Compare commits

...

2 Commits

Author SHA1 Message Date
4d9e901139 Merge feature/import-backfill: toleranter KC-Matcher + Herkunft-Backfill (fill-NULL) + Farbschlag-Zaehler
Some checks failed
CI / Backend Tests (.NET) (push) Successful in 52s
CI / Docker Build & Push (push) Has been cancelled
CI / Frontend Tests (Node/Vite) (push) Has been cancelled
- extract.py: norm_zucht-Regex-Fix (trailing \b nach '.'), is_clan_zucht() — alle KC-Schreibvarianten → canon 'kleinechaote'
- ImportService: Herkunft-Backfill (OriginBreeder NULL+resident → aus Eltern, sonst 'Zucht der Kleinen Chaoten'); fixt C bei naechstem Import-execute; ueberschreibt nie non-null
- FarbschlagWouldRebackfill no-op-Zaehler (Overwrite-Pfad gated auf Julian A/B/C)
- Keine Schema-Aenderung. Gate 133/133 C# + 57/57 python, ef has-pending=No
[god-QA: disjunkt zu qa-regression-Merge; Herkunft-Backfill laeuft nur bei Import-execute = REIMPORT-3 supervised]

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-06 17:33:58 +02:00
358e30db1f IMPORT-BACKFILL: toleranter KC-Matcher + Herkunft-Backfill + FarbschlagWouldRebackfill-Zaehler
1) TOLERANTER KC-MATCHER (extract.py norm_zucht): trailing \b nach '.' greift nicht
   zwischen two non-word-chars (z.B. nach '.' vor ' '). Fix: r\bv\.\s?d\. (kein \b
   am Ende). Alle Schreibvarianten ('Zucht der Kleinen Chaoten', 'kleinen Chaoten',
   'v.d. Kleinen Chaoten', '[ZdkC]') -> canon 'kleinechaote'. +is_clan_zucht() helper.
   +11 Python-Tests (Regression + neue Varianten). FIX-1-Entscheidungs-Matching
   unberuehrt (canon_pair loest v.d. bereits via split_name_zucht).

2) HERKUNFT-BACKFILL (ImportService.cs, fill-NULL-only): POST-Sweep ueber alle
   DB-Tiere mit OriginBreeder==null && IsResident==true. Leitet OriginBreeder aus
   dem Elterntier (FatherId/MotherId -> OriginBreeder) ab; Fallback 'Zucht der
   Kleinen Chaoten'. NIEMALS ueberschreibt nicht-leeren OriginBreeder. Trocken-Lauf
   zaehlt HerkunftBackfilled; Execute schreibt. Fixt Tier 'C' (OriginBreeder null).

3) FARBSCHLAG-WOULD-REBACKFILL (no-op Zaehler): zaehlt bereits-importierte Tiere,
   bei denen der aktuelle Extraktor einen anderen Farbschlag liefert als in der DB.
   Kein Overwrite (Sicherheitsmechanismus ausstehend auf god/Julian-Freigabe);
   Optionen A/B/C an god gemeldet, Empfehlung: Option B (Timestamp-basiert).

4) ResidencySummary um HerkunftBackfilled + FarbschlagWouldRebackfill erweitert.
   ImportReport-Notizen fuer beide neuen Zaehler.

GATE: 133/133 C#-Tests, 57 Python-Tests, ef has-pending=No.
2026-06-06 17:29:02 +02:00
4 changed files with 103 additions and 7 deletions

View File

@@ -82,8 +82,12 @@ namespace GerbilManagerWebAPI.Import
ResidencySummary? Residency = null);
/// <summary>Bestand (resident) vs external pedigree ancestors; FlippedByParentRule = foreign-
/// Zuchtname animals made resident because they parented a Clan offspring (rule b).</summary>
public sealed record ResidencySummary(int Resident, int External, int FlippedByParentRule);
/// Zuchtname animals made resident because they parented a Clan offspring (rule b).
/// HerkunftBackfilled = resident animals whose null OriginBreeder was filled (safe, no overwrite).
/// FarbschlagWouldRebackfill = already-imported animals with a stale ColorVariety that the
/// current extract would update (no-op counter until the safety mechanism is ratified).</summary>
public sealed record ResidencySummary(int Resident, int External, int FlippedByParentRule,
int HerkunftBackfilled = 0, int FarbschlagWouldRebackfill = 0);
public sealed record LitterSummary(int InSource, int Created, int AlreadyImported,
int DerivedFromChart = 0, int DerivedSkipped = 0, int ParentFksDropped = 0,

View File

@@ -137,12 +137,14 @@ namespace GerbilManagerWebAPI.Import
// 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();
.Select(g => new { g.Id, g.Name, g.DateOfBirth, g.ExternalRef, g.LitterId, g.ColorVarietyId }).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);
var existingColorVarietyByExtRef = existingRows.Where(g => g.ExternalRef != null)
.ToDictionary(g => g.ExternalRef!, g => g.ColorVarietyId);
// PASS 1: assign ids + resolve fb/gender/Wurfchronik link (no writes yet).
var plan = new List<AnimalPlan>();
@@ -169,7 +171,8 @@ namespace GerbilManagerWebAPI.Import
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));
var currentColorVarietyId = exists && existingColorVarietyByExtRef.TryGetValue(a.Id, out var ecv) ? ecv : null;
plan.Add(new AnimalPlan(a, gid, exists, wurfLitterId, currentLitter, colorVarietyId, gender, currentColorVarietyId));
}
// PASS 1.5: PEDIGREE-LINK — synthesize/reuse a litter from chart-position parentRefs for
@@ -460,6 +463,51 @@ namespace GerbilManagerWebAPI.Import
if (execute && parentFksBackfilled > 0) await _db.SaveChangesAsync();
}
// FARBSCHLAG-RE-MATCH — no-op counter (safety mechanism pending god/Julian sign-off).
// Counts already-imported animals where the current extract matched a DIFFERENT
// ColorVariety than what is currently stored in the DB. Does NOT update any row.
int farbschlagWouldRebackfill = plan.Count(p =>
p.Exists && p.ColorVarietyId is not null && p.ColorVarietyId != p.CurrentColorVarietyId);
// HERKUNFT BACKFILL (fill-NULL-only, safe): sweep all resident animals whose
// OriginBreeder is null and fill it with a derived value or 'Zucht der Kleinen Chaoten'.
// NEVER overwrites a non-null OriginBreeder (Julian: "alle Schreibweisen unterstützen").
const string DefaultClanBreeder = "Zucht der Kleinen Chaoten";
int herkunftBackfilled = 0;
{
var needsHerkunft = await _db.Gerbils
.Where(g => g.OriginBreeder == null && g.IsResident)
.Select(g => new { g.Id, g.LitterId })
.ToListAsync();
foreach (var g in needsHerkunft)
{
herkunftBackfilled++;
if (execute)
{
// Prefer the OriginBreeder of an existing parent (father first, then mother).
string? derived = null;
if (g.LitterId is not null)
{
var parentIds = await _db.Litters
.Where(l => l.Id == g.LitterId)
.Select(l => new { l.FatherId, l.MotherId })
.FirstOrDefaultAsync();
if (parentIds?.FatherId is Guid fid)
derived = await _db.Gerbils.Where(gb => gb.Id == fid && gb.OriginBreeder != null)
.Select(gb => gb.OriginBreeder).FirstOrDefaultAsync();
if (derived is null && parentIds?.MotherId is Guid mid)
derived = await _db.Gerbils.Where(gb => gb.Id == mid && gb.OriginBreeder != null)
.Select(gb => gb.OriginBreeder).FirstOrDefaultAsync();
}
var row = await _db.Gerbils.FindAsync(g.Id);
if (row is not null && row.OriginBreeder is null)
row.OriginBreeder = derived ?? DefaultClanBreeder;
}
}
if (execute && herkunftBackfilled > 0) await _db.SaveChangesAsync();
}
if (littersWithoutDate > 0)
notes.Add($"Würfe ohne Datum: {littersWithoutDate} Wurfchronik-Einträge ohne parsbares Geburtsdatum übersprungen (weder erstellt noch verknüpft).");
notes.Add("Quarantäne (kein Import): Konflikte + Stubs ohne Geburtsdatum + unsichere Wurf-Zuordnungen — warten auf die Prüfung durch die Züchterin.");
@@ -469,6 +517,10 @@ namespace GerbilManagerWebAPI.Import
if (parentFksBackfilled > 0)
notes.Add($"Parent-FK-Backfill: {parentFksBackfilled} bereits importierte Würfe haben jetzt eine Eltern-Verknüpfung (Elternteil war zuvor in Quarantäne, jetzt geladen).");
notes.Add($"Bestand/Herkunft: {residentTotal} im Bestand (Clan Kleine Chaoten), {externalTotal} externe Ahnen ({flippedByParentRule} davon über die Eltern-Regel als Bestand erkannt).");
if (herkunftBackfilled > 0)
notes.Add($"Herkunft-Backfill: {herkunftBackfilled} Bestand-Tier(e) mit leerem Herkunft-Feld befüllt (Zucht der Kleinen Chaoten oder von Elternteil abgeleitet). Niemals überschrieben.");
if (farbschlagWouldRebackfill > 0)
notes.Add($"Farbschlag-Hinweis (kein Overwrite): {farbschlagWouldRebackfill} bereits importierte Tier(e) haben einen veralteten Farbschlag, den der aktuelle Extraktor korrigieren würde — Overwrite-Mechanismus ausstehend (god/Julian Freigabe).");
int conflictsResolvedByDecision = loadable.Count(a => a.ResolvedByDecision);
if (conflictsResolvedByDecision > 0)
notes.Add($"Konfliktauflösungen: {conflictsResolvedByDecision} Tier(e) anhand von conflict-decisions.json un-quarantänet (Genotyp/Farbschlag der Züchterin ist maßgeblich).");
@@ -484,7 +536,8 @@ namespace GerbilManagerWebAPI.Import
Photos: new PhotoSummary(photosAttached, photosMissing),
Samples: samples,
Notes: notes,
Residency: new ResidencySummary(residentTotal, externalTotal, flippedByParentRule));
Residency: new ResidencySummary(residentTotal, externalTotal, flippedByParentRule,
HerkunftBackfilled: herkunftBackfilled, FarbschlagWouldRebackfill: farbschlagWouldRebackfill));
}
private T? Load<T>(string file)
@@ -574,7 +627,8 @@ namespace GerbilManagerWebAPI.Import
/// <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);
Guid? CurrentLitterId, Guid? ColorVarietyId, Gender Gender,
Guid? CurrentColorVarietyId = null);
/// <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);

View File

@@ -129,7 +129,9 @@ def norm_zucht(z):
if not z:
return ""
n = z.lower()
n = re.sub(r"\bv\.\s?d\.\b", " ", n)
# TOLERANT KC-MATCHER FIX: trailing \b after '.' never fires when next char is ' '
# (both are non-word chars), so "v.d. kleinen" was NOT stripped. Drop the trailing \b.
n = re.sub(r"\bv\.\s?d\.", " ", n)
n = re.sub(r"\b(zucht|privatzucht|der|die|den|des|dem|von|of)\b", " ", n)
n = re.sub(r"[^a-z0-9äöüß ]", " ", n)
words = [w[:-1] if len(w) > 4 and w.endswith("n") else w for w in n.split()]
@@ -137,6 +139,15 @@ def norm_zucht(z):
return ZUCHT_ALIASES.get(key, key)
def is_clan_zucht(z):
"""True if the zucht name (raw or canonical) identifies the Kleine Chaoten home cattery.
Accepts all known spellings: 'Zucht der Kleinen Chaoten', 'kleinen Chaoten',
'v.d. Kleinen Chaoten', '[ZdkC]', 'kleinechaote', etc.
"""
return norm_zucht(z) == "kleinechaote"
def canon_pair(raw):
"""Full raw name -> (normalised call-name, canonical zucht)."""
name, zucht = split_name_zucht(raw)

View File

@@ -280,6 +280,33 @@ check("gen.+v.d. name rejected", e.looks_like_animal_name("Victoria Welby gen. W
check("real Farbschlag accepted", not e.looks_like_animal_name("Kohlfuchsschimmel"))
check("real Farbschlag accepted 2", not e.looks_like_animal_name("Orangeschimmel, hell"))
# --- TOLERANT KC-MATCHER (IMPORT-BACKFILL): all clan spelling variants -> canon 'kleinechaote' ---
# Julian-Entscheidung: Zucht = Kleine Chaoten wenn 'klein'+'chaoten' ODER bekannte Abkürzungen.
# The v.d. fix: trailing \b after '.' failed when next char is ' ' (non-word), so
# "v.d. kleinen chaoten" was NOT stripped before. Fix: drop the trailing \b.
check("KC-matcher: 'Zucht der Kleinen Chaoten'",
e.is_clan_zucht("Zucht der Kleinen Chaoten"))
check("KC-matcher: 'kleinen Chaoten' (no prefix)",
e.is_clan_zucht("kleinen Chaoten"))
check("KC-matcher: 'v.d. Kleinen Chaoten' (v.d. prefix — was broken before fix)",
e.is_clan_zucht("v.d. Kleinen Chaoten"))
check("KC-matcher: '[ZdkC]' shorthand (bracket form, alias in ZUCHT_ALIASES)",
e.is_clan_zucht("ZdkC"))
check("KC-matcher: 'von den Kleinen Chaoten' (full long form)",
e.is_clan_zucht("von den Kleinen Chaoten"))
check("KC-matcher: empty string -> NOT clan",
not e.is_clan_zucht(""))
check("KC-matcher: 'Black Forest' -> NOT clan",
not e.is_clan_zucht("Black Forest"))
check("KC-matcher: norm_zucht regression — 'Kleine Chaoten' (base form still works)",
e.norm_zucht("Kleine Chaoten") == "kleinechaote")
check("KC-matcher: norm_zucht regression — 'von den Kleinen Chaoten'",
e.norm_zucht("von den Kleinen Chaoten") == "kleinechaote")
# Decision-matching FIX-1 already tested above; v.d. in decision matches 'von den' in record
# because both reduce to the same canon_pair. Verify norm_zucht directly for v.d.:
check("KC-matcher: norm_zucht('v.d. Kleinen Chaoten') == 'kleinechaote' (was broken before fix)",
e.norm_zucht("v.d. Kleinen Chaoten") == "kleinechaote")
if failed:
print(f"\n{failed} test(s) FAILED")
sys.exit(1)