dedup: 'presence wins' — present-vs-absent token is not a conflict (Julian)

Breeder merge rule: when two source variants of the SAME animal differ ONLY
by a token PRESENT in one and ABSENT in the other — a whole locus (e.g. spsp
charted in one source, omitted in another) or a modifier on the same base
allele (e^f vs e, the [f] marker) — keep the present token; that is NOT a
conflict. Genuine VALUE contradictions still quarantine: different base
alleles (Ee↔ee), unknown-vs-filled (D-↔DD), different modifiers (c[h]↔c[chm]),
C-↔Cc[h], P-↔Pp.

Replaces the old `len(distinct normalized geno keys) > 1` test with
_genotype_conflict() (per-locus, per-allele compatibility; '?'-vs-filled is a
contradiction, modifier-present-vs-absent and whole-locus-absence are not).
Markers/flags (WP/DP/WFNZ/hörend) are already tags/flags, never genotype, so
they never reach conflict detection; empty Farbschlag/death already don't
conflict (only non-empty values are compared).

Clears Daja (keep spsp), Ichika (keep ee[f]) and the D4 marker cases:
Konflikte 19 -> 15. test_extract covers spsp/[f] present-vs-absent =
no conflict and the four genuine-contradiction shapes. python + dotnet
121/121 green; extractor-only.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

tools/import/extract.py

@@ -502,6 +502,52 @@ def _geno_key(genodict):
     return "|".join(f"{locus}:{','.join(sorted(m[locus]))}" for locus in sorted(m))
 
 
+# --- "presence wins" merge rule (Julian) -------------------------------------
+# When two source variants of the SAME animal differ ONLY by a token PRESENT in one and
+# ABSENT in the other — a whole locus (e.g. spsp recorded in one chart, omitted in another)
+# or a modifier on the same base allele (e^f vs e, i.e. the [f] marker) — keep the present
+# token; that is NOT a conflict. A genuine VALUE contradiction (different filled alleles:
+# E vs e, D vs d, c^h vs c^chm) OR unknown-vs-filled (D- vs DD, the '?' second allele) STILL
+# quarantines for human decision. (Markers/flags WP/DP/WFNZ/hörend are already tags/flags,
+# never part of the genotype, so they never reach here.)
+def _split_allele(a):
+    return tuple(a.split("^", 1)) if "^" in a else (a, "")
+
+
+def _alleles_compatible(a, b):
+    if a == b:
+        return True
+    if a == "?" or b == "?":
+        return False                       # unknown vs filled = contradiction (D- vs DD)
+    (ba, ma), (bb, mb) = _split_allele(a), _split_allele(b)
+    if ba != bb:
+        return False                       # different base allele = real value diff (E vs e)
+    return ma == "" or mb == ""            # same base, modifier present-vs-absent -> presence wins
+
+
+def _pair_compatible(p, q):
+    if len(p) != 2 or len(q) != 2:
+        return p == q
+    return ((_alleles_compatible(p[0], q[0]) and _alleles_compatible(p[1], q[1])) or
+            (_alleles_compatible(p[0], q[1]) and _alleles_compatible(p[1], q[0])))
+
+
+def _genotype_conflict(mapped_list):
+    """True only if two variants GENUINELY contradict at a shared locus. A locus present in
+    one variant and absent in another is fine (presence wins); so is a modifier present-vs-
+    absent on the same base allele. Replaces the old `len(distinct geno keys) > 1` test."""
+    loci = set()
+    for m in mapped_list:
+        loci.update(m.keys())
+    for locus in loci:
+        pairs = [m[locus] for m in mapped_list if locus in m]
+        for i in range(len(pairs)):
+            for j in range(i + 1, len(pairs)):
+                if not _pair_compatible(pairs[i], pairs[j]):
+                    return True
+    return False
+
+
 def dedup(animals):
     """Merge by normalise(call-name)+DOB, with the canonical Zucht as
     DISCRIMINATOR (Julian: same name+DOB+Zucht = same animal; different Zucht =
@@ -552,6 +598,7 @@ def dedup(animals):
         parent_refs = list(base["parentRefs"])
         genos = set()
         geno_keys = set()   # GEN-3b: conflict on NORMALIZED genotype (Uw==G) not raw text
+        mapped_variants = []  # mapped8locus per variant — for the 'presence wins' conflict test
         farb = set()
         deaths = set()
         deaf_seen = set()
@@ -567,6 +614,7 @@ def dedup(animals):
             if a["genotype"]["mapped8locus"]:
                 genos.add(a["genotype"]["rawGenotype"])
                 geno_keys.add(_geno_key(a["genotype"]))
+                mapped_variants.append(a["genotype"]["mapped8locus"])
             if a["farbschlag"]:
                 farb.add(a["farbschlag"])
             if a["death"]:
@@ -603,8 +651,9 @@ def dedup(animals):
             "conflict": False,
         }
         merged.append(out)
-        # conflict: same animal, disagreeing NORMALIZED genotype (Uw==G) or farbschlag or death
-        if len(geno_keys) > 1 or len(farb) > 1 or len(deaths) > 1:
+        # conflict: same animal, GENUINELY disagreeing genotype (presence-vs-absence is NOT a
+        # conflict — Julian's 'presence wins') or >1 distinct farbschlag or >1 distinct death.
+        if _genotype_conflict(mapped_variants) or len(farb) > 1 or len(deaths) > 1:
             out["conflict"] = True
             conflicts.append({
                 "id": out["id"], "name": base["name"], "dob": out["dob"],