#!/usr/bin/env python3
"""
Auto-pipeline: Lean build → extract metadata → populate DB → RRC classify.
Runs after every push to Semantics Lean sources.

Usage:
  python3 auto_pipeline.py                     # full pipeline
  python3 auto_pipeline.py --db-only           # recreate DB schema only
  python3 auto_pipeline.py --ci                # CI mode (no build, just extract+predict)
"""
import subprocess, json, os, sys, argparse
from pathlib import Path

ROOT = Path(__file__).resolve().parent.parent
NEON_PG = "postgres://postgres:postgres@100.92.88.64:5432"

def sh(cmd, **kw):
    return subprocess.run(cmd, shell=True, capture_output=True, text=True, **kw)

def pg(sql, db="research_stack"):
    r = sh(f"psql {NEON_PG}/{db} -c {shlex.quote(sql)}")
    if r.returncode != 0:
        print(f"  DB error: {r.stderr[:200]}")

# ── 1. Extract Lean metadata ──────────────────────────────────────────────
SCAN_DIRS = [
    ROOT / "0-Core-Formalism" / "lean" / "Semantics",
    ROOT / "0-Core-Formalism" / "lean" / "SilverSight",
]

def extract_theorems():
    """Scan Lean files for theorems, lemmas, defs, sorries."""
    theorems = []
    for d in SCAN_DIRS:
        for f in sorted(d.rglob("*.lean")):
            if ".lake" in str(f):
                continue
            rel = f.relative_to(ROOT)
            text = f.read_text()
            for line_no, line in enumerate(text.split("\n"), 1):
                for kw in ("theorem ", "lemma ", "def "):
                    if kw in line:
                        name = line.split(kw)[1].split()[0].split(":")[0].split(" ")[0]
                        theorems.append({
                            "name": name,
                            "kind": kw.strip(),
                            "file": str(rel),
                            "line": line_no,
                            "has_sorry": "sorry" in text,
                            "source": f.readlines(),
                        })
    return theorems

# ── 2. Populate ENE DB ────────────────────────────────────────────────────
def populate_ene(theorems):
    pg("CREATE SCHEMA IF NOT EXISTS ene", "research_stack")
    for t in theorems:
        pg(f"""INSERT INTO ene.packages (pkg, package_type, title, source, domain)
            VALUES ('lean:{t["file"]}:{t["name"]}', 'lean_theorem', '{t["name"]}', '{t["file"]}', 'lean')
            ON CONFLICT (pkg) DO NOTHING""", "research_stack")

# ── 3. Run RRC Classification ─────────────────────────────────────────────
def run_rrc():
    """Run RRC compile pipeline and update predictions."""
    r = sh("cd {} && lake build Compiler 2>&1".format(
        ROOT / "0-Core-Formalism" / "lean" / "Semantics"), timeout=600)
    return r.returncode == 0

# ── Main ──────────────────────────────────────────────────────────────────
def main():
    parser = argparse.ArgumentParser()
    parser.add_argument("--db-only", action="store_true")
    parser.add_argument("--ci", action="store_true")
    args = parser.parse_args()

    if args.db_only:
        import shlex
        sql_path = Path(__file__).with_name("ene_schema.sql")
        r = sh(f"psql {NEON_PG}/research_stack -f {sql_path}")
        print(r.stdout[-200:] if r.stdout else r.stderr[-200:])
        return

    if not args.ci:
        print("[pipeline] Building Lean...")
        ok = run_rrc()
        print(f"[pipeline] Build {'OK' if ok else 'FAILED'}")

    print("[pipeline] Extracting theorems...")
    theorems = extract_theorems()
    print(f"  Found {len(theorems)} theorem/lemma/def sites")

    print("[pipeline] Populating ENE...")
    populate_ene(theorems)
    print("  Done")

    print("[pipeline] RRC classification...")
    # Call the RRC compile skill logic here
    print("  RRC: pending integration")

    print("[pipeline] Complete")

if __name__ == "__main__":
    main()