"""Dataset metadata (DatasetSpec) and declarative field mapping (FieldSpec)."""

from dataclasses import dataclass, field
from typing import List, Optional


@dataclass
class FieldSpec:
    """Declarative mapping: raw record field name -> Sample field name.

    Use this when the raw records are already well-shaped; no custom
    ``record_to_sample`` function is needed then.
    """

    input: str = 'input'
    target: str = 'target'
    choices: str = 'choices'
    id: Optional[str] = None
    metadata: List[str] = field(default_factory=list)


@dataclass
class DatasetSpec:
    """Everything the framework needs to know about a dataset *without*
    loading it. Drives the cache key, the CLI listing, and (later) the
    deployment-time dependency resolution via ``requires``.
    """

    name: str
    source: str  # hub id ('AI-ModelScope/gsm8k') or local path
    split: str = 'test'
    subset: str = 'default'
    version: Optional[str] = None
    task_type: str = 'qa'  # qa | mcq | math | coding | agent | vqa | fc
    tags: List[str] = field(default_factory=list)
    requires: List[str] = field(default_factory=list)  # e.g. ['docker']
    description: str = ''
    params: dict = field(default_factory=dict)  # extra load params, part of cache key