""" AI Processor - HTML Builder Build clean HTML worksheets from analysis data. """ from pathlib import Path import json import logging from ..config import BEREINIGT_DIR logger = logging.getLogger(__name__) def build_clean_html_from_analysis(analysis_path: Path) -> Path: """ Build a clean HTML worksheet from an analysis JSON file. Features: - Focus on printed text (canonical_text / printed_blocks) - Handwritten entries and crossed-out words are NOT included - Uses open-source font stack (Inter / Noto Sans) Args: analysis_path: Path to *_analyse.json file Returns: Path to the generated HTML file """ if not analysis_path.exists(): raise FileNotFoundError(f"Analysedatei nicht gefunden: {analysis_path}") try: data = json.loads(analysis_path.read_text(encoding="utf-8")) except json.JSONDecodeError as e: raise RuntimeError(f"Analyse-Datei enthaelt kein gueltiges JSON: {analysis_path}\n{e}") from e title = data.get("title") or "Arbeitsblatt" subject = data.get("subject") or "" grade_level = data.get("grade_level") or "" instructions = data.get("instructions") or "" tasks = data.get("tasks", []) or [] canonical_text = data.get("canonical_text") or "" printed_blocks = data.get("printed_blocks") or [] struck = data.get("struck_through_words") or [] html_parts = [] html_parts.append("") html_parts.append("") html_parts.append("") html_parts.append("") html_parts.append(f"{title}") html_parts.append(_get_html_styles()) html_parts.append("") html_parts.append("") html_parts.append("
") # Header section html_parts.append(f"

{title}

") meta_bits = [] if subject: meta_bits.append(f"Fach: {subject}") if grade_level: meta_bits.append(f"Klassenstufe: {grade_level}") if meta_bits: html_parts.append(f"
{' | '.join(meta_bits)}
") if instructions: html_parts.append( f"
Arbeitsanweisung: {instructions}
" ) # Main text / printed blocks html_parts.append("
") if printed_blocks: for block in printed_blocks: role = (block.get("role") or "body").lower() text = (block.get("text") or "").strip() if not text: continue html_parts.append("
") if role == "title": html_parts.append(f"
{text}
") else: html_parts.append(f"
{text}
") html_parts.append("
") elif canonical_text: # Fallback: split canonical_text into paragraphs paragraphs = [ p.strip() for p in canonical_text.replace("\r\n", "\n").split("\n\n") if p.strip() ] for p in paragraphs: html_parts.append(f"
{p}
") html_parts.append("
") # Tasks section if tasks: html_parts.append("

Aufgaben

") html_parts.append("
") for idx, task in enumerate(tasks, start=1): t_type = task.get("type") or "other" desc = task.get("description") or "" text_with_gaps = task.get("text_with_gaps") html_parts.append("
") html_parts.append( f"
Aufgabe {idx} ({t_type}): {desc}
" ) if text_with_gaps: rendered = text_with_gaps.replace("___", " ") html_parts.append(f"
{rendered}
") html_parts.append("
") html_parts.append("
") # Footer note if struck: html_parts.append( "
Hinweis: Einige im Original durchgestrichene Woerter wurden " "von der KI erkannt und NICHT in dieses saubere Arbeitsblatt uebernommen.
" ) else: html_parts.append( "
Dieses Arbeitsblatt wurde automatisch aus einem Scan rekonstruiert " "und von handschriftlichen Eintragungen bereinigt.
" ) html_parts.append("
") # .page html_parts.append("") html_content = "\n".join(html_parts) out_name = analysis_path.stem.replace("_analyse", "") + "_clean.html" out_path = BEREINIGT_DIR / out_name out_path.write_text(html_content, encoding="utf-8") return out_path def _get_html_styles() -> str: """Get CSS styles for clean HTML output.""" return """ """