feat: RRF and cross-segment max-score dedupe

src/fusion.rs

@@ -1 +1,54 @@
-// implemented in a later task
+use crate::model::Candidate;
+use std::collections::HashMap;
+
+/// Reciprocal Rank Fusion of two ranked lists of entry indices.
+/// Returns deduped entry indices ordered by fused score desc.
+pub fn rrf_merge(a: &[usize], b: &[usize], k: usize) -> Vec<usize> {
+    let mut score: HashMap<usize, f64> = HashMap::new();
+    for (rank, &id) in a.iter().enumerate() {
+        *score.entry(id).or_default() += 1.0 / (k as f64 + rank as f64 + 1.0);
+    }
+    for (rank, &id) in b.iter().enumerate() {
+        *score.entry(id).or_default() += 1.0 / (k as f64 + rank as f64 + 1.0);
+    }
+    let mut v: Vec<(usize, f64)> = score.into_iter().collect();
+    v.sort_by(|x, y| y.1.partial_cmp(&x.1).unwrap());
+    v.into_iter().map(|(id, _)| id).collect()
+}
+
+/// Group candidates by normalized ICD code across all segments.
+/// Score = max over occurrences; retain all source segments and
+/// the matched phrase of the best-scoring occurrence.
+pub fn cross_segment_dedupe(cands: Vec<Candidate>) -> Vec<(DedupCandidate, f32)> {
+    let mut by_code: HashMap<String, DedupCandidate> = HashMap::new();
+    for c in cands {
+        let s = c.rerank.or(c.semantic).or(c.lexical).unwrap_or(0.0);
+        let e = by_code.entry(c.icd_code.clone()).or_insert_with(|| DedupCandidate {
+            icd_code: c.icd_code.clone(),
+            best_phrase: c.alpha_text.clone(),
+            best_score: f32::MIN,
+            source_segments: Vec::new(),
+        });
+        if !e.source_segments.contains(&c.segment_idx) {
+            e.source_segments.push(c.segment_idx);
+        }
+        if s > e.best_score {
+            e.best_score = s;
+            e.best_phrase = c.alpha_text.clone();
+        }
+    }
+    let mut out: Vec<(DedupCandidate, f32)> = by_code
+        .into_values()
+        .map(|mut d| { d.source_segments.sort(); let s = d.best_score; (d, s) })
+        .collect();
+    out.sort_by(|a, b| b.1.partial_cmp(&a.1).unwrap());
+    out
+}
+
+#[derive(Debug, Clone)]
+pub struct DedupCandidate {
+    pub icd_code: String,
+    pub best_phrase: String,
+    pub best_score: f32,
+    pub source_segments: Vec<usize>,
+}