From 52bad48399df2971af03278f33ac550f760cc55d Mon Sep 17 00:00:00 2001
From: Egor Potemkin <epotyom@amazon.com>
Date: Mon, 10 Feb 2025 23:00:51 +0000
Subject: [PATCH] Addressed PR comments

---
 README.md                      | 12 ++++++++++++
 src/main/perf/SearchTask.java  | 15 +++++++++++++--
 src/main/perf/TestContext.java | 17 +++++++++++++++++
 3 files changed, 42 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index 50ddb42b5..f75d04cdc 100644
--- a/README.md
+++ b/README.md
@@ -179,3 +179,15 @@ To test vector search with [Cohere/wikipedia-22-12-en-embeddings](https://huggin
 in the format that luceneutil vector search can understand. Instead of `10000000` increase the number of documents to `100000000` if you want to run vector search on 10M documents.
 2. In `src/python/knnPerTest.py` uncomment lines that define doc and query vectors for cohere dataset.
 3. run `src/python/knnPerTest.py` 
+
+# Running the facets benchmark
+
+## Compare facet implementations
+
+There are currently two facets implementations - one that first collects document IDs and then computes facets in a separate phase, and a new implementation that computes facets during collection.
+
+To compare performance for the two implementations run
+
+```
+python src/python/localrunFacets.py -source facetsWikimediumAll
+```
\ No newline at end of file
diff --git a/src/main/perf/SearchTask.java b/src/main/perf/SearchTask.java
index 68beef15f..741a65d01 100644
--- a/src/main/perf/SearchTask.java
+++ b/src/main/perf/SearchTask.java
@@ -19,7 +19,12 @@
 
 import org.apache.lucene.analysis.TokenStream;
 import org.apache.lucene.document.Document;
-import org.apache.lucene.facet.*;
+import org.apache.lucene.facet.FacetResult;
+import org.apache.lucene.facet.Facets;
+import org.apache.lucene.facet.FacetsCollector;
+import org.apache.lucene.facet.FacetsCollectorManager;
+import org.apache.lucene.facet.FacetsConfig;
+import org.apache.lucene.facet.LabelAndValue;
 import org.apache.lucene.facet.range.LongRange;
 import org.apache.lucene.facet.range.LongRangeFacetCounts;
 import org.apache.lucene.facet.sortedset.SortedSetDocValuesFacetCounts;
@@ -73,7 +78,13 @@
 
 import java.io.IOException;
 import java.io.PrintStream;
-import java.util.*;
+import java.util.ArrayList;
+import java.util.Arrays;
+import java.util.Collection;
+import java.util.HashMap;
+import java.util.List;
+import java.util.Locale;
+import java.util.Map;
 
 final class SearchTask extends Task {
   private final String category;
diff --git a/src/main/perf/TestContext.java b/src/main/perf/TestContext.java
index 8c21ba1e1..92933afb8 100644
--- a/src/main/perf/TestContext.java
+++ b/src/main/perf/TestContext.java
@@ -1,5 +1,22 @@
 package perf;
 
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements.  See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License.  You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
 import java.util.Objects;
 
 /**