Fixed bglinking.

Author: lintool

docs/regressions/regressions-backgroundlinking18.md

@@ -47,21 +47,21 @@ target/appassembler/bin/SearchCollection \
   -topics tools/topics-and-qrels/topics.backgroundlinking18.txt \
   -topicReader BackgroundLinking \
   -output runs/run.wapo.v2.bm25.topics.backgroundlinking18.txt \
-  -backgroundlinking -backgroundlinking.k 100 -bm25 -hits 100 &
+  -backgroundLinking -backgroundLinking.k 100 -bm25 -hits 100 &
 
 target/appassembler/bin/SearchCollection \
   -index indexes/lucene-index.wapo.v2/ \
   -topics tools/topics-and-qrels/topics.backgroundlinking18.txt \
   -topicReader BackgroundLinking \
   -output runs/run.wapo.v2.bm25+rm3.topics.backgroundlinking18.txt \
-  -backgroundlinking -backgroundlinking.k 100 -bm25 -rm3 -hits 100 &
+  -backgroundLinking -backgroundLinking.k 100 -bm25 -rm3 -hits 100 &
 
 target/appassembler/bin/SearchCollection \
   -index indexes/lucene-index.wapo.v2/ \
   -topics tools/topics-and-qrels/topics.backgroundlinking18.txt \
   -topicReader BackgroundLinking \
   -output runs/run.wapo.v2.bm25+rm3+df.topics.backgroundlinking18.txt \
-  -backgroundlinking -backgroundlinking.datefilter -backgroundlinking.k 100 -bm25 -rm3 -hits 100 &
+  -backgroundLinking -backgroundLinking.dateFilter -backgroundLinking.k 100 -bm25 -rm3 -hits 100 &
 ```
 
 Evaluation can be performed using `trec_eval`:

docs/regressions/regressions-backgroundlinking19.md

@@ -47,21 +47,21 @@ target/appassembler/bin/SearchCollection \
   -topics tools/topics-and-qrels/topics.backgroundlinking19.txt \
   -topicReader BackgroundLinking \
   -output runs/run.wapo.v2.bm25.topics.backgroundlinking19.txt \
-  -backgroundlinking -backgroundlinking.k 100 -bm25 -hits 100 &
+  -backgroundLinking -backgroundLinking.k 100 -bm25 -hits 100 &
 
 target/appassembler/bin/SearchCollection \
   -index indexes/lucene-index.wapo.v2/ \
   -topics tools/topics-and-qrels/topics.backgroundlinking19.txt \
   -topicReader BackgroundLinking \
   -output runs/run.wapo.v2.bm25+rm3.topics.backgroundlinking19.txt \
-  -backgroundlinking -backgroundlinking.k 100 -bm25 -rm3 -hits 100 &
+  -backgroundLinking -backgroundLinking.k 100 -bm25 -rm3 -hits 100 &
 
 target/appassembler/bin/SearchCollection \
   -index indexes/lucene-index.wapo.v2/ \
   -topics tools/topics-and-qrels/topics.backgroundlinking19.txt \
   -topicReader BackgroundLinking \
   -output runs/run.wapo.v2.bm25+rm3+df.topics.backgroundlinking19.txt \
-  -backgroundlinking -backgroundlinking.datefilter -backgroundlinking.k 100 -bm25 -rm3 -hits 100 &
+  -backgroundLinking -backgroundLinking.dateFilter -backgroundLinking.k 100 -bm25 -rm3 -hits 100 &
 ```
 
 Evaluation can be performed using `trec_eval`:

docs/regressions/regressions-backgroundlinking20.md

@@ -47,21 +47,21 @@ target/appassembler/bin/SearchCollection \
   -topics tools/topics-and-qrels/topics.backgroundlinking20.txt \
   -topicReader BackgroundLinking \
   -output runs/run.wapo.v3.bm25.topics.backgroundlinking20.txt \
-  -backgroundlinking -backgroundlinking.k 100 -bm25 -hits 100 &
+  -backgroundLinking -backgroundLinking.k 100 -bm25 -hits 100 &
 
 target/appassembler/bin/SearchCollection \
   -index indexes/lucene-index.wapo.v3/ \
   -topics tools/topics-and-qrels/topics.backgroundlinking20.txt \
   -topicReader BackgroundLinking \
   -output runs/run.wapo.v3.bm25+rm3.topics.backgroundlinking20.txt \
-  -backgroundlinking -backgroundlinking.k 100 -bm25 -rm3 -hits 100 &
+  -backgroundLinking -backgroundLinking.k 100 -bm25 -rm3 -hits 100 &
 
 target/appassembler/bin/SearchCollection \
   -index indexes/lucene-index.wapo.v3/ \
   -topics tools/topics-and-qrels/topics.backgroundlinking20.txt \
   -topicReader BackgroundLinking \
   -output runs/run.wapo.v3.bm25+rm3+df.topics.backgroundlinking20.txt \
-  -backgroundlinking -backgroundlinking.datefilter -backgroundlinking.k 100 -bm25 -rm3 -hits 100 &
+  -backgroundLinking -backgroundLinking.dateFilter -backgroundLinking.k 100 -bm25 -rm3 -hits 100 &
 ```
 
 Evaluation can be performed using `trec_eval`:

src/main/java/io/anserini/rerank/lib/NewsBackgroundLinkingReranker.java

@@ -48,13 +48,18 @@ public class NewsBackgroundLinkingReranker implements Reranker {
   private final Class parser;
 
   public NewsBackgroundLinkingReranker(Analyzer analyzer, Class parser) {
+    assert analyzer != null;
+    assert parser != null;
+
     this.analyzer = analyzer;
     this.parser = parser;
-
   }
 
   @Override
   public ScoredDocs rerank(ScoredDocs docs, RerankerContext context) {
+    assert docs != null;
+    assert context != null;
+
     IndexReader reader = context.getIndexSearcher().getIndexReader();
     String queryDocId = context.getQueryDocId();
     final Map<String, Long> queryTermsMap = convertDocVectorToMap(reader, queryDocId);
@@ -99,12 +104,14 @@ public ScoredDocs rerank(ScoredDocs docs, RerankerContext context) {
     ScoredDocs scoredDocs = new ScoredDocs();
     int resSize = docs.lucene_documents.length - toRemove.size();
     scoredDocs.lucene_documents = new Document[resSize];
+    scoredDocs.docids = new String[resSize];
     scoredDocs.lucene_docids = new int[resSize];
     scoredDocs.scores = new float[resSize];
     int idx = 0;
     for (int i = 0; i < docs.lucene_documents.length; i++) {
       if (!toRemove.contains(i)) {
         scoredDocs.lucene_documents[idx] = docs.lucene_documents[i];
+        scoredDocs.docids[idx] = docs.docids[i];
         scoredDocs.scores[idx] = docs.scores[i];
         scoredDocs.lucene_docids[idx] = docs.lucene_docids[i];
         idx++;

src/main/java/io/anserini/search/BaseSearcher.java

@@ -20,7 +20,6 @@
 import org.apache.lucene.document.Document;
 import org.apache.lucene.search.IndexSearcher;
 import org.apache.lucene.search.TopDocs;
-import org.jetbrains.annotations.NotNull;
 
 import java.io.IOException;
 import java.util.ArrayList;
@@ -119,10 +118,9 @@ public ScoredDoc[] processLuceneTopDocs(K qid, TopDocs docs) {
    * @param keepLuceneDocument whether to retain references to the original Lucene docs
    * @return processed ranked list
    */
-  public ScoredDoc[] processLuceneTopDocs(K qid, @NotNull TopDocs docs, boolean keepLuceneDocument) {
+  public ScoredDoc[] processLuceneTopDocs(K qid, TopDocs docs, boolean keepLuceneDocument) {
     List<ScoredDoc> results = new ArrayList<>();
-    // For removing duplicate docids.
-    Set<String> docids = new HashSet<>();
+    Set<String> docids = new HashSet<>(); // For removing duplicate docids.
 
     int rank = 1;
     for (int i = 0; i < docs.scoreDocs.length; i++) {
@@ -194,7 +192,12 @@ public ScoredDoc[] processScoredDocs(K qid, ScoredDocs docs) {
    * @param keepLuceneDocument whether to retain references to the original Lucene docs
    * @return processed ranked list
    */
-  public ScoredDoc[] processScoredDocs(K qid, @NotNull ScoredDocs docs, boolean keepLuceneDocument) {
+  public ScoredDoc[] processScoredDocs(K qid, ScoredDocs docs, boolean keepLuceneDocument) {
+    assert docs.docids != null;
+    assert docs.lucene_docids != null;
+    assert docs.lucene_documents != null;
+    assert docs.scores != null;
+
     List<ScoredDoc> results = new ArrayList<>();
     // For removing duplicate docids.
     Set<String> docids = new HashSet<>();

src/main/java/io/anserini/search/ScoredDocs.java

@@ -28,7 +28,6 @@
 import org.apache.lucene.search.Query;
 import org.apache.lucene.search.TermQuery;
 import org.apache.lucene.search.TopDocs;
-import org.mockito.internal.matchers.Null;
 
 import java.io.IOException;
 import java.util.ArrayList;
@@ -52,8 +51,6 @@ public class ScoredDocs {
   public float[] scores;
 
   public static ScoredDocs fromTopDocs(TopDocs rs, IndexSearcher searcher) {
-    assert rs != null;
-
     ScoredDocs scoredDocs = new ScoredDocs();
     scoredDocs.docids = new String[rs.scoreDocs.length];
     scoredDocs.lucene_documents = new Document[rs.scoreDocs.length];

src/main/java/io/anserini/search/SearchCollection.java

@@ -943,7 +943,7 @@ public void run() {
               out.writeTopic((T) arr[0], results.get(Integer.parseInt(arr[0])));
             }
           } catch (IOException e) {
-            e.printStackTrace();
+            throw new RuntimeException(String.format("Error writing output to %s", outputPath));
           }
         } else {
           results.forEach((qid, hits) -> out.writeTopic(qid, results.get(qid)));
@@ -1304,7 +1304,6 @@ private Analyzer getAnalyzer() {
   }
 
   @Override
-  @SuppressWarnings("unchecked")
   public void run() {
     final String runTag = args.runtag == null ? "Anserini" : args.runtag;
     LOG.info("runtag: " + runTag);