feat(import): merge animals with different DOBs if their parent names match

tools/import/extract.py

@@ -612,6 +612,49 @@ def dedup(animals):
             "files": sorted(set(f for a in grp for f in a["sourceFiles"])),
         })
 
+    # 2. Merge groups that have different DOBs but same call-name (and Zucht) and matching parents
+    def get_parent_keys(a):
+        parent_refs = a.get("parentRefs", [])
+        f_name = next((p["name"] for p in parent_refs if p.get("roleGuess") == "father"), "")
+        m_name = next((p["name"] for p in parent_refs if p.get("roleGuess") == "mother"), "")
+        return norm_name(f_name), norm_name(m_name)
+
+    def groups_parents_match(g1, g2):
+        for a1 in g1:
+            for a2 in g2:
+                f1, m1 = get_parent_keys(a1)
+                f2, m2 = get_parent_keys(a2)
+                if f1 and f2 and f1 == f2 and m1 and m2 and m1 == m2:
+                    return True
+        return False
+
+    i = 0
+    while i < len(final_groups):
+        g1 = final_groups[i]
+        call1, _ = split_name_zucht(g1[0]["name"])
+        n_call1 = norm_name(call1)
+        zucht1 = g1[0].get("_zucht", "")
+        
+        j = i + 1
+        merged_any = False
+        while j < len(final_groups):
+            g2 = final_groups[j]
+            call2, _ = split_name_zucht(g2[0]["name"])
+            n_call2 = norm_name(call2)
+            zucht2 = g2[0].get("_zucht", "")
+            
+            if n_call1 == n_call2:
+                if zucht1 == zucht2 or not zucht1 or not zucht2:
+                    if groups_parents_match(g1, g2):
+                        g1.extend(g2)
+                        final_groups.pop(j)
+                        merged_any = True
+                        continue
+            j += 1
+        if merged_any:
+            continue
+        i += 1
+
     merged = []
     conflicts = []
     for grp in final_groups:
@@ -652,11 +695,25 @@ def dedup(animals):
             return sum(1 for pair in gd["mapped8locus"].values() for a in pair if a != "?")
         best = max((a["genotype"] for a in grp),
                    key=lambda gd: (len(gd["mapped8locus"]), _specificity(gd), len(gd["rawGenotype"])))
+        
+        # Find best DOB (proband first)
+        best_dob = ""
+        for a in grp:
+            if a.get("_gen") == 0 and a.get("dob"):
+                best_dob = a["dob"]
+                break
+        if not best_dob:
+            for a in grp:
+                if a.get("dob"):
+                    best_dob = a["dob"]
+                    break
+        chosen_dob = norm_dob(best_dob or base["dob"])
+
         out = {
-            "id": slug(base["name"], base["dob"]),
+            "id": slug(base["name"], chosen_dob),
             "name": base["name"],
             "nameVariants": sorted(v for v in variants if v),
-            "dob": norm_dob(base["dob"]),
+            "dob": chosen_dob,
             "death": sorted(deaths)[0] if deaths else "",
             # box-colour sex (blue=male, white=female): majority across mentions, else None.
             "gender": Counter(genders).most_common(1)[0][0] if genders else None,