from datetime import datetime
from typing import Optional, Dict, Any
from pydantic import BaseModel, Field
from bson import ObjectId


class PyObjectId(ObjectId):
    """Custom ObjectId type for Pydantic"""
    @classmethod
    def __get_validators__(cls):
        yield cls.validate

    @classmethod
    def validate(cls, v):
        if not ObjectId.is_valid(v):
            raise ValueError("Invalid ObjectId")
        return ObjectId(v)

    @classmethod
    def __get_pydantic_json_schema__(cls, field_schema):
        field_schema.update(type="string")


class Keyword(BaseModel):
    """Keyword data model for pipeline management"""

    id: Optional[PyObjectId] = Field(default=None, alias="_id")
    keyword: str = Field(..., min_length=1, max_length=200)
    category: str = Field(..., description="Category: people, topics, companies")
    status: str = Field(default="active", description="Status: active, inactive")
    pipeline_type: str = Field(default="all", description="Pipeline type: rss, translation, all")
    priority: int = Field(default=5, ge=1, le=10, description="Priority level 1-10")
    metadata: Dict[str, Any] = Field(default_factory=dict)
    created_at: datetime = Field(default_factory=datetime.utcnow)
    updated_at: datetime = Field(default_factory=datetime.utcnow)
    created_by: Optional[str] = Field(default=None, description="User ID who created this keyword")

    class Config:
        populate_by_name = True
        arbitrary_types_allowed = True
        json_encoders = {ObjectId: str}
        json_schema_extra = {
            "example": {
                "keyword": "도널드 트럼프",
                "category": "people",
                "status": "active",
                "pipeline_type": "all",
                "priority": 8,
                "metadata": {
                    "description": "Former US President",
                    "aliases": ["Donald Trump", "Trump"]
                },
                "created_by": "admin"
            }
        }