Author: snagel
Date: Sun Oct 5 20:35:41 2014
New Revision: 1629539
URL: http://svn.apache.org/r1629539
Log:
NUTCH-1867 CrawlDbReader: use setFloat to pass min score
Modified:
nutch/trunk/CHANGES.txt
nutch/trunk/src/java/org/apache/nutch/crawl/CrawlDbReader.java
Modified: nutch/trunk/CHANGES.txt
URL:
http://svn.apache.org/viewvc/nutch/trunk/CHANGES.txt?rev=1629539&r1=1629538&r2=1629539&view=diff
==============================================================================
--- nutch/trunk/CHANGES.txt (original)
+++ nutch/trunk/CHANGES.txt Sun Oct 5 20:35:41 2014
@@ -2,6 +2,8 @@ Nutch Change Log
Nutch Current Development 1.10-SNAPSHOT
+* NUTCH-1867 CrawlDbReader: use setFloat to pass min score (lewismc, snagel)
+
* NUTCH-1826, NUTCH-1864 indexchecker fails if solr.server.url not configured
(lewismc, snagel)
* NUTCH-1866 ant eclipse target should not delete runtime (nimafl vai lewismc)
Modified: nutch/trunk/src/java/org/apache/nutch/crawl/CrawlDbReader.java
URL:
http://svn.apache.org/viewvc/nutch/trunk/src/java/org/apache/nutch/crawl/CrawlDbReader.java?rev=1629539&r1=1629538&r2=1629539&view=diff
==============================================================================
--- nutch/trunk/src/java/org/apache/nutch/crawl/CrawlDbReader.java (original)
+++ nutch/trunk/src/java/org/apache/nutch/crawl/CrawlDbReader.java Sun Oct 5
20:35:41 2014
@@ -264,10 +264,7 @@ public class CrawlDbReader implements Cl
private float min = 0.0f;
public void configure(JobConf job) {
- long lmin = job.getLong("db.reader.topn.min", 0);
- if (lmin != 0) {
- min = (float)lmin / 1000000.0f;
- }
+ min = job.getFloat("db.reader.topn.min", 0.0f);
}
public void close() {}
public void map(Text key, CrawlDatum value, OutputCollector<FloatWritable,
Text> output, Reporter reporter)
@@ -509,8 +506,7 @@ public class CrawlDbReader implements Cl
job.setOutputKeyClass(FloatWritable.class);
job.setOutputValueClass(Text.class);
- // XXX hmmm, no setFloat() in the API ... :(
- job.setLong("db.reader.topn.min", Math.round(1000000.0 * min));
+ job.setFloat("db.reader.topn.min", min);
JobClient.runJob(job);
if (LOG.isInfoEnabled()) {