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>
71 lines
1.8 KiB
Python
71 lines
1.8 KiB
Python
"""
|
|
NRU Worksheet Models — data classes and entry separation logic.
|
|
|
|
Extracted from nru_worksheet_generator.py for modularity.
|
|
"""
|
|
|
|
import logging
|
|
from typing import List, Dict, Tuple
|
|
from dataclasses import dataclass
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
@dataclass
|
|
class VocabEntry:
|
|
english: str
|
|
german: str
|
|
source_page: int = 1
|
|
|
|
|
|
@dataclass
|
|
class SentenceEntry:
|
|
german: str
|
|
english: str # For solution sheet
|
|
source_page: int = 1
|
|
|
|
|
|
def separate_vocab_and_sentences(entries: List[Dict]) -> Tuple[List[VocabEntry], List[SentenceEntry]]:
|
|
"""
|
|
Separate vocabulary entries into single words/phrases and full sentences.
|
|
|
|
Sentences are identified by:
|
|
- Ending with punctuation (. ! ?)
|
|
- Being longer than 40 characters
|
|
- Containing multiple words with capital letters mid-sentence
|
|
"""
|
|
vocab_list = []
|
|
sentence_list = []
|
|
|
|
for entry in entries:
|
|
english = entry.get("english", "").strip()
|
|
german = entry.get("german", "").strip()
|
|
source_page = entry.get("source_page", 1)
|
|
|
|
if not english or not german:
|
|
continue
|
|
|
|
# Detect if this is a sentence
|
|
is_sentence = (
|
|
english.endswith('.') or
|
|
english.endswith('!') or
|
|
english.endswith('?') or
|
|
len(english) > 50 or
|
|
(len(english.split()) > 5 and any(w[0].isupper() for w in english.split()[1:] if w))
|
|
)
|
|
|
|
if is_sentence:
|
|
sentence_list.append(SentenceEntry(
|
|
german=german,
|
|
english=english,
|
|
source_page=source_page
|
|
))
|
|
else:
|
|
vocab_list.append(VocabEntry(
|
|
english=english,
|
|
german=german,
|
|
source_page=source_page
|
|
))
|
|
|
|
return vocab_list, sentence_list
|