bd4b956e3c
klausur-service (11 files): - cv_gutter_repair, ocr_pipeline_regression, upload_api - ocr_pipeline_sessions, smart_spell, nru_worksheet_generator - ocr_pipeline_overlays, mail/aggregator, zeugnis_api - cv_syllable_detect, self_rag backend-lehrer (17 files): - classroom_engine/suggestions, generators/quiz_generator - worksheets_api, llm_gateway/comparison, state_engine_api - classroom/models (→ 4 submodules), services/file_processor - alerts_agent/api/wizard+digests+routes, content_generators/pdf - classroom/routes/sessions, llm_gateway/inference - classroom_engine/analytics, auth/keycloak_auth - alerts_agent/processing/rule_engine, ai_processor/print_versions agent-core (5 files): - brain/memory_store, brain/knowledge_graph, brain/context_manager - orchestrator/supervisor, sessions/session_manager admin-lehrer (5 components): - GridOverlay, StepGridReview, DevOpsPipelineSidebar - DataFlowDiagram, sbom/wizard/page website (2 files): - DependencyMap, lehrer/abitur-archiv Other: nibis_ingestion, grid_detection_service, export-doclayout-onnx Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
114 lines
3.4 KiB
Python
114 lines
3.4 KiB
Python
"""
|
|
NiBiS Filename Parsers
|
|
|
|
Parses old and new naming conventions for NiBiS Abitur documents.
|
|
"""
|
|
|
|
import re
|
|
from typing import Dict, Optional
|
|
|
|
# Niveau-Mapping
|
|
NIVEAU_MAPPING = {
|
|
"ea": "eA", # erhoehtes Anforderungsniveau
|
|
"ga": "gA", # grundlegendes Anforderungsniveau
|
|
"neuga": "gA (neu einsetzend)",
|
|
"neuea": "eA (neu einsetzend)",
|
|
}
|
|
|
|
|
|
def parse_filename_old_format(filename: str, file_path) -> Optional[Dict]:
|
|
"""
|
|
Parst alte Namenskonvention (2016, 2017):
|
|
- {Jahr}{Fach}{Niveau}Lehrer/{Jahr}{Fach}{Niveau}A{Nr}L.pdf
|
|
- Beispiel: 2016DeutschEALehrer/2016DeutschEAA1L.pdf
|
|
"""
|
|
# Pattern fuer Lehrer-Dateien
|
|
pattern = r"(\d{4})([A-Za-z\u00e4\u00f6\u00fc\u00c4\u00d6\u00dc]+)(EA|GA|NeuGA|NeuEA)(?:Lehrer)?.*?(?:A(\d+)|Aufg(\d+))?L?\.pdf$"
|
|
|
|
match = re.search(pattern, filename, re.IGNORECASE)
|
|
if not match:
|
|
return None
|
|
|
|
year = int(match.group(1))
|
|
subject_raw = match.group(2).lower()
|
|
niveau = match.group(3).upper()
|
|
task_num = match.group(4) or match.group(5)
|
|
|
|
# Pruefe ob es ein Lehrer-Dokument ist (EWH)
|
|
is_ewh = "lehrer" in str(file_path).lower() or filename.endswith("L.pdf")
|
|
|
|
# Extrahiere Variante (Tech, Wirt, CAS, GTR, etc.)
|
|
variant = None
|
|
variant_patterns = ["Tech", "Wirt", "CAS", "GTR", "Pflicht", "BG", "mitExp", "ohneExp"]
|
|
for v in variant_patterns:
|
|
if v.lower() in str(file_path).lower():
|
|
variant = v
|
|
break
|
|
|
|
return {
|
|
"year": year,
|
|
"subject": subject_raw,
|
|
"niveau": NIVEAU_MAPPING.get(niveau.lower(), niveau),
|
|
"task_number": int(task_num) if task_num else None,
|
|
"doc_type": "EWH" if is_ewh else "Aufgabe",
|
|
"variant": variant,
|
|
}
|
|
|
|
|
|
def parse_filename_new_format(filename: str, file_path) -> Optional[Dict]:
|
|
"""
|
|
Parst neue Namenskonvention (2024, 2025):
|
|
- {Jahr}_{Fach}_{niveau}_{Nr}_EWH.pdf
|
|
- Beispiel: 2025_Deutsch_eA_I_EWH.pdf
|
|
"""
|
|
# Pattern fuer neue Dateien
|
|
pattern = r"(\d{4})_([A-Za-z\u00e4\u00f6\u00fc\u00c4\u00d6\u00dc]+)(?:BG)?_(eA|gA)(?:_([IVX\d]+))?(?:_(.+))?\.pdf$"
|
|
|
|
match = re.search(pattern, filename, re.IGNORECASE)
|
|
if not match:
|
|
return None
|
|
|
|
year = int(match.group(1))
|
|
subject_raw = match.group(2).lower()
|
|
niveau = match.group(3)
|
|
task_id = match.group(4)
|
|
suffix = match.group(5) or ""
|
|
|
|
# Task-Nummer aus roemischen Zahlen
|
|
task_num = None
|
|
if task_id:
|
|
roman_map = {"I": 1, "II": 2, "III": 3, "IV": 4, "V": 5}
|
|
task_num = roman_map.get(task_id) or (int(task_id) if task_id.isdigit() else None)
|
|
|
|
# Dokumenttyp
|
|
is_ewh = "EWH" in filename or "ewh" in filename.lower()
|
|
|
|
# Spezielle Dokumenttypen
|
|
doc_type = "EWH" if is_ewh else "Aufgabe"
|
|
if "Material" in suffix:
|
|
doc_type = "Material"
|
|
elif "GBU" in suffix:
|
|
doc_type = "GBU"
|
|
elif "Ergebnis" in suffix:
|
|
doc_type = "Ergebnis"
|
|
elif "Bewertungsbogen" in suffix:
|
|
doc_type = "Bewertungsbogen"
|
|
elif "HV" in suffix:
|
|
doc_type = "Hoerverstehen"
|
|
elif "ME" in suffix:
|
|
doc_type = "Mediation"
|
|
|
|
# BG Variante
|
|
variant = "BG" if "BG" in filename else None
|
|
if "mitExp" in str(file_path):
|
|
variant = "mitExp"
|
|
|
|
return {
|
|
"year": year,
|
|
"subject": subject_raw,
|
|
"niveau": NIVEAU_MAPPING.get(niveau.lower(), niveau),
|
|
"task_number": task_num,
|
|
"doc_type": doc_type,
|
|
"variant": variant,
|
|
}
|