models/event_models.py

"""
Event-Centric Pydantic Models for MongoDB
Author: AI Generated
Created: 2025-11-24
Purpose: Define schemas for event-specific analysis results
"""

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


class PyObjectId(ObjectId):
    """Custom ObjectId type for Pydantic v2"""
    
    @classmethod
    def __get_pydantic_core_schema__(cls, source_type, handler):
        from pydantic_core import core_schema
        
        return core_schema.union_schema([
            core_schema.is_instance_schema(ObjectId),
            core_schema.chain_schema([
                core_schema.str_schema(),
                core_schema.no_info_plain_validator_function(cls.validate),
            ])
        ],
        serialization=core_schema.plain_serializer_function_ser_schema(
            lambda x: str(x)
        ))
    
    @classmethod
    def validate(cls, v):
        if isinstance(v, ObjectId):
            return v
        if isinstance(v, str):
            if not ObjectId.is_valid(v):
                raise ValueError(f"Invalid ObjectId: {v}")
            return ObjectId(v)
        raise ValueError(f"Expected ObjectId or string, got {type(v)}")



class MarketingContent(BaseModel):
    """Marketing email content generated by AI"""
    email_subject: str
    email_body: str
    status: str = "Draft"  # Draft, Approved, Sent
    generated_at: datetime = Field(default_factory=datetime.utcnow)
    approved_at: Optional[datetime] = None
    approved_by: Optional[str] = None


class EventAudienceSegment(BaseModel):
    """
    Audience segment specific to an event.
    Stores clustering results and marketing content for Event Owner review.
    """
    id: Optional[PyObjectId] = Field(default=None, alias="_id")
    event_code: str = Field(..., description="Event identifier")
    segment_name: str = Field(..., description="Human-readable segment name in Vietnamese")
    segment_type: str = Field(..., description="Segment category (e.g., VIP, Potential, Dormant)")
    user_count: int = Field(..., description="Number of users in this segment")
    user_ids: List[PyObjectId] = Field(default_factory=list, description="List of user ObjectIds in this segment")
    
    criteria: Dict[str, Any] = Field(
        default_factory=dict,
        description="Average statistics for this segment (e.g., avg_spend, avg_tickets, avg_recency)"
    )
    
    marketing_content: Optional[MarketingContent] = Field(
        default=None,
        description="AI-generated marketing email (Draft, pending approval)"
    )
    
    created_at: datetime = Field(default_factory=datetime.utcnow)
    last_updated: datetime = Field(default_factory=datetime.utcnow)
    
    class Config:
        populate_by_name = True
        arbitrary_types_allowed = True
        json_encoders = {ObjectId: str}


class AIInsights(BaseModel):
    """AI-generated insights from sentiment analysis"""
    summary: str = Field(..., description="Overall sentiment summary in Vietnamese")
    top_issues: List[str] = Field(default_factory=list, description="Top 5 recurring issues")
    improvement_suggestions: List[str] = Field(default_factory=list, description="Actionable suggestions")
    predicted_nps: Optional[float] = Field(None, description="Predicted Net Promoter Score (0-100)")


class EventSentimentSummary(BaseModel):
    """
    Aggregated sentiment analysis summary for an event.
    Provides Event Owner with quick insights about attendee feedback.
    """
    id: Optional[PyObjectId] = Field(default=None, alias="_id")
    event_code: str = Field(..., description="Event identifier")
    
    total_comments: int = Field(default=0, description="Total number of comments analyzed")
    
    sentiment_distribution: Dict[str, int] = Field(
        default_factory=dict,
        description="Count of Positive, Negative, Neutral comments"
    )
    
    avg_confidence: float = Field(default=0.0, description="Average confidence score of sentiment predictions")
    
    top_keywords: List[str] = Field(
        default_factory=list,
        description="Most frequently mentioned keywords/phrases"
    )
    
    ai_insights: Optional[AIInsights] = Field(
        default=None,
        description="AI-generated insights and recommendations"
    )
    
    last_updated: datetime = Field(default_factory=datetime.utcnow)
    
    class Config:
        populate_by_name = True
        arbitrary_types_allowed = True
        json_encoders = {ObjectId: str}