pdf-quiz-generator/backend/app/routers/quizzes.py

import random
from fastapi import APIRouter, Depends, HTTPException, Query
from sqlalchemy import cast, String, or_, and_, func
from sqlalchemy.orm import Session

from app.database import get_db
from app.models.quiz import Quiz
from app.models.question import Question as QuestionModel
from app.models.section import Section
from app.models.attempt import QuizAttempt
from app.models.user import User
from app.schemas.quiz import QuizCreate, QuizResponse, QuizDetail, QuizLearningDetail, QuizReview
from app.services import quiz_service
from app.utils.auth import get_current_user, require_moderator
from app.utils.quiz_questions import get_quiz_questions, question_in_quiz, remove_question_from_quiz

router = APIRouter()


@router.post("/")
def create_quiz(
    quiz_data: QuizCreate,
    db: Session = Depends(get_db),
    current_user: User = Depends(require_moderator),
):
    """Start async quiz extraction. Returns {job_id} immediately; poll /quizzes/job/{job_id} for progress."""
    import uuid
    section = db.query(Section).filter(Section.id == quiz_data.section_id).first()
    if not section:
        raise HTTPException(status_code=404, detail="Section not found")
    if not current_user.is_admin and section.document.user_id != current_user.id:
        raise HTTPException(status_code=403, detail="Not your document")
    if quiz_data.mode not in ("timed", "learning"):
        raise HTTPException(status_code=400, detail="Mode must be 'timed' or 'learning'")

    job_id = str(uuid.uuid4())

    try:
        from app.tasks.quiz_tasks import extract_quiz
        import redis as redis_lib
        from app.config import settings
        r = redis_lib.from_url(settings.REDIS_URL, decode_responses=True)
        r.set(f"extraction:status:{job_id}", "pending", ex=3600)
        # Store job under user so any session can query it
        title = quiz_data.title
        r.lpush(f"extraction:user_jobs:{current_user.id}", job_id)
        r.expire(f"extraction:user_jobs:{current_user.id}", 86400)
        r.set(f"extraction:job_title:{job_id}", title, ex=3600)

        extract_quiz.delay(
            job_id=job_id,
            user_id=current_user.id,
            section_id=quiz_data.section_id,
            title=quiz_data.title,
            mode=quiz_data.mode,
            time_limit_minutes=quiz_data.time_limit_minutes,
            model_id=quiz_data.model_id,
            question_category_id=quiz_data.question_category_id,
        )
    except Exception:
        # Celery/Redis unavailable — fall back to synchronous extraction
        try:
            quiz = quiz_service.create_quiz_from_section(
                db=db, user_id=current_user.id,
                section_id=quiz_data.section_id, title=quiz_data.title,
                mode=quiz_data.mode, time_limit_minutes=quiz_data.time_limit_minutes,
                model_id=quiz_data.model_id, question_category_id=quiz_data.question_category_id,
            )
            return {"job_id": job_id, "status": "completed", "quiz_id": quiz.id}
        except (ValueError, RuntimeError) as e:
            raise HTTPException(status_code=400, detail=str(e))

    return {"job_id": job_id, "status": "pending"}


@router.get("/jobs")
def list_user_jobs(current_user: User = Depends(get_current_user)):
    """Return all recent extraction jobs for the logged-in user (any browser/session)."""
    import json as _json
    import redis as redis_lib
    from app.config import settings

    r = redis_lib.from_url(settings.REDIS_URL, decode_responses=True)
    job_ids = r.lrange(f"extraction:user_jobs:{current_user.id}", 0, 19)
    jobs = []
    for jid in job_ids:
        status = r.get(f"extraction:status:{jid}")
        if not status:
            continue
        steps = r.lrange(f"extraction:steps:{jid}", 0, -1)
        last_step = ""
        if steps:
            last_step = _json.loads(steps[-1]).get("message", "")
        quiz_id = r.get(f"extraction:quiz_id:{jid}")
        title = r.get(f"extraction:job_title:{jid}") or "Quiz"
        jobs.append({
            "job_id": jid,
            "title": title,
            "status": status,
            "steps_count": len(steps),
            "last_step": last_step[:80],
            "quiz_id": int(quiz_id) if quiz_id else None,
        })
    return jobs


@router.get("/job/{job_id}")
def get_extraction_job(job_id: str, current_user: User = Depends(require_moderator)):
    """Poll extraction job progress. Returns steps list, status, and quiz_id when done."""
    import json as _json
    import redis as redis_lib
    from app.config import settings

    r = redis_lib.from_url(settings.REDIS_URL, decode_responses=True)
    status = r.get(f"extraction:status:{job_id}") or "unknown"
    raw_steps = r.lrange(f"extraction:steps:{job_id}", 0, -1)
    steps = [_json.loads(s) for s in raw_steps]
    result = {"job_id": job_id, "status": status, "steps": steps}
    if status == "completed":
        result["quiz_id"] = int(r.get(f"extraction:quiz_id:{job_id}") or 0)
    if status == "failed":
        result["error"] = r.get(f"extraction:error:{job_id}") or "Unknown error"
    return result


@router.get("/search")
def search_quizzes(
    q: str = Query(..., min_length=2, max_length=200),
    mode: str = Query("all"),  # "title" | "questions" | "all"
    db: Session = Depends(get_db),
    current_user: User = Depends(get_current_user),
):
    """Hybrid semantic + keyword search across quiz titles and questions."""
    from sqlalchemy import text as sa_text
    from app.services import embedding_service

    phrase = q.strip()
    if not phrase:
        return []

    results = {}  # quiz_id -> result dict

    def _ensure_quiz(quiz_id: int, match_type: str):
        if quiz_id not in results:
            quiz = db.query(Quiz).filter(Quiz.id == quiz_id).first()
            if not quiz:
                return False
            results[quiz_id] = {
                "quiz_id": quiz.id,
                "quiz_title": quiz.title,
                "questions_count": quiz.questions_count,
                "mode": quiz.mode,
                "time_limit_minutes": quiz.time_limit_minutes,
                "match_type": match_type,
                "matching_questions": [],
            }
        elif results[quiz_id]["match_type"] != match_type and match_type != "title":
            results[quiz_id]["match_type"] = "both"
        return True

    # ── Title search ─────────────────────────────────────────────
    if mode in ("title", "all"):
        for quiz in db.query(Quiz).filter(Quiz.title.ilike(f"%{phrase}%")).limit(30).all():
            _ensure_quiz(quiz.id, "title")

    # ── Semantic (vector) search ──────────────────────────────────
    seen_question_ids = set()
    if mode in ("questions", "all"):
        query_emb = embedding_service.generate_embedding(phrase)
        if query_emb:
            # Use f-string for the vector literal — safe because it's a list of floats
            emb_literal = "[" + ",".join(str(x) for x in query_emb) + "]"
            rows = db.execute(sa_text(f"""
                SELECT q.id, q.quiz_id, q.question_text, q.options,
                       q.correct_answer, q.explanation,
                       1 - (q.embedding <=> '{emb_literal}'::vector) AS similarity
                FROM questions q
                WHERE q.embedding IS NOT NULL
                ORDER BY q.embedding <=> '{emb_literal}'::vector
                LIMIT 40
            """)).fetchall()

            for row in rows:
                similarity = float(row.similarity)
                if similarity < 0.30:
                    continue
                quiz_id_val = row.quiz_id  # DB column still named quiz_id
                if quiz_id_val and _ensure_quiz(quiz_id_val, "questions"):
                    seen_question_ids.add(row.id)
                    results[quiz_id_val]["matching_questions"].append({
                        "id": row.id,
                        "question_text": row.question_text,
                        "options": row.options,
                        "correct_answer": row.correct_answer,
                        "explanation": row.explanation,
                        "similarity": round(similarity, 3),
                        "match_source": "semantic",
                    })

    # ── Keyword (ILIKE) search ────────────────────────────────────
    if mode in ("questions", "all"):
        q_filter = or_(
            QuestionModel.question_text.ilike(f"%{phrase}%"),
            cast(QuestionModel.options, String).ilike(f"%{phrase}%"),
        )
        keyword_rows = (
            db.query(QuestionModel)
            .filter(q_filter)
            .order_by(QuestionModel.source_quiz_id, QuestionModel.id)
            .limit(200)
            .all()
        )
        for question in keyword_rows:
            src_qid = question.source_quiz_id
            if src_qid and _ensure_quiz(src_qid, "questions"):
                if question.id not in seen_question_ids:
                    seen_question_ids.add(question.id)
                    results[src_qid]["matching_questions"].append({
                        "id": question.id,
                        "question_text": question.question_text,
                        "options": question.options,
                        "correct_answer": question.correct_answer,
                        "explanation": question.explanation,
                        "similarity": None,
                        "match_source": "keyword",
                    })

    # Sort each quiz's questions: semantic first (by similarity desc), then keyword
    for r in results.values():
        r["matching_questions"].sort(
            key=lambda x: (0 if x.get("match_source") == "semantic" else 1,
                           -(x.get("similarity") or 0))
        )

    # Sort results: title matches first, then by number of semantic hits desc
    sorted_results = sorted(
        results.values(),
        key=lambda r: (
            0 if r["match_type"] == "title" else 1,
            -sum(1 for q in r["matching_questions"] if q.get("match_source") == "semantic"),
        ),
    )
    return sorted_results


@router.get("/", response_model=list[QuizResponse])
def list_quizzes(
    db: Session = Depends(get_db),
    current_user: User = Depends(get_current_user),
):
    """List all available quizzes. Admins/mods see all, users see all published."""
    if current_user.is_moderator:
        quizzes = db.query(Quiz).order_by(Quiz.created_at.desc()).all()
    else:
        quizzes = db.query(Quiz).order_by(Quiz.created_at.desc()).all()
    return quizzes


@router.get("/{quiz_id}")
def get_quiz(
    quiz_id: int,
    study: bool = Query(False),
    db: Session = Depends(get_db),
    current_user: User = Depends(get_current_user),
):
    """Get quiz for taking. study=true forces answers/explanations to be included."""
    quiz = db.query(Quiz).filter(Quiz.id == quiz_id).first()
    if not quiz:
        raise HTTPException(status_code=404, detail="Quiz not found")

    if study or quiz.mode == "learning":
        return QuizLearningDetail.model_validate(quiz)
    return QuizDetail.model_validate(quiz)


@router.post("/{quiz_id}/shuffle", response_model=QuizDetail)
def shuffle_quiz(
    quiz_id: int,
    shuffle_options: bool = Query(True, description="Also shuffle answer options within each question"),
    db: Session = Depends(get_db),
    current_user: User = Depends(get_current_user),
):
    """Return quiz with question order and optionally option order shuffled. Does not modify DB."""
    from app.models.question import Question as QuestionModel
    from app.schemas.quiz import QuestionResponse

    quiz = db.query(Quiz).filter(Quiz.id == quiz_id).first()
    if not quiz:
        raise HTTPException(status_code=404, detail="Quiz not found")

    questions = get_quiz_questions(db, quiz_id)
    shuffled_questions = questions.copy()
    random.shuffle(shuffled_questions)

    result = []
    for q in shuffled_questions:
        options = list(q.options) if q.options else None
        if shuffle_options and options:
            random.shuffle(options)
        result.append(QuestionResponse(
            id=q.id,
            question_text=q.question_text,
            question_type=q.question_type,
            options=options,
            image_path=q.image_path,
        ))

    return {
        "id": quiz.id,
        "section_id": quiz.section_id,
        "user_id": quiz.user_id,
        "title": quiz.title,
        "questions_count": quiz.questions_count,
        "mode": quiz.mode,
        "time_limit_minutes": quiz.time_limit_minutes,
        "created_at": quiz.created_at,
        "questions": result,
    }


@router.get("/{quiz_id}/review", response_model=QuizReview)
def review_quiz(
    quiz_id: int,
    db: Session = Depends(get_db),
    current_user: User = Depends(get_current_user),
):
    """Get quiz with answers — only if user has completed an attempt."""
    quiz = db.query(Quiz).filter(Quiz.id == quiz_id).first()
    if not quiz:
        raise HTTPException(status_code=404, detail="Quiz not found")

    has_attempt = db.query(QuizAttempt).filter(
        QuizAttempt.quiz_id == quiz_id,
        QuizAttempt.user_id == current_user.id,
        QuizAttempt.completed_at.isnot(None),
    ).first()
    if not has_attempt and not current_user.is_moderator:
        raise HTTPException(status_code=403, detail="Complete an attempt first to review answers")

    return quiz


@router.get("/{quiz_id}/questions")
def get_quiz_questions_for_edit(
    quiz_id: int,
    db: Session = Depends(get_db),
    current_user: User = Depends(require_moderator),
):
    """Get all questions with answers for editing — moderator/admin only."""
    quiz = db.query(Quiz).filter(Quiz.id == quiz_id).first()
    if not quiz:
        raise HTTPException(status_code=404, detail="Quiz not found")
    questions = get_quiz_questions(db, quiz_id)
    return [
        {
            "id": q.id,
            "question_text": q.question_text,
            "question_type": q.question_type,
            "options": q.options,
            "correct_answer": q.correct_answer,
            "explanation": q.explanation,
        }
        for q in questions
    ]


@router.patch("/{quiz_id}/questions/{question_id}")
def update_question(
    quiz_id: int,
    question_id: int,
    data: dict,
    db: Session = Depends(get_db),
    current_user: User = Depends(require_moderator),
):
    """Update a quiz question — change is shared: affects all quizzes using this question."""
    if not question_in_quiz(db, quiz_id, question_id):
        raise HTTPException(status_code=404, detail="Question not found in this quiz")
    question = db.query(QuestionModel).filter(QuestionModel.id == question_id).first()
    if not question:
        raise HTTPException(status_code=404, detail="Question not found")

    allowed = {"question_text", "options", "correct_answer", "explanation", "question_type"}
    for key, value in data.items():
        if key in allowed:
            setattr(question, key, value)

    # Validate correct_answer is one of the options
    if question.options and question.correct_answer not in question.options:
        raise HTTPException(
            status_code=400,
            detail=f"correct_answer must match one of the options exactly. Options: {question.options}"
        )

    db.commit()
    db.refresh(question)
    return {
        "id": question.id,
        "question_text": question.question_text,
        "question_type": question.question_type,
        "options": question.options,
        "correct_answer": question.correct_answer,
        "explanation": question.explanation,
    }


@router.delete("/{quiz_id}/questions/{question_id}", status_code=204)
def delete_question(
    quiz_id: int,
    question_id: int,
    db: Session = Depends(get_db),
    current_user: User = Depends(require_moderator),
):
    """Remove a question from this quiz. If it's shared, only removes the link (question stays in bank).
    If it's only in this quiz, deletes it from the bank too."""
    if not question_in_quiz(db, quiz_id, question_id):
        raise HTTPException(status_code=404, detail="Question not found in this quiz")

    from app.models.quiz_question_link import QuizQuestionLink
    # Check if used by any OTHER quiz
    other_uses = db.query(QuizQuestionLink).filter(
        QuizQuestionLink.question_id == question_id,
        QuizQuestionLink.quiz_id != quiz_id,
    ).count()

    remove_question_from_quiz(db, quiz_id, question_id)

    quiz = db.query(Quiz).filter(Quiz.id == quiz_id).first()
    if quiz and quiz.questions_count > 0:
        quiz.questions_count -= 1

    # Only delete the question record if no other quiz references it
    if other_uses == 0:
        db.query(QuestionModel).filter(QuestionModel.id == question_id).delete()

    db.commit()


@router.delete("/{quiz_id}", status_code=204)
def delete_quiz(
    quiz_id: int,
    db: Session = Depends(get_db),
    current_user: User = Depends(require_moderator),
):
    """Delete quiz. Questions shared with other quizzes stay in the bank.
    Questions only in this quiz are detached (source_quiz_id cleared) so they
    remain in the bank instead of being deleted."""
    from app.models.quiz_question_link import QuizQuestionLink

    quiz = db.query(Quiz).filter(Quiz.id == quiz_id).first()
    if not quiz:
        raise HTTPException(status_code=404, detail="Quiz not found")

    # For each question linked to this quiz: if no other quiz uses it,
    # detach it (clear source_quiz_id) so it stays as a bank-only question
    links = db.query(QuizQuestionLink).filter(QuizQuestionLink.quiz_id == quiz_id).all()
    for link in links:
        other = db.query(QuizQuestionLink).filter(
            QuizQuestionLink.question_id == link.question_id,
            QuizQuestionLink.quiz_id != quiz_id,
        ).count()
        if other == 0:
            # Detach from this quiz but keep in bank
            db.query(QuestionModel).filter(QuestionModel.id == link.question_id).update(
                {"quiz_id": None}  # source_quiz_id → null
            )

    db.delete(quiz)  # cascades quiz_question_links
    db.commit()