PEDIGREE-LINK: chart parentRefs→litters, box-colour=sex, name-bleed fix

Structural fix (god, Julian-reported via 'C'): the loader ignored
SourceAnimal.ParentRefs, so animals whose ancestry exists only as
Stammbaum chart-position refs loaded with LitterId=null ("unbekannt").
ImportService now synthesizes/reuses a derived litter from parentRefs:
resolves father+mother via name+DOB, groups siblings (same parents+dob)
into one litter, sets Father/Mother + offspring LitterId, dates it to the
offspring DOB, and tags Notes "aus Stammbaum-Diagramm abgeleitet
(Konfidenz: …)" so it's transparent/reversible. Existing animals that
become linkable are re-linked on re-run (sweep-idempotent). Dry-run counts
included. Projected: ~124 loadable animals gain a parent link.

Box-colour = sex (Julian): blue box = male, white box = female. All 11
pedigrees encode this as a solid theme-8 (accent5/blue) fill vs no fill.
xlsx_util.cell_fill_sex reads it; extract.py sets animal.gender from the
box; ImportService.InferGender prefers it over sire/dam name inference.
Result: 306/306 loadable animals now sexed (154♂/152♀).

Extractor noise fix (god): reject Farbschlag values that are actually a
parent NAME bled across cells (contain v.d./von/of/gen.) — cleared phantom
conflicts (e.g. Chayton). Combined with GEN-3 Uw→G: Konflikte 32→21.
Also skip Excel "~$" lock files in the glob.

GEN-3a contract (Kevin): ComposeGenotype appends "Slsl" for WP/Sls
carriers (wild-type sl/sl omitted) so 8-locus strings stay unchanged.

Importer-only. The live re-import into Julian's DB stays a separate
supervised gated step. 95 C# tests + python genotype tests green;
has-pending-model-changes clean (no schema change on this branch).

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

GerbilManager.Tests/ImportServiceTests.cs

@@ -115,8 +115,67 @@ namespace GerbilManager.Tests
             // (kept out of the 8-locus compact Genotype contract until GEN-3a adopts them).
             Assert.Contains("Sls", a1.RawImportData!);
             Assert.Contains("WFNZ", a1.RawImportData!);
-            // and Sls must NOT leak into the compact 8-locus genotype string
-            Assert.DoesNotContain("Sl", a1.Genotype!);
+            // GEN-3a contract: a WP/Sls carrier appends the trailing "Slsl" token (Kevin).
+            Assert.EndsWith("Slsl", a1.Genotype!);
+        }
+
+        [Fact]
+        public void ComposeGenotype_appends_Slsl_only_for_carriers()
+        {
+            // wild-type sl/sl is omitted -> plain 8-locus string
+            var wild = new SourceGenotype { Mapped8locus = new() { ["A"] = new() { "a", "a" }, ["Sls"] = new() { "sl", "sl" } } };
+            Assert.DoesNotContain("Sl", ImportService.ComposeGenotype(wild));
+            // WP heterozygote -> trailing Slsl
+            var wp = new SourceGenotype { Mapped8locus = new() { ["A"] = new() { "a", "a" }, ["Sls"] = new() { "Sl", "sl" } } };
+            Assert.EndsWith("Slsl", ImportService.ComposeGenotype(wp));
+        }
+
+        [Fact]
+        public async Task Synthesizes_litter_from_chart_parentRefs_links_offspring_and_parents()
+        {
+            // Offspring 'C' has chart-position parentRefs to father 'Papa' (loaded) and mother
+            // 'Mama' (loaded), but NO Wurfchronik litterRef -> the loader must synthesize a derived
+            // litter, link C to it, and set the litter's Father/Mother (PEDIGREE-LINK structural fix).
+            var dir = Path.Combine(Path.GetTempPath(), "pedlink-" + Guid.NewGuid().ToString("N"));
+            Directory.CreateDirectory(dir);
+            try
+            {
+                File.WriteAllText(Path.Combine(dir, "litters.json"), "[]");
+                File.WriteAllText(Path.Combine(dir, "animals.json"), """
+                [
+                  {"id":"papa","name":"Papa v.d. Test","dob":"01.01.2022","death":"","farbschlag":"","gender":"male",
+                   "genotype":{"mapped8locus":{},"rawGenotype":"","unmappedTokens":[]},"conflict":false},
+                  {"id":"mama","name":"Mama v.d. Test","dob":"02.02.2022","death":"","farbschlag":"","gender":"female",
+                   "genotype":{"mapped8locus":{},"rawGenotype":"","unmappedTokens":[]},"conflict":false},
+                  {"id":"c","name":"C","dob":"29.04.2024","death":"","farbschlag":"",
+                   "genotype":{"mapped8locus":{},"rawGenotype":"","unmappedTokens":[]},"conflict":false,
+                   "parentRefs":[
+                     {"name":"Papa v.d. Test","dob":"01.01.2022","roleGuess":"father","method":"chart-position","confidence":"medium"},
+                     {"name":"Mama v.d. Test","dob":"02.02.2022","roleGuess":"mother","method":"chart-position","confidence":"medium"}
+                   ]}
+                ]
+                """);
+                using var db = NewDb();
+                var report = await new ImportService(db, dir, dir).RunAsync(execute: true);
+
+                Assert.Equal(1, report.Animals.ParentLinksFromChart);
+                Assert.Equal(1, report.Litters.DerivedFromChart);
+
+                var papa = await db.Gerbils.SingleAsync(g => g.ExternalRef == "papa");
+                var mama = await db.Gerbils.SingleAsync(g => g.ExternalRef == "mama");
+                var c = await db.Gerbils.SingleAsync(g => g.ExternalRef == "c");
+                Assert.NotNull(c.LitterId);                              // C no longer "unbekannt"
+
+                // box-colour sex flows through (blue=male, white=female)
+                Assert.Equal(Gender.male, papa.Gender);
+                Assert.Equal(Gender.female, mama.Gender);
+
+                var litter = await db.Litters.SingleAsync(l => l.Id == c.LitterId);
+                Assert.Equal(papa.Id, litter.FatherId);
+                Assert.Equal(mama.Id, litter.MotherId);
+                Assert.Contains("Diagramm", litter.Notes!);             // transparent + reversible
+            }
+            finally { try { Directory.Delete(dir, recursive: true); } catch { } }
         }
 
         [Fact]

GerbilManagerWebAPI/Import/ImportModels.cs

@@ -39,7 +39,9 @@ namespace GerbilManagerWebAPI.Import
     {
         public string Name { get; set; } = "";
         public string Dob { get; set; } = "";
-        public string RoleGuess { get; set; } = "";
+        public string RoleGuess { get; set; } = "";       // "father" | "mother"
+        public string Method { get; set; } = "";          // e.g. "chart-position"
+        public string Confidence { get; set; } = "";       // "hoch" | "medium" | "niedrig"
     }
 
     public sealed class SourceLitterRef
@@ -73,7 +75,7 @@ namespace GerbilManagerWebAPI.Import
         IReadOnlyList<string> Samples,
         IReadOnlyList<string> Notes);
 
-    public sealed record LitterSummary(int InSource, int Created, int AlreadyImported);
+    public sealed record LitterSummary(int InSource, int Created, int AlreadyImported, int DerivedFromChart = 0);
 
     public sealed record AnimalSummary(
         int InSource,
@@ -82,7 +84,8 @@ namespace GerbilManagerWebAPI.Import
         int FarbschlagMatched,
         int FarbschlagUnmatched,
         int AlreadyImported,
-        QuarantineSummary Quarantined);
+        QuarantineSummary Quarantined,
+        int ParentLinksFromChart = 0);
 
     public sealed record QuarantineSummary(
         int Conflicts,

GerbilManagerWebAPI/Import/ImportService.cs

@@ -128,74 +128,165 @@ namespace GerbilManagerWebAPI.Import
             int photosAttached = 0, photosMissing = 0;
             var createdAnimalByName = new Dictionary<string, Guid>();  // normalized name -> gerbil id (for litter back-link)
 
+            // name+DOB -> gid index, across EXISTING rows AND this run's planned animals, so that
+            // chart-position parentRefs (PEDIGREE-LINK) can resolve a parent to a real gerbil id.
+            var existingRows = await _db.Gerbils
+                .Select(g => new { g.Id, g.Name, g.DateOfBirth, g.ExternalRef, g.LitterId }).ToListAsync();
+            var gidByNameDob = new Dictionary<string, Guid>();
+            foreach (var g in existingRows)
+                gidByNameDob[NameDobKey(g.Name, g.DateOfBirth)] = g.Id;
+            var existingLitterByExtRef = existingRows.Where(g => g.ExternalRef != null)
+                .ToDictionary(g => g.ExternalRef!, g => g.LitterId);
+
+            // PASS 1: assign ids + resolve fb/gender/Wurfchronik link (no writes yet).
+            var plan = new List<AnimalPlan>();
             foreach (var a in loadable)
             {
-                if (existingGerbilSet.Contains(a.Id)) { animalsExisting++; continue; }
-                animalsCreated++;
+                bool exists = existingGerbilSet.Contains(a.Id);
+                var gid = exists ? gidByNameDob[NameDobKey(a.Name, ParseDate(a.Dob))] : Guid.NewGuid();
 
-                Guid? litterId = null;
+                Guid? wurfLitterId = null;
                 if (a.LitterRef?.Confidence == "hoch" && a.LitterRef.Candidates is not { Count: > 0 }
                     && litterIdMap.TryGetValue(a.LitterRef.LitterId, out var lid))
-                {
-                    litterId = lid;
-                    linked++;
-                }
+                    wurfLitterId = lid;
 
                 Guid? colorVarietyId = null;
                 var fbCandidates = new[] { a.Farbschlag }.Concat(a.FarbschlagVariants)
                     .Where(s => !string.IsNullOrWhiteSpace(s));
                 foreach (var fb in fbCandidates)
-                {
                     if (varietyByName.TryGetValue(fb.Trim().ToLowerInvariant(), out var vid))
                     { colorVarietyId = vid; break; }
-                }
-                if (colorVarietyId is null) fbUnmatched++; else fbMatched++;
 
                 var gender = InferGender(a, sireNames, damNames);
-                var gid = Guid.NewGuid();
                 var norm = Normalize(StripZucht(a.Name));
                 if (norm.Length > 0) createdAnimalByName.TryAdd(norm, gid);
+                if (!exists) gidByNameDob.TryAdd(NameDobKey(a.Name, ParseDate(a.Dob)), gid);
+
+                var currentLitter = exists && existingLitterByExtRef.TryGetValue(a.Id, out var el) ? el : null;
+                plan.Add(new AnimalPlan(a, gid, exists, wurfLitterId, currentLitter, colorVarietyId, gender));
+            }
+
+            // PASS 1.5: PEDIGREE-LINK — synthesize/reuse a litter from chart-position parentRefs for
+            // any animal that has no Wurfchronik litter and isn't already litter-linked. Siblings
+            // (same father+mother+dob) share one derived litter. Computed for dry-run counts too.
+            int parentLinksAdded = 0, derivedLitters = 0;
+            var synthLitterForGid = new Dictionary<Guid, Guid>();          // offspring gid -> synth litter id
+            var synthLitters = new Dictionary<string, SynthLitter>();      // parents+date key -> synth litter
+            foreach (var p in plan)
+            {
+                if (p.WurfLitterId is not null || p.CurrentLitterId is not null) continue;
+                if (p.A.ParentRefs is not { Count: > 0 }) continue;
+                var father = ResolveParentGid(p.A, "father", gidByNameDob);
+                var mother = ResolveParentGid(p.A, "mother", gidByNameDob);
+                if (father is null && mother is null) continue;            // nothing resolvable to link
+                var dob = ParseDate(p.A.Dob);
+                var conf = p.A.ParentRefs.FirstOrDefault()?.Confidence ?? "medium";
+                var key = $"{father}|{mother}|{dob:yyyy-MM-dd}";
+                if (!synthLitters.TryGetValue(key, out var sl))
+                {
+                    sl = new SynthLitter(Guid.NewGuid(), father, mother, dob, conf);
+                    synthLitters[key] = sl;
+                    derivedLitters++;
+                }
+                synthLitterForGid[p.Gid] = sl.Id;
+                parentLinksAdded++;
+            }
+
+            // PASS 2: write (litters synthesized first so offspring FK resolves), then animals + photos.
+            if (execute)
+            {
+                // reuse an existing litter with the same parents+date instead of duplicating.
+                var existingLitterRows = await _db.Litters
+                    .Select(l => new { l.Id, l.FatherId, l.MotherId, l.Date }).ToListAsync();
+                var litterByParentsDate = new Dictionary<string, Guid>();
+                foreach (var l in existingLitterRows)
+                    litterByParentsDate[$"{l.FatherId}|{l.MotherId}|{l.Date:yyyy-MM-dd}"] = l.Id;
+
+                foreach (var sl in synthLitters.Values.ToList())
+                {
+                    var reuseKey = $"{sl.Father}|{sl.Mother}|{sl.Date:yyyy-MM-dd}";
+                    if (litterByParentsDate.TryGetValue(reuseKey, out var existingId))
+                    {
+                        // remap offspring to the existing litter; don't create a duplicate.
+                        foreach (var g in synthLitterForGid.Where(kv => kv.Value == sl.Id).Select(kv => kv.Key).ToList())
+                            synthLitterForGid[g] = existingId;
+                        derivedLitters--;
+                        continue;
+                    }
+                    _db.Litters.Add(new Litter
+                    {
+                        Id = sl.Id,
+                        Name = $"Wurf (aus Diagramm) {sl.Date:yyyy-MM-dd}".Trim(),
+                        Date = sl.Date ?? default,
+                        FatherId = sl.Father,
+                        MotherId = sl.Mother,
+                        Notes = $"aus Stammbaum-Diagramm abgeleitet (Konfidenz: {sl.Confidence})",
+                    });
+                }
+                await _db.SaveChangesAsync();
+            }
+
+            foreach (var p in plan)
+            {
+                Guid? litterId = p.WurfLitterId
+                    ?? (synthLitterForGid.TryGetValue(p.Gid, out var slid) ? slid : (Guid?)null);
+                if (litterId is not null) linked++;
+
+                if (p.ColorVarietyId is null) fbUnmatched++; else fbMatched++;
 
                 if (samples.Count < 16)
-                    samples.Add($"Tier: {a.Name} (*{a.Dob}), Genotyp {ComposeGenotype(a.Genotype)}"
-                        + (litterId is not null ? ", Wurf-verknüpft" : "")
-                        + (colorVarietyId is not null ? $", Farbschlag „{a.Farbschlag}\"" : ""));
+                    samples.Add($"Tier: {p.A.Name} (*{p.A.Dob}), Genotyp {ComposeGenotype(p.A.Genotype)}"
+                        + (litterId is not null ? (p.WurfLitterId is not null ? ", Wurf-verknüpft" : ", Eltern aus Diagramm") : "")
+                        + (p.ColorVarietyId is not null ? $", Farbschlag „{p.A.Farbschlag}\"" : ""));
+
+                if (p.Exists)
+                {
+                    animalsExisting++;
+                    // re-link an existing animal that just became linkable (sweep idempotency).
+                    if (execute && p.CurrentLitterId is null && litterId is not null)
+                    {
+                        var row = await _db.Gerbils.FirstOrDefaultAsync(g => g.Id == p.Gid);
+                        if (row is not null) row.LitterId = litterId;
+                    }
+                    continue;
+                }
+                animalsCreated++;
 
                 if (execute)
                 {
                     _db.Gerbils.Add(new Gerbil
                     {
-                        Id = gid,
-                        Name = a.Name,
-                        Gender = gender,
+                        Id = p.Gid,
+                        Name = p.A.Name,
+                        Gender = p.Gender,
                         Status = GerbilStatus.Active,
-                        DateOfBirth = ParseDate(a.Dob),
-                        DateOfDeath = ParseDate(a.Death),
+                        DateOfBirth = ParseDate(p.A.Dob),
+                        DateOfDeath = ParseDate(p.A.Death),
                         LitterId = litterId,
-                        ColorVarietyId = colorVarietyId,
-                        Genotype = ComposeGenotype(a.Genotype),
-                        IsDeaf = a.Deaf,
+                        ColorVarietyId = p.ColorVarietyId,
+                        Genotype = ComposeGenotype(p.A.Genotype),
+                        IsDeaf = p.A.Deaf,
                         ImportSource = ImportSourceTag,
-                        ExternalRef = a.Id,
-                        OriginBreeder = string.IsNullOrWhiteSpace(a.Zucht) ? null : a.Zucht.Trim(),
+                        ExternalRef = p.A.Id,
+                        OriginBreeder = string.IsNullOrWhiteSpace(p.A.Zucht) ? null : p.A.Zucht.Trim(),
                         RawImportData = JsonSerializer.Serialize(new
                         {
-                            a.Genotype.RawGenotype,
-                            a.Genotype.UnmappedTokens,
+                            p.A.Genotype.RawGenotype,
+                            p.A.Genotype.UnmappedTokens,
                             // GEN-3b: Sls (2nd spotting locus) preserved here until Kevin's GEN-3a
                             // parser adopts it into the compact Genotype contract; tags + deaf too.
-                            Sls = a.Genotype.Mapped8locus.TryGetValue("Sls", out var sls) ? sls : null,
-                            a.Tags,
-                            a.Deaf,
-                            a.Zucht,
-                            a.SourceFiles,
-                            FarbschlagRaw = a.Farbschlag,
+                            Sls = p.A.Genotype.Mapped8locus.TryGetValue("Sls", out var sls) ? sls : null,
+                            p.A.Tags,
+                            p.A.Deaf,
+                            p.A.Zucht,
+                            p.A.SourceFiles,
+                            FarbschlagRaw = p.A.Farbschlag,
                         }),
                     });
                 }
 
                 // photos
-                foreach (var rel in a.Photos)
+                foreach (var rel in p.A.Photos)
                 {
                     var src = Path.Combine(_sourceDir, rel.Replace('/', Path.DirectorySeparatorChar));
                     if (!File.Exists(src)) { photosMissing++; continue; }
@@ -208,7 +299,7 @@ namespace GerbilManagerWebAPI.Import
                         _db.GerbilPhotos.Add(new GerbilPhoto
                         {
                             Id = Guid.NewGuid(),
-                            GerbilId = gid,
+                            GerbilId = p.Gid,
                             FileName = fileName,
                             SortOrder = 0,
                             CreatedAt = DateTimeOffset.UtcNow,
@@ -218,7 +309,7 @@ namespace GerbilManagerWebAPI.Import
             }
             if (execute) await _db.SaveChangesAsync();
 
-            // ---- back-link litter parents by name (best effort) ----
+            // ---- back-link Wurfchronik litter parents by name (best effort) ----
             if (execute)
             {
                 foreach (var sl in litters)
@@ -235,14 +326,17 @@ namespace GerbilManagerWebAPI.Import
             }
 
             notes.Add("Quarantäne (kein Import): Konflikte + Stubs ohne Geburtsdatum + unsichere Wurf-Zuordnungen — warten auf die Prüfung durch die Züchterin.");
+            if (parentLinksAdded > 0)
+                notes.Add($"Stammbaum-Diagramm: {parentLinksAdded} Tiere über Eltern-Verknüpfung einem (abgeleiteten) Wurf zugeordnet ({derivedLitters} abgeleitete Würfe).");
             if (!execute) notes.Add("DRY-RUN: nichts gespeichert. /import/execute lädt die konfliktfreien Daten.");
 
             return new ImportReport(
                 Executed: execute,
-                Litters: new LitterSummary(litters.Count, littersCreated, littersExisting),
+                Litters: new LitterSummary(litters.Count, littersCreated, littersExisting, derivedLitters),
                 Animals: new AnimalSummary(
                     animals.Count, animalsCreated, linked, fbMatched, fbUnmatched, animalsExisting,
-                    new QuarantineSummary(conflicts, stubs, dateOnly, ambiguous, conflicts + stubs)),
+                    new QuarantineSummary(conflicts, stubs, dateOnly, ambiguous, conflicts + stubs),
+                    parentLinksAdded),
                 Photos: new PhotoSummary(photosAttached, photosMissing),
                 Samples: samples,
                 Notes: notes);
@@ -263,7 +357,16 @@ namespace GerbilManagerWebAPI.Import
                 if (g.Mapped8locus.TryGetValue(locus, out var pair) && pair.Count == 2)
                     return StripCaret(pair[0]) + StripCaret(pair[1]);
                 return "??";
-            });
+            }).ToList();
+
+            // GEN-3a contract (Kevin): Sls is appended LAST and ONLY for carriers — the
+            // wild-type sl/sl is omitted so existing 8-locus strings stay unchanged. WP het
+            // renders as the trailing token "Slsl"; S(l)S(l) is lethal so never appears.
+            if (g.Mapped8locus.TryGetValue("Sls", out var sls) && sls.Count == 2
+                && !(sls[0] == "sl" && sls[1] == "sl"))
+            {
+                tokens.Add(StripCaret(sls[0]) + StripCaret(sls[1]));
+            }
             return string.Join(' ', tokens);
         }
 
@@ -271,6 +374,11 @@ namespace GerbilManagerWebAPI.Import
 
         private static Gender InferGender(SourceAnimal a, HashSet<string> sires, HashSet<string> dams)
         {
+            // Box colour (blue=male, white=female) is the authoritative breeder signal — prefer it
+            // over sire/dam name inference (PEDIGREE-LINK, Julian 2026-06-06).
+            if (string.Equals(a.Gender, "male", StringComparison.OrdinalIgnoreCase)) return Gender.male;
+            if (string.Equals(a.Gender, "female", StringComparison.OrdinalIgnoreCase)) return Gender.female;
+
             var n = Normalize(StripZucht(a.Name));
             bool isSire = sires.Contains(n), isDam = dams.Contains(n);
             if (isSire && !isDam) return Gender.male;
@@ -304,5 +412,26 @@ namespace GerbilManagerWebAPI.Import
             n = Regex.Replace(n, @"[^a-z0-9äöüß]", "");
             return n;
         }
+
+        /// <summary>Dedup identity for parent resolution: normalized call-name + DOB.</summary>
+        private static string NameDobKey(string name, DateOnly? dob) =>
+            $"{Normalize(StripZucht(name))}|{dob:yyyy-MM-dd}";
+
+        /// <summary>Resolve a chart-position parentRef (by role) to a known gerbil id, or null.</summary>
+        private static Guid? ResolveParentGid(SourceAnimal a, string role, Dictionary<string, Guid> gidByNameDob)
+        {
+            var pr = a.ParentRefs.FirstOrDefault(p =>
+                string.Equals(p.RoleGuess, role, StringComparison.OrdinalIgnoreCase));
+            if (pr is null || string.IsNullOrWhiteSpace(pr.Name)) return null;
+            return gidByNameDob.TryGetValue(NameDobKey(pr.Name, ParseDate(pr.Dob)), out var id) ? id : null;
+        }
+
+        /// <summary>Per-animal plan computed before any write so synthesis can run in dry-run too.</summary>
+        private sealed record AnimalPlan(
+            SourceAnimal A, Guid Gid, bool Exists, Guid? WurfLitterId,
+            Guid? CurrentLitterId, Guid? ColorVarietyId, Gender Gender);
+
+        /// <summary>A litter synthesized from chart-position parentRefs (PEDIGREE-LINK).</summary>
+        private sealed record SynthLitter(Guid Id, Guid? Father, Guid? Mother, DateOnly? Date, string Confidence);
     }
 }

tools/import/extract.py

@@ -20,6 +20,7 @@ import glob
 import shutil
 import argparse
 import unicodedata
+from collections import Counter
 
 import xlsx_util as xu
 import genotype as gt
@@ -96,6 +97,18 @@ ZUCHT_ALIASES = {
     "zdkc": "kleinechaote",   # "Zucht der kleinen Chaoten" (home cattery shorthand)
 }
 
+# A Farbschlag value must NOT contain cattery/line connectors (v.d./von/of/gen.) — when it
+# does, a parent's NAME has bled into the Farbschlag cell (cross-cell chart read, PEDIGREE-LINK
+# bug: e.g. "Victoria Welby gen. Welby v.d. Kleinen Chaoten" became a Farbschlag variant and
+# spawned a phantom conflict). Reject such values so they don't pollute farbschlag/conflicts.
+_NAME_MARKER = re.compile(r"\bv\.\s?d\.|\bvon\b|\bof\b|\bgen\.", re.IGNORECASE)
+
+
+def looks_like_animal_name(text):
+    """True if a candidate Farbschlag cell actually looks like an animal name (has a
+    cattery/line connector). Real Farbschläge are short colour words without these."""
+    return bool(_NAME_MARKER.search(text or ""))
+
 
 def split_name_zucht(raw):
     """'Luna [ZdkC]' -> ('Luna','ZdkC'); 'Pikachu of Black Forest' ->
@@ -159,6 +172,7 @@ def extract_stammbaum(path):
     ss = xu.shared_strings(z)
     sheets = xu.sheet_paths(z)
     cells = xu.read_cells(z, sheets[0], ss)
+    fillsex = xu.cell_fill_sex(z, sheets[0])     # box colour -> sex (blue=male, white=female)
 
     # group cells by column for block reconstruction
     by_col = {}
@@ -207,7 +221,8 @@ def extract_stammbaum(path):
                 elif re.search(r"\b(Zucht|Privatzucht)\b", cell) or cell.startswith("("):
                     breeder = cell
                     used.add((c, rr))
-                elif not farbschlag and not re.match(r"^\*?\s?\d", cell):
+                elif not farbschlag and not re.match(r"^\*?\s?\d", cell) \
+                        and not looks_like_animal_name(cell):
                     farbschlag = cell
                     used.add((c, rr))
             used.add((c, r))
@@ -224,7 +239,7 @@ def extract_stammbaum(path):
             "nameVariants": [],
             "dob": dob,
             "death": death,
-            "gender": None,
+            "gender": fillsex.get((c, r)),    # box colour: blue=male, white=female
             "farbschlag": farbschlag,
             "genotype": genodict,
             "deaf": genodict.get("deaf"),
@@ -536,11 +551,14 @@ def dedup(animals):
         deaths = set()
         deaf_seen = set()
         tags_set = set()
+        genders = []
         for a in grp:
             variants.add(a["name"])
             files.update(a["sourceFiles"])
             photos.extend(a["photos"])
             parent_refs.extend(a["parentRefs"])
+            if a.get("gender"):
+                genders.append(a["gender"])
             if a["genotype"]["mapped8locus"]:
                 genos.add(a["genotype"]["rawGenotype"])
                 geno_keys.add(_geno_key(a["genotype"]))
@@ -560,7 +578,8 @@ def dedup(animals):
             "nameVariants": sorted(v for v in variants if v),
             "dob": norm_dob(base["dob"]),
             "death": sorted(deaths)[0] if deaths else "",
-            "gender": None,
+            # box-colour sex (blue=male, white=female): majority across mentions, else None.
+            "gender": Counter(genders).most_common(1)[0][0] if genders else None,
             "farbschlag": sorted(farb)[0] if farb else "",
             "farbschlagVariants": sorted(farb),
             "genotype": best,
@@ -829,7 +848,9 @@ def main():
     os.makedirs(OUT, exist_ok=True)
 
     raw_animals = []
-    files = sorted(glob.glob(os.path.join(args.stammbaeume, "*.xlsx")))
+    # Skip Excel lock/owner files ("~$...") that appear while a workbook is open.
+    files = sorted(f for f in glob.glob(os.path.join(args.stammbaeume, "*.xlsx"))
+                   if not os.path.basename(f).startswith("~$"))
     print(f"Stammbaum-Dateien: {len(files)}")
     for path in files:
         got = extract_stammbaum(path)

tools/import/output/review-report.md

@@ -8,7 +8,7 @@ _Automatisch erzeugt von `tools/import/extract.py` — **noch nichts in die Date
 - Nach Zusammenführung (eindeutige Tiere): **622**
   - davon mit Geburtsdatum: 327
   - in mehreren Dateien gefunden (Dubletten zusammengeführt): 158
-- Konflikte zur Klärung: **27**
+- Konflikte zur Klärung: **21**
 - Mehrdeutige / unvollständige Einträge (ohne Name+Datum): **310**
 - Fotos zugeordnet: **137**
 - Würfe aus der Wurfchronik: **752**
@@ -26,30 +26,24 @@ Gleiches Tier (Name+Datum), aber widersprüchliche Angaben in verschiedenen Date
 | Tier | Geburtsdatum | abweichende Genotypen | abweichende Farbschläge | Sterbedaten | Dateien |
 |---|---|---|---|---|---|
 | Ella | 10.06.2019 | Aa C D- ee[f] GG P- spsp // Aa Cc[chm] D- ee[f] UwUw P- spsp | Algierfuchsschimmel, hell | 03.02.2023 | Stammbaum von Akio Kids, Stammbaum von CP-Fuchs, CP-Sa Sp von Unity, Stammbaum von Valentino Firehearts Kids |
-| ZoneFire | 07.12.2020 | Aa c[chm]c[chm] D- Ee Gg P- Spsp | CP-Agouti Kragenschecke // Kalea von den Kleinen Chaoten | — | Stammbaum von Akio Kids |
-| Louis von den Kleinen Chaoten | 15.07.2017 | Aa Cc[] D- Ee Gg P- spsp // Aa Cc[chm] D- Ee Uwuw[d] P- spsp | Roswitha von den Kleinen Chaoten | 01.07.2020 | Stammbaum von Akio Kids, Stammbaum von CP-Fuchs, CP-Sa Sp von Unity |
+| Louis von den Kleinen Chaoten | 15.07.2017 | Aa Cc[] D- Ee Gg P- spsp // Aa Cc[chm] D- Ee Uwuw[d] P- spsp | — | 01.07.2020 | Stammbaum von Akio Kids, Stammbaum von CP-Fuchs, CP-Sa Sp von Unity |
 | Firefly von den Kleinen Chaoten | 18.12.2019 | /+, Aa c[chm]c[chm] D- Ee Gg PP Spsp // Aa c[chm]c[chm] DD Ee Gg PP Spsp | — | 2024 | Stammbaum von Akio Kids, Stammbaum von CP-Fuchs, CP-Sa Sp von Unity, Stammbaum von Fire Kids, Stammbaum von Valentino Firehearts Kids |
 | Zuleika von den Kleinen Chaoten | 24.10.2015 | aa c[chm]c[h] D- E G P- spsp // aa c[chm]c[h] D- Ee Gg P- spsp // aa c[chm]c[h] DD Ee Gg P- spsp | — | 24.02.2019 | Stammbaum von Akio Kids, Stammbaum von CP-Fuchs, CP-Sa Sp von Unity, Stammbaum von Valentino Firehearts Kids |
 | WildFire von den Kleinen Chaoten | 05.10.2017 | aa c[chm]c[chm] D- Ee gg P- spsp // aa c[chm]c[chm] D- Ee gg PP spsp | — | — | Stammbaum von Akio Kids, Stammbaum von CP-Fuchs, CP-Sa Sp von Unity, Stammbaum von Fire Kids, Stammbaum von Valentino Firehearts Kids |
 | Vestra von den Schlossmäusen | 08.02.2019 | Aa Cc[chm] D- EE GG PP Spsp [WP] // Aa Cc[chm] DD EE GG PP Spsp [WP] | — | 26.05.2023 | Stammbaum von Akio Kids, Stammbaum von CP-Fuchs, CP-Sa Sp von Unity, Stammbaum von Fire Kids, Stammbaum von Valentino Firehearts Kids |
 | Flint von den Kleinen Chaoten | 23.12.2017 | aa Cc[chm] D- ee Gg P- spsp | — | 10.05.2021 // 10.05.2022 | Stammbaum von Akio Kids, Stammbaum von CP-Fuchs, CP-Sa Sp von Unity |
 | Kazu von den Kleinen Chaoten | 23.04.2013 | Aa Cc[chm] DD e[f]e[f] Gg P Spsp // Aa Cc[chm] DD ee[f] UwUw PP Spsp | — | 03.09.2017 | Stammbaum von Akio Kids, Stammbaum von Vance |
-| Bruno of Black Forest | 01.06.2022 | aa C- dd Ee Gg P- spsp | Blau // Mystique of Black Forest | — | Stammbaum von Alberto Kids, Stammbaum von Fire Kids, Stammbaum von Stella Kids |
 | Milka of LennyLengo | 09.12.2018 | aa C- dd E- Gg P- Spsp // aa Cc[h] dd EE Gg P- Spsp | — | 22.12.2021 | Stammbaum von Alberto Kids, Stammbaum von Stella Kids |
 | Silvain von den Kleinen Chaoten | 27.03.2022 | aa c[chm]c[chm] Dd Ee[-] Gg P- Spsp // aa c[chm]c[chm] Dd ee[-] Gg Pp Spsp | — | 31.12.2024 | Stammbaum von Alberto Kids, Stammbaum von CP-Fuchs, CP-Sa Sp von Unity |
 | Enya von den Kleinen Chaoten | 01.11.2017 | Aa c[chm]c[chm] D- ee[-] G- P- spsp // Aa c[chm]c[chm] D- ee[-] Uwuw[d] P- spsp | — | — | Stammbaum von Alberto Kids, Stammbaum von Fire Kids, Stammbaum von Kohlief, Goldfuchsef Sp von Chrissi, Stammbaum von Stella Kids |
 | Little Hero of Black Forest | 22.02.2018 | AA CC DD EE GG PP [WFNZ] // AA CC DD EE GG PP spsp [WFNZ] | — | 18.06.2021 | Stammbaum von Alberto Kids, Stammbaum von CP-Fuchs, CP-Sa Sp von Unity, Stammbaum von Fire Kids, Stammbaum von Kohlief, Goldfuchsef Sp von Chrissi, Stammbaum von Stella Kids, Stammbaum von Valentino Firehearts Kids |
 | Molly of Black Forest | 13.09.2021 | /+, Aa Cc[chm] D- Ee gg P- spsp // Aa Cc[chm] Dd Ee gg Pp spsp | — | 03.05.2021 | Stammbaum von Alberto Kids, Stammbaum von CP-Fuchs, CP-Sa Sp von Unity |
-| Little Runner's Big Ben | 03.02.2020 | Aa Cc[chm] DD Ee Gg PP Spsp // Aa Cc[chm] DD Ee Gg Pp Spsp | Daja of Little Rose | 14.10.2023 | Stammbaum von CP-Fuchs, CP-Sa Sp von Unity, Stammbaum von Fire Kids, Stammbaum von Goldfuchs Sp (Pikachu) Kids, Stammbaum von Kohlief, Goldfuchsef Sp von Chrissi, Stammbaum von Valentino Firehearts Kids, Stammbaum von Watarus Kids |
+| Little Runner's Big Ben | 03.02.2020 | Aa Cc[chm] DD Ee Gg PP Spsp // Aa Cc[chm] DD Ee Gg Pp Spsp | — | 14.10.2023 | Stammbaum von CP-Fuchs, CP-Sa Sp von Unity, Stammbaum von Fire Kids, Stammbaum von Goldfuchs Sp (Pikachu) Kids, Stammbaum von Kohlief, Goldfuchsef Sp von Chrissi, Stammbaum von Valentino Firehearts Kids, Stammbaum von Watarus Kids |
 | Daja of Little Rose | 16.05.2021 | aa chmchm D- EE Gg P- // aa chmchm D- EE Gg P- spsp | — | — | Stammbaum von CP-Fuchs, CP-Sa Sp von Unity, Stammbaum von Fire Kids, Stammbaum von Valentino Firehearts Kids |
-| Vance Jr. von den Kleinen Chaoten | 10.04.2022 | aa Cc[hm] Dd Ee gg P- Spsp // aa Cc[hm] Dd Ee gg P- spsp | Kohlfuchs, hell // Velvet von den Kleinen Chaoten | — | Stammbaum von Fire Kids, Stammbaum von Stella Kids |
+| Vance Jr. von den Kleinen Chaoten | 10.04.2022 | aa Cc[hm] Dd Ee gg P- Spsp // aa Cc[hm] Dd Ee gg P- spsp | Kohlfuchs, hell | — | Stammbaum von Fire Kids, Stammbaum von Stella Kids |
 | Ichika von den Kleinen Chaoten | 19.04.2020 | aa CC D- ee Gg pp spsp // aa CC D- ee[f] Gg pp spsp | — | 27.11.2023 | Stammbaum von Goldfuchs Sp (Pikachu) Kids, Stammbaum von Watarus Kids |
-| Trogir von den Kleinen Chaoten | 21.03.2022 | Aa CC DD EE GG pp Spsp | Gold Ansatzschecke // Mahima von den Kleinen Chaoten | 29.05.2024 | Stammbaum von Goldfuchs Sp (Pikachu) Kids, Stammbaum von Kohlief, Goldfuchsef Sp von Chrissi, Stammbaum von Watarus Kids |
-| Chayton v.d. Kleinen Chaoten (extern SC) | 04.02.2022 | aa Cc[-] D- e[f]e[f] Gg Pp spsp | Orangeschimmel, hell // Victoria Welby gen. Welby v.d. Kleinen Chaoten | 30.04.2024 | Stammbaum von Goldfuchs Sp (Pikachu) Kids, Stammbaum von Kohlief, Goldfuchsef Sp von Chrissi, Stammbaum von Watarus Kids |
 | Victoria Welby gen. Welby v.d. Kleinen Chaoten | 16.01.2023 | Aa CC D- Ee[f] Gg pp Spsp [DP] // Aa CC D- ee[f] Gg pp Spsp [DP] | Goldfuchsschimmel Punktschecke DP | 17.02.2026 | Stammbaum von Goldfuchs Sp (Pikachu) Kids, Stammbaum von Kohlief, Goldfuchsef Sp von Chrissi, Stammbaum von Watarus Kids |
-| Zac gen. Action von den Kleinen Chaoten | 25.12.2020 | aa C- D- Ee G- Pp Spsp [DP] // aa CC D- Ee G- Pp Spsp [DP] | Belica gen. Emi von den Kleinen Chaoten | 31.01.2025 | Stammbaum von Goldfuchs Sp (Pikachu) Kids, Stammbaum von Kohlief, Goldfuchsef Sp von Chrissi, Stammbaum von Watarus Kids |
-| Chesnut | 13.11.2019 | aa C- D- ee[f] GG PP spsp | Kohlfuchsschimmel // Tennessee von den Kleinen Chaoten | 22.11.2023 | Stammbaum von Kentucky |
-| Ethan von den Kleinen Chaoten | 09.07.2020 | Aa Cc[chm] D- ee[f] Gg Pp Spsp | Ichika von den Kleinen Chaoten // Orangeschimmel, hell Kragenschecke | 30.07.2024 | Stammbaum von Kentucky, Stammbaum von Watarus Kids |
+| Zac gen. Action von den Kleinen Chaoten | 25.12.2020 | aa C- D- Ee G- Pp Spsp [DP] // aa CC D- Ee G- Pp Spsp [DP] | — | 31.01.2025 | Stammbaum von Goldfuchs Sp (Pikachu) Kids, Stammbaum von Kohlief, Goldfuchsef Sp von Chrissi, Stammbaum von Watarus Kids |
 | Hanami von den Kleinen Chaoten | 10.09.2015 | aa Cc[chm] D- Ee gg P- spsp | — | 12.12.2019 // 14.01.2020 | Stammbaum von Kentucky, Stammbaum von Stella Kids |
 | Skarlett v.d. Kleinen Chaoten | 14.07.2013 | / +2018, Aa Cc[chm] DD ee uw[d]uw[d] PP spsp // Aa Cc[chm] DD ee uw[d]uw[d] PP spsp | — | 17.04.2016 // 2018 | Stammbaum von Vance |
 

tools/import/xlsx_util.py

@@ -78,6 +78,46 @@ def read_cells(z, sheet_path, ss=None):
     return cells
 
 
+def cell_fill_sex(z, sheet_path):
+    """{(colnum, row): 'male' | 'female'} from the cell's box fill colour.
+
+    Breeder convention (Julian, 2026-06-06): a BLUE box = männlich (male), a WHITE box =
+    weiblich (female). In these Stammbaum templates every coloured box uses one solid theme
+    fill (Office accent5 = blue); unfilled/none cells render white. So: a cell whose style
+    uses a real solid fill -> 'male'; an unfilled (none/gray125) cell -> 'female'.
+    """
+    try:
+        st = z.read("xl/styles.xml").decode("utf-8")
+    except KeyError:
+        return {}
+    fills = re.search(r"<fills.*?</fills>", st, re.S)
+    colored = set()
+    if fills:
+        for i, fb in enumerate(re.findall(r"<fill>(.*?)</fill>", fills.group(0), re.S)):
+            if 'patternType="solid"' in fb and re.search(r"<fgColor\s", fb) and "gray125" not in fb:
+                colored.add(i)               # fillId of a real solid colour (blue)
+    xfs = re.search(r"<cellXfs.*?</cellXfs>", st, re.S)
+    idx2fill = {}
+    if xfs:
+        for i, xf in enumerate(re.findall(r"<xf\b([^>]*?)/?>", xfs.group(0))):
+            m = re.search(r'fillId="(\d+)"', xf)
+            idx2fill[i] = int(m.group(1)) if m else 0
+    raw = z.read(sheet_path).decode("utf-8")
+    out = {}
+    for m in re.finditer(r"<c\s+([^>]*?)>", raw):
+        a = dict(_ATTR.findall(m.group(1)))
+        ref = a.get("r")
+        if not ref:
+            continue
+        mm = re.match(r"([A-Z]+)(\d+)", ref)
+        if not mm:
+            continue
+        s = int(a.get("s", "0"))
+        out[(col_to_num(mm.group(1)), int(mm.group(2)))] = (
+            "male" if idx2fill.get(s, 0) in colored else "female")
+    return out
+
+
 def header_row(cells):
     """Return {colnum: header_text} for the topmost row that has text."""
     if not cells: