(1);
diff --git a/lucene/facet/src/java/org/apache/lucene/facet/taxonomy/writercache/lru/LruTaxonomyWriterCache.java b/lucene/facet/src/java/org/apache/lucene/facet/taxonomy/writercache/lru/LruTaxonomyWriterCache.java
index ecd05555432..af34d42dbc3 100644
--- a/lucene/facet/src/java/org/apache/lucene/facet/taxonomy/writercache/lru/LruTaxonomyWriterCache.java
+++ b/lucene/facet/src/java/org/apache/lucene/facet/taxonomy/writercache/lru/LruTaxonomyWriterCache.java
@@ -27,6 +27,11 @@ import org.apache.lucene.facet.taxonomy.writercache.TaxonomyWriterCache;
*/
public class LruTaxonomyWriterCache implements TaxonomyWriterCache {
+ /**
+ * Determines cache type.
+ * For guaranteed correctness - not relying on no-collisions in the hash
+ * function, LRU_STRING should be used.
+ */
public enum LRUType { LRU_HASHED, LRU_STRING }
private NameIntCacheLRU cache;
diff --git a/lucene/sandbox/src/java/org/apache/lucene/sandbox/queries/DuplicateFilter.java b/lucene/sandbox/src/java/org/apache/lucene/sandbox/queries/DuplicateFilter.java
index a9326166cdb..81384d66138 100644
--- a/lucene/sandbox/src/java/org/apache/lucene/sandbox/queries/DuplicateFilter.java
+++ b/lucene/sandbox/src/java/org/apache/lucene/sandbox/queries/DuplicateFilter.java
@@ -26,6 +26,15 @@ import org.apache.lucene.util.FixedBitSet;
import java.io.IOException;
+/**
+ * Filter to remove duplicate values from search results.
+ *
+ * WARNING: for this to work correctly, you may have to wrap
+ * your reader as it cannot current deduplicate across different
+ * index segments.
+ *
+ * @see SlowCompositeReaderWrapper
+ */
public class DuplicateFilter extends Filter {
// TODO: make duplicate filter aware of ReaderContext such that we can
// filter duplicates across segments
@@ -45,7 +54,7 @@ public class DuplicateFilter extends Filter {
* for documents that contain the given field and are identified as none-duplicates.
*
* "Fast" processing sets all bits to true then unsets all duplicate docs found for the
- * given field. This approach avoids the need to read TermDocs for terms that are seen
+ * given field. This approach avoids the need to read DocsEnum for terms that are seen
* to have a document frequency of exactly "1" (i.e. no duplicates). While a potentially
* faster approach , the downside is that bitsets produced will include bits set for
* documents that do not actually contain the field given.