#!/usr/bin/env python3
"""
kb-health — объективная метрика качества KB (karpathy-style val_bpb).

Считаем штрафы. Меньше = лучше.

Категории:
  - broken_wikilinks    [[foo]] не ведёт никуда
  - broken_paths        [text](./foo.md) — путь не существует
  - missing_frontmatter .md без `---\\n...\\n---`
  - orphan_files        нет входящих wikilinks, не в системных папках
  - undated_todos       "- [ ] ..." без YYYY-MM-DD в строке
  - duplicate_basenames два файла с одинаковым basename в разных папках

Веса (итоговый score = сумма):
  broken_wikilinks * 10
  broken_paths     * 10
  missing_frontmatter * 3
  orphan_files     * 2
  undated_todos    * 1
  duplicate_basenames * 5

Вывод:
  audit/YYYY-MM-DD-health.md — человекочитаемый отчёт
  audit/health-latest.json   — JSON для kb-agent-loop.sh (сравнение score между прогонами)
"""

import json
import re
import sys
from collections import defaultdict
from datetime import date
from pathlib import Path

VAULT = Path(__file__).resolve().parent.parent
OUT_DIR = VAULT / "audit"

# папки/файлы которые сканируем
INCLUDE_DIRS = ["decisions", "notes", "projects", "snippets", "daily",
                "claude-memory", "templates", "scripts", "audit"]
INCLUDE_ROOT_FILES = ["CLAUDE.md", "README.md"]

# папки исключаем полностью
EXCLUDE_DIRS = {".git", ".obsidian", ".claude"}

# файлы где orphan-статус норма (системные, служебные)
ORPHAN_OK_PATTERNS = [
    re.compile(r"^daily/.*"),           # daily-notes редко бэклинкуются
    re.compile(r"^audit/.*"),           # audit-отчёты
    re.compile(r"^templates/.*"),       # шаблоны
    re.compile(r"^notes/claude/.*"),    # автосейвы сессий Claude
    re.compile(r"^scripts/.*"),         # скрипты
    re.compile(r"^CLAUDE\.md$"),
    re.compile(r"^README\.md$"),
]

WEIGHTS = {
    "broken_wikilinks": 10,
    "broken_paths": 10,
    "missing_frontmatter": 3,
    "orphan_files": 2,
    "undated_todos": 1,
    "duplicate_basenames": 5,
}


def collect_md_files():
    """Возвращает list[Path] — все .md файлы в scope."""
    files = []
    for name in INCLUDE_ROOT_FILES:
        p = VAULT / name
        if p.is_file():
            files.append(p)
    for dname in INCLUDE_DIRS:
        root = VAULT / dname
        if not root.exists():
            continue
        for p in root.rglob("*.md"):
            if any(part in EXCLUDE_DIRS for part in p.parts):
                continue
            files.append(p)
    return files


def rel(p: Path) -> str:
    return str(p.relative_to(VAULT))


def has_frontmatter(text: str) -> bool:
    """Frontmatter = `---\\n...\\n---` в самом начале."""
    if not text.startswith("---\n"):
        return False
    return bool(re.match(r"---\n(.*?\n)*?---\n", text))


def strip_code(text: str) -> str:
    """Убираем inline `...` и fenced ```...``` — чтобы regex не цеплял примеры кода."""
    text = re.sub(r"```[\s\S]*?```", "", text)
    text = re.sub(r"`[^`\n]*`", "", text)
    return text


def extract_wikilinks(text: str):
    """Возвращает list[str] — таргеты без alias/heading. Игнорим код-блоки."""
    out = []
    for m in re.finditer(r"\[\[([^\]]+)\]\]", strip_code(text)):
        target = m.group(1).split("|")[0].split("#")[0].strip()
        if target:
            out.append(target)
    return out


def extract_md_paths(text: str):
    """Относительные пути типа [text](./foo.md) или (../foo/bar.md)."""
    out = []
    for m in re.finditer(r"\]\(([^)]+?\.md)(?:#[^)]*)?\)", strip_code(text)):
        path = m.group(1)
        if path.startswith("http"):
            continue
        out.append(path)
    return out


def count_undated_todos(text: str) -> int:
    """'- [ ] ...' без упоминания даты YYYY-MM-DD в той же строке."""
    count = 0
    for line in text.splitlines():
        if re.match(r"^\s*-\s*\[\s*\]\s+", line):
            if not re.search(r"\d{4}-\d{2}-\d{2}", line):
                count += 1
    return count


def resolve_wikilink(target: str, all_basenames: dict, from_file: Path):
    """Ищем файл по wikilink-target. Возвращает Path или None.
    Стратегии:
      1. '../foo/bar' — relative от файла-источника
      2. 'folder/bar' — от корня vault
      3. 'bar' — по basename в любой папке (Obsidian flat namespace)
    """
    target_clean = target.replace(".md", "")
    # relative с ../ или ./
    if target_clean.startswith((".", "/")):
        try:
            resolved = (from_file.parent / target_clean).resolve()
            # добавляем .md если нет
            candidates = [resolved.with_suffix(".md"), resolved]
            for c in candidates:
                if c.is_file() and str(c).endswith(".md"):
                    return c
        except Exception:
            pass
    # полный путь от корня vault
    guess = VAULT / f"{target_clean}.md"
    if guess.is_file():
        return guess
    # только basename — flat namespace
    basename = target_clean.rsplit("/", 1)[-1]
    if basename in all_basenames:
        return all_basenames[basename][0]
    return None


def resolve_md_path(path: str, from_file: Path):
    """Относительный путь из файла from_file."""
    try:
        resolved = (from_file.parent / path).resolve()
        if resolved.is_file():
            return resolved
    except Exception:
        pass
    return None


def is_orphan_ok(relpath: str) -> bool:
    return any(pat.match(relpath) for pat in ORPHAN_OK_PATTERNS)


def main():
    today = date.today().isoformat()
    OUT_DIR.mkdir(parents=True, exist_ok=True)

    files = collect_md_files()
    if not files:
        print("no md files found", file=sys.stderr)
        sys.exit(1)

    # basename-index (для wikilink-резолва)
    basenames = defaultdict(list)
    for p in files:
        key = p.stem
        basenames[key].append(p)

    # метрики
    broken_wl = []           # (file, target)
    broken_paths = []        # (file, path)
    missing_fm = []          # file
    undated_todos_per_file = {}  # file: count
    duplicate_basenames = [] # (basename, files)
    incoming_links = defaultdict(set)  # file → set of files linking TO it

    # CLAUDE.md, README.md, шаблоны — служебные, frontmatter не требуем
    fm_exempt = {"CLAUDE.md", "README.md", ".cursorrules"}

    for f in files:
        text = f.read_text(errors="ignore")
        rel_f = rel(f)

        if rel_f not in fm_exempt and f.name != "README.md" and not has_frontmatter(text):
            missing_fm.append(rel_f)

        for target in extract_wikilinks(text):
            resolved = resolve_wikilink(target, basenames, f)
            if resolved is None:
                broken_wl.append((rel_f, target))
            else:
                incoming_links[resolved].add(f)

        for path in extract_md_paths(text):
            resolved = resolve_md_path(path, f)
            if resolved is None:
                broken_paths.append((rel_f, path))

        n_todos = count_undated_todos(text)
        if n_todos > 0:
            undated_todos_per_file[rel_f] = n_todos

    # orphan = нет incoming links, не в OK-zones
    orphans = []
    for f in files:
        if f not in incoming_links:
            rel_f = rel(f)
            if not is_orphan_ok(rel_f):
                orphans.append(rel_f)

    # duplicate basenames
    for name, paths in basenames.items():
        if len(paths) > 1:
            duplicate_basenames.append((name, [rel(p) for p in paths]))

    counts = {
        "broken_wikilinks": len(broken_wl),
        "broken_paths": len(broken_paths),
        "missing_frontmatter": len(missing_fm),
        "orphan_files": len(orphans),
        "undated_todos": sum(undated_todos_per_file.values()),
        "duplicate_basenames": len(duplicate_basenames),
    }
    score = sum(counts[k] * WEIGHTS[k] for k in counts)

    # JSON
    latest = {
        "date": today,
        "score": score,
        "counts": counts,
        "weights": WEIGHTS,
        "files_scanned": len(files),
    }
    (OUT_DIR / "health-latest.json").write_text(json.dumps(latest, indent=2, ensure_ascii=False))

    # Markdown report
    lines = [
        "---",
        f"date: {today}",
        "type: audit",
        "source: kb-health.py",
        f"score: {score}",
        "tags: [audit, health, metric]",
        "---",
        "",
        f"# KB health — {today}",
        "",
        f"**Score (меньше = лучше): `{score}`**",
        f"Проверено файлов: {len(files)}",
        "",
        "## Разбивка",
        "",
        "| Категория | Кол-во | Вес | Штраф |",
        "|---|---:|---:|---:|",
    ]
    for k in WEIGHTS:
        c = counts[k]
        w = WEIGHTS[k]
        lines.append(f"| {k} | {c} | {w} | {c * w} |")
    lines += ["| **ИТОГО** | | | **" + str(score) + "** |", ""]

    if broken_wl:
        lines += ["## Битые wikilinks", ""]
        lines += ["| Откуда | `[[таргет]]` |", "|---|---|"]
        for fr, tg in broken_wl[:50]:
            lines.append(f"| `{fr}` | `[[{tg}]]` |")
        if len(broken_wl) > 50:
            lines.append(f"| ... | +{len(broken_wl)-50} ещё |")
        lines.append("")

    if broken_paths:
        lines += ["## Битые relative-пути", ""]
        lines += ["| Откуда | Путь |", "|---|---|"]
        for fr, pt in broken_paths[:50]:
            lines.append(f"| `{fr}` | `{pt}` |")
        if len(broken_paths) > 50:
            lines.append(f"| ... | +{len(broken_paths)-50} ещё |")
        lines.append("")

    if missing_fm:
        lines += [f"## Без frontmatter ({len(missing_fm)})", ""]
        for f in missing_fm[:30]:
            lines.append(f"- `{f}`")
        if len(missing_fm) > 30:
            lines.append(f"- ... +{len(missing_fm)-30} ещё")
        lines.append("")

    if orphans:
        lines += [f"## Orphan — без бэклинков ({len(orphans)})", "",
                  "_Эти файлы никто не упоминает через `[[..]]`. Кандидаты на удаление или добавление ссылок._", ""]
        for f in orphans[:30]:
            lines.append(f"- `{f}`")
        if len(orphans) > 30:
            lines.append(f"- ... +{len(orphans)-30} ещё")
        lines.append("")

    if undated_todos_per_file:
        lines += [f"## TODO без даты ({sum(undated_todos_per_file.values())} шт в {len(undated_todos_per_file)} файлах)", ""]
        for f, n in sorted(undated_todos_per_file.items(), key=lambda x: -x[1])[:20]:
            lines.append(f"- `{f}` — {n} шт")
        lines.append("")

    if duplicate_basenames:
        lines += [f"## Дубликаты имён ({len(duplicate_basenames)})", ""]
        for name, paths in duplicate_basenames[:20]:
            lines.append(f"- `{name}.md`:")
            for p in paths:
                lines.append(f"  - `{p}`")
        lines.append("")

    lines += [
        "---",
        "*Генерируется `scripts/kb-health.py`. JSON-версия в `audit/health-latest.json` для agent-loop.*",
    ]

    out = OUT_DIR / f"{today}-health.md"
    out.write_text("\n".join(lines))
    print(f"health report: {out}")
    print(f"  score: {score}")
    for k, v in counts.items():
        print(f"    {k}: {v}")


if __name__ == "__main__":
    main()