breakpilot-pwa/backend/ai_processor/export/print_versions.py

"""
AI Processor - Print Version Generators

Generate printable HTML versions for Q&A, Cloze, and Multiple Choice.
"""

from pathlib import Path
import json
import logging
import random

from ..config import BEREINIGT_DIR

logger = logging.getLogger(__name__)


def generate_print_version_qa(qa_path: Path, include_answers: bool = False) -> Path:
    """
    Generate a printable HTML version of the Q&A pairs.

    Args:
        qa_path: Path to *_qa.json file
        include_answers: True for solution sheet (for parents)

    Returns:
        Path to generated HTML file
    """
    if not qa_path.exists():
        raise FileNotFoundError(f"Q&A-Datei nicht gefunden: {qa_path}")

    qa_data = json.loads(qa_path.read_text(encoding="utf-8"))
    items = qa_data.get("qa_items", [])
    metadata = qa_data.get("metadata", {})

    title = metadata.get("source_title", "Arbeitsblatt")
    subject = metadata.get("subject", "")
    grade = metadata.get("grade_level", "")

    html_parts = []
    html_parts.append(_get_qa_html_header(title))

    # Header
    version_text = "Loesungsblatt" if include_answers else "Fragenblatt"
    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"Anzahl Fragen: {len(items)}")
    html_parts.append(f"<div class='meta'>{' | '.join(meta_parts)}</div>")

    # Questions
    for idx, item in enumerate(items, 1):
        html_parts.append("<div class='question-block'>")
        html_parts.append(f"<div class='question-number'>Frage {idx}</div>")
        html_parts.append(f"<div class='question-text'>{item.get('question', '')}</div>")

        if include_answers:
            html_parts.append(f"<div class='answer'><strong>Antwort:</strong> {item.get('answer', '')}</div>")
            key_terms = item.get("key_terms", [])
            if key_terms:
                terms_html = " ".join([f"<span>{term}</span>" for term in key_terms])
                html_parts.append(f"<div class='key-terms'>Wichtige Begriffe: {terms_html}</div>")
        else:
            html_parts.append("<div class='answer-lines'>")
            for _ in range(3):
                html_parts.append("<div class='answer-line'></div>")
            html_parts.append("</div>")

        html_parts.append("</div>")

    html_parts.append("</body></html>")

    # Save
    suffix = "_qa_solutions.html" if include_answers else "_qa_print.html"
    out_name = qa_path.stem.replace("_qa", "") + suffix
    out_path = BEREINIGT_DIR / out_name
    out_path.write_text("\n".join(html_parts), encoding="utf-8")

    logger.info(f"Print-Version gespeichert: {out_path.name}")
    return out_path


def generate_print_version_cloze(cloze_path: Path, include_answers: bool = False) -> Path:
    """
    Generate a printable HTML version of the cloze texts.

    Args:
        cloze_path: Path to *_cloze.json file
        include_answers: True for solution sheet (for parents)

    Returns:
        Path to generated HTML file
    """
    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(_get_cloze_html_header(title))

    # 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>")

    # Collect all gap words for word bank
    all_words = []

    # Cloze texts
    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:
            # Solution sheet: fill gaps with answers
            for gap in gaps:
                word = gap.get("word", "")
                sentence = sentence.replace("___", f"<span class='gap-filled'>{word}</span>", 1)
        else:
            # Question sheet: gaps as lines
            sentence = sentence.replace("___", "<span class='gap'>&nbsp;</span>")
            for gap in gaps:
                all_words.append(gap.get("word", ""))

        html_parts.append(f"<div class='cloze-sentence'>{sentence}</div>")

        # Show translation
        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>")

    # Word bank (only for question sheet)
    if not include_answers and all_words:
        random.shuffle(all_words)
        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>")

    # Save
    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


def generate_print_version_mc(mc_path: Path, include_answers: bool = False) -> str:
    """
    Generate a printable HTML version of the multiple choice questions.

    Args:
        mc_path: Path to *_mc.json file
        include_answers: True for solution sheet with marked correct answers

    Returns:
        HTML string (for direct delivery)
    """
    if not mc_path.exists():
        raise FileNotFoundError(f"MC-Datei nicht gefunden: {mc_path}")

    mc_data = json.loads(mc_path.read_text(encoding="utf-8"))
    questions = mc_data.get("questions", [])
    metadata = mc_data.get("metadata", {})

    title = metadata.get("source_title", "Arbeitsblatt")
    subject = metadata.get("subject", "")
    grade = metadata.get("grade_level", "")

    html_parts = []
    html_parts.append(_get_mc_html_header(title))

    # Header
    version_text = "Loesungsblatt" if include_answers else "Multiple Choice Test"
    html_parts.append(f"<h1>{title}</h1>")
    html_parts.append(f"<div class='meta'><strong>{version_text}</strong>")
    if subject:
        html_parts.append(f" | Fach: {subject}")
    if grade:
        html_parts.append(f" | Klasse: {grade}")
    html_parts.append(f" | Anzahl Fragen: {len(questions)}</div>")

    if not include_answers:
        html_parts.append("<div class='instructions'>")
        html_parts.append("<strong>Anleitung:</strong> Kreuze bei jeder Frage die richtige Antwort an. ")
        html_parts.append("Es ist immer nur eine Antwort richtig.")
        html_parts.append("</div>")

    # Questions
    for idx, q in enumerate(questions, 1):
        html_parts.append("<div class='question-block'>")
        html_parts.append(f"<div class='question-number'>Frage {idx}</div>")
        html_parts.append(f"<div class='question-text'>{q.get('question', '')}</div>")

        html_parts.append("<div class='options'>")
        correct_answer = q.get("correct_answer", "")

        for opt in q.get("options", []):
            opt_id = opt.get("id", "")
            is_correct = opt_id == correct_answer

            opt_class = "option"
            checkbox_class = "option-checkbox"
            if include_answers and is_correct:
                opt_class += " option-correct"
                checkbox_class += " checked"

            html_parts.append(f"<div class='{opt_class}'>")
            html_parts.append(f"<div class='{checkbox_class}'></div>")
            html_parts.append(f"<span class='option-label'>{opt_id})</span>")
            html_parts.append(f"<span class='option-text'>{opt.get('text', '')}</span>")
            html_parts.append("</div>")

        html_parts.append("</div>")

        # Explanation only for solution sheet
        if include_answers and q.get("explanation"):
            html_parts.append(f"<div class='explanation'><strong>Erklaerung:</strong> {q.get('explanation')}</div>")

        html_parts.append("</div>")

    # Answer key (compact) - only for solution sheet
    if include_answers:
        html_parts.append("<div class='answer-key'>")
        html_parts.append("<div class='answer-key-title'>Loesungsschluessel</div>")
        html_parts.append("<div class='answer-key-grid'>")
        for idx, q in enumerate(questions, 1):
            html_parts.append("<div class='answer-key-item'>")
            html_parts.append(f"<span class='answer-key-q'>{idx}.</span> ")
            html_parts.append(f"<span class='answer-key-a'>{q.get('correct_answer', '')}</span>")
            html_parts.append("</div>")
        html_parts.append("</div>")
        html_parts.append("</div>")

    html_parts.append("</body></html>")

    return "\n".join(html_parts)


def _get_qa_html_header(title: str) -> str:
    """Get HTML header for Q&A print version."""
    return f"""<!DOCTYPE html>
<html lang="de">
<head>
<meta charset="UTF-8">
<title>{title} - Fragen</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: 1.6;
  }}
  h1 {{ font-size: 24px; margin-bottom: 8px; }}
  .meta {{ color: #666; margin-bottom: 24px; }}
  .question-block {{
    margin-bottom: 32px;
    padding-bottom: 16px;
    border-bottom: 1px dashed #ccc;
  }}
  .question-number {{ font-weight: bold; color: #333; }}
  .question-text {{ font-size: 16px; margin: 8px 0; }}
  .answer-lines {{ margin-top: 12px; }}
  .answer-line {{ border-bottom: 1px solid #999; height: 28px; }}
  .answer {{
    margin-top: 8px;
    padding: 8px;
    background: #e8f5e9;
    border-left: 3px solid #4caf50;
  }}
  .key-terms {{ font-size: 12px; color: #666; margin-top: 8px; }}
  .key-terms span {{
    background: #fff3e0;
    padding: 2px 6px;
    border-radius: 3px;
    margin-right: 4px;
  }}
</style>
</head>
<body>
"""


def _get_cloze_html_header(title: str) -> str:
    """Get HTML header for cloze print version."""
    return f"""<!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>
"""


def _get_mc_html_header(title: str) -> str:
    """Get HTML header for MC print version."""
    return f"""<!DOCTYPE html>
<html lang="de">
<head>
<meta charset="UTF-8">
<title>{title} - Multiple Choice</title>
<style>
  @media print {{
    .no-print {{ display: none; }}
    .page-break {{ page-break-before: always; }}
    body {{ font-size: 14pt; }}
  }}
  body {{
    font-family: Arial, Helvetica, sans-serif;
    max-width: 800px;
    margin: 40px auto;
    padding: 20px;
    line-height: 1.6;
    color: #000;
  }}
  h1 {{
    font-size: 28px;
    margin-bottom: 8px;
    border-bottom: 2px solid #000;
    padding-bottom: 8px;
  }}
  .meta {{ color: #333; margin-bottom: 32px; font-size: 14px; }}
  .instructions {{
    background: #f5f5f5;
    padding: 12px 16px;
    border-radius: 4px;
    margin-bottom: 24px;
    font-size: 14px;
  }}
  .question-block {{
    margin-bottom: 28px;
    padding-bottom: 16px;
    border-bottom: 1px solid #ddd;
  }}
  .question-number {{ font-weight: bold; font-size: 18px; color: #000; margin-bottom: 8px; }}
  .question-text {{ font-size: 16px; margin: 8px 0 16px 0; line-height: 1.5; }}
  .options {{ margin-left: 20px; }}
  .option {{
    display: flex;
    align-items: flex-start;
    margin-bottom: 12px;
    padding: 8px 12px;
    border: 1px solid #ccc;
    border-radius: 4px;
    background: #fff;
  }}
  .option-correct {{
    background: #e8f5e9;
    border-color: #4caf50;
    border-width: 2px;
  }}
  .option-checkbox {{
    width: 20px;
    height: 20px;
    border: 2px solid #333;
    border-radius: 50%;
    margin-right: 12px;
    flex-shrink: 0;
    display: flex;
    align-items: center;
    justify-content: center;
  }}
  .option-checkbox.checked::after {{
    content: "✓";
    font-weight: bold;
    color: #4caf50;
  }}
  .option-label {{ font-weight: bold; margin-right: 8px; min-width: 24px; }}
  .option-text {{ flex: 1; }}
  .explanation {{
    margin-top: 8px;
    padding: 8px 12px;
    background: #e3f2fd;
    border-left: 3px solid #2196f3;
    font-size: 13px;
    color: #333;
  }}
  .answer-key {{
    margin-top: 40px;
    padding: 16px;
    background: #f5f5f5;
    border-radius: 8px;
  }}
  .answer-key-title {{
    font-weight: bold;
    font-size: 18px;
    margin-bottom: 12px;
    border-bottom: 1px solid #999;
    padding-bottom: 8px;
  }}
  .answer-key-grid {{
    display: grid;
    grid-template-columns: repeat(5, 1fr);
    gap: 8px;
  }}
  .answer-key-item {{
    padding: 8px;
    text-align: center;
    background: white;
    border: 1px solid #ddd;
    border-radius: 4px;
  }}
  .answer-key-q {{ font-weight: bold; }}
  .answer-key-a {{ color: #4caf50; font-weight: bold; }}
</style>
</head>
<body>
"""