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

"""Question bank — view, search, categorise, and create quizzes from individual questions."""
from fastapi import APIRouter, Depends, HTTPException, Query
from pydantic import BaseModel
from sqlalchemy import cast, String, or_, text as sa_text
from sqlalchemy.orm import Session

from app.database import get_db
from app.models.question import Question
from app.models.question_category import QuestionCategory
from app.models.quiz import Quiz
from app.models.user import User
from app.models.favorite import Favorite
from app.utils.auth import get_current_user, require_moderator

router = APIRouter()


@router.patch("/{question_id}/category")
def set_question_category(
    question_id: int,
    category_id: int | None = None,
    db: Session = Depends(get_db),
    current_user: User = Depends(require_moderator),
):
    """Assign or remove a question category."""
    question = db.query(Question).filter(Question.id == question_id).first()
    if not question:
        raise HTTPException(status_code=404, detail="Question not found")
    if category_id is not None:
        cat = db.query(QuestionCategory).filter(QuestionCategory.id == category_id).first()
        if not cat:
            raise HTTPException(status_code=404, detail="Category not found")
    question.question_category_id = category_id
    db.commit()
    return {"question_id": question_id, "question_category_id": category_id}


@router.get("/bank/ids")
def get_bank_ids(
    q: str | None = Query(None),
    quiz_id: int | None = Query(None),
    category_id: int | None = Query(None),
    category_ids: str | None = Query(None, description="Comma-separated category IDs (OR filter)"),
    uncategorized: bool = Query(False),
    favorites_only: bool = Query(False),
    tag_ids: str | None = Query(None, description="Comma-separated tag IDs (AND filter)"),
    db: Session = Depends(get_db),
    current_user: User = Depends(get_current_user),
):
    """Return just IDs for all matching questions (for server-side select-all)."""
    query = db.query(Question.id)
    if quiz_id:
        query = query.filter(Question.source_quiz_id == quiz_id)
    if category_ids:
        cat_id_list = [int(c.strip()) for c in category_ids.split(",") if c.strip().isdigit()]
        if cat_id_list:
            query = query.filter(Question.question_category_id.in_(cat_id_list))
    elif category_id is not None:
        query = query.filter(Question.question_category_id == category_id)
    if uncategorized:
        query = query.filter(Question.question_category_id.is_(None))
    if favorites_only:
        favorite_ids = db.query(Favorite.question_id).filter(Favorite.user_id == current_user.id).all()
        fav_ids = [f[0] for f in favorite_ids]
        if not fav_ids:
            return []
        query = query.filter(Question.id.in_(fav_ids))
    if q and q.strip():
        phrase = q.strip()
        query = query.filter(
            or_(
                Question.question_text.ilike(f"%{phrase}%"),
                cast(Question.options, String).ilike(f"%{phrase}%"),
            )
        )
    # Tag filter: questions must have ALL specified tags
    if tag_ids:
        tag_id_list = [int(t.strip()) for t in tag_ids.split(",") if t.strip().isdigit()]
        if tag_id_list:
            matching_ids = list(db.execute(sa_text("""
                SELECT question_id FROM question_tag_links
                WHERE tag_id = ANY(:tag_ids)
                GROUP BY question_id
                HAVING COUNT(DISTINCT tag_id) = :cnt
            """), {"tag_ids": tag_id_list, "cnt": len(tag_id_list)}).scalars())
            if matching_ids:
                query = query.filter(Question.id.in_(matching_ids))
            else:
                return []
    return [row[0] for row in query.all()]


@router.get("/bank")
def get_question_bank(
    q: str | None = Query(None),
    quiz_id: int | None = Query(None),
    category_id: int | None = Query(None),
    category_ids: str | None = Query(None, description="Comma-separated category IDs (OR filter)"),
    uncategorized: bool = Query(False),
    favorites_only: bool = Query(False),
    tag_ids: str | None = Query(None, description="Comma-separated tag IDs (AND filter)"),
    search_mode: str = Query("hybrid"),  # "keyword" | "semantic" | "hybrid"
    limit: int = Query(50, le=200),
    offset: int = Query(0),
    db: Session = Depends(get_db),
    current_user: User = Depends(get_current_user),
):
    """List all questions across all quizzes. Supports keyword filter and quiz filter."""
    query = db.query(Question)

    if quiz_id:
        query = query.filter(Question.source_quiz_id == quiz_id)

    if category_ids:
        cat_id_list = [int(c.strip()) for c in category_ids.split(",") if c.strip().isdigit()]
        if cat_id_list:
            query = query.filter(Question.question_category_id.in_(cat_id_list))
    elif category_id is not None:
        query = query.filter(Question.question_category_id == category_id)

    if uncategorized:
        query = query.filter(Question.question_category_id.is_(None))

    # Tag filter: questions must have ALL specified tags
    if tag_ids:
        import logging as _log
        _log.getLogger(__name__).info(f"Tag filter: tag_ids={tag_ids!r}")
        tag_id_list = [int(t.strip()) for t in tag_ids.split(",") if t.strip().isdigit()]
        if tag_id_list:
            matching_ids = list(db.execute(sa_text("""
                SELECT question_id FROM question_tag_links
                WHERE tag_id = ANY(:tag_ids)
                GROUP BY question_id
                HAVING COUNT(DISTINCT tag_id) = :cnt
            """), {"tag_ids": tag_id_list, "cnt": len(tag_id_list)}).scalars())
            _log.getLogger(__name__).info(f"Tag filter matched {len(matching_ids)} questions for tags {tag_id_list}")
            if matching_ids:
                query = query.filter(Question.id.in_(matching_ids))
            else:
                return {"total": 0, "questions": []}

    if favorites_only:
        favorite_ids = db.query(Favorite.question_id).filter(Favorite.user_id == current_user.id).all()
        fav_ids = [f[0] for f in favorite_ids]
        if not fav_ids:
            return {"total": 0, "questions": []}
        query = query.filter(Question.id.in_(fav_ids))

    # ── Semantic search (pgvector) ─────────────────────────────────
    semantic_ids_ordered: list[int] = []
    if q and q.strip() and search_mode in ("semantic", "hybrid"):
        from app.services.embedding_service import generate_embedding
        emb = generate_embedding(q.strip())
        if emb:
            # Validate all values are finite floats before interpolating into SQL
            emb_literal = "[" + ",".join(str(float(x)) for x in emb) + "]"
            rows = db.execute(sa_text("""
                SELECT id, 1 - (embedding <=> CAST(:vec AS vector)) AS sim
                FROM questions
                WHERE embedding IS NOT NULL
                ORDER BY embedding <=> CAST(:vec AS vector)
                LIMIT :lim
            """), {"vec": emb_literal, "lim": limit * 2}).fetchall()
            semantic_ids_ordered = [r.id for r in rows if float(r.sim) >= 0.55]

    # ── Keyword filter ─────────────────────────────────────────────
    if q and q.strip() and search_mode in ("keyword", "hybrid"):
        phrase = q.strip()
        query = query.filter(
            or_(
                Question.question_text.ilike(f"%{phrase}%"),
                cast(Question.options, String).ilike(f"%{phrase}%"),
            )
        )

    # Apply semantic ID filter if semantic-only mode
    if q and q.strip() and search_mode == "semantic" and semantic_ids_ordered:
        query = query.filter(Question.id.in_(semantic_ids_ordered))

    total = query.count()
    questions = query.order_by(Question.source_quiz_id, Question.id).offset(offset).limit(limit).all()

    # If hybrid: merge semantic first then keyword remainder
    if semantic_ids_ordered and search_mode == "hybrid":
        sem_set = set(semantic_ids_ordered)
        sem_qs = [qu for qu in questions if qu.id in sem_set]
        kw_qs = [qu for qu in questions if qu.id not in sem_set]
        # Sort semantic by original similarity order
        sem_order = {qid: i for i, qid in enumerate(semantic_ids_ordered)}
        sem_qs.sort(key=lambda qu: sem_order.get(qu.id, 999))
        questions = sem_qs + kw_qs

    quiz_cache: dict[int, str] = {}
    cat_cache: dict[int, str] = {}
    result = []
    for qu in questions:
        src_id = qu.source_quiz_id
        if src_id not in quiz_cache:
            quiz = db.query(Quiz).filter(Quiz.id == src_id).first() if src_id else None
            quiz_cache[src_id] = quiz.title if quiz else (f"Quiz {src_id}" if src_id else "Unknown")
        cat_name = None
        if qu.question_category_id:
            if qu.question_category_id not in cat_cache:
                cat = db.query(QuestionCategory).filter(QuestionCategory.id == qu.question_category_id).first()
                cat_cache[qu.question_category_id] = cat.name if cat else None
            cat_name = cat_cache.get(qu.question_category_id)
        result.append({
            "id": qu.id,
            "quiz_id": qu.source_quiz_id,
            "quiz_title": quiz_cache[src_id],
            "question_category_id": qu.question_category_id,
            "question_category_name": cat_name,
            "question_text": qu.question_text,
            "question_type": qu.question_type,
            "options": qu.options,
            "correct_answer": qu.correct_answer,
            "explanation": qu.explanation,
            "image_path": qu.image_path,
        })

    return {"total": total, "questions": result}


class CreateFromBankRequest(BaseModel):
    title: str
    question_ids: list[int]
    mode: str = "timed"
    time_limit_minutes: int | None = None


@router.post("/from-bank")
def create_quiz_from_bank(
    data: CreateFromBankRequest,
    db: Session = Depends(get_db),
    current_user: User = Depends(require_moderator),
):
    """Create a new quiz referencing existing bank questions (no copying — edits propagate)."""
    if not data.title.strip():
        raise HTTPException(status_code=400, detail="Title is required")
    if not data.question_ids:
        raise HTTPException(status_code=400, detail="Select at least one question")
    if data.mode not in ("timed", "learning"):
        raise HTTPException(status_code=400, detail="Mode must be timed or learning")

    source_questions = db.query(Question).filter(Question.id.in_(data.question_ids)).all()
    if not source_questions:
        raise HTTPException(status_code=404, detail="No valid questions found")
    # Preserve caller's requested order
    id_order = {qid: i for i, qid in enumerate(data.question_ids)}
    source_questions.sort(key=lambda q: id_order.get(q.id, len(data.question_ids)))

    # Find a section_id from the source questions' origin quiz
    first_src_quiz_id = source_questions[0].source_quiz_id
    first_quiz = db.query(Quiz).filter(Quiz.id == first_src_quiz_id).first() if first_src_quiz_id else None
    section_id = first_quiz.section_id if first_quiz else source_questions[0].source_quiz_id or 1

    new_quiz = Quiz(
        section_id=section_id,
        user_id=current_user.id,
        title=data.title.strip(),
        questions_count=len(source_questions),
        mode=data.mode,
        time_limit_minutes=data.time_limit_minutes,
    )
    db.add(new_quiz)
    db.flush()

    # Reference existing questions via junction (no copies)
    from app.models.quiz_question_link import QuizQuestionLink
    for pos, sq in enumerate(source_questions):
        db.add(QuizQuestionLink(quiz_id=new_quiz.id, question_id=sq.id, position=pos))

    db.commit()
    db.refresh(new_quiz)
    return {"id": new_quiz.id, "title": new_quiz.title, "questions_count": new_quiz.questions_count}


class BulkCategoryRequest(BaseModel):
    question_ids: list[int]
    category_id: int | None = None


@router.post("/bulk-category")
def bulk_set_question_category(
    data: BulkCategoryRequest,
    db: Session = Depends(get_db),
    current_user: User = Depends(require_moderator),
):
    """Assign or remove a category from multiple questions."""
    if data.category_id is not None:
        cat = db.query(QuestionCategory).filter(QuestionCategory.id == data.category_id).first()
        if not cat:
            raise HTTPException(status_code=404, detail="Category not found")
    updated = db.query(Question).filter(Question.id.in_(data.question_ids)).update(
        {"question_category_id": data.category_id}, synchronize_session=False
    )
    db.commit()
    return {"updated": updated, "question_category_id": data.category_id}