You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@nutch.apache.org by ab...@apache.org on 2009/11/25 18:10:25 UTC
svn commit: r884198 - in /lucene/nutch/trunk: CHANGES.txt
src/java/org/apache/nutch/crawl/AbstractFetchSchedule.java
Author: ab
Date: Wed Nov 25 17:10:25 2009
New Revision: 884198
URL: http://svn.apache.org/viewvc?rev=884198&view=rev
Log:
NUTCH-773 Some minor bugs in AbstractFetchSchedule.
Modified:
lucene/nutch/trunk/CHANGES.txt
lucene/nutch/trunk/src/java/org/apache/nutch/crawl/AbstractFetchSchedule.java
Modified: lucene/nutch/trunk/CHANGES.txt
URL: http://svn.apache.org/viewvc/lucene/nutch/trunk/CHANGES.txt?rev=884198&r1=884197&r2=884198&view=diff
==============================================================================
--- lucene/nutch/trunk/CHANGES.txt (original)
+++ lucene/nutch/trunk/CHANGES.txt Wed Nov 25 17:10:25 2009
@@ -2,6 +2,8 @@
Unreleased Changes
+* NUTCH-773 - Some minor bugs in AbstractFetchSchedule (Reinhard Schwab)
+
* NUTCH-765 - Allow Crawl class to call Either Solr or Lucene Indexer (kubes)
* NUTCH-735 - crawl-tool.xml must be read before nutch-site.xml when
Modified: lucene/nutch/trunk/src/java/org/apache/nutch/crawl/AbstractFetchSchedule.java
URL: http://svn.apache.org/viewvc/lucene/nutch/trunk/src/java/org/apache/nutch/crawl/AbstractFetchSchedule.java?rev=884198&r1=884197&r2=884198&view=diff
==============================================================================
--- lucene/nutch/trunk/src/java/org/apache/nutch/crawl/AbstractFetchSchedule.java (original)
+++ lucene/nutch/trunk/src/java/org/apache/nutch/crawl/AbstractFetchSchedule.java Wed Nov 25 17:10:25 2009
@@ -125,7 +125,7 @@
*/
public CrawlDatum setPageRetrySchedule(Text url, CrawlDatum datum,
long prevFetchTime, long prevModifiedTime, long fetchTime) {
- datum.setFetchTime(fetchTime + (long)SECONDS_PER_DAY);
+ datum.setFetchTime(fetchTime + (long)SECONDS_PER_DAY*1000);
datum.setRetriesSinceFetch(datum.getRetriesSinceFetch() + 1);
return datum;
}
@@ -159,7 +159,9 @@
// pages with too long fetchInterval are adjusted so that they fit within
// maximum fetchInterval (segment retention period).
if (datum.getFetchTime() - curTime > (long) maxInterval * 1000) {
- datum.setFetchInterval(maxInterval * 0.9f);
+ if (datum.getFetchInterval() > maxInterval) {
+ datum.setFetchInterval(maxInterval * 0.9f);
+ }
datum.setFetchTime(curTime);
}
if (datum.getFetchTime() > curTime) {