Author: lewismc
Date: Tue Jun 23 22:32:03 2015
New Revision: 1687145
URL: http://svn.apache.org/r1687145
Log:
NUTCH-2045 index-basic incorrect assignment of next fetch time
(page.getFetchTime()) as page fetch time
Modified:
nutch/branches/2.x/CHANGES.txt
nutch/branches/2.x/src/plugin/index-basic/src/java/org/apache/nutch/indexer/basic/BasicIndexingFilter.java
Modified: nutch/branches/2.x/CHANGES.txt
URL:
http://svn.apache.org/viewvc/nutch/branches/2.x/CHANGES.txt?rev=1687145&r1=1687144&r2=1687145&view=diff
==============================================================================
--- nutch/branches/2.x/CHANGES.txt (original)
+++ nutch/branches/2.x/CHANGES.txt Tue Jun 23 22:32:03 2015
@@ -2,6 +2,8 @@ Nutch Change Log
Current Development 2.4-SNAPSHOT
+* NUTCH-2045 index-basic incorrect assignment of next fetch time
(page.getFetchTime()) as page fetch time (lewismc)
+
* NUTCH-2019 ClassPathException sending topN argument for /job/create using
Nutch 2.x RESTApi (Alex Koh, lewismc)
* NUTCH-1923 Nutch + Cassandra Docker (Mohamed Meabed via lewismc)
Modified:
nutch/branches/2.x/src/plugin/index-basic/src/java/org/apache/nutch/indexer/basic/BasicIndexingFilter.java
URL:
http://svn.apache.org/viewvc/nutch/branches/2.x/src/plugin/index-basic/src/java/org/apache/nutch/indexer/basic/BasicIndexingFilter.java?rev=1687145&r1=1687144&r2=1687145&view=diff
==============================================================================
---
nutch/branches/2.x/src/plugin/index-basic/src/java/org/apache/nutch/indexer/basic/BasicIndexingFilter.java
(original)
+++
nutch/branches/2.x/src/plugin/index-basic/src/java/org/apache/nutch/indexer/basic/BasicIndexingFilter.java
Tue Jun 23 22:32:03 2015
@@ -125,10 +125,13 @@ public class BasicIndexingFilter impleme
}
// add timestamp when fetched, for deduplication
- String tstamp = DateUtil.getThreadLocalDateFormat().format(
- new Date(page.getFetchTime()));
+ String tstamp = null;
+ if(page.getPrevFetchTime() != null) {
+ tstamp = DateUtil.getThreadLocalDateFormat().format(new
Date(page.getPrevFetchTime()));
+ } else {
+ tstamp = DateUtil.getThreadLocalDateFormat().format(new
Date(page.getFetchTime()));
+ }
doc.add("tstamp", tstamp);
-
return doc;
}