"""
ContentTypeProfile protocol and config dataclasses.

The pipeline graph is fixed — what varies per content type is configuration
and hooks. Each profile provides stage configs, a brand dictionary,
VLM prompt templates, and an aggregation strategy.
"""

from __future__ import annotations

from dataclasses import dataclass, field
from typing import Protocol

from detect.models import BrandDetection, DetectionReport


@dataclass
class FrameExtractionConfig:
    fps: float = 2.0
    max_frames: int = 500


@dataclass
class SceneFilterConfig:
    hamming_threshold: int = 8
    enabled: bool = True


@dataclass
class DetectionConfig:
    model_name: str = "yolov8n.pt"
    confidence_threshold: float = 0.3
    target_classes: list[str] = field(default_factory=lambda: ["logo", "text"])


@dataclass
class OCRConfig:
    languages: list[str] = field(default_factory=lambda: ["en"])
    min_confidence: float = 0.5


@dataclass
class ResolverConfig:
    fuzzy_threshold: int = 75


@dataclass
class BrandDictionary:
    """Maps canonical brand name → list of known aliases/spellings."""
    brands: dict[str, list[str]] = field(default_factory=dict)


@dataclass
class CropContext:
    image: bytes
    surrounding_text: str = ""
    position_hint: str = ""


class ContentTypeProfile(Protocol):
    name: str

    def frame_extraction_config(self) -> FrameExtractionConfig: ...
    def scene_filter_config(self) -> SceneFilterConfig: ...
    def detection_config(self) -> DetectionConfig: ...
    def ocr_config(self) -> OCRConfig: ...
    def brand_dictionary(self) -> BrandDictionary: ...
    def resolver_config(self) -> ResolverConfig: ...
    def vlm_prompt(self, crop_context: CropContext) -> str: ...
    def aggregate(self, detections: list[BrandDetection]) -> DetectionReport: ...
    def auxiliary_detections(self, source: str) -> list[BrandDetection]: ...