139 lines
5.0 KiB
Python
139 lines
5.0 KiB
Python
#!/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)
|
|
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]
|
|
"""
|
|
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 main():
|
|
global STALE_DAYS
|
|
if "--stale-days" in sys.argv:
|
|
STALE_DAYS = int(sys.argv[sys.argv.index("--stale-days") + 1])
|
|
|
|
errors, warnings = [], []
|
|
entries = load_entries()
|
|
if not entries:
|
|
print("ERROR: no codex entries found under codex/")
|
|
return 1
|
|
|
|
ids = {}
|
|
today = datetime.date.today()
|
|
|
|
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
|
|
|
|
# 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")
|
|
|
|
# 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())
|