Fix missing photon reconstruction caused by charged track overlap in MatchClusters.cc (#2154)

Previously, some photons that overlapped with charged tracks were being
incorrectly discarded, leading to reduced reconstruction efficiency.
This change adjusts the matching logic to retain valid photons without
affecting charged particle suppression.


### Briefly, what does this PR introduce?
This PR improves the cluster-to-MC association logic in MatchClusters by
selecting the best MC particle per cluster based on association weight,
instead of taking the first match found. Default behavior is slightly
changed for clusters with multiple MC associations; otherwise, results
are identical. No API or function signature changes are required for
users.

This code change :
1. Builds a map keyed by cluster object index, storing the
best-associated MC id and its weight.
2. When matching charged tracks, it only removes a cluster if that
cluster's best association is to that charged MC particle (and chooses
the best cluster for that MC by highest association weight if multiple
clusters claim the same MC). Remaining clusters are treated as neutrals.


### What kind of change does this PR introduce?
- [ ] Bug fix (issue #__)
- [ ] New feature (issue #__)
- [ ] Documentation update
- [ ] Other: __

### Please check if this PR fulfills the following:
- [ ] Tests for the changes have been added
- [ ] Documentation has been added / updated
- [ ] Changes have been communicated to collaborators

### Does this PR introduce breaking changes? What changes might users
need to make to their code?

### Does this PR change default behavior?

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Wouter Deconinck <[email protected]>

Author: 4 people

src/algorithms/reco/MatchClusters.cc

@@ -17,7 +17,9 @@
 #include <podio/ObjectID.h>
 #include <cmath>
 #include <gsl/pointers>
+#include <iterator>
 #include <map>
+#include <utility>
 
 #include "MatchClusters.h"
 
@@ -119,43 +121,60 @@ void MatchClusters::process(const MatchClusters::Input& input,
 }
 
 // get a map of mcID --> cluster
-// input: clusters --> all clusters
+// For each cluster, pick the best associated MC particle by association weight.
+// Returns a map keyed by mcID and valued with the selected cluster.
 std::map<int, edm4eic::Cluster> MatchClusters::indexedClusters(
     const edm4eic::ClusterCollection* clusters,
     const edm4eic::MCRecoClusterParticleAssociationCollection* associations) const {
 
-  std::map<int, edm4eic::Cluster> matched = {};
+  // temporary map: mcID -> (cluster, weight) so we can choose the cluster with highest weight per mcID
+  std::map<int, std::pair<edm4eic::Cluster, float>> bestForMc;
 
-  // loop over clusters
+  // loop over clusters and pick their best MC association by weight
   for (const auto cluster : *clusters) {
 
-    int mcID = -1;
+    int bestMcID     = -1;
+    float bestWeight = -1.F;
 
-    // find associated particle
+    // find best associated MC particle for this cluster (largest association weight)
     for (const auto assoc : *associations) {
       if (assoc.getRec() == cluster) {
-        mcID = assoc.getSim().getObjectID().index;
-        break;
+        const int candMcID = assoc.getSim().getObjectID().index;
+        const float w      = assoc.getWeight();
+        if (w > bestWeight) {
+          bestWeight = w;
+          bestMcID   = candMcID;
+        }
       }
     }
 
-    trace(" --> Found cluster with mcID {} and energy {}", mcID, cluster.getEnergy());
+    trace(" --> Found cluster with best mcID {} weight {} and energy {}", bestMcID, bestWeight,
+          cluster.getEnergy());
 
-    if (mcID < 0) {
+    if (bestMcID < 0) {
       trace("   --> WARNING: no valid MC truth link found, skipping cluster...");
       continue;
     }
 
-    const bool duplicate = matched.contains(mcID);
-    if (duplicate) {
-      trace("   --> WARNING: this is a duplicate mcID, keeping the higher energy cluster");
-
-      if (cluster.getEnergy() < matched[mcID].getEnergy()) {
-        continue;
+    // For this mcID, keep the cluster with the highest association weight (tie-break by energy).
+    auto it = bestForMc.find(bestMcID);
+    if (it == bestForMc.end()) {
+      bestForMc.emplace(bestMcID, std::make_pair(cluster, bestWeight));
+    } else {
+      const float existingWeight = it->second.second;
+      if (bestWeight > existingWeight ||
+          (bestWeight == existingWeight && cluster.getEnergy() > it->second.first.getEnergy())) {
+        it->second = std::make_pair(cluster, bestWeight);
       }
     }
-    matched[mcID] = cluster;
   }
+
+  // Convert to the old API: map<int, edm4eic::Cluster>
+  std::map<int, edm4eic::Cluster> matched;
+  for (const auto& kv : bestForMc) {
+    matched.emplace(kv.first, kv.second.first);
+  }
+
   return matched;
 }