import yaml
import argparse
import sys
import json
from pathlib import Path

ROOT = Path(__file__).resolve().parents[1]

def main():
    parser = argparse.ArgumentParser()
    parser.add_argument("--taxonomy", default="spec/43_quant_factor_taxonomy.yaml")
    args = parser.parse_args()

    taxonomy_path = ROOT / args.taxonomy
    if not taxonomy_path.exists():
        print(f"Taxonomy file not found: {taxonomy_path}")
        return 1

    try:
        tax = yaml.safe_load(taxonomy_path.read_text(encoding="utf-8"))
    except Exception as e:
        print(f"Error parsing taxonomy: {e}")
        return 1

    required_fields = tax.get("required_lifecycle_fields", [])
    if not required_fields:
        # Fallback to 14 fields if not in taxonomy
        required_fields = [
            "factor_id", "hypothesis", "horizon", "decay_half_life",
            "input_fields", "formula_id", "conflict_precedence",
            "activation_threshold", "retirement_condition", "owner",
            "reviewer", "lifecycle_state", "activation_date", "expected_edge_formula"
        ]

    factors_path = ROOT / "spec" / "factor_lifecycle_registry.yaml"
    if not factors_path.exists():
        print(f"Factors registry not found: {factors_path}")
        return 1
    
    try:
        factors_data = yaml.safe_load(factors_path.read_text(encoding="utf-8"))
    except Exception as e:
        print(f"Error parsing factors: {e}")
        return 1

    factors = factors_data.get("factors", [])
    if isinstance(factors_data, dict) and "factors" not in factors_data:
        factors = list(factors_data.values())

    report = {
        "formula_id": "FACTOR_LIFECYCLE_COMPLETENESS_V2",
        "factor_count": len(factors),
        "missing_fields": []
    }

    total_fields = len(factors) * len(required_fields)
    filled_fields = 0

    for factor in factors:
        if not isinstance(factor, dict): continue
        for field in required_fields:
            if field in factor and factor[field]:
                filled_fields += 1
            else:
                report["missing_fields"].append({
                    "factor_id": factor.get("factor_id", "unknown"),
                    "field": field
                })

    report["completeness_pct"] = (filled_fields / total_fields * 100) if total_fields > 0 else 100
    report["gate"] = "PASS" if report["completeness_pct"] == 100 else "WARN"

    print(json.dumps(report, indent=2))
    return 0

if __name__ == "__main__":
    main()