[split-required] Split 700-870 LOC files across all services
backend-lehrer (11 files): - llm_gateway/routes/schools.py (867 → 5), recording_api.py (848 → 6) - messenger_api.py (840 → 5), print_generator.py (824 → 5) - unit_analytics_api.py (751 → 5), classroom/routes/context.py (726 → 4) - llm_gateway/routes/edu_search_seeds.py (710 → 4) klausur-service (12 files): - ocr_labeling_api.py (845 → 4), metrics_db.py (833 → 4) - legal_corpus_api.py (790 → 4), page_crop.py (758 → 3) - mail/ai_service.py (747 → 4), github_crawler.py (767 → 3) - trocr_service.py (730 → 4), full_compliance_pipeline.py (723 → 4) - dsfa_rag_api.py (715 → 4), ocr_pipeline_auto.py (705 → 4) website (6 pages): - audit-checklist (867 → 8), content (806 → 6) - screen-flow (790 → 4), scraper (789 → 5) - zeugnisse (776 → 5), modules (745 → 4) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
193
backend-lehrer/ai_processing/print_cloze.py
Normal file
193
backend-lehrer/ai_processing/print_cloze.py
Normal file
@@ -0,0 +1,193 @@
|
||||
"""
|
||||
AI Processing - Print Version Generator: Cloze (Lueckentext).
|
||||
|
||||
Generates printable HTML for cloze/fill-in-the-blank worksheets.
|
||||
"""
|
||||
|
||||
from pathlib import Path
|
||||
import json
|
||||
import random
|
||||
import logging
|
||||
|
||||
from .core import BEREINIGT_DIR
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def generate_print_version_cloze(cloze_path: Path, include_answers: bool = False) -> Path:
|
||||
"""
|
||||
Generiert eine druckbare HTML-Version der Lueckentexte.
|
||||
|
||||
Args:
|
||||
cloze_path: Pfad zur *_cloze.json Datei
|
||||
include_answers: True fuer Loesungsblatt (fuer Eltern)
|
||||
|
||||
Returns:
|
||||
Pfad zur generierten HTML-Datei
|
||||
"""
|
||||
if not cloze_path.exists():
|
||||
raise FileNotFoundError(f"Cloze-Datei nicht gefunden: {cloze_path}")
|
||||
|
||||
cloze_data = json.loads(cloze_path.read_text(encoding="utf-8"))
|
||||
items = cloze_data.get("cloze_items", [])
|
||||
metadata = cloze_data.get("metadata", {})
|
||||
|
||||
title = metadata.get("source_title", "Arbeitsblatt")
|
||||
subject = metadata.get("subject", "")
|
||||
grade = metadata.get("grade_level", "")
|
||||
total_gaps = metadata.get("total_gaps", 0)
|
||||
|
||||
html_parts = []
|
||||
html_parts.append("""<!DOCTYPE html>
|
||||
<html lang="de">
|
||||
<head>
|
||||
<meta charset="UTF-8">
|
||||
<title>""" + title + """ - Lueckentext</title>
|
||||
<style>
|
||||
@media print {
|
||||
.no-print { display: none; }
|
||||
.page-break { page-break-before: always; }
|
||||
}
|
||||
body {
|
||||
font-family: Arial, sans-serif;
|
||||
max-width: 800px;
|
||||
margin: 40px auto;
|
||||
padding: 20px;
|
||||
line-height: 1.8;
|
||||
}
|
||||
h1 { font-size: 24px; margin-bottom: 8px; }
|
||||
.meta { color: #666; margin-bottom: 24px; }
|
||||
.cloze-item {
|
||||
margin-bottom: 24px;
|
||||
padding: 16px;
|
||||
background: #f9f9f9;
|
||||
border-radius: 8px;
|
||||
}
|
||||
.cloze-number {
|
||||
font-weight: bold;
|
||||
color: #333;
|
||||
margin-bottom: 8px;
|
||||
}
|
||||
.cloze-sentence {
|
||||
font-size: 16px;
|
||||
line-height: 2;
|
||||
}
|
||||
.gap {
|
||||
display: inline-block;
|
||||
min-width: 80px;
|
||||
border-bottom: 2px solid #333;
|
||||
margin: 0 4px;
|
||||
text-align: center;
|
||||
}
|
||||
.gap-filled {
|
||||
display: inline-block;
|
||||
padding: 2px 8px;
|
||||
background: #e8f5e9;
|
||||
border: 1px solid #4caf50;
|
||||
border-radius: 4px;
|
||||
font-weight: bold;
|
||||
}
|
||||
.translation {
|
||||
margin-top: 12px;
|
||||
padding: 8px;
|
||||
background: #e3f2fd;
|
||||
border-left: 3px solid #2196f3;
|
||||
font-size: 14px;
|
||||
color: #555;
|
||||
}
|
||||
.translation-label {
|
||||
font-size: 12px;
|
||||
color: #777;
|
||||
margin-bottom: 4px;
|
||||
}
|
||||
.word-bank {
|
||||
margin-top: 32px;
|
||||
padding: 16px;
|
||||
background: #fff3e0;
|
||||
border-radius: 8px;
|
||||
}
|
||||
.word-bank-title {
|
||||
font-weight: bold;
|
||||
margin-bottom: 12px;
|
||||
}
|
||||
.word {
|
||||
display: inline-block;
|
||||
padding: 4px 12px;
|
||||
margin: 4px;
|
||||
background: white;
|
||||
border: 1px solid #ddd;
|
||||
border-radius: 4px;
|
||||
}
|
||||
</style>
|
||||
</head>
|
||||
<body>
|
||||
""")
|
||||
|
||||
# Header
|
||||
version_text = "Loesungsblatt" if include_answers else "Lueckentext"
|
||||
html_parts.append(f"<h1>{title} - {version_text}</h1>")
|
||||
meta_parts = []
|
||||
if subject:
|
||||
meta_parts.append(f"Fach: {subject}")
|
||||
if grade:
|
||||
meta_parts.append(f"Klasse: {grade}")
|
||||
meta_parts.append(f"Luecken gesamt: {total_gaps}")
|
||||
html_parts.append(f"<div class='meta'>{' | '.join(meta_parts)}</div>")
|
||||
|
||||
# Sammle alle Lueckenwoerter fuer Wortbank
|
||||
all_words = []
|
||||
|
||||
# Lueckentexte
|
||||
for idx, item in enumerate(items, 1):
|
||||
html_parts.append("<div class='cloze-item'>")
|
||||
html_parts.append(f"<div class='cloze-number'>{idx}.</div>")
|
||||
|
||||
gaps = item.get("gaps", [])
|
||||
sentence = item.get("sentence_with_gaps", "")
|
||||
|
||||
if include_answers:
|
||||
# Loesungsblatt: Luecken mit Antworten fuellen
|
||||
for gap in gaps:
|
||||
word = gap.get("word", "")
|
||||
sentence = sentence.replace("___", f"<span class='gap-filled'>{word}</span>", 1)
|
||||
else:
|
||||
# Fragenblatt: Luecken als Linien
|
||||
sentence = sentence.replace("___", "<span class='gap'> </span>")
|
||||
# Woerter fuer Wortbank sammeln
|
||||
for gap in gaps:
|
||||
all_words.append(gap.get("word", ""))
|
||||
|
||||
html_parts.append(f"<div class='cloze-sentence'>{sentence}</div>")
|
||||
|
||||
# Uebersetzung anzeigen
|
||||
translation = item.get("translation", {})
|
||||
if translation:
|
||||
lang_name = translation.get("language_name", "Uebersetzung")
|
||||
full_sentence = translation.get("full_sentence", "")
|
||||
if full_sentence:
|
||||
html_parts.append("<div class='translation'>")
|
||||
html_parts.append(f"<div class='translation-label'>{lang_name}:</div>")
|
||||
html_parts.append(full_sentence)
|
||||
html_parts.append("</div>")
|
||||
|
||||
html_parts.append("</div>")
|
||||
|
||||
# Wortbank (nur fuer Fragenblatt)
|
||||
if not include_answers and all_words:
|
||||
random.shuffle(all_words) # Mische die Woerter
|
||||
html_parts.append("<div class='word-bank'>")
|
||||
html_parts.append("<div class='word-bank-title'>Wortbank (diese Woerter fehlen):</div>")
|
||||
for word in all_words:
|
||||
html_parts.append(f"<span class='word'>{word}</span>")
|
||||
html_parts.append("</div>")
|
||||
|
||||
html_parts.append("</body></html>")
|
||||
|
||||
# Speichern
|
||||
suffix = "_cloze_solutions.html" if include_answers else "_cloze_print.html"
|
||||
out_name = cloze_path.stem.replace("_cloze", "") + suffix
|
||||
out_path = BEREINIGT_DIR / out_name
|
||||
out_path.write_text("\n".join(html_parts), encoding="utf-8")
|
||||
|
||||
logger.info(f"Cloze Print-Version gespeichert: {out_path.name}")
|
||||
return out_path
|
||||
Reference in New Issue
Block a user