"""Soccer broadcast profile — pitch hoardings, kits, scoreboards."""

from __future__ import annotations

from detect.models import BrandDetection, BrandStats, DetectionReport, PipelineStats

from .base import (
    BrandDictionary,
    CropContext,
    DetectionConfig,
    FrameExtractionConfig,
    OCRConfig,
    ResolverConfig,
    SceneFilterConfig,
)


class SoccerBroadcastProfile:
    name = "soccer_broadcast"

    def frame_extraction_config(self) -> FrameExtractionConfig:
        return FrameExtractionConfig(fps=2.0, max_frames=500)

    def scene_filter_config(self) -> SceneFilterConfig:
        return SceneFilterConfig(hamming_threshold=8, enabled=True)

    def detection_config(self) -> DetectionConfig:
        return DetectionConfig(
            model_name="yolov8n.pt",
            confidence_threshold=0.3,
            target_classes=[],  # empty = accept all COCO classes (until custom model)
        )

    def ocr_config(self) -> OCRConfig:
        return OCRConfig(languages=["en", "es"], min_confidence=0.5)

    def brand_dictionary(self) -> BrandDictionary:
        return BrandDictionary(brands={
            "Nike": ["nike", "NIKE", "swoosh"],
            "Adidas": ["adidas", "ADIDAS", "adi"],
            "Puma": ["puma", "PUMA"],
            "Emirates": ["emirates", "fly emirates", "EMIRATES"],
            "Coca-Cola": ["coca-cola", "coca cola", "coke", "COCA-COLA"],
            "Pepsi": ["pepsi", "PEPSI"],
            "Mastercard": ["mastercard", "MASTERCARD"],
            "Heineken": ["heineken", "HEINEKEN"],
            "Santander": ["santander", "SANTANDER"],
            "Gazprom": ["gazprom", "GAZPROM"],
            "Qatar Airways": ["qatar airways", "QATAR AIRWAYS"],
            "Lay's": ["lays", "lay's", "LAYS", "LAY'S"],
        })

    def resolver_config(self) -> ResolverConfig:
        return ResolverConfig(fuzzy_threshold=75)

    def vlm_prompt(self, crop_context: CropContext) -> str:
        hint = f" Position: {crop_context.position_hint}." if crop_context.position_hint else ""
        text = f" Nearby text: '{crop_context.surrounding_text}'." if crop_context.surrounding_text else ""
        return (
            f"Identify the brand or sponsor visible in this cropped region "
            f"from a soccer broadcast.{hint}{text} "
            f"Respond with: brand, confidence (0-1), reasoning."
        )

    def aggregate(self, detections: list[BrandDetection]) -> DetectionReport:
        brands: dict[str, BrandStats] = {}
        for d in detections:
            if d.brand not in brands:
                brands[d.brand] = BrandStats()
            s = brands[d.brand]
            s.total_appearances += 1
            s.total_screen_time += d.duration
            s.avg_confidence = (
                (s.avg_confidence * (s.total_appearances - 1) + d.confidence)
                / s.total_appearances
            )
            if s.first_seen == 0.0 or d.timestamp < s.first_seen:
                s.first_seen = d.timestamp
            if d.timestamp > s.last_seen:
                s.last_seen = d.timestamp

        return DetectionReport(
            video_source="",
            content_type=self.name,
            duration_seconds=0.0,
            brands=brands,
            timeline=sorted(detections, key=lambda d: d.timestamp),
            pipeline_stats=PipelineStats(),
        )

    def auxiliary_detections(self, source: str) -> list[BrandDetection]:
        return []