# pipeline/validation.py
from typing import Literal, Optional
from pydantic import BaseModel, Field, field_validator

class DocMetadata(BaseModel):
    methodology_type: Literal["experimental", "observational", "review", "simulation", "mixed"]
    dataset_source: str = Field(min_length=3)
    year: int = Field(ge=1950, le=2030)
    primary_metric: Optional[str] = None
    confidence_score: Optional[float] = Field(default=None, ge=0.0, le=1.0)

    @field_validator("dataset_source")
    @classmethod
    def strip_whitespace(cls, v: str) -> str:
        return v.strip()

    @field_validator("methodology_type", mode="before")
    @classmethod
    def normalize_methodology(cls, v: str) -> str:
        # Qwen occasionally returns "Experimental" despite instructions
        return v.lower().strip() if isinstance(v, str) else v