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>
This commit is contained in:
@@ -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)
|
||||
|
||||
@@ -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 |
|
||||
|
||||
|
||||
@@ -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:
|
||||
|
||||
Reference in New Issue
Block a user