You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by to...@apache.org on 2013/02/20 16:08:01 UTC

svn commit: r1448210 - in /lucene/dev/branches/branch_4x: ./ dev-tools/ lucene/ lucene/analysis/ lucene/analysis/icu/src/java/org/apache/lucene/collation/ lucene/backwards/ lucene/benchmark/ lucene/classification/ lucene/classification/src/java/org/apa...

Author: tommaso
Date: Wed Feb 20 15:07:59 2013
New Revision: 1448210

URL: http://svn.apache.org/r1448210
Log:
LUCENE-4782 - backported fix to branch_4x

Modified:
    lucene/dev/branches/branch_4x/   (props changed)
    lucene/dev/branches/branch_4x/dev-tools/   (props changed)
    lucene/dev/branches/branch_4x/lucene/   (props changed)
    lucene/dev/branches/branch_4x/lucene/BUILD.txt   (props changed)
    lucene/dev/branches/branch_4x/lucene/CHANGES.txt   (props changed)
    lucene/dev/branches/branch_4x/lucene/JRE_VERSION_MIGRATION.txt   (props changed)
    lucene/dev/branches/branch_4x/lucene/LICENSE.txt   (props changed)
    lucene/dev/branches/branch_4x/lucene/MIGRATE.txt   (props changed)
    lucene/dev/branches/branch_4x/lucene/NOTICE.txt   (props changed)
    lucene/dev/branches/branch_4x/lucene/README.txt   (props changed)
    lucene/dev/branches/branch_4x/lucene/SYSTEM_REQUIREMENTS.txt   (props changed)
    lucene/dev/branches/branch_4x/lucene/analysis/   (props changed)
    lucene/dev/branches/branch_4x/lucene/analysis/icu/src/java/org/apache/lucene/collation/ICUCollationKeyFilterFactory.java   (props changed)
    lucene/dev/branches/branch_4x/lucene/backwards/   (props changed)
    lucene/dev/branches/branch_4x/lucene/benchmark/   (props changed)
    lucene/dev/branches/branch_4x/lucene/build.xml   (props changed)
    lucene/dev/branches/branch_4x/lucene/classification/   (props changed)
    lucene/dev/branches/branch_4x/lucene/classification/src/java/org/apache/lucene/classification/SimpleNaiveBayesClassifier.java
    lucene/dev/branches/branch_4x/lucene/codecs/   (props changed)
    lucene/dev/branches/branch_4x/lucene/common-build.xml   (props changed)
    lucene/dev/branches/branch_4x/lucene/core/   (props changed)
    lucene/dev/branches/branch_4x/lucene/core/src/test/org/apache/lucene/index/TestBackwardsCompatibility.java   (props changed)
    lucene/dev/branches/branch_4x/lucene/core/src/test/org/apache/lucene/index/index.40.cfs.zip   (props changed)
    lucene/dev/branches/branch_4x/lucene/core/src/test/org/apache/lucene/index/index.40.nocfs.zip   (props changed)
    lucene/dev/branches/branch_4x/lucene/core/src/test/org/apache/lucene/index/index.40.optimized.cfs.zip   (props changed)
    lucene/dev/branches/branch_4x/lucene/core/src/test/org/apache/lucene/index/index.40.optimized.nocfs.zip   (props changed)
    lucene/dev/branches/branch_4x/lucene/core/src/test/org/apache/lucene/search/TestSort.java   (props changed)
    lucene/dev/branches/branch_4x/lucene/core/src/test/org/apache/lucene/search/TestSortDocValues.java   (props changed)
    lucene/dev/branches/branch_4x/lucene/core/src/test/org/apache/lucene/search/TestSortRandom.java   (props changed)
    lucene/dev/branches/branch_4x/lucene/core/src/test/org/apache/lucene/search/TestTopFieldCollector.java   (props changed)
    lucene/dev/branches/branch_4x/lucene/core/src/test/org/apache/lucene/search/TestTotalHitCountCollector.java   (props changed)
    lucene/dev/branches/branch_4x/lucene/demo/   (props changed)
    lucene/dev/branches/branch_4x/lucene/facet/   (props changed)
    lucene/dev/branches/branch_4x/lucene/grouping/   (props changed)
    lucene/dev/branches/branch_4x/lucene/highlighter/   (props changed)
    lucene/dev/branches/branch_4x/lucene/ivy-settings.xml   (props changed)
    lucene/dev/branches/branch_4x/lucene/join/   (props changed)
    lucene/dev/branches/branch_4x/lucene/licenses/   (props changed)
    lucene/dev/branches/branch_4x/lucene/memory/   (props changed)
    lucene/dev/branches/branch_4x/lucene/misc/   (props changed)
    lucene/dev/branches/branch_4x/lucene/module-build.xml   (props changed)
    lucene/dev/branches/branch_4x/lucene/queries/   (props changed)
    lucene/dev/branches/branch_4x/lucene/queryparser/   (props changed)
    lucene/dev/branches/branch_4x/lucene/sandbox/   (props changed)
    lucene/dev/branches/branch_4x/lucene/site/   (props changed)
    lucene/dev/branches/branch_4x/lucene/spatial/   (props changed)
    lucene/dev/branches/branch_4x/lucene/suggest/   (props changed)
    lucene/dev/branches/branch_4x/lucene/test-framework/   (props changed)
    lucene/dev/branches/branch_4x/lucene/tools/   (props changed)
    lucene/dev/branches/branch_4x/solr/   (props changed)
    lucene/dev/branches/branch_4x/solr/CHANGES.txt   (props changed)
    lucene/dev/branches/branch_4x/solr/LICENSE.txt   (props changed)
    lucene/dev/branches/branch_4x/solr/NOTICE.txt   (props changed)
    lucene/dev/branches/branch_4x/solr/README.txt   (props changed)
    lucene/dev/branches/branch_4x/solr/SYSTEM_REQUIREMENTS.txt   (props changed)
    lucene/dev/branches/branch_4x/solr/build.xml   (props changed)
    lucene/dev/branches/branch_4x/solr/cloud-dev/   (props changed)
    lucene/dev/branches/branch_4x/solr/common-build.xml   (props changed)
    lucene/dev/branches/branch_4x/solr/contrib/   (props changed)
    lucene/dev/branches/branch_4x/solr/core/   (props changed)
    lucene/dev/branches/branch_4x/solr/example/   (props changed)
    lucene/dev/branches/branch_4x/solr/licenses/   (props changed)
    lucene/dev/branches/branch_4x/solr/licenses/httpclient-LICENSE-ASL.txt   (props changed)
    lucene/dev/branches/branch_4x/solr/licenses/httpclient-NOTICE.txt   (props changed)
    lucene/dev/branches/branch_4x/solr/licenses/httpcore-LICENSE-ASL.txt   (props changed)
    lucene/dev/branches/branch_4x/solr/licenses/httpcore-NOTICE.txt   (props changed)
    lucene/dev/branches/branch_4x/solr/licenses/httpmime-LICENSE-ASL.txt   (props changed)
    lucene/dev/branches/branch_4x/solr/licenses/httpmime-NOTICE.txt   (props changed)
    lucene/dev/branches/branch_4x/solr/scripts/   (props changed)
    lucene/dev/branches/branch_4x/solr/site/   (props changed)
    lucene/dev/branches/branch_4x/solr/solrj/   (props changed)
    lucene/dev/branches/branch_4x/solr/test-framework/   (props changed)
    lucene/dev/branches/branch_4x/solr/testlogging.properties   (props changed)
    lucene/dev/branches/branch_4x/solr/webapp/   (props changed)

Modified: lucene/dev/branches/branch_4x/lucene/classification/src/java/org/apache/lucene/classification/SimpleNaiveBayesClassifier.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/classification/src/java/org/apache/lucene/classification/SimpleNaiveBayesClassifier.java?rev=1448210&r1=1448209&r2=1448210&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/classification/src/java/org/apache/lucene/classification/SimpleNaiveBayesClassifier.java (original)
+++ lucene/dev/branches/branch_4x/lucene/classification/src/java/org/apache/lucene/classification/SimpleNaiveBayesClassifier.java Wed Feb 20 15:07:59 2013
@@ -29,6 +29,7 @@ import org.apache.lucene.search.BooleanQ
 import org.apache.lucene.search.IndexSearcher;
 import org.apache.lucene.search.TermQuery;
 import org.apache.lucene.search.TotalHitCountCollector;
+import org.apache.lucene.search.WildcardQuery;
 import org.apache.lucene.util.BytesRef;
 
 import java.io.IOException;
@@ -69,7 +70,18 @@ public class SimpleNaiveBayesClassifier 
     this.textFieldName = textFieldName;
     this.classFieldName = classFieldName;
     this.analyzer = analyzer;
-    this.docsWithClassSize = MultiFields.getTerms(this.atomicReader, this.classFieldName).getDocCount();
+    this.docsWithClassSize = countDocsWithClass();
+  }
+
+  private int countDocsWithClass() throws IOException {
+    int docCount = MultiFields.getTerms(this.atomicReader, this.classFieldName).getDocCount();
+    if (docCount == -1) { // in case codec doesn't support getDocCount
+      TotalHitCountCollector totalHitCountCollector = new TotalHitCountCollector();
+      indexSearcher.search(new WildcardQuery(new Term(classFieldName, String.valueOf(WildcardQuery.WILDCARD_STRING))),
+          totalHitCountCollector);
+      docCount = totalHitCountCollector.getTotalHits();
+    }
+    return docCount;
   }
 
   private String[] tokenizeDoc(String doc) throws IOException {