Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 10 of 25 for internals (0.05 sec)

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

     * either express or implied. See the License for the specific language
     * governing permissions and limitations under the License.
     */
    package org.codelibs.fess.crawler.interval;
    
    /**
     * The {@code IntervalController} interface defines methods for controlling
     * the delay intervals in a web crawler. It includes constants representing
     * different types of processing states and a method to introduce a delay
     * based on the type of processing.
     * <p>
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 1.8K bytes
    - Viewed (0)
  2. fess-crawler/src/main/java/org/codelibs/fess/crawler/client/FaultTolerantClient.java

            this.maxRetryCount = maxRetryCount;
        }
    
        /**
         * Returns the retry interval.
         * @return The retry interval in milliseconds.
         */
        public long getRetryInterval() {
            return retryInterval;
        }
    
        /**
         * Sets the retry interval.
         * @param retryInterval The retry interval in milliseconds.
         */
        public void setRetryInterval(final long retryInterval) {
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 7.8K bytes
    - Viewed (0)
  3. fess-crawler/src/main/java/org/codelibs/fess/crawler/CrawlerContext.java

            this.ruleManager = ruleManager;
        }
    
        /**
         * Returns the interval controller.
         * @return The IntervalController.
         */
        public IntervalController getIntervalController() {
            return intervalController;
        }
    
        /**
         * Sets the interval controller.
         * @param intervalController The IntervalController.
         */
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 8.9K bytes
    - Viewed (0)
  4. fess-crawler/src/main/java/org/codelibs/fess/crawler/Crawler.java

            this.ruleManager = ruleManager;
        }
    
        /**
         * Returns the interval controller.
         * @return The IntervalController instance.
         */
        public IntervalController getIntervalController() {
            return intervalController;
        }
    
        /**
         * Sets the interval controller.
         * @param intervalController The IntervalController instance to set.
         */
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 14K bytes
    - Viewed (0)
  5. fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/ZipExtractor.java

                                buf.append('\n');
                            } catch (final Exception e) {
                                if (logger.isDebugEnabled()) {
                                    logger.debug("Exception in an internal extractor.", e);
                                }
                            }
                        }
                    }
                }
            } catch (final MaxLengthExceededException e) {
                throw e;
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 4.5K bytes
    - Viewed (0)
  6. fess-crawler/src/main/java/org/codelibs/fess/crawler/interval/impl/HostIntervalController.java

    import org.codelibs.fess.crawler.util.CrawlingParameterUtil;
    
    /**
     * HostIntervalController is an implementation of {@link org.codelibs.fess.crawler.interval.IntervalController}
     * that controls the interval between requests to the same host.
     * It uses a ConcurrentMap to store the last access time for each host.
     * The delayBeforeProcessing method is overridden to introduce a delay before processing a URL,
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 4.2K bytes
    - Viewed (0)
  7. fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/TarExtractor.java

                                buf.append('\n');
                            } catch (final Exception e) {
                                if (logger.isDebugEnabled()) {
                                    logger.debug("Exception in an internal extractor.", e);
                                }
                            }
                        }
                    }
                }
            } catch (final MaxLengthExceededException e) {
                throw e;
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 5K bytes
    - Viewed (0)
  8. fess-crawler/src/main/java/org/codelibs/fess/crawler/interval/impl/AbstractIntervalController.java

     * either express or implied. See the License for the specific language
     * governing permissions and limitations under the License.
     */
    package org.codelibs.fess.crawler.interval.impl;
    
    import org.codelibs.fess.crawler.exception.CrawlerSystemException;
    import org.codelibs.fess.crawler.interval.IntervalController;
    
    /**
     * An abstract base class for implementing {@link IntervalController}.
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 4.5K bytes
    - Viewed (0)
  9. README.md

    - **Flexible Configuration**: XML-based dependency injection with LastaFlute DI
    - **Extensible Architecture**: Plugin system for custom extractors, transformers, and clients
    - **Rate Limiting**: Politeness policies and interval controllers
    - **URL Filtering**: Regex-based inclusion/exclusion patterns
    - **Data Persistence**: Multiple backend options including OpenSearch integration
    
    ## Technology Stack
    
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Aug 31 05:32:52 UTC 2025
    - 15.3K bytes
    - Viewed (0)
  10. fess-crawler/src/main/java/org/codelibs/fess/crawler/interval/impl/DefaultIntervalController.java

     * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
     * either express or implied. See the License for the specific language
     * governing permissions and limitations under the License.
     */
    package org.codelibs.fess.crawler.interval.impl;
    
    import java.util.Map;
    
    import org.codelibs.core.lang.ThreadUtil;
    
    /**
     * Default implementation of the IntervalController.
     * This class provides a default way to manage delays between crawler operations.
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 3.4K bytes
    - Viewed (0)
Back to top