Merge feature/extract-band-aware: band-aware Farbschlag + conflict-decisions consumption + GEN-3f backend re-seed (ReseedColorVarietiesGen3f) [god-QA pending]

2026-06-06 12:05:02 +02:00
parent ea8c3e9966 b9033238c9
commit 0317c5d454
11 changed files with 2222 additions and 190 deletions
--- a/tools/import/extract.py
+++ b/tools/import/extract.py
@@ -211,6 +211,11 @@ def extract_stammbaum(path):
            farbschlag = ""
            geno = geno0
            breeder = ""
+            # BAND-AWARE (Julian-confirmed): early bands (gen 0-1, cols B/E/H) are 5-cell blocks
+            # WITH a Farbschlag cell; deep bands (gen >= 2, cols K/N/Q...) are 3-cell blocks
+            # (Name/DOB/Genotype) with NO Farbschlag — colour is derived from the genotype. So in
+            # deep bands we must NOT grab the next block's name or a stray health note as Farbschlag.
+            deep_band = gen_of(c) >= 2
            for rr in range(r + 1, r + 4):
                cell = cells.get((c, rr))
                if not cell:
@@ -221,7 +226,7 @@ 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 deep_band and not farbschlag and not re.match(r"^\*?\s?\d", cell) \
                        and not looks_like_animal_name(cell):
                    farbschlag = cell
                    used.add((c, rr))
@@ -829,6 +834,43 @@ def write_report(merged, conflicts, orphans, raw_count, litters, photo_count,


 # ------------------------------------------------------------------------ main
+def apply_conflict_decisions(merged, conflicts, path):
+    """Consume human conflict resolutions (tools/import/conflict-decisions.json) so the wife's
+    answers UN-QUARANTINE animals. Schema: {"resolutions":[{name, dob, decision, genotype?,
+    farbschlag?, source}]}. Match = norm_name(name)+norm_dob(dob) (same identity as dedup). A
+    matching animal: clear its conflict, mark resolvedByDecision; an explicit `genotype`
+    (breeder notation) is parsed and becomes authoritative, `farbschlag` overrides too. Tolerates
+    a missing/empty/garbled file. Returns the number of conflicts resolved. (god/HUMANQUESTION D.)"""
+    decisions = {}
+    try:
+        with open(path, encoding="utf-8") as fh:
+            for r in (json.load(fh).get("resolutions") or []):
+                decisions[(norm_name(r.get("name", "")), norm_dob(r.get("dob", "")))] = r
+    except (OSError, ValueError):
+        return 0
+    if not decisions:
+        return 0
+
+    resolved = 0
+    for a in merged:
+        d = decisions.get((norm_name(a["name"]), norm_dob(a["dob"])))
+        if not d:
+            continue
+        a["resolvedByDecision"] = True
+        if d.get("genotype"):
+            a["genotype"] = gt.parse(d["genotype"])
+        if d.get("farbschlag"):
+            a["farbschlag"] = d["farbschlag"]
+            a["farbschlagVariants"] = [d["farbschlag"]]
+        if d.get("dateOfDeath"):                       # D5 death-date resolutions
+            a["death"] = norm_dob(d["dateOfDeath"])
+        if a.get("conflict"):
+            a["conflict"] = False
+            conflicts[:] = [c for c in conflicts if c.get("id") != a["id"]]
+            resolved += 1
+    return resolved
+
+
 def main():
    try:
        sys.stdout.reconfigure(encoding="utf-8", errors="replace")
@@ -863,6 +905,8 @@ def main():
        print(f"Wurfchronik: {len(litters)} Würfe")

    merged, conflicts, orphans, zucht_splits = dedup(raw_animals)
+    decisions_path = os.path.join(HERE, "conflict-decisions.json")
+    resolved_by_decision = apply_conflict_decisions(merged, conflicts, decisions_path)
    match_stats = match_litters(merged, litters)
    photo_count = sum(len(a["photos"]) for a in merged)

@@ -879,7 +923,8 @@ def main():
                 zucht_splits, match_stats)

    print(f"\nRoh: {len(raw_animals)}  →  eindeutig: {len(merged)}  "
-          f"| Konflikte: {len(conflicts)}  | Zucht-Splits: {len(zucht_splits)}  "
+          f"| Konflikte: {len(conflicts)}  | per Entscheidung gelöst: {resolved_by_decision}  "
+          f"| Zucht-Splits: {len(zucht_splits)}  "
          f"| Orphans: {len(orphans)}  | Fotos: {photo_count}")
    print(f"Wurf-Verknüpfung: {match_stats['parents']} (Datum+Eltern), "
          f"{match_stats['dateOnly']} (nur Datum), {match_stats['ambiguous']} mehrdeutig "
--- a/tools/import/output/review-report.md
+++ b/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: **21**
+- Konflikte zur Klärung: **19**
 - Mehrdeutige / unvollständige Einträge (ohne Name+Datum): **310**
 - Fotos zugeordnet: **137**
 - Würfe aus der Wurfchronik: **752**
@@ -27,9 +27,7 @@ Gleiches Tier (Name+Datum), aber widersprüchliche Angaben in verschiedenen Date
 |---|---|---|---|---|---|
 | 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 |
 | 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 |
@@ -142,7 +140,7 @@ Diese Tokens stehen weiter in `rawGenotype`/`unmappedTokens` — Entscheidung (M

 | Token | Vorkommen | Bedeutung (Vermutung) |
 |---|---|---|
-| `/+` | 8 | ? |
+| `/+` | 7 | ? |
 | `-g` | 2 | ? |
 | `C(C)` | 2 | Schreibweise (C trägt c) |
 | `chmchm` | 2 | Schreibweise (c[chm]c[chm]) |
--- a/tools/import/test_extract.py
+++ b/tools/import/test_extract.py
@@ -0,0 +1,116 @@
+"""Zero-dep tests for extract.py band-aware Farbschlag + name-bleed guard.
+
+Run: python test_extract.py   (exit 0 = all pass)
+Covers (PEDIGREE-LINK / Julian-confirmed): deep pedigree bands (gen >= 2, cols K/N/Q...)
+are Name/DOB/Genotype ONLY — no Farbschlag cell — so a stray health note or the next
+block's name must NOT be captured as Farbschlag; early bands (gen 0-1) keep their real
+Farbschlag. Plus the looks_like_animal_name guard (a parent name must not be a Farbschlag).
+"""
+import os
+import sys
+import zipfile
+import tempfile
+import extract as e
+
+failed = 0
+
+
+def check(name, cond):
+    global failed
+    print(("ok:   " if cond else "FAIL: ") + name)
+    if not cond:
+        failed += 1
+
+
+def _cell(ref, text):
+    return f'<c r="{ref}" t="inlineStr"><is><t>{text}</t></is></c>'
+
+
+def _make_xlsx(path, cells):
+    """cells: {(colLetter+row): text}. Build a minimal single-sheet xlsx (no styles)."""
+    rows = {}
+    for ref, text in cells.items():
+        r = int("".join(ch for ch in ref if ch.isdigit()))
+        rows.setdefault(r, []).append(_cell(ref, text))
+    body = "".join(f'<row r="{r}">{"".join(cs)}</row>' for r, cs in sorted(rows.items()))
+    sheet = ('<?xml version="1.0"?><worksheet xmlns="http://x"><sheetData>'
+             + body + "</sheetData></worksheet>")
+    with zipfile.ZipFile(path, "w") as z:
+        z.writestr("xl/worksheets/sheet1.xml", sheet)
+
+
+# --- band-aware Farbschlag ---
+# col E = gen 0 (early, HAS Farbschlag); col K = col 11 = gen 2 (deep, NO Farbschlag).
+tmp = os.path.join(tempfile.gettempdir(), "bandtest.xlsx")
+_make_xlsx(tmp, {
+    # early band (E): Name / *DOB / Farbschlag / Genotype
+    "E10": "Chesnut",
+    "E11": "*13.11.2019",
+    "E12": "Kohlfuchsschimmel",
+    "E13": "aa CC DD ee GG PP spsp rere",
+    # deep band (K): Name / *DOB / Genotype / stray NOTE (must NOT become Farbschlag)
+    "K10": "DeepAnimal",
+    "K11": "*01.01.2020",
+    "K12": "aa CC DD EE GG PP spsp rere",
+    "K13": "DD-Tumor",
+})
+try:
+    animals = e.extract_stammbaum(tmp)
+    by_name = {a["name"]: a for a in animals}
+    check("early band keeps real Farbschlag",
+          by_name.get("Chesnut", {}).get("farbschlag") == "Kohlfuchsschimmel")
+    check("deep band has NO Farbschlag (note not grabbed)",
+          by_name.get("DeepAnimal", {}).get("farbschlag") == "")
+    check("deep-band animal still parsed (Name/DOB/Genotype)",
+          "DeepAnimal" in by_name and by_name["DeepAnimal"]["dob"].startswith("01.01"))
+finally:
+    try: os.remove(tmp)
+    except OSError: pass
+
+gen = e.gen_of
+check("gen_of: early bands < 2 (E,H)", gen(5) < 2 and gen(8) < 2)
+check("gen_of: deep bands >= 2 (K,N,Q)", gen(11) >= 2 and gen(14) >= 2)
+
+# --- conflict-decisions consumption (HUMANQUESTION D / C6) ---
+dec_path = os.path.join(tempfile.gettempdir(), "conflict-decisions-test.json")
+import json as _json
+_json.dump({"resolutions": [
+    {"name": "Firefly von den Kleinen Chaoten", "dob": "18.12.2019",
+     "decision": "D-locus = D-", "genotype": "Aa c[chm]c[chm] D- Ee Gg PP Spsp",
+     "source": "test"},
+    {"name": "Flint von den Kleinen Chaoten", "dob": "23.12.2017",
+     "decision": "Todesdatum 10.05.2021 (2022 war Tippfehler)", "dateOfDeath": "10.05.2021",
+     "source": "test"},
+]}, open(dec_path, "w", encoding="utf-8"))
+merged = [
+    {"id": "x1", "name": "Firefly von den Kleinen Chaoten", "dob": "18.12.2019",
+     "conflict": True, "farbschlag": "", "death": "",
+     "genotype": {"mapped8locus": {"D": ["D", "D"]}, "rawGenotype": "DD", "unmappedTokens": []}},
+    {"id": "x2", "name": "Flint von den Kleinen Chaoten", "dob": "23.12.2017",
+     "conflict": True, "farbschlag": "", "death": "10.05.2022",
+     "genotype": {"mapped8locus": {}, "rawGenotype": "", "unmappedTokens": []}},
+]
+conflicts = [{"id": "x1", "name": "Firefly von den Kleinen Chaoten", "dob": "18.12.2019"},
+             {"id": "x2", "name": "Flint von den Kleinen Chaoten", "dob": "23.12.2017"}]
+n = e.apply_conflict_decisions(merged, conflicts, dec_path)
+check("decision un-quarantines (conflict cleared)", merged[0]["conflict"] is False)
+check("decision marks resolvedByDecision", merged[0].get("resolvedByDecision") is True)
+check("decision genotype is authoritative (D- not DD)", merged[0]["genotype"]["mapped8locus"]["D"] == ["D", "?"])
+check("decision dateOfDeath is authoritative (D5)", merged[1]["death"] == "10.05.2021")
+check("decision removes both entries from conflicts list", conflicts == [])
+check("apply_conflict_decisions returns resolved count", n == 2)
+check("missing decisions file tolerated (returns 0)",
+      e.apply_conflict_decisions([], [], os.path.join(tempfile.gettempdir(), "does-not-exist.json")) == 0)
+try: os.remove(dec_path)
+except OSError: pass
+
+# --- name-bleed guard (a parent name is not a Farbschlag) ---
+check("v.d. name rejected", e.looks_like_animal_name("Tennessee von den Kleinen Chaoten"))
+check("gen.+v.d. name rejected", e.looks_like_animal_name("Victoria Welby gen. Welby v.d. Kleinen Chaoten"))
+check("real Farbschlag accepted", not e.looks_like_animal_name("Kohlfuchsschimmel"))
+check("real Farbschlag accepted 2", not e.looks_like_animal_name("Orangeschimmel, hell"))
+
+if failed:
+    print(f"\n{failed} test(s) FAILED")
+    sys.exit(1)
+print("\nALL PASS")