#!/usr/bin/env bash
# kb-lint.sh — OKF v0.1 conformance + link-integrity lint for a knowledge bundle.
# Usage: scripts/kb-lint.sh <kb-dir>   (default: omp-docs)
# Exits 0 when the KB is conformant; prints one line per violation otherwise.
set -uo pipefail
KB="$(cd "${1:-omp-docs}" 2>/dev/null && pwd)" || { echo "kb-lint: no such dir: ${1:-omp-docs}" >&2; exit 2; }

python3 - "$KB" <<'PY'
import re, sys
from pathlib import Path
kb = Path(sys.argv[1])
violations = []

for p in sorted(kb.rglob("*.md")):
    rel = p.relative_to(kb)
    text = p.read_text(errors="replace")
    if p.name == "index.md":
        # OKF rule: index files are directory listings and carry NO frontmatter.
        if text.startswith("---"):
            violations.append(f"{rel}: index.md must not have frontmatter (OKF spec)")
        continue
    if not text.startswith("---"):
        violations.append(f"{rel}: missing frontmatter")
        continue
    end = text.find("\n---", 3)
    fm = text[3:end] if end != -1 else ""
    if not re.search(r"^type:", fm, re.M):
        violations.append(f"{rel}: frontmatter lacks required 'type:'")

# link integrity: fenced code blocks hold example paths, not live links — strip first.
# Vendored spec is exempt: its example paths are illustrations, not live links.
for p in sorted(kb.rglob("*.md")):
    if str(p.relative_to(kb)) == "references/okf-spec.md":
        continue
    text = re.sub(r"^```[^\n]*$^```[^\n]*$", "", p.read_text(errors="replace"), flags=re.M)
    rel = p.relative_to(kb)
    for m in re.finditer(r"\]\((?!https?:|#)([^)#\s]+\.md)", text):
        target = (p.parent / m.group(1)).resolve() if not m.group(1).startswith("/") else (kb / m.group(1).lstrip("/"))
        if not Path(target).is_file():
            violations.append(f"{rel}: broken relative link -> {m.group(1)}")
    for m in re.finditer(r"\[\[([^\]|#]+)", text):
        # wikilinks resolve by filename anywhere in the KB (Obsidian semantics)
        name = m.group(1).strip().rsplit("/", 1)[-1]
        if not list(kb.rglob(name + ".md")):
            violations.append(f"{rel}: broken wikilink -> [[{m.group(1).strip()}]]")

for v in violations:
    print(v)
print(f"kb-lint: {len(violations)} violation(s)")
sys.exit(1 if violations else 0)
PY