#!/usr/bin/env python3
"""Fail if decomposition docs regress hybrid vocabulary (gig vs non-combat skill).

Catches phrases like "one combat skill" or bare "combat skill" that imply a combat
SkillDef. Allows "non-combat skill(s)" and "anti-combat …" when the hyphen prefix
is immediately before ``combat``.

Run in CI (PR gate) and locally after editing ``docs/decomposition/**``.
"""

from __future__ import annotations

import re
import sys
from pathlib import Path

REPO_ROOT = Path(__file__).resolve().parent.parent
DECOMP_ROOT = REPO_ROOT / "docs/decomposition"

# Standalone phrases that almost always indicate a doc bug vs game-design hybrid model.
LITERAL_BANS = [
    "one combat skill",
    "one combat skills",
]

# Match "combat skill" / "combat skills" unless prefixed by "non-" or "anti-" (hyphenated).
COMBAT_SKILL = re.compile(r"\bcombat skills?\b", re.IGNORECASE)


def line_has_bad_combat_skill(line: str) -> bool:
    for m in COMBAT_SKILL.finditer(line):
        start = m.start()
        if start >= 4 and line[start - 4 : start].lower() == "non-":
            continue
        if start >= 5 and line[start - 5 : start].lower() == "anti-":
            continue
        return True
    return False


def check_file(path: Path) -> list[str]:
    errors: list[str] = []
    text = path.read_text(encoding="utf-8")
    lower = text.lower()
    for banned in LITERAL_BANS:
        if banned in lower:
            errors.append(f"{path.relative_to(REPO_ROOT)}: contains forbidden phrase {banned!r}")

    for i, line in enumerate(text.splitlines(), start=1):
        if line_has_bad_combat_skill(line):
            errors.append(f"{path.relative_to(REPO_ROOT)}:{i}: suspicious 'combat skill' (use gig or 'non-combat skill'): {line.strip()[:200]}")
    return errors


def main() -> int:
    if not DECOMP_ROOT.is_dir():
        print(f"error: missing {DECOMP_ROOT}", file=sys.stderr)
        return 1

    all_errors: list[str] = []
    for path in sorted(DECOMP_ROOT.rglob("*.md")):
        all_errors.extend(check_file(path))

    if all_errors:
        for msg in all_errors:
            print(msg, file=sys.stderr)
        print(f"decomposition language check failed ({len(all_errors)} issue(s))", file=sys.stderr)
        return 1

    print("decomposition language OK: hybrid vocabulary (no stray combat SkillDef phrasing)")
    return 0


if __name__ == "__main__":
    raise SystemExit(main())