Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 10 of 134 for Bratch (0.03 sec)

  1. fess-crawler/src/main/java/org/codelibs/fess/crawler/filter/impl/UrlFilterImpl.java

                } catch (final Exception e) {
                    logger.warn("Failed to add exclude_urls on " + sessionId, e);
                }
                cachedExcludeSet.clear();
            }
        }
    
        /*
         * (non-Javadoc)
         *
         * @see org.codelibs.fess.crawler.filter.UrlFilter#match(java.lang.String)
         */
        @Override
        public boolean match(final String url) {
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 9.2K bytes
    - Viewed (0)
  2. fess-crawler/src/test/java/org/codelibs/fess/crawler/client/http/HcHttpClientTest.java

                assertTrue(crawlerContext.getRobotsTxtUrlSet().contains("http://localhost:7070/robots.txt"));
                assertFalse(urlFilter.match("http://localhost:7070/admin/"));
                assertFalse(urlFilter.match("http://localhost:7070/websvn/"));
            } finally {
                server.stop();
            }
        }
    
        public void test_processRobotsTxt_disabled() {
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sat Sep 06 04:15:37 UTC 2025
    - 11.7K bytes
    - Viewed (0)
  3. fess-crawler/src/main/java/org/codelibs/fess/crawler/client/CrawlerClientFactory.java

                    creator.register(this);
                }
            } catch (final Exception e) {
                if (logger.isDebugEnabled()) {
                    logger.debug("CrawlerClientCreator is unavailable.", e);
                }
            }
        }
    
        /**
         * Adds a client with a regular expression pattern.
         * @param regex The regular expression to match URLs.
         * @param client The CrawlerClient instance.
         */
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 7K bytes
    - Viewed (0)
  4. fess-crawler/src/test/java/org/codelibs/fess/crawler/rule/impl/AbstractRuleTest.java

        }
    
        /**
         * Test match method implementation
         */
        public void test_match_implementation() {
            ResponseData responseData = new ResponseData();
            responseData.setUrl("http://example.com");
    
            // Test default match (true)
            assertTrue(testRule.match(responseData));
            assertEquals(1, testRule.getMatchCallCount());
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Wed Sep 03 14:42:53 UTC 2025
    - 21.9K bytes
    - Viewed (0)
  5. fess-crawler/src/test/java/org/codelibs/fess/crawler/filter/UrlFilterTest.java

            // Without any patterns, all URLs should match
            assertTrue(urlFilter.match("https://example.com/"));
            assertTrue(urlFilter.match("https://test.com/page"));
            assertTrue(urlFilter.match("ftp://files.com/document.pdf"));
            assertTrue(urlFilter.match("file:///home/user/file.txt"));
        }
    
        /**
         * Test match with complex URL patterns
         */
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Wed Sep 03 14:42:53 UTC 2025
    - 19K bytes
    - Viewed (0)
  6. fess-crawler/src/main/java/org/codelibs/fess/crawler/rule/impl/SitemapsRule.java

         */
        @Override
        public boolean match(final ResponseData responseData) {
            if (super.match(responseData)) {
                try (final InputStream is = responseData.getResponseBody()) {
                    final SitemapsHelper sitemapsHelper = crawlerContainer.getComponent("sitemapsHelper");
                    return sitemapsHelper.isValid(is);
                } catch (final CrawlingAccessException e) {
                    throw e;
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 2.6K bytes
    - Viewed (0)
  7. fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/PasswordBasedExtractor.java

     *   <li>Dynamic passwords provided through extraction parameters</li>
     * </ul>
     *
     * <p>Passwords are matched against URLs or resource names using regular expression patterns.
     * The extractor first tries to match against the URL, then falls back to the resource name if available.
     *
     * @author shinsuke
     */
    public abstract class PasswordBasedExtractor extends AbstractExtractor {
    
        /** Logger instance for this class. */
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Thu Aug 07 02:55:08 UTC 2025
    - 5.1K bytes
    - Viewed (0)
  8. fess-crawler/src/main/java/org/codelibs/fess/crawler/CrawlerThread.java

                            } catch (final Exception e1) {
                                log(logHelper, LogType.CRAWLING_EXCEPTION, crawlerContext, urlQueue, e1);
                            }
                            if (noWaitOnFolder) {
                                continue;
                            }
                        } catch (final CrawlingAccessException e) {
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Thu Aug 07 02:55:08 UTC 2025
    - 20.4K bytes
    - Viewed (0)
  9. fess-crawler/src/test/java/org/codelibs/fess/crawler/rule/RuleManagerTest.java

                fail("Should throw IndexOutOfBoundsException for negative index");
            } catch (IndexOutOfBoundsException e) {
                // Expected
            }
    
            try {
                ruleManager.addRule(5, rule2);
                fail("Should throw IndexOutOfBoundsException for index > size");
            } catch (IndexOutOfBoundsException e) {
                // Expected
            }
        }
    
        /**
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sat Sep 06 04:15:37 UTC 2025
    - 23.8K bytes
    - Viewed (0)
  10. fess-crawler/src/main/java/org/codelibs/fess/crawler/client/CrawlerClientCreator.java

            }
        }
    
        /**
         * Registers a client component with a regular expression.
         * The component will be loaded into all registered CrawlerClientFactories.
         * @param regex The regular expression to match URLs.
         * @param componentName The name of the component to register.
         */
        public synchronized void register(final String regex, final String componentName) {
            clientMap.put(regex, componentName);
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 4.5K bytes
    - Viewed (0)
Back to top