b6983ab1dc
backend-lehrer (5 files): - alerts_agent/db/repository.py (992 → 5), abitur_docs_api.py (956 → 3) - teacher_dashboard_api.py (951 → 3), services/pdf_service.py (916 → 3) - mail/mail_db.py (987 → 6) klausur-service (5 files): - legal_templates_ingestion.py (942 → 3), ocr_pipeline_postprocess.py (929 → 4) - ocr_pipeline_words.py (876 → 3), ocr_pipeline_ocr_merge.py (616 → 2) - KorrekturPage.tsx (956 → 6) website (5 pages): - mail (985 → 9), edu-search (958 → 8), mac-mini (950 → 7) - ocr-labeling (946 → 7), audit-workspace (871 → 4) studio-v2 (5 files + 1 deleted): - page.tsx (946 → 5), MessagesContext.tsx (925 → 4) - korrektur (914 → 6), worksheet-cleanup (899 → 6) - useVocabWorksheet.ts (888 → 3) - Deleted dead page-original.tsx (934 LOC) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
125 lines
3.6 KiB
Python
125 lines
3.6 KiB
Python
"""
|
|
Abitur Document Store - Dateinamen-Erkennung und Helfer.
|
|
|
|
Erkennt Metadaten aus NiBiS-Dateinamen (Niedersachsen).
|
|
"""
|
|
|
|
import re
|
|
from typing import Dict, Any
|
|
from pathlib import Path
|
|
|
|
from abitur_docs_models import (
|
|
Bundesland, Fach, Niveau, DokumentTyp, VerarbeitungsStatus,
|
|
RecognitionResult, AbiturDokument, DokumentResponse,
|
|
FACH_NAME_MAPPING,
|
|
)
|
|
|
|
|
|
def parse_nibis_filename(filename: str) -> RecognitionResult:
|
|
"""
|
|
Erkennt Metadaten aus NiBiS-Dateinamen.
|
|
|
|
Beispiele:
|
|
- 2025_Deutsch_eA_I.pdf
|
|
- 2025_Deutsch_eA_I_EWH.pdf
|
|
- 2025_Biologie_gA_1.pdf
|
|
- 2025_Englisch_eA_HV.pdf (Hörverstehen)
|
|
"""
|
|
result = RecognitionResult(
|
|
success=False,
|
|
bundesland=Bundesland.NIEDERSACHSEN,
|
|
fach=None,
|
|
jahr=None,
|
|
niveau=None,
|
|
typ=None,
|
|
aufgaben_nummer=None,
|
|
confidence=0.0,
|
|
raw_filename=filename,
|
|
suggestions=[]
|
|
)
|
|
|
|
# Bereinige Dateiname
|
|
name = Path(filename).stem.lower()
|
|
|
|
# Extrahiere Jahr (4 Ziffern am Anfang)
|
|
jahr_match = re.match(r'^(\d{4})', name)
|
|
if jahr_match:
|
|
result.jahr = int(jahr_match.group(1))
|
|
result.confidence += 0.2
|
|
|
|
# Extrahiere Fach
|
|
for fach_key, fach_enum in FACH_NAME_MAPPING.items():
|
|
if fach_key in name.replace("_", "").replace("-", ""):
|
|
result.fach = fach_enum
|
|
result.confidence += 0.3
|
|
break
|
|
|
|
# Extrahiere Niveau (eA/gA)
|
|
if "_ea" in name or "_ea_" in name or "ea_" in name:
|
|
result.niveau = Niveau.EA
|
|
result.confidence += 0.2
|
|
elif "_ga" in name or "_ga_" in name or "ga_" in name:
|
|
result.niveau = Niveau.GA
|
|
result.confidence += 0.2
|
|
|
|
# Extrahiere Typ
|
|
if "_ewh" in name:
|
|
result.typ = DokumentTyp.ERWARTUNGSHORIZONT
|
|
result.confidence += 0.2
|
|
elif "_hv" in name or "hoerverstehen" in name:
|
|
result.typ = DokumentTyp.HOERVERSTEHEN
|
|
result.confidence += 0.15
|
|
elif "_sm" in name or "_me" in name or "sprachmittlung" in name:
|
|
result.typ = DokumentTyp.SPRACHMITTLUNG
|
|
result.confidence += 0.15
|
|
elif "deckblatt" in name:
|
|
result.typ = DokumentTyp.DECKBLATT
|
|
result.confidence += 0.15
|
|
elif "material" in name:
|
|
result.typ = DokumentTyp.MATERIAL
|
|
result.confidence += 0.15
|
|
elif "bewertung" in name:
|
|
result.typ = DokumentTyp.BEWERTUNGSBOGEN
|
|
result.confidence += 0.15
|
|
else:
|
|
result.typ = DokumentTyp.AUFGABE
|
|
result.confidence += 0.1
|
|
|
|
# Extrahiere Aufgabennummer (römisch oder arabisch)
|
|
aufgabe_match = re.search(r'_([ivx]+|[1-4][abc]?)(?:_|\.pdf|$)', name, re.IGNORECASE)
|
|
if aufgabe_match:
|
|
result.aufgaben_nummer = aufgabe_match.group(1).upper()
|
|
result.confidence += 0.1
|
|
|
|
# Erfolg wenn mindestens Fach und Jahr erkannt
|
|
if result.fach and result.jahr:
|
|
result.success = True
|
|
|
|
# Normalisiere Confidence auf max 1.0
|
|
result.confidence = min(result.confidence, 1.0)
|
|
|
|
return result
|
|
|
|
|
|
def to_dokument_response(doc: AbiturDokument) -> DokumentResponse:
|
|
"""Konvertiert internes Dokument zu Response."""
|
|
return DokumentResponse(
|
|
id=doc.id,
|
|
dateiname=doc.dateiname,
|
|
original_dateiname=doc.original_dateiname,
|
|
bundesland=doc.bundesland,
|
|
fach=doc.fach,
|
|
jahr=doc.jahr,
|
|
niveau=doc.niveau,
|
|
typ=doc.typ,
|
|
aufgaben_nummer=doc.aufgaben_nummer,
|
|
status=doc.status,
|
|
confidence=doc.confidence,
|
|
file_path=doc.file_path,
|
|
file_size=doc.file_size,
|
|
indexed=doc.indexed,
|
|
vector_ids=doc.vector_ids,
|
|
created_at=doc.created_at,
|
|
updated_at=doc.updated_at
|
|
)
|