Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 10 of 20 for delas (0.23 sec)

  1. fess-crawler/src/main/java/org/codelibs/fess/crawler/interval/impl/DefaultIntervalController.java

     * 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 {
    
        /** Delay in milliseconds after processing a URL */
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Thu Nov 20 08:58:39 UTC 2025
    - 5.8K bytes
    - Viewed (0)
  2. fess-crawler/src/main/java/org/codelibs/fess/crawler/interval/impl/AbstractIntervalController.java

    /**
     * An abstract base class for implementing {@link IntervalController}.
     * Provides a common structure for handling delays at different stages of the crawling process.
     * It encapsulates the delay logic and exception handling, allowing subclasses to focus on
     * defining the specific delay behavior for each stage.
     *
     * <p>
     * This class defines the contract for delaying the crawling process at various points, such as:
     * </p>
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Thu Nov 20 08:58:39 UTC 2025
    - 4.8K bytes
    - Viewed (0)
  3. src/main/java/org/codelibs/fess/crawler/interval/FessIntervalController.java

            super();
        }
    
        /**
         * Gets the delay time in milliseconds after processing a URL.
         *
         * @return the delay time in milliseconds after processing
         */
        public long getDelayMillisAfterProcessing() {
            return delayMillisAfterProcessing;
        }
    
        /**
         * Sets the delay time in milliseconds after processing a URL.
         *
    Registered: Sat Dec 20 09:19:18 UTC 2025
    - Last Modified: Wed Nov 19 07:09:17 UTC 2025
    - 5.1K bytes
    - Viewed (0)
  4. src/main/java/org/codelibs/fess/helper/IntervalControlHelper.java

            }
        }
    
        /**
         * Applies delay based on the configured interval rules.
         * This method calculates the appropriate delay for the current time
         * and applies it by sleeping the current thread.
         */
        public void delayByRules() {
            final long delay = getDelay();
            if (delay > 0) {
                ThreadUtil.sleep(delay);
            }
        }
    
        /**
    Registered: Sat Dec 20 09:19:18 UTC 2025
    - Last Modified: Sun Nov 23 12:34:02 UTC 2025
    - 10K bytes
    - Viewed (0)
  5. fess-crawler/src/main/java/org/codelibs/fess/crawler/interval/impl/HostIntervalController.java

     * The delayBeforeProcessing method is overridden to introduce a delay before processing a URL,
     * ensuring that requests to the same host are not made too frequently.
     * The delay is calculated based on the configured delayMillisBeforeProcessing parameter.
     * If the time since the last request to the host is less than the configured delay,
     * the thread waits until the delay has elapsed.
     * This class is thread-safe.
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Mon Nov 24 03:59:47 UTC 2025
    - 5.2K bytes
    - Viewed (0)
  6. 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: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Mon Nov 24 03:59:47 UTC 2025
    - 18.5K bytes
    - Viewed (0)
  7. fess-crawler/src/test/java/org/codelibs/fess/crawler/interval/impl/AbstractIntervalControllerTest.java

        }
    
        /**
         * Test multiple delay calls
         */
        public void test_multipleDelayCalls() {
            final TestIntervalController controller = new TestIntervalController();
    
            controller.delay(IntervalController.PRE_PROCESSING);
            controller.delay(IntervalController.POST_PROCESSING);
            controller.delay(IntervalController.NO_URL_IN_QUEUE);
            controller.delay(IntervalController.WAIT_NEW_URL);
    
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Thu Nov 20 08:58:39 UTC 2025
    - 9.8K bytes
    - Viewed (0)
  8. fess-crawler/src/test/java/org/codelibs/fess/crawler/interval/impl/DefaultIntervalControllerTest.java

            controller.delayAfterProcessing();
            final long elapsed = (System.nanoTime() - start) / 1000000;
    
            assertTrue("No delay expected", elapsed < 50); // Should be nearly instant
        }
    
        /**
         * Test delayAfterProcessing with actual delay
         */
        public void test_delayAfterProcessing_withDelay() {
            final DefaultIntervalController controller = new DefaultIntervalController();
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Thu Nov 20 08:58:39 UTC 2025
    - 8.1K bytes
    - Viewed (0)
  9. fess-crawler/src/test/resources/org/codelibs/fess/crawler/helper/robots_malformed.txt

    Disallow: /admin/
    InvalidDirective: some-value
    unknown-field: test
    Disallow /missing-colon
    Disallow:    # empty value (should be treated as allowing all)
    Allow: /public/
    Crawl-delay: invalid-number
    Crawl-delay: -10
    Crawl-delay: 5.5
    Crawl-delay:
    Allow:    # empty value
    
    # Case 3: Multiple colons in directive
    User-agent: MultiColonBot
    Disallow: http://example.com:8080/path
    Allow: /path:with:colons
    
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Fri Nov 14 12:52:01 UTC 2025
    - 2.6K bytes
    - Viewed (0)
  10. fess-crawler/src/test/java/org/codelibs/fess/crawler/helper/RobotsTxtHelperTest.java

            } finally {
                CloseableUtil.closeQuietly(in);
            }
    
            // Should not throw exception for invalid crawl-delay
            assertNotNull(robotsTxt);
            // Invalid crawl-delay should be ignored (default 0)
            assertEquals(0, robotsTxt.getCrawlDelay("TestBot"));
            // Other directives should still work
            assertFalse(robotsTxt.allows("/test/", "TestBot"));
        }
    
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Mon Nov 24 03:59:47 UTC 2025
    - 20.6K bytes
    - Viewed (0)
Back to top