osrs-codex/tools/validate.py

#!/usr/bin/env python3
"""OSRS Codex validator — the gate for every codex/**.yaml entry.

Runs:
  1. JSON-Schema validation (schemas/entry.schema.json)
  2. Cross-field consistency checks the schema can't express:
     - state_machine `next`/transition targets must be declared states
     - `initial` must be a declared state
     - duplicate action ids / step names
     - status:verified entries with `verified:` older than --stale-days
       => WARNING (entry should be re-verified, not dropped)
     - `best_practice` lines whose source starts with "researched"
       => WARNING (citation TODO — file a follow-up issue)
     - Cross-entry supply-fact consistency: the same (supply item,
       source) across entries must carry the same ge_limit. A diverging
       limit (e.g. nature rune "12500" in one entry vs "18000" in
       another) is a silent fact error, not a per-entry choice — GE
       buy limits are item-global.
  3. Global id uniqueness across the whole codex tree.

Exit codes: 0 = clean (warnings ok), 1 = validation errors.

Usage: python3 tools/validate.py [--stale-days 30] [--selftest]
      --selftest: run the supply-consistency regression fixtures only
"""
import datetime
import json
import re
import sys
from pathlib import Path

import jsonschema
import yaml

ROOT = Path(__file__).resolve().parent.parent
SCHEMA = json.loads((ROOT / "schemas" / "entry.schema.json").read_text())
CODEX = ROOT / "codex"
STALE_DAYS = 30


def load_entries():
    out = []
    for p in CODEX.rglob("*.yaml"):
        if p.name.startswith("_"):  # dataset files (e.g. _f2p-alch-catalog.yaml)
            continue
        out.append(p)
    return sorted(out)


def supply_limit_conflicts(rows):
    """Cross-entry consistency for duplicate supply facts.

    rows: iterable of (rel, data). The same (item, source) appearing in
    more than one entry must agree on ge_limit — GE buy limits are a
    property of the item, so a divergence is a silent fact error.
    Returns a list of error strings.
    """
    facts = {}
    for rel, data in rows:
        eco = data.get("economy") or {}
        for sup in eco.get("supplies", []):
            lim = sup.get("ge_limit")
            if lim is None:
                continue
            key = (sup.get("item"), sup.get("source"))
            facts.setdefault(key, {}).setdefault(lim, set()).add(rel)
    errors = []
    for (item, source), by_lim in sorted(facts.items()):
        if len(by_lim) > 1:
            detail = "; ".join(
                f"limit {lim} in {', '.join(sorted(rs))}"
                for lim, rs in sorted(by_lim.items()))
            errors.append(
                f"conflicting ge_limit for supply '{item}' (source {source}): {detail}")
    return errors


def run_selftest(verbose=False):
    """Regression fixtures for the supply-consistency gate; error strings."""
    fixtures = [
        # name, rows, expect_error
        ("identical (item, source) with diverging ge_limit (18000 vs 12500)",
         [("e1.yaml", {"economy": {"supplies": [
              {"item": "nature rune", "source": "ge", "ge_limit": 18000}]}}),
          ("e2.yaml", {"economy": {"supplies": [
              {"item": "nature rune", "source": "ge", "ge_limit": 12500}]}})], True),
        ("identical (item, source) with agreeing ge_limit (18000 both)",
         [("e1.yaml", {"economy": {"supplies": [
              {"item": "nature rune", "source": "ge", "ge_limit": 18000}]}}),
          ("e2.yaml", {"economy": {"supplies": [
              {"item": "nature rune", "source": "ge", "ge_limit": 18000}]}})], False),
        ("no supplies / missing ge_limit are not gated",
         [("e1.yaml", {"economy": {}}),
          ("e2.yaml", {"economy": {"supplies": [
              {"item": "gold necklace", "source": "ge"}]}})], False),
    ]
    errors = []
    for name, rows, expect_error in fixtures:
        got = bool(supply_limit_conflicts(rows))
        passed = got == expect_error
        if verbose:
            print(f"SELFTEST {'PASS' if passed else 'FAIL'}  {name}")
        if not passed:
            errors.append(
                f"selftest: '{name}' expected "
                f"{'an error' if expect_error else 'no error'} but got "
                f"{'an error' if got else 'no error'}")
    return errors


def main():
    global STALE_DAYS
    if "--stale-days" in sys.argv:
        STALE_DAYS = int(sys.argv[sys.argv.index("--stale-days") + 1])

    errors, warnings = [], []
    if "--selftest" in sys.argv:
        errors += run_selftest(verbose=True)
        print(f"RESULT: selftest, {len(errors)} errors, 0 warnings")
        return 1 if errors else 0
    entries = load_entries()
    if not entries:
        print("ERROR: no codex entries found under codex/")
        return 1

    ids = {}
    today = datetime.date.today()
    rows = []

    for path in entries:
        rel = str(path.relative_to(ROOT))
        try:
            data = yaml.safe_load(path.read_text())
        except yaml.YAMLError as e:
            errors.append(f"{rel}: YAML parse error: {e}")
            continue
        rows.append((rel, data))

        # 1. schema
        v = jsonschema.Draft7Validator(SCHEMA)
        for err in sorted(v.iter_errors(data), key=lambda e: list(e.path)):
            loc = "/".join(str(p) for p in err.path) or "(root)"
            errors.append(f"{rel} [{loc}]: {err.message}")
        if errors and errors[-1].startswith(rel):
            # schema already broke; cross-checks on a broken doc are noise
            continue

        eid = data.get("id", rel)
        if eid in ids:
            errors.append(f"{rel}: duplicate entry id '{eid}' (also in {ids[eid]})")
        ids[eid] = rel

        # 2. state machine consistency
        sm = data.get("state_machine", {})
        states = sm.get("states", {})
        declared = set(states)
        terminals = set(sm.get("terminal", []))
        for sname, sdef in states.items():
            if sname not in terminals and not sdef.get("next"):
                errors.append(f"{rel}: non-terminal state '{sname}' has no 'next'")
            for nxt in sdef.get("next", []):
                if nxt not in declared:
                    errors.append(f"{rel}: state '{sname}' next->'{nxt}' not declared")
        if sm.get("initial") not in declared:
            errors.append(f"{rel}: initial state '{sm.get('initial')}' not declared")
        for t in sm.get("transitions", []):
            if t["from"] not in declared:
                errors.append(f"{rel}: transition from '{t['from']}' not declared")
            if t["to"] not in declared:
                errors.append(f"{rel}: transition to '{t['to']}' not declared")
        for term in sm.get("terminal", []):
            if term not in declared:
                errors.append(f"{rel}: terminal '{term}' not declared")

        # action id/step uniqueness
        a_ids = [a["id"] for a in data["actions"]]
        a_steps = [a["step"] for a in data["actions"]]
        if len(a_ids) != len(set(a_ids)):
            errors.append(f"{rel}: duplicate action ids")
        if len(a_steps) != len(set(a_steps)):
            errors.append(f"{rel}: duplicate action step names")

        # 3. staleness / research TODOs
        if data.get("status") == "verified":
            try:
                vdate = datetime.date.fromisoformat(data["verified"])
                age = (today - vdate).days
                if age > STALE_DAYS:
                    warnings.append(
                        f"{rel}: status=verified but facts are {age}d old "
                        f"(> {STALE_DAYS}d) — re-verify or drop to status:stale")
            except ValueError:
                pass
        for line in data.get("best_practice", {}).get("equipment", []) + \
                    data.get("best_practice", {}).get("techniques", []):
            if str(line.get("source", "")).startswith("researched"):
                warnings.append(
                    f"{rel}: best_practice '{line.get('item') or line.get('name')}' "
                    f"carries a 'researched' source — citation TODO, file follow-up")

    # 2b. cross-entry supply-fact consistency (GE buy limits are item-global)
    errors += supply_limit_conflicts(rows)

    # report
    for w in warnings:
        print(f"WARN  {w}")
    for e in errors:
        print(f"ERROR {e}")
    print(f"RESULT: {len(entries)} entries, {len(errors)} errors, {len(warnings)} warnings")
    return 1 if errors else 0


if __name__ == "__main__":
    sys.exit(main())