Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 10 of 68 for com (0.01 sec)

  1. fess-crawler/src/test/java/org/codelibs/fess/crawler/filter/impl/CustomUrlFilterImplTest.java

            domainFilter.processUrl("http://example.com/");
    
            assertEquals(1, domainFilter.cachedIncludeSet.size());
            assertEquals(1, domainFilter.cachedExcludeSet.size());
            assertEquals("http://example.com/.*", domainFilter.cachedIncludeSet.toArray()[0]);
            assertEquals("http://example.com/.*", domainFilter.cachedExcludeSet.toArray()[0]);
    
            domainFilter.processUrl("https://test.com");
    
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sat Mar 15 06:52:00 UTC 2025
    - 4.3K bytes
    - Viewed (0)
  2. fess-crawler/src/test/java/org/codelibs/fess/crawler/helper/SitemapsHelperTest.java

            assertEquals("http://www.example.com/", sitemaps[0].getLoc());
            assertEquals("monthly", ((SitemapUrl) sitemaps[0]).getChangefreq());
            assertEquals("0.8", ((SitemapUrl) sitemaps[0]).getPriority());
    
            assertNull(sitemaps[1].getLastmod());
            assertEquals("http://www.example.com/catalog?item=12&desc=vacation_hawaii", sitemaps[1].getLoc());
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sat Mar 15 06:52:00 UTC 2025
    - 9.6K bytes
    - Viewed (0)
  3. fess-crawler/src/test/java/org/codelibs/fess/crawler/rule/RuleTest.java

            rule.addCondition("url", "https?://.*\\.example\\.com/.*");
    
            ResponseData responseData1 = new ResponseData();
            responseData1.setUrl("http://www.example.com/page");
            assertTrue(rule.match(responseData1));
    
            ResponseData responseData2 = new ResponseData();
            responseData2.setUrl("https://api.example.com/v1/users");
            assertTrue(rule.match(responseData2));
    
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Wed Sep 03 14:42:53 UTC 2025
    - 22.7K bytes
    - Viewed (0)
  4. fess-crawler/src/test/resources/extractor/eml/sample1.eml

    株式会社ソニー・コンピュータエンタテインメント
    〒108-8270 東京都港区港南1丁目6番27号
    
    ■"PlayStation Network"のご利用に関する規約
    http://www.jp.playstation.com/R/psn_kiyaku
    
    ■特定商取引法に基づく表示
    http://www.jp.playstation.com/R/aboutstore
    
    ■よくあるお問い合わせ(FAQ)
    http://www.jp.playstation.com/support/
    
    ■株式会社ソニー・コンピュータエンタテインメントの個人情報保護方針
    http://www.jp.playstation.com/about/privacy.html
    
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sat Jan 16 07:50:35 UTC 2016
    - 9.3K bytes
    - Viewed (0)
  5. 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)
  6. fess-crawler/src/test/resources/sitemaps/sitemap2.xml

    <?xml version="1.0" encoding="UTF-8"?>
    <sitemapindex xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
       <sitemap>
          <loc>http://www.example.com/sitemap1.xml.gz</loc>
          <lastmod>2004-10-01T18:23:17+00:00</lastmod>
       </sitemap>
       <sitemap>
          <loc>http://www.example.com/sitemap2.xml.gz</loc>
          <lastmod>2005-01-01</lastmod>
       </sitemap>
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Oct 11 02:16:55 UTC 2015
    - 376 bytes
    - Viewed (0)
  7. fess-crawler/src/test/java/org/codelibs/fess/crawler/rule/impl/RuleManagerImplTest.java

            assertEquals("fileRule", rule.getRuleId());
        }
    
        public void test_getRule_sitemaps1() {
            final ResponseData responseData = new ResponseData();
            responseData.setUrl("http://www.example.com/sitemap1.xml");
            File file = ResourceUtil.getResourceAsFile("sitemaps/sitemap1.xml");
            responseData.setResponseBody(file, false);
            final Rule rule = ruleManager.getRule(responseData);
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sat Mar 15 06:52:00 UTC 2025
    - 6.2K bytes
    - Viewed (0)
  8. fess-crawler/pom.xml

    		</dependency>
    		<dependency>
    			<groupId>com.sun.mail</groupId>
    			<artifactId>jakarta.mail</artifactId>
    			<version>${jakarta.mail.version}</version>
    		</dependency>
    		<dependency>
    			<groupId>org.apache.pdfbox</groupId>
    			<artifactId>jbig2-imageio</artifactId>
    			<version>${jbig2.imageio.version}</version>
    		</dependency>
    		<dependency>
    			<groupId>com.github.jai-imageio</groupId>
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sat Sep 06 04:15:37 UTC 2025
    - 11.3K bytes
    - Viewed (0)
  9. fess-crawler-opensearch/src/test/java/org/codelibs/fess/crawler/service/impl/OpenSearchUrlQueueServiceTest.java

            urlQueue.setUrl("http://www.id1.com/");
    
            urlQueueService.insert(urlQueue);
    
            final OpenSearchUrlQueue urlQueue2 = new OpenSearchUrlQueue();
            urlQueue2.setCreateTime(System.currentTimeMillis());
            urlQueue2.setDepth(1);
            urlQueue2.setMethod("GET");
            urlQueue2.setSessionId("id2");
            urlQueue2.setUrl("http://www.id2.com/");
    
            urlQueueService.insert(urlQueue2);
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Thu Aug 07 02:55:08 UTC 2025
    - 5.8K bytes
    - Viewed (0)
  10. 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)
Back to top