[split-required] Split final 43 files (500-668 LOC) to complete refactoring
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>
This commit is contained in:
Benjamin Admin
@@ -10,66 +10,27 @@ Generiert:
|
||||
|
||||
import logging
|
||||
import json
|
||||
import re
|
||||
from typing import List, Dict, Any, Optional, Tuple
|
||||
from dataclasses import dataclass
|
||||
from enum import Enum
|
||||
from typing import List, Dict, Any, Optional
|
||||
|
||||
from .quiz_models import (
|
||||
QuizType,
|
||||
TrueFalseQuestion,
|
||||
MatchingPair,
|
||||
SortingItem,
|
||||
OpenQuestion,
|
||||
Quiz,
|
||||
)
|
||||
from .quiz_helpers import (
|
||||
extract_factual_sentences,
|
||||
negate_sentence,
|
||||
extract_definitions,
|
||||
extract_sequence,
|
||||
extract_keywords,
|
||||
)
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class QuizType(str, Enum):
|
||||
"""Typen von Quiz-Aufgaben."""
|
||||
TRUE_FALSE = "true_false"
|
||||
MATCHING = "matching"
|
||||
SORTING = "sorting"
|
||||
OPEN_ENDED = "open_ended"
|
||||
|
||||
|
||||
@dataclass
|
||||
class TrueFalseQuestion:
|
||||
"""Eine Wahr/Falsch-Frage."""
|
||||
statement: str
|
||||
is_true: bool
|
||||
explanation: str
|
||||
source_reference: Optional[str] = None
|
||||
|
||||
|
||||
@dataclass
|
||||
class MatchingPair:
|
||||
"""Ein Zuordnungspaar."""
|
||||
left: str
|
||||
right: str
|
||||
hint: Optional[str] = None
|
||||
|
||||
|
||||
@dataclass
|
||||
class SortingItem:
|
||||
"""Ein Element zum Sortieren."""
|
||||
text: str
|
||||
correct_position: int
|
||||
category: Optional[str] = None
|
||||
|
||||
|
||||
@dataclass
|
||||
class OpenQuestion:
|
||||
"""Eine offene Frage."""
|
||||
question: str
|
||||
model_answer: str
|
||||
keywords: List[str]
|
||||
points: int = 1
|
||||
|
||||
|
||||
@dataclass
|
||||
class Quiz:
|
||||
"""Ein komplettes Quiz."""
|
||||
quiz_type: QuizType
|
||||
title: str
|
||||
questions: List[Any] # Je nach Typ unterschiedlich
|
||||
topic: Optional[str] = None
|
||||
difficulty: str = "medium"
|
||||
|
||||
|
||||
class QuizGenerator:
|
||||
"""
|
||||
Generiert verschiedene Quiz-Typen aus Quelltexten.
|
||||
@@ -146,13 +107,12 @@ class QuizGenerator:
|
||||
return self._generate_true_false_llm(source_text, num_questions, difficulty)
|
||||
|
||||
# Automatische Generierung
|
||||
sentences = self._extract_factual_sentences(source_text)
|
||||
sentences = extract_factual_sentences(source_text)
|
||||
questions = []
|
||||
|
||||
for i, sentence in enumerate(sentences[:num_questions]):
|
||||
# Abwechselnd wahre und falsche Aussagen
|
||||
if i % 2 == 0:
|
||||
# Wahre Aussage
|
||||
questions.append(TrueFalseQuestion(
|
||||
statement=sentence,
|
||||
is_true=True,
|
||||
@@ -160,8 +120,7 @@ class QuizGenerator:
|
||||
source_reference=sentence[:50]
|
||||
))
|
||||
else:
|
||||
# Falsche Aussage (Negation)
|
||||
false_statement = self._negate_sentence(sentence)
|
||||
false_statement = negate_sentence(sentence)
|
||||
questions.append(TrueFalseQuestion(
|
||||
statement=false_statement,
|
||||
is_true=False,
|
||||
@@ -222,9 +181,8 @@ Antworte im JSON-Format:
|
||||
if self.llm_client:
|
||||
return self._generate_matching_llm(source_text, num_pairs, difficulty)
|
||||
|
||||
# Automatische Generierung: Begriff -> Definition
|
||||
pairs = []
|
||||
definitions = self._extract_definitions(source_text)
|
||||
definitions = extract_definitions(source_text)
|
||||
|
||||
for term, definition in definitions[:num_pairs]:
|
||||
pairs.append(MatchingPair(
|
||||
@@ -286,9 +244,8 @@ Antworte im JSON-Format:
|
||||
if self.llm_client:
|
||||
return self._generate_sorting_llm(source_text, num_items, difficulty)
|
||||
|
||||
# Automatische Generierung: Chronologische Reihenfolge
|
||||
items = []
|
||||
steps = self._extract_sequence(source_text)
|
||||
steps = extract_sequence(source_text)
|
||||
|
||||
for i, step in enumerate(steps[:num_items]):
|
||||
items.append(SortingItem(
|
||||
@@ -349,9 +306,8 @@ Antworte im JSON-Format:
|
||||
if self.llm_client:
|
||||
return self._generate_open_ended_llm(source_text, num_questions, difficulty)
|
||||
|
||||
# Automatische Generierung
|
||||
questions = []
|
||||
sentences = self._extract_factual_sentences(source_text)
|
||||
sentences = extract_factual_sentences(source_text)
|
||||
|
||||
question_starters = [
|
||||
"Was bedeutet",
|
||||
@@ -362,8 +318,7 @@ Antworte im JSON-Format:
|
||||
]
|
||||
|
||||
for i, sentence in enumerate(sentences[:num_questions]):
|
||||
# Extrahiere Schlüsselwort
|
||||
keywords = self._extract_keywords(sentence)
|
||||
keywords = extract_keywords(sentence)
|
||||
if keywords:
|
||||
keyword = keywords[0]
|
||||
starter = question_starters[i % len(question_starters)]
|
||||
@@ -421,76 +376,6 @@ Antworte im JSON-Format:
|
||||
logger.error(f"LLM error: {e}")
|
||||
return self._generate_open_ended(source_text, num_questions, difficulty)
|
||||
|
||||
# Hilfsmethoden
|
||||
|
||||
def _extract_factual_sentences(self, text: str) -> List[str]:
|
||||
"""Extrahiert Fakten-Sätze aus dem Text."""
|
||||
sentences = re.split(r'[.!?]+', text)
|
||||
factual = []
|
||||
|
||||
for sentence in sentences:
|
||||
sentence = sentence.strip()
|
||||
# Filtere zu kurze oder fragende Sätze
|
||||
if len(sentence) > 20 and '?' not in sentence:
|
||||
factual.append(sentence)
|
||||
|
||||
return factual
|
||||
|
||||
def _negate_sentence(self, sentence: str) -> str:
|
||||
"""Negiert eine Aussage einfach."""
|
||||
# Einfache Negation durch Einfügen von "nicht"
|
||||
words = sentence.split()
|
||||
if len(words) > 2:
|
||||
# Nach erstem Verb "nicht" einfügen
|
||||
for i, word in enumerate(words):
|
||||
if word.endswith(('t', 'en', 'st')) and i > 0:
|
||||
words.insert(i + 1, 'nicht')
|
||||
break
|
||||
return ' '.join(words)
|
||||
|
||||
def _extract_definitions(self, text: str) -> List[Tuple[str, str]]:
|
||||
"""Extrahiert Begriff-Definition-Paare."""
|
||||
definitions = []
|
||||
|
||||
# Suche nach Mustern wie "X ist Y" oder "X bezeichnet Y"
|
||||
patterns = [
|
||||
r'(\w+)\s+ist\s+(.+?)[.]',
|
||||
r'(\w+)\s+bezeichnet\s+(.+?)[.]',
|
||||
r'(\w+)\s+bedeutet\s+(.+?)[.]',
|
||||
r'(\w+):\s+(.+?)[.]',
|
||||
]
|
||||
|
||||
for pattern in patterns:
|
||||
matches = re.findall(pattern, text)
|
||||
for term, definition in matches:
|
||||
if len(definition) > 10:
|
||||
definitions.append((term, definition.strip()))
|
||||
|
||||
return definitions
|
||||
|
||||
def _extract_sequence(self, text: str) -> List[str]:
|
||||
"""Extrahiert eine Sequenz von Schritten."""
|
||||
steps = []
|
||||
|
||||
# Suche nach nummerierten Schritten
|
||||
numbered = re.findall(r'\d+[.)]\s*([^.]+)', text)
|
||||
steps.extend(numbered)
|
||||
|
||||
# Suche nach Signalwörtern
|
||||
signal_words = ['zuerst', 'dann', 'danach', 'anschließend', 'schließlich']
|
||||
for word in signal_words:
|
||||
pattern = rf'{word}\s+([^.]+)'
|
||||
matches = re.findall(pattern, text, re.IGNORECASE)
|
||||
steps.extend(matches)
|
||||
|
||||
return steps
|
||||
|
||||
def _extract_keywords(self, text: str) -> List[str]:
|
||||
"""Extrahiert Schlüsselwörter."""
|
||||
# Längere Wörter mit Großbuchstaben (meist Substantive)
|
||||
words = re.findall(r'\b[A-ZÄÖÜ][a-zäöüß]+\b', text)
|
||||
return list(set(words))[:5]
|
||||
|
||||
def _empty_quiz(self, quiz_type: QuizType, title: str) -> Quiz:
|
||||
"""Erstellt leeres Quiz bei Fehler."""
|
||||
return Quiz(
|
||||
@@ -549,7 +434,6 @@ Antworte im JSON-Format:
|
||||
return self._true_false_to_h5p(quiz)
|
||||
elif quiz.quiz_type == QuizType.MATCHING:
|
||||
return self._matching_to_h5p(quiz)
|
||||
# Weitere Typen...
|
||||
return {}
|
||||
|
||||
def _true_false_to_h5p(self, quiz: Quiz) -> Dict[str, Any]:
|
||||
|
||||
70
backend-lehrer/generators/quiz_helpers.py
Normal file
70
backend-lehrer/generators/quiz_helpers.py
Normal file
@@ -0,0 +1,70 @@
|
||||
"""
|
||||
Quiz Helpers - Text-Verarbeitungs-Hilfsfunktionen fuer Quiz-Generierung.
|
||||
"""
|
||||
|
||||
import re
|
||||
from typing import List, Tuple
|
||||
|
||||
|
||||
def extract_factual_sentences(text: str) -> List[str]:
|
||||
"""Extrahiert Fakten-Sätze aus dem Text."""
|
||||
sentences = re.split(r'[.!?]+', text)
|
||||
factual = []
|
||||
|
||||
for sentence in sentences:
|
||||
sentence = sentence.strip()
|
||||
if len(sentence) > 20 and '?' not in sentence:
|
||||
factual.append(sentence)
|
||||
|
||||
return factual
|
||||
|
||||
|
||||
def negate_sentence(sentence: str) -> str:
|
||||
"""Negiert eine Aussage einfach."""
|
||||
words = sentence.split()
|
||||
if len(words) > 2:
|
||||
for i, word in enumerate(words):
|
||||
if word.endswith(('t', 'en', 'st')) and i > 0:
|
||||
words.insert(i + 1, 'nicht')
|
||||
break
|
||||
return ' '.join(words)
|
||||
|
||||
|
||||
def extract_definitions(text: str) -> List[Tuple[str, str]]:
|
||||
"""Extrahiert Begriff-Definition-Paare."""
|
||||
definitions = []
|
||||
patterns = [
|
||||
r'(\w+)\s+ist\s+(.+?)[.]',
|
||||
r'(\w+)\s+bezeichnet\s+(.+?)[.]',
|
||||
r'(\w+)\s+bedeutet\s+(.+?)[.]',
|
||||
r'(\w+):\s+(.+?)[.]',
|
||||
]
|
||||
|
||||
for pattern in patterns:
|
||||
matches = re.findall(pattern, text)
|
||||
for term, definition in matches:
|
||||
if len(definition) > 10:
|
||||
definitions.append((term, definition.strip()))
|
||||
|
||||
return definitions
|
||||
|
||||
|
||||
def extract_sequence(text: str) -> List[str]:
|
||||
"""Extrahiert eine Sequenz von Schritten."""
|
||||
steps = []
|
||||
numbered = re.findall(r'\d+[.)]\s*([^.]+)', text)
|
||||
steps.extend(numbered)
|
||||
|
||||
signal_words = ['zuerst', 'dann', 'danach', 'anschließend', 'schließlich']
|
||||
for word in signal_words:
|
||||
pattern = rf'{word}\s+([^.]+)'
|
||||
matches = re.findall(pattern, text, re.IGNORECASE)
|
||||
steps.extend(matches)
|
||||
|
||||
return steps
|
||||
|
||||
|
||||
def extract_keywords(text: str) -> List[str]:
|
||||
"""Extrahiert Schlüsselwörter."""
|
||||
words = re.findall(r'\b[A-ZÄÖÜ][a-zäöüß]+\b', text)
|
||||
return list(set(words))[:5]
|
||||
65
backend-lehrer/generators/quiz_models.py
Normal file
65
backend-lehrer/generators/quiz_models.py
Normal file
@@ -0,0 +1,65 @@
|
||||
"""
|
||||
Quiz Models - Datenmodelle fuer Quiz-Generierung.
|
||||
|
||||
Enthaelt alle Dataclasses und Enums fuer Quiz-Typen:
|
||||
- True/False Fragen
|
||||
- Zuordnungsaufgaben (Matching)
|
||||
- Sortieraufgaben
|
||||
- Offene Fragen
|
||||
"""
|
||||
|
||||
from typing import List, Any, Optional
|
||||
from dataclasses import dataclass
|
||||
from enum import Enum
|
||||
|
||||
|
||||
class QuizType(str, Enum):
|
||||
"""Typen von Quiz-Aufgaben."""
|
||||
TRUE_FALSE = "true_false"
|
||||
MATCHING = "matching"
|
||||
SORTING = "sorting"
|
||||
OPEN_ENDED = "open_ended"
|
||||
|
||||
|
||||
@dataclass
|
||||
class TrueFalseQuestion:
|
||||
"""Eine Wahr/Falsch-Frage."""
|
||||
statement: str
|
||||
is_true: bool
|
||||
explanation: str
|
||||
source_reference: Optional[str] = None
|
||||
|
||||
|
||||
@dataclass
|
||||
class MatchingPair:
|
||||
"""Ein Zuordnungspaar."""
|
||||
left: str
|
||||
right: str
|
||||
hint: Optional[str] = None
|
||||
|
||||
|
||||
@dataclass
|
||||
class SortingItem:
|
||||
"""Ein Element zum Sortieren."""
|
||||
text: str
|
||||
correct_position: int
|
||||
category: Optional[str] = None
|
||||
|
||||
|
||||
@dataclass
|
||||
class OpenQuestion:
|
||||
"""Eine offene Frage."""
|
||||
question: str
|
||||
model_answer: str
|
||||
keywords: List[str]
|
||||
points: int = 1
|
||||
|
||||
|
||||
@dataclass
|
||||
class Quiz:
|
||||
"""Ein komplettes Quiz."""
|
||||
quiz_type: QuizType
|
||||
title: str
|
||||
questions: List[Any] # Je nach Typ unterschiedlich
|
||||
topic: Optional[str] = None
|
||||
difficulty: str = "medium"
|
||||
Reference in New Issue
Block a user