"""Split COMP2211 Spring 2024 final into subquestions."""

from __future__ import annotations

import json
import re
from dataclasses import dataclass
from pathlib import Path

from app.services.supabase_client import get_supabase


EXAM_KEY = "COMP2211-2024-spring-final"
PROBLEM_SEED_PATH = (
    Path(__file__).resolve().parent.parent
    / "pastpaper-scraper"
    / "reviews"
    / "COMP2211"
    / "problem_seed.json"
)
TRUE_FALSE_OPTIONS = [{"label": "True", "text": "True"}, {"label": "False", "text": "False"}]


@dataclass(frozen=True)
class ChildSpec:
    question_number: str
    parent_question: str
    top_level_number: str
    path: tuple[str, ...]
    score: float
    question_type: str
    question_format: str | None = None
    analytics_topic: str | None = None
    topic_primary: str | None = None
    topic_tags: tuple[str, ...] | None = None
    skill_tags: tuple[str, ...] | None = None
    options: tuple[tuple[str, str], ...] | None = None
    correct_option: str | None = None
    correct_answer: str | None = None
    page_number: int = 1


def short_answer(
    question_number: str,
    parent_question: str,
    top_level_number: str,
    path: tuple[str, ...],
    score: float,
    *,
    analytics_topic: str | None = None,
    topic_primary: str | None = None,
    topic_tags: tuple[str, ...] | None = None,
    skill_tags: tuple[str, ...] | None = None,
    correct_answer: str | None = None,
    page_number: int,
) -> ChildSpec:
    return ChildSpec(
        question_number=question_number,
        parent_question=parent_question,
        top_level_number=top_level_number,
        path=path,
        score=score,
        question_type="long_question",
        question_format="short_answer",
        analytics_topic=analytics_topic,
        topic_primary=topic_primary,
        topic_tags=topic_tags,
        skill_tags=skill_tags,
        correct_answer=correct_answer,
        page_number=page_number,
    )


CHILDREN: list[ChildSpec] = [
    ChildSpec("1a", "1", "1", ("a",), 1, "true_false", "true_false", "Python Fundamentals", "Python Fundamentals", ("Python Fundamentals",), ("concept_check", "code_tracing"), page_number=2),
    ChildSpec("1b", "1", "1", ("b",), 1, "true_false", "true_false", "Probabilistic Models", "Probabilistic Models", ("Probabilistic Models",), ("concept_check", "classification_decision"), page_number=2),
    ChildSpec("1c", "1", "1", ("c",), 1, "true_false", "true_false", "KNN and Clustering", "KNN and Clustering", ("KNN and Clustering",), ("concept_check", "algorithm_property"), page_number=2),
    ChildSpec("1d", "1", "1", ("d",), 1, "true_false", "true_false", "KNN and Clustering", "KNN and Clustering", ("KNN and Clustering",), ("concept_check", "algorithm_property"), page_number=2),
    ChildSpec("1e", "1", "1", ("e",), 1, "true_false", "true_false", "Perceptron and MLP", "Perceptron and MLP", ("Perceptron and MLP",), ("concept_check", "activation_reasoning"), page_number=2),
    ChildSpec("1f", "1", "1", ("f",), 1, "true_false", "true_false", "Vision and CNN", "Vision and CNN", ("Vision and CNN",), ("concept_check", "image_processing"), page_number=2),
    ChildSpec("1g", "1", "1", ("g",), 1, "true_false", "true_false", "Vision and CNN", "Vision and CNN", ("Vision and CNN",), ("concept_check", "cnn_complexity"), page_number=2),
    ChildSpec("1h", "1", "1", ("h",), 1, "true_false", "true_false", "Vision and CNN", "Vision and CNN", ("Vision and CNN",), ("concept_check", "regularization"), page_number=2),
    ChildSpec("1i", "1", "1", ("i",), 1, "true_false", "true_false", "Search and Games", "Search and Games", ("Search and Games",), ("concept_check", "pruning_reasoning"), page_number=2),
    ChildSpec("1j", "1", "1", ("j",), 1, "true_false", "true_false", "Ethics of AI", "Ethics of AI", ("Ethics of AI",), ("concept_check", "research_ethics"), page_number=2),
    ChildSpec("2a", "2", "2", ("a",), 4, "long_question", "coding", "Python Fundamentals", "Python Fundamentals", ("Python Fundamentals",), ("implementation", "vectorization", "masking"), page_number=3),
    ChildSpec("2b", "2", "2", ("b",), 6, "long_question", "coding", "Python Fundamentals", "Python Fundamentals", ("Python Fundamentals",), ("implementation", "convolution", "array_manipulation"), page_number=4),
    short_answer("3a_i", "3a", "3", ("a", "i"), 1.5, analytics_topic="Probabilistic Models", topic_primary="Probabilistic Models", topic_tags=("Probabilistic Models",), skill_tags=("manual_computation", "probability_reasoning"), page_number=6),
    short_answer("3a_ii", "3a", "3", ("a", "ii"), 1.5, analytics_topic="Probabilistic Models", topic_primary="Probabilistic Models", topic_tags=("Probabilistic Models",), skill_tags=("manual_computation", "probability_reasoning"), page_number=6),
    short_answer("3a_iii", "3a", "3", ("a", "iii"), 1.5, analytics_topic="Probabilistic Models", topic_primary="Probabilistic Models", topic_tags=("Probabilistic Models",), skill_tags=("manual_computation", "probability_reasoning"), page_number=6),
    short_answer("3a_iv", "3a", "3", ("a", "iv"), 1.5, analytics_topic="Probabilistic Models", topic_primary="Probabilistic Models", topic_tags=("Probabilistic Models",), skill_tags=("manual_computation", "probability_reasoning"), page_number=6),
    short_answer("3b_i", "3b", "3", ("b", "i"), 1.5, analytics_topic="Evaluation and Validation", topic_primary="Evaluation and Validation", topic_tags=("Evaluation and Validation",), skill_tags=("validation_reasoning",), page_number=6),
    short_answer("3b_ii", "3b", "3", ("b", "ii"), 1.5, analytics_topic="Evaluation and Validation", topic_primary="Evaluation and Validation", topic_tags=("Evaluation and Validation",), skill_tags=("validation_reasoning",), page_number=6),
    short_answer("3b_iii", "3b", "3", ("b", "iii"), 1.5, analytics_topic="Evaluation and Validation", topic_primary="Evaluation and Validation", topic_tags=("Evaluation and Validation",), skill_tags=("validation_reasoning",), page_number=6),
    short_answer("3c", "3", "3", ("c",), 1.5, analytics_topic="Perceptron and MLP", topic_primary="Perceptron and MLP", topic_tags=("Perceptron and MLP",), skill_tags=("linearity_reasoning", "classification_decision"), page_number=6),
    short_answer("4a_i", "4a", "4", ("a", "i"), 2.5, analytics_topic="Perceptron and MLP", topic_primary="Perceptron and MLP", topic_tags=("Perceptron and MLP",), skill_tags=("parameter_counting",), page_number=7),
    short_answer("4a_ii", "4a", "4", ("a", "ii"), 2.5, analytics_topic="Perceptron and MLP", topic_primary="Perceptron and MLP", topic_tags=("Perceptron and MLP",), skill_tags=("model_selection",), page_number=7),
    short_answer("4b", "4", "4", ("b",), 1, analytics_topic="Perceptron and MLP", topic_primary="Perceptron and MLP", topic_tags=("Perceptron and MLP",), skill_tags=("concept_explanation",), page_number=7),
    short_answer("4c", "4", "4", ("c",), 2, analytics_topic="Perceptron and MLP", topic_primary="Perceptron and MLP", topic_tags=("Perceptron and MLP",), skill_tags=("activation_reasoning", "optimization_reasoning"), page_number=7),
    ChildSpec("4d_i", "4d", "4", ("d", "i"), 1.5, "long_question", "long_answer", "Perceptron and MLP", "Perceptron and MLP", ("Perceptron and MLP",), ("forward_pass", "activation_reasoning"), page_number=8),
    ChildSpec("4d_ii", "4d", "4", ("d", "ii"), 1.5, "long_question", "long_answer", "Perceptron and MLP", "Perceptron and MLP", ("Perceptron and MLP",), ("backpropagation", "weight_update"), page_number=8),
    ChildSpec("5a", "5", "5", ("a",), 4.5, "long_question", "long_answer", "Vision and CNN", "Vision and CNN", ("Vision and CNN",), ("histogram_reasoning", "image_transform"), page_number=9),
    ChildSpec("5b", "5", "5", ("b",), 3, "long_question", "long_answer", "Vision and CNN", "Vision and CNN", ("Vision and CNN",), ("thresholding", "manual_computation"), page_number=10),
    ChildSpec("5c", "5", "5", ("c",), 2, "long_question", "long_answer", "Vision and CNN", "Vision and CNN", ("Vision and CNN",), ("padding", "manual_construction"), page_number=10),
    short_answer("5d_i", "5d", "5", ("d", "i"), 0.5, analytics_topic="Vision and CNN", topic_primary="Vision and CNN", topic_tags=("Vision and CNN",), skill_tags=("filter_effect_reasoning",), page_number=11),
    short_answer("5d_ii", "5d", "5", ("d", "ii"), 0.5, analytics_topic="Vision and CNN", topic_primary="Vision and CNN", topic_tags=("Vision and CNN",), skill_tags=("filter_effect_reasoning",), page_number=11),
    short_answer("5d_iii", "5d", "5", ("d", "iii"), 0.5, analytics_topic="Vision and CNN", topic_primary="Vision and CNN", topic_tags=("Vision and CNN",), skill_tags=("filter_effect_reasoning",), page_number=11),
    short_answer("5e", "5", "5", ("e",), 2, analytics_topic="Vision and CNN", topic_primary="Vision and CNN", topic_tags=("Vision and CNN",), skill_tags=("concept_explanation", "local_vs_global"), page_number=11),
    ChildSpec("6a", "6", "6", ("a",), 10, "long_question", "coding", "Vision and CNN", "Vision and CNN", ("Vision and CNN",), ("implementation", "convolution", "debugging"), page_number=12),
    ChildSpec("6b", "6", "6", ("b",), 3, "long_question", "coding", "Vision and CNN", "Vision and CNN", ("Vision and CNN",), ("implementation", "regularization"), page_number=15),
    short_answer("7a_i", "7a", "7", ("a", "i"), 1, analytics_topic="Vision and CNN", topic_primary="Vision and CNN", topic_tags=("Vision and CNN",), skill_tags=("cnn_architecture",), page_number=16),
    short_answer("7a_ii", "7a", "7", ("a", "ii"), 4, analytics_topic="Vision and CNN", topic_primary="Vision and CNN", topic_tags=("Vision and CNN",), skill_tags=("shape_reasoning", "parameter_counting"), page_number=16),
    short_answer("7a_iii", "7a", "7", ("a", "iii"), 3, analytics_topic="Vision and CNN", topic_primary="Vision and CNN", topic_tags=("Vision and CNN",), skill_tags=("overfitting", "regularization"), page_number=16),
    ChildSpec("7b", "7", "7", ("b",), 5, "long_question", "long_answer", "Vision and CNN", "Vision and CNN", ("Vision and CNN",), ("manual_computation", "cnn_forward_pass"), page_number=17),
    short_answer("7c_i", "7c", "7", ("c", "i"), 2, analytics_topic="Vision and CNN", topic_primary="Vision and CNN", topic_tags=("Vision and CNN",), skill_tags=("shape_reasoning", "3d_convolution"), page_number=17),
    short_answer("7c_ii", "7c", "7", ("c", "ii"), 1.5, analytics_topic="Vision and CNN", topic_primary="Vision and CNN", topic_tags=("Vision and CNN",), skill_tags=("parameter_counting", "3d_convolution"), page_number=17),
    short_answer("7c_iii", "7c", "7", ("c", "iii"), 1.5, analytics_topic="Vision and CNN", topic_primary="Vision and CNN", topic_tags=("Vision and CNN",), skill_tags=("parameter_counting", "3d_convolution"), page_number=17),
    short_answer("8a_i", "8a", "8", ("a", "i"), 1, analytics_topic="Search and Games", topic_primary="Search and Games", topic_tags=("Search and Games",), skill_tags=("tree_search", "manual_tracing"), page_number=18),
    short_answer("8a_ii", "8a", "8", ("a", "ii"), 3, analytics_topic="Search and Games", topic_primary="Search and Games", topic_tags=("Search and Games",), skill_tags=("pruning", "manual_tracing"), page_number=18),
    short_answer("8a_iii", "8a", "8", ("a", "iii"), 1, analytics_topic="Search and Games", topic_primary="Search and Games", topic_tags=("Search and Games",), skill_tags=("game_reasoning",), page_number=18),
    short_answer("8b_i", "8b", "8", ("b", "i"), 2.5, analytics_topic="Search and Games", topic_primary="Search and Games", topic_tags=("Search and Games",), skill_tags=("utility_reasoning",), page_number=18),
    short_answer("8b_ii", "8b", "8", ("b", "ii"), 2.5, analytics_topic="Search and Games", topic_primary="Search and Games", topic_tags=("Search and Games",), skill_tags=("pruning_reasoning", "concept_explanation"), page_number=18),
    short_answer("9", "9", "9", (), 3, analytics_topic="Ethics of AI", topic_primary="Ethics of AI", topic_tags=("Ethics of AI",), skill_tags=("concept_explanation", "governance"), page_number=19),
]


MARKER_RE = re.compile(r"(?m)^\(([a-z]+|[ivx]+)\)\s*")


def split_sections(text: str) -> tuple[str, dict[str, str]]:
    matches = list(MARKER_RE.finditer(text))
    if not matches:
        return text.strip(), {}
    intro = text[: matches[0].start()].strip()
    sections: dict[str, str] = {}
    for idx, match in enumerate(matches):
        marker = match.group(1)
        end = matches[idx + 1].start() if idx + 1 < len(matches) else len(text)
        sections[marker] = text[match.start() : end].strip()
    return intro, sections


def extract_segment(text: str, path: tuple[str, ...]) -> str:
    if not path:
        return text.strip()
    current = text.strip()
    carried_intro: list[str] = []
    for depth, marker in enumerate(path):
        intro, sections = split_sections(current)
        if depth == 0 and intro:
            carried_intro.append(intro)
        current = sections.get(marker, current)
    return "\n".join(part for part in [*carried_intro, current] if part).strip()


def extract_true_false_answers(answer_text: str) -> dict[str, str]:
    answers: dict[str, str] = {}
    table_match = re.search(r"Answer\s+(T\s+F\s+T\s+F\s+F\s+T\s+F\s+F\s+F\s+T)", answer_text, re.S)
    if table_match:
        seq = re.findall(r"[TF]", table_match.group(1))
        if len(seq) == 10:
            for idx, val in enumerate(seq):
                answers[chr(ord("a") + idx)] = val
            return answers
    seq = re.findall(r"\b([TF])\b", answer_text)
    if len(seq) >= 10:
        for idx, val in enumerate(seq[:10]):
            answers[chr(ord("a") + idx)] = val
    return answers


def load_seed_rows() -> dict[str, dict]:
    data = json.loads(PROBLEM_SEED_PATH.read_text())
    return {row["question_number"]: row for row in data if row["source_exam_key"] == EXAM_KEY}


def main() -> None:
    sb = get_supabase()
    paper = sb.table("papers").select("id").eq("source_exam_key", EXAM_KEY).execute().data[0]
    paper_id = paper["id"]
    current_rows = (
        sb.table("paper_questions")
        .select("*")
        .eq("paper_id", paper_id)
        .order("display_order")
        .execute()
        .data
    )
    existing_by_number = {row["question_number"]: row for row in current_rows}
    parent_rows = load_seed_rows()
    tf_answers = extract_true_false_answers(parent_rows["1"]["raw_answer_text"] or "")

    inserts = []
    for display_order, child in enumerate(CHILDREN, start=1):
        parent = parent_rows[child.top_level_number]
        existing = existing_by_number.get(child.question_number, {})
        question_text = extract_segment(parent["question_text"] or "", child.path)
        raw_answer_text = extract_segment(parent["raw_answer_text"] or "", child.path) if child.path else (parent["raw_answer_text"] or "")

        options = None
        correct_option = child.correct_option
        if child.question_type == "true_false":
            options = TRUE_FALSE_OPTIONS
            correct_option = tf_answers.get(child.path[0])
        elif child.options:
            options = [{"label": label, "text": text} for label, text in child.options]

        inserts.append(
            {
                "paper_id": paper_id,
                "question_number": child.question_number,
                "parent_question": child.parent_question,
                "display_order": display_order,
                "question_type": child.question_type,
                "question_format": child.question_format,
                "question_text": question_text,
                "score": child.score,
                "page_number": child.page_number,
                "page_y_ratio": existing.get("page_y_ratio"),
                "options": options,
                "correct_option": correct_option,
                "correct_answer": child.correct_answer,
                "raw_answer_text": raw_answer_text,
                "topics": existing.get("topics") or (list(child.topic_tags) if child.topic_tags else parent.get("topics")),
                "topic_primary": existing.get("topic_primary") or child.topic_primary or parent.get("topic_primary"),
                "analytics_topic": existing.get("analytics_topic") or child.analytics_topic or parent.get("analytics_topic"),
                "topic_tags": existing.get("topic_tags") or (list(child.topic_tags) if child.topic_tags else parent.get("topic_tags")),
                "skill_tags": existing.get("skill_tags") or (list(child.skill_tags) if child.skill_tags else parent.get("skill_tags")),
                "difficulty": existing.get("difficulty") or parent.get("difficulty"),
                "knowledge_reminder": existing.get("knowledge_reminder", ""),
                "ai_hint": existing.get("ai_hint", ""),
                "solution": existing.get("solution", ""),
            }
        )

    sb.table("paper_questions").delete().eq("paper_id", paper_id).execute()
    sb.table("paper_questions").insert(inserts).execute()
    sb.table("papers").update({"question_count": len(inserts), "status": "processing"}).eq("id", paper_id).execute()
    print(f"Inserted {len(inserts)} rows for {EXAM_KEY}.")


if __name__ == "__main__":
    main()