Author: srowen
Date: Mon Nov 28 12:23:05 2011
New Revision: 1207102
URL: http://svn.apache.org/viewvc?rev=1207102&view=rev
Log:
MAHOUT-871 ignore irrelevant files like _SUCCESS
Modified:
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/lda/LDADriver.java
Modified:
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/lda/LDADriver.java
URL:
http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/clustering/lda/LDADriver.java?rev=1207102&r1=1207101&r2=1207102&view=diff
==============================================================================
---
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/lda/LDADriver.java
(original)
+++
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/lda/LDADriver.java
Mon Nov 28 12:23:05 2011
@@ -40,6 +40,7 @@ import org.apache.mahout.common.IntPairW
import org.apache.mahout.common.Pair;
import org.apache.mahout.common.RandomUtils;
import org.apache.mahout.common.commandline.DefaultOptionCreator;
+import org.apache.mahout.common.iterator.sequencefile.PathFilters;
import org.apache.mahout.common.iterator.sequencefile.PathType;
import org.apache.mahout.common.iterator.sequencefile.SequenceFileDirIterable;
import
org.apache.mahout.common.iterator.sequencefile.SequenceFileDirValueIterator;
@@ -199,7 +200,12 @@ public final class LDADriver extends Abs
*/
private int determineNumberOfWordsFromFirstVector() throws IOException {
SequenceFileDirValueIterator<VectorWritable> it =
- new SequenceFileDirValueIterator<VectorWritable>(getInputPath(),
PathType.LIST, null, null, true, getConf());
+ new SequenceFileDirValueIterator<VectorWritable>(getInputPath(),
+ PathType.LIST,
+
PathFilters.logsCRCFilter(),
+ null,
+ true,
+ getConf());
try {
while (it.hasNext()) {
VectorWritable v = it.next();