X-Git-Url: http://wamblee.org/gitweb/?a=blobdiff_plain;ds=sidebyside;f=crawler%2Fkissweb%2Fsrc%2Fmain%2Fjava%2Forg%2Fwamblee%2Fcrawler%2Fkiss%2Fscheduling%2FCrawlerStatus.java;fp=crawler%2Fkissweb%2Fsrc%2Fmain%2Fjava%2Forg%2Fwamblee%2Fcrawler%2Fkiss%2Fscheduling%2FCrawlerStatus.java;h=065a229487b6d87fded759f7ba5e03fb2da6fba8;hb=62f165891f08ae532b5a794af11d7338a93f9a43;hp=0000000000000000000000000000000000000000;hpb=07cedd3f0730646ea35a7f668b3e1e872a4605d9;p=utils diff --git a/crawler/kissweb/src/main/java/org/wamblee/crawler/kiss/scheduling/CrawlerStatus.java b/crawler/kissweb/src/main/java/org/wamblee/crawler/kiss/scheduling/CrawlerStatus.java new file mode 100644 index 00000000..065a2294 --- /dev/null +++ b/crawler/kissweb/src/main/java/org/wamblee/crawler/kiss/scheduling/CrawlerStatus.java @@ -0,0 +1,193 @@ +/* + * Copyright 2006 the original author or authors. + * + * Licensed under the Apache License, Version 2.0 (the "License"); + * you may not use this file except in compliance with the License. + * You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * 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.wamblee.crawler.kiss.scheduling; + +import java.io.Serializable; +import java.util.Calendar; +import java.util.Date; + +import org.apache.commons.logging.Log; +import org.apache.commons.logging.LogFactory; +import org.wamblee.crawler.kiss.main.Report; + +/** + * This class encapsulates the logic for deciding whether to + * run the crawler. This provides the mechanism to keep the + * scheduler simple (e.g. scheduling every hour) and providing + * more complex logic for determining whether to run the + * crawler. + */ +public class CrawlerStatus implements Serializable { + + private static final Log LOG = LogFactory.getLog(CrawlerStatus.class); + + private CrawlerExecutor _crawler; + private Date _lastExecuted; + private boolean _lastResult; + private Exception _lastException; + private Report _lastReport; + private int _hourMin; + private int _hourMax; + private boolean _mustExecute; + + /** + * Constructs the scheduler. + * The crawler will run if it is triggered in the range between the minimum (included) + * and maximum (included) hour of the day if either + *
aHourMin
+ * @param aHourMax The crawler may only run if hour <= aHourMax
+ */
+ public CrawlerStatus(CrawlerExecutor aCrawler, int aHourMin, int aHourMax) {
+ _crawler = aCrawler;
+ _lastExecuted = new Date();
+ _lastResult = true; // the crawler will automatically run the next day.
+ _lastException = null;
+ _lastReport = null;
+ _hourMin = aHourMin;
+ _hourMax = aHourMax;
+ _mustExecute = false;
+ }
+
+ /**
+ * Determines whether or not the crawler must be run the next time it is triggered.
+ * @param aMustExecute If true then the crawler will run the next time it is triggered
+ * by the scheduler.
+ */
+ public void setMustExecute(boolean aMustExecute) {
+ _mustExecute = aMustExecute;
+ }
+
+ /**
+ * Called by a scheduled job. This determines whether the crawler must be run or
+ * not. This encapsulates the rukes for retrying and scheduling the crawler.
+ * @param aDate Time at which we are executing now.
+ */
+ public void execute(Date aDate) {
+
+ if (mustExecute(aDate)) {
+ LOG.info("Executing crawler at " + aDate);
+ Report report = new Report();
+ try {
+ _crawler.execute(aDate, report);
+ _lastResult = true;
+ _lastException = null;
+ } catch (Exception e) {
+ _lastResult = false;
+ _lastException = e;
+ } finally {
+ _lastExecuted = aDate;
+ _lastReport = report;
+ }
+ }
+ }
+
+ /**
+ * Gets the time the crawler was last executed.
+ * @return Time of last execution.
+ */
+ public Date getLastExecuted() {
+ return _lastExecuted;
+ }
+
+ /**
+ * Gets the result of the last execution.
+ * @return True iff last execution was a success.
+ */
+ public boolean getLastResult() {
+ return _lastResult;
+ }
+
+ /**
+ * Gets the exception thrown by the last execution.
+ * @return null if the last execution was successful or an exception
+ * otherwise.
+ */
+ public Exception getLastException() {
+ return _lastException;
+ }
+
+ /**
+ * Gets the last report from the scheduler.
+ * @return Report.
+ */
+ public Report getLastReport() {
+ return _lastReport;
+ }
+
+ /**
+ * Determines whether or not the crawler must be run.
+ * @param aDate Current time.
+ * @return True iff the crawler must be run.
+ */
+ private boolean mustExecute(Date aDate) {
+ if (_mustExecute) {
+ _mustExecute = false;
+ return true;
+ }
+ if ( _lastExecuted == null ) {
+ return false; // crawler must be started manually at least once after deployment.
+ }
+ Calendar calendar = Calendar.getInstance();
+ calendar.setTime(aDate);
+ int hour = calendar.get(Calendar.HOUR_OF_DAY);
+ if ( hour < _hourMin ) {
+ return false;
+ }
+ if (hour > _hourMax ) {
+ return false;
+ }
+
+ if ( !lastExecutionWasOnSameDay(aDate)) {
+ return true; // First execution of today.
+ }
+ // last execution was on the same day.
+ if ( !_lastResult ) {
+ return true; // last execution of today was unsuccessful, retry.
+ }
+ return false; // already run successfully today.
+ }
+
+ /**
+ * Determines if the last execution was on the same day.
+ * @param aDate Current time.
+ * @return True iff last execution was on the same day.
+ */
+ private boolean lastExecutionWasOnSameDay(Date aDate) {
+ if ( _lastExecuted == null ) {
+ return false;
+ }
+ int curDay = getDayOfYear(aDate);
+ int lastDay = getDayOfYear(_lastExecuted);
+ return curDay == lastDay; // check can be invalid only if scheduling interval is one year,
+ // which is ridiculous.
+ }
+
+ /**
+ * Gets the day of the year
+ * @param aDate Date to compute day for.
+ */
+ private int getDayOfYear(Date aDate) {
+ Calendar calendar = Calendar.getInstance();
+ calendar.setTime(aDate);
+ return calendar.get(Calendar.DAY_OF_YEAR);
+ }
+}