"""
validation/reporter.py — Aggregates all validation reports into a unified summary.

Used by: python main.py validate
"""

from datetime import date as Date
from typing import Optional
import logging

from .factor_validator import FactorValidator, FactorReport
from .regime_validator import RegimeValidator, RegimeReport
from .transition_validator import TransitionValidator, TransitionReport

logger = logging.getLogger(__name__)


class ValidationReporter:
    """
    Orchestrates full validation pipeline:

    1. Factor validation (IC, ICIR, Hit Ratio) for each factor
    2. Regime validation (MI, KL, ANOVA) for each factor
    3. Transition validation (stability, flip rate)
    """

    def __init__(self, db_path: Optional[str] = None):
        from config import config
        self.db_path = db_path or config.db_path
        self.factor_validator = FactorValidator(self.db_path)
        self.regime_validator = RegimeValidator(self.db_path)
        self.transition_validator = TransitionValidator(self.db_path)

    def run_all(self) -> str:
        """Run all validations and return a formatted report string."""
        lines = []
        lines.append("=" * 70)
        lines.append(f"  ChanMacro Validation Report — {Date.today()}")
        lines.append("=" * 70)

        # ── Factor Validation ──────────────────────────
        lines.append("")
        lines.append("─" * 50)
        lines.append("  FACTOR VALIDATION (Predictive Power)")
        lines.append("─" * 50)

        factor_queries = {
            "Price Structure": "SELECT date, score FROM ohlcv_daily WHERE ema20 IS NOT NULL",
            "Breadth": """
                SELECT bd.date,
                    (bd.advance_top50*1.0/(bd.advance_top50+bd.decline_top50+1)*100*0.30
                     + bd.above_ema20_top50*1.0/50*100*0.35
                     + bd.new_highs_20d_top50*1.0/50*100*0.20
                     + 50*0.15) as score
                FROM breadth_daily bd
            """,
        }

        factor_reports: list[FactorReport] = []
        for name, query in factor_queries.items():
            try:
                report = self.factor_validator.validate_from_db(name, query)
                factor_reports.append(report)
                lines.append(report.summary())
                lines.append("")
            except Exception as e:
                logger.warning(f"Factor validation failed for {name}: {e}")

        # ── Regime Validation ──────────────────────────
        lines.append("─" * 50)
        lines.append("  REGIME VALIDATION (Regime Separation)")
        lines.append("─" * 50)

        regime_reports: list[RegimeReport] = []
        for name, query in factor_queries.items():
            try:
                report = self.regime_validator.validate_from_db(name, query)
                regime_reports.append(report)
                lines.append(report.summary())
                lines.append("")
            except Exception as e:
                logger.warning(f"Regime validation failed for {name}: {e}")

        # ── Transition Validation ──────────────────────
        lines.append("─" * 50)
        lines.append("  TRANSITION VALIDATION (Regime Stability)")
        lines.append("─" * 50)

        try:
            t_report = self.transition_validator.validate_from_db()
            lines.append(t_report.summary())
        except Exception as e:
            logger.warning(f"Transition validation failed: {e}")

        # ── Summary ────────────────────────────────────
        lines.append("")
        lines.append("=" * 70)
        lines.append("  SUMMARY")
        lines.append("=" * 70)

        # Factor ranking by IC
        if factor_reports:
            ranked = sorted(factor_reports, key=lambda r: abs(r.ic_mean), reverse=True)
            lines.append("  Factor Ranking (by |IC|):")
            for i, r in enumerate(ranked):
                tag = "★★★" if abs(r.ic_mean) > 0.05 else "★★" if abs(r.ic_mean) > 0.03 else "★"
                lines.append(f"    {i+1}. {r.factor_name:20s} IC={r.ic_mean:+.4f} {tag}  {r.conclusion}")

        # Regime factor ranking
        if regime_reports:
            ranked_r = sorted(regime_reports, key=lambda r: r.separation_score, reverse=True)
            lines.append("")
            lines.append("  Regime Factor Ranking (by Separation Score):")
            for i, r in enumerate(ranked_r):
                lines.append(f"    {i+1}. {r.factor_name:20s} Score={r.separation_score:.2f}  {r.conclusion}")

        lines.append("")
        lines.append("=" * 70)

        return "\n".join(lines)