From 640102a4a30e3913b4d498a465bb2ecd4f9cb7a3 Mon Sep 17 00:00:00 2001
From: Julie Tibshirani <julietibs@apache.org>
Date: Tue, 28 May 2024 14:51:34 -0700
Subject: [PATCH] Increase filename boost (#785)

When we introduced filename boosting in BM25, we set it to a very conservative
weight. This PR increases the weight from 2.0 -> 5.0, which improves results on
relevant evals.

Relates to SPLF-88
---
 build/scoring_test.go | 6 +++---
 score.go              | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/build/scoring_test.go b/build/scoring_test.go
index 03a13928..e4e2e51e 100644
--- a/build/scoring_test.go
+++ b/build/scoring_test.go
@@ -78,7 +78,7 @@ func TestBM25(t *testing.T) {
 			content:  exampleJava,
 			language: "Java",
 			// bm25-score:1.69 (sum-tf: 7.00, length-ratio: 2.00)
-			wantScore: 1.69,
+			wantScore: 1.82,
 		}, {
 			// Matches only on content
 			fileName: "example.java",
@@ -99,7 +99,7 @@ func TestBM25(t *testing.T) {
 			content:  exampleJava,
 			language: "Java",
 			// bm25-score:1.07 (sum-tf: 2.00, length-ratio: 2.00)
-			wantScore: 1.07,
+			wantScore: 1.55,
 		},
 		{
 			// Matches only on filename, and content is missing
@@ -107,7 +107,7 @@ func TestBM25(t *testing.T) {
 			query:    &query.Substring{Pattern: "config.go"},
 			language: "Go",
 			// bm25-score:1.91 (sum-tf: 2.00, length-ratio: 0.00)
-			wantScore: 1.91,
+			wantScore: 2.08,
 		},
 	}
 
diff --git a/score.go b/score.go
index dc0f4c19..9bcf1bbc 100644
--- a/score.go
+++ b/score.go
@@ -132,7 +132,7 @@ func (d *indexData) scoreFileUsingBM25(fileMatch *FileMatch, doc uint32, cands [
 		term := string(cand.substrLowered)
 
 		if cand.fileName {
-			termFreqs[term] += 2
+			termFreqs[term] += 5
 		} else {
 			termFreqs[term]++
 		}