFsIndexExecTime=Indexing Execution Time (Web/File)
    labels.crawling_info_WebFsIndexSize=Index Size (Web/File)
    labels.crawling_info_DataCrawlExecTime=Crawl Execution Time (Data Store)
    Registered: Thu Sep 04 12:52:25 UTC 2025
    - Last Modified: Thu Jul 10 04:56:21 UTC 2025
    - 40.7K bytes
    - Viewed (0)
  10. src/test/java/org/codelibs/fess/exec/CrawlerTest.java

                @Override
                public void crawl(String sessionId, List<String> webConfigIdList, List<String> fileConfigIdList) {
                    // Mock crawl implementation
                }
            };
            crawler.webFsIndexHelper = webFsIndexHelper;
    
            dataIndexHelper = new DataIndexHelper() {
                @Override
                public void crawl(String sessionId, List<String> dataConfigIdList) {
    Registered: Thu Sep 04 12:52:25 UTC 2025
    - Last Modified: Tue Aug 19 14:09:36 UTC 2025
    - 30.5K bytes
    - Viewed (0)
Back to top