from __future__ import annotations

from collections.abc import Sequence

import torch
from torch.utils.data import Dataset

from .io import assigned_split
from .schemas import RewardRecord, route_text


class RouterDataset(Dataset):
    def __init__(self, records: Sequence[RewardRecord], split: str | None = None):
        self.records = [
            record
            for record in records
            if split is None or assigned_split(record.task_id, record.split) == split
        ]

    def __len__(self) -> int:
        return len(self.records)

    def __getitem__(self, index: int) -> dict:
        record = self.records[index]
        return {
            "task_id": record.task_id,
            "text": route_text(record.prompt, record.domain, record.tags),
            "rewards": torch.tensor(record.rewards, dtype=torch.float32),
        }


class RouterCollator:
    def __init__(self, tokenizer, max_length: int):
        self.tokenizer = tokenizer
        self.max_length = max_length

    def __call__(self, examples: list[dict]) -> dict:
        encoded = self.tokenizer(
            [example["text"] for example in examples],
            padding=True,
            truncation=True,
            max_length=self.max_length,
            return_tensors="pt",
        )
        encoded["rewards"] = torch.stack([example["rewards"] for example in examples])
        encoded["task_ids"] = [example["task_id"] for example in examples]
        return encoded