* 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>

        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) {

        this.ruleManager = ruleManager;
    }

    /**
     * Returns the interval controller.
     * @return The IntervalController.
     */
    public IntervalController getIntervalController() {
        return intervalController;
    }

    /**
     * Sets the interval controller.
     * @param intervalController The IntervalController.
     */

        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.
     */

                            buf.append('\n');
                        } catch (final Exception e) {
                            if (logger.isDebugEnabled()) {
                                logger.debug("Exception in an internal extractor.", e);
                            }
                        }
                    }
                }
            }
        } catch (final MaxLengthExceededException e) {
            throw e;

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,

                            buf.append('\n');
                        } catch (final Exception e) {
                            if (logger.isDebugEnabled()) {
                                logger.debug("Exception in an internal extractor.", e);
                            }
                        }
                    }
                }
            }
        } catch (final MaxLengthExceededException e) {
            throw e;

 * 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}.

- **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

<components namespace="fessCrawler">
    <include path="crawler/container.xml"/>
    <include path="crawler/client.xml"/>
    <include path="crawler/rule.xml"/>
    <include path="crawler/filter.xml"/>
    <include path="crawler/interval.xml"/>
    <include path="crawler/extractor.xml"/>
    <include path="crawler/mimetype.xml"/>
    <include path="crawler/encoding.xml"/>
    <include path="crawler/urlconverter.xml"/>
    <include path="crawler/log.xml"/>