svn commit: r1023340 - /mahout/trunk/core/src/main/java/org/apache/mahout/clustering/kmeans/RandomSeedGenerator.java

[jeastman]

Author: jeastman
Date: Sat Oct 16 17:47:54 2010
New Revision: 1023340

URL: http://svn.apache.org/viewvc?rev=1023340&view=rev
Log:
CHD3 adds a _SUCCESS file to the vectors directory and the RandomSeedGenerator 
was trying to process it as a vector file. All tests run, including 
build-reuters.sh on CHD3

Modified:
    
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/kmeans/RandomSeedGenerator.java

Modified: 
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/kmeans/RandomSeedGenerator.java
URL: 
http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/clustering/kmeans/RandomSeedGenerator.java?rev=1023340&r1=1023339&r2=1023340&view=diff
==============================================================================
--- 
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/kmeans/RandomSeedGenerator.java
 (original)
+++ 
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/kmeans/RandomSeedGenerator.java
 Sat Oct 16 17:47:54 2010
@@ -78,8 +78,8 @@ public final class RandomSeedGenerator {
       int nextClusterId = 0;
       
       for (FileStatus fileStatus : inputFiles) {
-        if (fileStatus.isDir()) {
-          continue; // select only the top level files
+        if (fileStatus.isDir() || 
fileStatus.getPath().getName().startsWith("_")) {
+          continue; // select only the top level files that do not begin with 
"_" (Cloudera CHD3 adds _SUCCESS file)
         }
         SequenceFile.Reader reader = new SequenceFile.Reader(fs, 
fileStatus.getPath(), conf);
         Writable key = 
reader.getKeyClass().asSubclass(Writable.class).newInstance();