[Archive-access-cvs] SF.net SVN: archive-access:[2657] trunk/archive-access/projects/nutchwax/ archive/src/plugin/scoring-nutchwax/src/java/org/archive/nutchwax/scoring/ PageRankScoringFilter.java

[<bi...@us...>]

Revision: 2657
          http://archive-access.svn.sourceforge.net/archive-access/?rev=2657&view=rev
Author:   binzino
Date:     2008-12-10 05:01:14 +0000 (Wed, 10 Dec 2008)

Log Message:
-----------
Removed use of floor() in calculating the book multiplier.

Modified Paths:
--------------
    trunk/archive-access/projects/nutchwax/archive/src/plugin/scoring-nutchwax/src/java/org/archive/nutchwax/scoring/PageRankScoringFilter.java

Modified: trunk/archive-access/projects/nutchwax/archive/src/plugin/scoring-nutchwax/src/java/org/archive/nutchwax/scoring/PageRankScoringFilter.java
===================================================================
--- trunk/archive-access/projects/nutchwax/archive/src/plugin/scoring-nutchwax/src/java/org/archive/nutchwax/scoring/PageRankScoringFilter.java	2008-12-10 04:59:10 UTC (rev 2656)
+++ trunk/archive-access/projects/nutchwax/archive/src/plugin/scoring-nutchwax/src/java/org/archive/nutchwax/scoring/PageRankScoringFilter.java	2008-12-10 05:01:14 UTC (rev 2657)
@@ -56,17 +56,14 @@
  * </p><p>
  * Applies a simple log10 multipler to the document score based on the
  * base-10 log value of the number of inlinks.  For example, a page with
- * 13,032 inlinks will have a score/boost of 5.  The actual formula is
+ * 13,032 inlinks will have a score/boost of 5.115.  The actual formula is
  * </p>
  * <code>
- *  initialScore *= ( floor( log10( # inlinks ) ) + 1 )
+ *  newScore = initialScore * ( log10( # inlinks ) + 1 )
  * </code>
  * <p>
- * We use floor() to get an integer value from the log10() function
- * since we're only interested in order of magnitude.  We then add 1
- * so that a page with &lt; 10 inlins will have a multipler of 1, and
- * thus stay the same, 10-100 gets a multipler of 2, 100-1000 is 3, and
- * so forth.
+ * We add the extra 1 for pages with only 1 inlink since log10(1)=0 and we
+ * don't want a 0 multiplier.
  * </p>
  * <p>
  * The number of inlinks for a page is not taken from the <code>inlinks</code>
@@ -115,8 +112,6 @@
   public void setConf( Configuration conf )
   {
     this.conf = conf;
-
-    //this.ranks = getPageRanks( conf );
   }
   
   public void injectedScore(Text url, CrawlDatum datum) 
@@ -181,7 +176,7 @@
         return initScore;
       }
 
-    String keyParts[] = key.toString( ).split( "\\s+" );
+    String keyParts[] = key.toString( ).split( "\\s+", 2 );
 
     if ( keyParts.length != 2 )
       {
@@ -201,7 +196,7 @@
         return initScore;
       }
 
-    float newScore = initScore * (float) ( Math.floor( Math.log( rank ) ) + 1 );
+    float newScore = initScore * (float) ( Math.log( rank ) + 1 );
 
     LOG.info( "PageRankScoringFilter: initScore = " + newScore + " ; key = " + key );
 


This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.