Author: jnioche
Date: Tue Aug 10 15:22:00 2010
New Revision: 984082
URL: http://svn.apache.org/viewvc?rev=984082&view=rev
Log:
NUTCH-878 ScoringFilters should not override the injected score
Modified:
nutch/trunk/src/java/org/apache/nutch/crawl/InjectorJob.java
nutch/trunk/src/plugin/scoring-link/src/java/org/apache/nutch/scoring/link/LinkAnalysisScoringFilter.java
nutch/trunk/src/plugin/scoring-opic/src/java/org/apache/nutch/scoring/opic/OPICScoringFilter.java
Modified: nutch/trunk/src/java/org/apache/nutch/crawl/InjectorJob.java
URL:
http://svn.apache.org/viewvc/nutch/trunk/src/java/org/apache/nutch/crawl/InjectorJob.java?rev=984082&r1=984081&r2=984082&view=diff
==============================================================================
--- nutch/trunk/src/java/org/apache/nutch/crawl/InjectorJob.java (original)
+++ nutch/trunk/src/java/org/apache/nutch/crawl/InjectorJob.java Tue Aug 10
15:22:00 2010
@@ -152,20 +152,18 @@ public class InjectorJob extends GoraMap
row.putToMetadata(new Utf8(keymd),
ByteBuffer.wrap(valuemd.getBytes()));
}
-
if (customScore != -1)
- row.setScore(customScore);
- else {
- row.setScore(scoreInjected);
- try {
- scfilters.injectedScore(url, row);
- } catch (ScoringFilterException e) {
- if (LOG.isWarnEnabled()) {
- LOG.warn("Cannot filter injected score for url " + url
- + ", using default (" + e.getMessage() + ")");
- }
- row.setScore(scoreInjected);
- }
+ row.setScore(customScore);
+ else
+ row.setScore(scoreInjected);
+
+ try {
+ scfilters.injectedScore(url, row);
+ } catch (ScoringFilterException e) {
+ if (LOG.isWarnEnabled()) {
+ LOG.warn("Cannot filter injected score for url " + url
+ + ", using default (" + e.getMessage() + ")");
+ }
}
Mark.INJECT_MARK.putMark(row, YES_STRING);
Modified:
nutch/trunk/src/plugin/scoring-link/src/java/org/apache/nutch/scoring/link/LinkAnalysisScoringFilter.java
URL:
http://svn.apache.org/viewvc/nutch/trunk/src/plugin/scoring-link/src/java/org/apache/nutch/scoring/link/LinkAnalysisScoringFilter.java?rev=984082&r1=984081&r2=984082&view=diff
==============================================================================
---
nutch/trunk/src/plugin/scoring-link/src/java/org/apache/nutch/scoring/link/LinkAnalysisScoringFilter.java
(original)
+++
nutch/trunk/src/plugin/scoring-link/src/java/org/apache/nutch/scoring/link/LinkAnalysisScoringFilter.java
Tue Aug 10 15:22:00 2010
@@ -31,7 +31,6 @@ import org.apache.nutch.storage.WebPage;
public class LinkAnalysisScoringFilter implements ScoringFilter {
private Configuration conf;
- private float scoreInjected = 0.001f;
private float normalizedScore = 1.00f;
private final static Set<WebPage.Field> FIELDS = new
HashSet<WebPage.Field>();
@@ -51,7 +50,6 @@ public class LinkAnalysisScoringFilter i
public void setConf(Configuration conf) {
this.conf = conf;
normalizedScore = conf.getFloat("link.analyze.normalize.score",
1.00f);
- scoreInjected = conf.getFloat("link.analyze.injected.score",
1.00f);
}
@Override
@@ -62,7 +60,6 @@ public class LinkAnalysisScoringFilter i
@Override
public void injectedScore(String url, WebPage page)
throws ScoringFilterException {
- page.setScore(scoreInjected);
}
@Override
Modified:
nutch/trunk/src/plugin/scoring-opic/src/java/org/apache/nutch/scoring/opic/OPICScoringFilter.java
URL:
http://svn.apache.org/viewvc/nutch/trunk/src/plugin/scoring-opic/src/java/org/apache/nutch/scoring/opic/OPICScoringFilter.java?rev=984082&r1=984081&r2=984082&view=diff
==============================================================================
---
nutch/trunk/src/plugin/scoring-opic/src/java/org/apache/nutch/scoring/opic/OPICScoringFilter.java
(original)
+++
nutch/trunk/src/plugin/scoring-opic/src/java/org/apache/nutch/scoring/opic/OPICScoringFilter.java
Tue Aug 10 15:22:00 2010
@@ -61,7 +61,6 @@ public class OPICScoringFilter implement
}
private Configuration conf;
- private float scoreInjected;
private float scorePower;
private float internalScoreFactor;
private float externalScoreFactor;
@@ -74,19 +73,17 @@ public class OPICScoringFilter implement
public void setConf(Configuration conf) {
this.conf = conf;
- scoreInjected = conf.getFloat("db.score.injected", 1.0f);
scorePower = conf.getFloat("indexer.score.power", 0.5f);
internalScoreFactor = conf.getFloat("db.score.link.internal", 1.0f);
externalScoreFactor = conf.getFloat("db.score.link.external", 1.0f);
countFiltered = conf.getBoolean("db.score.count.filtered", false);
}
- /** Set to the value defined in config, 1.0f by default. */
@Override
public void injectedScore(String url, WebPage row)
throws ScoringFilterException {
- row.setScore(scoreInjected);
- row.putToMetadata(CASH_KEY, ByteBuffer.wrap(Bytes.toBytes(scoreInjected)));
+ float score = row.getScore();
+ row.putToMetadata(CASH_KEY, ByteBuffer.wrap(Bytes.toBytes(score)));
}
/** Set to 0.0f (unknown value) - inlink contributions will bring it to