#!/usr/bin/env python3
"""
Wiki ↔ Raw 三向同步工具

功能：
  - 检测 raw/ 下文件变化（新增/修改/删除）
  - 维护 manifest.json 状态映射
  - 检测 orphan entity/concept（仅报告，不删除）

用法：
    python tools/sync.py --check        预览变化（不执行）
    python tools/sync.py --sync         执行同步（更新 manifest）
    python tools/sync.py --pending      显示待处理文件列表
    python tools/sync.py --json         JSON 行输出（供程序消费）
    python tools/sync.py --rebuild      从 manifest 重建 wiki/index（兜底）

manifest.json 格式：
{
  "version": 1,
  "updated_at": "ISO timestamp",
  "files": {
    "relative/path/to/file.md": {
      "hash": "sha256",
      "modified": "ISO timestamp",
      "slug": "wiki-source-slug",
      "source_path": "wiki/sources/slug.md",
      "ingested": true
    }
  }
}
"""

import json
import hashlib
import argparse
from pathlib import Path
from datetime import datetime, timezone


REPO_ROOT = Path(__file__).parent.parent.resolve()
WIKI_DIR = REPO_ROOT / "wiki"
MANIFEST_FILE = Path(__file__).parent / "manifest.json"


# ─── 工具函数 ───────────────────────────────────────────────

def green(text):
    return f"\033[92m{text}\033[0m"

def yellow(text):
    return f"\033[93m{text}\033[0m"

def red(text):
    return f"\033[91m{text}\033[0m"

def dim(text):
    return f"\033[2m{text}\033[0m"

def bold(text):
    return f"\033[1m{text}\033[0m"


def log(msg, style="normal"):
    prefixes = {
        "normal":   "  ",
        "info":     "  ℹ ",
        "success":  "  ✓ ",
        "warn":     "  ⚠ ",
        "error":    "  ✗ ",
        "section":  "\n── ",
    }
    print(f"{prefixes.get(style, '  ')}{msg}")


def sha256_file(path: Path) -> str:
    h = hashlib.sha256()
    h.update(path.read_bytes())
    return h.hexdigest()[:16]


def iso_now():
    return datetime.now(timezone.utc).isoformat()


def load_manifest() -> dict:
    if MANIFEST_FILE.exists():
        try:
            return json.loads(MANIFEST_FILE.read_text(encoding="utf-8"))
        except (json.JSONDecodeError, IOError):
            pass
    return {"version": 1, "updated_at": iso_now(), "files": {}}


def save_manifest(manifest: dict):
    manifest["updated_at"] = iso_now()
    MANIFEST_FILE.write_text(json.dumps(manifest, ensure_ascii=False, indent=2), encoding="utf-8")


def scan_raw() -> dict[str, dict]:
    """返回 {relative_path: {hash, modified, size}}"""
    raw_dir = REPO_ROOT / "raw"
    result = {}
    if not raw_dir.exists():
        return result
    for p in raw_dir.rglob("*.md"):
        if p.is_file() and not p.name.startswith("."):
            rel = str(p.relative_to(REPO_ROOT))
            stat = p.stat()
            result[rel] = {
                "hash": sha256_file(p),
                "modified": datetime.fromtimestamp(stat.st_mtime, tz=timezone.utc).isoformat(),
                "size": stat.st_size,
                "abs_path": str(p),
            }
    return result


def build_slug_from_path(rel_path: str) -> str:
    """从相对路径生成 slug（尽量保留中文，kebab-case）"""
    name = Path(rel_path).stem
    name = name.replace(" ", "-").replace("/", "-").replace("\\", "-")
    name = "".join(c if c.isalnum() or c in ("-", "_", "·") else "-" for c in name)
    name = name.strip("-")
    return name or "untitled"


def find_orphan_entity_concept(manifest: dict) -> tuple[list, list]:
    """检测未被任何 source page 引用的 entity 和 concept"""
    import re
    wikilink_pattern = re.compile(r"\[\[([^\]]+)\]\]")

    sources_dir = WIKI_DIR / "sources"
    referenced_entities = set()
    referenced_concepts = set()

    if sources_dir.exists():
        for src in sources_dir.glob("*.md"):
            content = src.read_text(encoding="utf-8")
            for link in wikilink_pattern.findall(content):
                name = link.strip()
                if name.startswith("entities/"):
                    referenced_entities.add(Path(name).stem)
                elif name.startswith("concepts/"):
                    referenced_concepts.add(Path(name).stem)
                elif "/" not in name:
                    referenced_entities.add(name)
                    referenced_concepts.add(name)

    orphan_entities = []
    entities_dir = WIKI_DIR / "entities"
    if entities_dir.exists():
        for f in entities_dir.glob("*.md"):
            if f.stem not in referenced_entities:
                orphan_entities.append(f.name)

    orphan_concepts = []
    concepts_dir = WIKI_DIR / "concepts"
    if concepts_dir.exists():
        for f in concepts_dir.glob("*.md"):
            if f.stem not in referenced_concepts:
                orphan_concepts.append(f.name)

    return orphan_entities, orphan_concepts


# ─── 核心同步逻辑 ───────────────────────────────────────────────

def check_changes(manifest: dict, raw_files: dict) -> dict:
    """对比 manifest 和实际 raw 文件，返回变化"""
    changes = {"new": [], "updated": [], "deleted": [], "unchanged": []}
    manifest_files = manifest.get("files", {})

    for rel_path, info in raw_files.items():
        if rel_path not in manifest_files:
            changes["new"].append({"rel_path": rel_path, **info})
        elif info["hash"] != manifest_files[rel_path]["hash"]:
            changes["updated"].append({
                "rel_path": rel_path,
                "old_hash": manifest_files[rel_path]["hash"],
                **info,
            })
        else:
            changes["unchanged"].append(rel_path)

    for rel_path in manifest_files:
        abs_path = REPO_ROOT / rel_path
        if not abs_path.exists():
            changes["deleted"].append({
                "rel_path": rel_path,
                "slug": manifest_files[rel_path].get("slug", build_slug_from_path(rel_path)),
                "source_path": manifest_files[rel_path].get("source_path"),
            })

    return changes


def run_sync(dry_run: bool = False, verbose: bool = False, json_mode: bool = False):
    print(f"\n{bold('=== Wiki Sync')}\n", end="")
    print(f"  Date:    {datetime.now().strftime('%Y-%m-%d %H:%M')}\n")
    print(f"  Raw:     {REPO_ROOT / 'raw'}\n")
    print(f"  Wiki:    {WIKI_DIR}\n")
    print(f"  Mode:    {'DRY-RUN (preview only)' if dry_run else 'LIVE SYNC'}")

    manifest = load_manifest()
    log("manifest.json loaded", "info")

    raw_files = scan_raw()
    log(f"raw/ scan: {len(raw_files)} .md files found", "info")

    changes = check_changes(manifest, raw_files)
    total_changes = len(changes["new"]) + len(changes["updated"]) + len(changes["deleted"])

    if total_changes == 0:
        log("No changes detected — wiki is up to date.", "success")
        return

    if not json_mode:
        print(f"\n{bold('--- Changes ---')}")
        print(f"  {green('+')} New:     {len(changes['new'])}")
        print(f"  {yellow('~')} Updated: {len(changes['updated'])}")
        print(f"  {red('-')} Deleted: {len(changes['deleted'])}")

    if verbose or not dry_run:
        if changes["new"]:
            if not json_mode:
                print(f"\n  {bold('New Files:')}")
            for f in changes["new"]:
                slug = build_slug_from_path(f["rel_path"])
                if json_mode:
                    print(json.dumps({"event": "new_detected", "rel_path": f["rel_path"], "slug": slug}))
                else:
                    log(f"{green('[+')} {f['rel_path']}", "normal")

        if changes["updated"]:
            if not json_mode:
                print(f"\n  {bold('Updated Files:')}")
            for f in changes["updated"]:
                slug = manifest["files"].get(f["rel_path"], {}).get("slug") or build_slug_from_path(f["rel_path"])
                if json_mode:
                    print(json.dumps({"event": "updated_detected", "rel_path": f["rel_path"], "slug": slug}))
                else:
                    log(f"{yellow('[~]')} {f['rel_path']} (hash changed)", "normal")

        if changes["deleted"]:
            if not json_mode:
                print(f"\n  {bold('Deleted Files:')}")
            for f in changes["deleted"]:
                if json_mode:
                    print(json.dumps({"event": "deleted_detected", "rel_path": f["rel_path"]}))
                else:
                    log(f"{red('[-]')} {f['rel_path']}", "normal")

    if dry_run:
        log("\nDry-run complete. Run with --sync to apply.", "warn")
        return

    # ─── Apply Sync ───
    if not json_mode:
        print(f"\n{bold('--- Applying Sync ---')}")

    updated_manifest = manifest.copy()
    updated_manifest["files"] = manifest.get("files", {}).copy()

    pending_files = []

    # ① 新增 → 加入 manifest
    for f in changes["new"]:
        rel_path = f["rel_path"]
        slug = build_slug_from_path(rel_path)

        if json_mode:
            print(json.dumps({"event": "pending", "rel_path": rel_path, "slug": slug, "action": "new"}))

        pending_files.append({"rel_path": rel_path, "abs_path": f["abs_path"], "slug": slug, "action": "new"})

        updated_manifest["files"][rel_path] = {
            "hash": f["hash"],
            "modified": f.get("modified"),
            "slug": slug,
            "source_path": f"wiki/sources/{slug}.md",
            "ingested": False,
            "ingested_at": None,
        }

    # ② 修改 → 更新 manifest
    for f in changes["updated"]:
        rel_path = f["rel_path"]
        old_entry = manifest["files"].get(rel_path, {})
        slug = old_entry.get("slug") or build_slug_from_path(rel_path)

        if json_mode:
            print(json.dumps({"event": "pending", "rel_path": rel_path, "slug": slug, "action": "updated"}))

        pending_files.append({"rel_path": rel_path, "abs_path": f["abs_path"], "slug": slug, "action": "updated"})

        updated_manifest["files"][rel_path] = {
            **old_entry,
            "hash": f["hash"],
            "modified": f.get("modified"),
            "ingested": False,
            "ingested_at": None,
        }

    # ③ 删除 → 保留 wiki 内容，从 manifest 移除
    deleted_files = []
    for f in changes["deleted"]:
        rel_path = f["rel_path"]
        source_path = f.get("source_path")
        if not json_mode:
            log(f"Deleted: {rel_path}", "warn")
            if source_path:
                sp = WIKI_DIR / source_path
                log(f"      Wiki source kept: {sp}", "warn")
        if rel_path in updated_manifest["files"]:
            del updated_manifest["files"][rel_path]
        deleted_files.append(rel_path)

    # 保存 manifest
    save_manifest(updated_manifest)
    log(f"\nmanifest.json updated ({len(updated_manifest['files'])} entries)", "success")

    if json_mode:
        print(json.dumps({
            "event": "sync_complete",
            "summary": {
                "pending": len(pending_files),
                "deleted": len(deleted_files),
                "manifest_entries": len(updated_manifest["files"]),
            },
            "pending_files": pending_files,
            "deleted_files": deleted_files,
        }))

    # Orphan detection
    orphan_entities, orphan_concepts = find_orphan_entity_concept(updated_manifest)
    if not json_mode:
        if orphan_entities or orphan_concepts:
            print(f"\n{bold('--- Orphan Report (kept as requested) ---')}")
            if orphan_entities:
                print(f"  {bold('Orphan Entities')} ({len(orphan_entities)}):")
                for e in sorted(orphan_entities):
                    print(f"    {dim('?')} {e}")
            if orphan_concepts:
                print(f"  {bold('Orphan Concepts')} ({len(orphan_concepts)}):")
                for c in sorted(orphan_concepts):
                    print(f"    {dim('?')} {c}")
            log("\nOrphan pages are kept (not deleted per user request).", "info")
        else:
            log("No orphan entity/concept detected.", "success")

    print(f"\n{bold('Done.')}")
    print(f"\n  Pending files for ingestion: {len(pending_files)}")


def run_check():
    """只预览变化，不执行（输出为标准 Markdown）"""
    manifest = load_manifest()
    raw_files = scan_raw()
    changes = check_changes(manifest, raw_files)
    total = len(changes["new"]) + len(changes["updated"]) + len(changes["deleted"])

    # Markdown header and summary
    print("# Wiki Sync Check\n")
    print(f"- Raw files: {len(raw_files)}")
    print(f"- Manifest entries: {len(manifest.get('files', {}))}")
    print(f"- New: {len(changes['new'])}")
    print(f"- Updated: {len(changes['updated'])}")
    print(f"- Deleted: {len(changes['deleted'])}\n")

    if total > 0:
        if changes["new"]:
            print("## New Files")
            for f in changes["new"]:
                print(f"- {f['rel_path']}")
            print()
        if changes["updated"]:
            print("## Updated Files")
            for f in changes["updated"]:
                print(f"- {f['rel_path']} (was {f['old_hash']}, now {f['hash']})")
            print()
        if changes["deleted"]:
            print("## Deleted Files")
            for f in changes["deleted"]:
                print(f"- {f['rel_path']}")
            print()
    else:
        print("No changes — wiki is in sync.\n")


def run_rebuild():
    """从 manifest 重建 wiki/index.md（兜底方案）"""
    manifest = load_manifest()
    print(f"\n{bold('=== Wiki Rebuild from Manifest')}\n")
    print(f"  Manifest entries: {len(manifest.get('files', {}))}")
    print(f"  Rebuilding index.md ...\n")

    index_lines = [
        "# Wiki Index\n",
        "\n## Overview\n",
        "- [Overview](overview.md) — living synthesis\n",
        "\n## Sources\n",
    ]

    files = manifest.get("files", {})
    sorted_files = sorted(files.items(), key=lambda x: x[1].get("modified", ""), reverse=True)

    for rel_path, info in sorted_files:
        slug = info.get("slug", build_slug_from_path(rel_path))
        source_md_path = WIKI_DIR / "sources" / f"{slug}.md"
        if source_md_path.exists():
            title = source_md_path.read_text(encoding="utf-8").split("\n")[0].lstrip("# ").strip()
            index_lines.append(f"- [{title}](sources/{slug}.md)\n")
        else:
            index_lines.append(f"- [{slug}](sources/{slug}.md) — (source missing)\n")

    index_lines.append("\n## Entities\n\n## Concepts\n\n## Syntheses\n")

    index_file = WIKI_DIR / "index.md"
    index_file.write_text("".join(index_lines), encoding="utf-8")
    print(f"  {green('✓')} index.md rebuilt with {len(sorted_files)} sources")

    orphan_entities, orphan_concepts = find_orphan_entity_concept(manifest)
    if orphan_entities:
        print(f"  {dim('?')} Orphan entities: {len(orphan_entities)}")
    if orphan_concepts:
        print(f"  {dim('?')} Orphan concepts: {len(orphan_concepts)}")

    print(f"\nDone.")


# ─── CLI 入口 ───────────────────────────────────────────────

if __name__ == "__main__":
    parser = argparse.ArgumentParser(
        description="Wiki ↔ Raw 三向同步工具",
        formatter_class=argparse.RawDescriptionHelpFormatter,
    )
    parser.add_argument(
        "--check",
        action="store_true",
        help="预览变化，不执行同步",
    )
    parser.add_argument(
        "--sync",
        action="store_true",
        help="执行完整同步（新增/修改/删除 + orphan 检测）",
    )
    parser.add_argument(
        "--rebuild",
        action="store_true",
        help="从 manifest 重建 wiki/index.md（兜底方案）",
    )
    parser.add_argument(
        "--reset-failed",
        action="store_true",
        help="重置所有 failed 的 ingest 状态（让它们重新待处理）",
    )
    parser.add_argument(
        "--pending",
        action="store_true",
        help="列出所有待摄取的 pending 文件",
    )
    parser.add_argument(
        "--verbose", "-v",
        action="store_true",
        help="详细输出",
    )
    parser.add_argument(
        "--json",
        action="store_true",
        help="JSON 行输出模式（供调用方解析）",
    )
    parser.add_argument(
        "--limit",
        type=int,
        default=None,
        help="与 --pending --json 配合使用：限制返回的条目数（1 返回单条，>1 返回多条）。默认不限制（返回全部）。",
    )

    args = parser.parse_args()

    if args.rebuild:
        run_rebuild()
    elif args.pending:
        manifest = load_manifest()
        pending = [(k, v) for k, v in manifest["files"].items() if not v.get("ingested")]
        if args.json:
            total = len(pending)
            # 未指定 limit -> 返回全部（files 列表）
            if args.limit is None:
                payload = {
                    "event": "pending_list",
                    "count": total,
                    "files": [
                        {
                            "rel_path": k,
                            "slug": v.get("slug", build_slug_from_path(k)),
                            "source_path": v.get("source_path"),
                            "modified": v.get("modified"),
                            "hash": v.get("hash"),
                        }
                        for k, v in pending
                    ],
                }
            elif args.limit <= 0:
                payload = {"event": "pending_list", "count": total, "files": []}
            elif args.limit == 1:
                first = pending[0] if pending else (None, None)
                if first[0] is None:
                    payload = {"event": "pending_list", "count": 0, "file": None}
                else:
                    k, v = first
                    payload = {
                        "event": "pending_list",
                        "count": total,
                        "file": {
                            "rel_path": k,
                            "slug": v.get("slug", build_slug_from_path(k)),
                            "source_path": v.get("source_path"),
                            "modified": v.get("modified"),
                            "hash": v.get("hash"),
                        },
                    }
            else:
                # 返回前 N 条 as files array
                n = min(args.limit, total)
                payload = {
                    "event": "pending_list",
                    "count": total,
                    "files": [
                        {
                            "rel_path": k,
                            "slug": v.get("slug", build_slug_from_path(k)),
                            "source_path": v.get("source_path"),
                            "modified": v.get("modified"),
                            "hash": v.get("hash"),
                        }
                        for k, v in pending[:n]
                    ],
                }
            print(json.dumps(payload))
        else:
            # 控制台输出也支持 --limit
            total = len(pending)
            n = total if args.limit is None else max(0, args.limit)
            print(f"=== Pending Ingest Files ({total}) ===\n")
            if n == 0:
                print("  (no items to show)")
            else:
                for i, (path, info) in enumerate(pending[:n], 1):
                    print(f"{i:3}. {path}")
    elif args.reset_failed:
        manifest = load_manifest()
        reset_count = 0
        for k, v in manifest["files"].items():
            if v.get("error"):
                v["ingested"] = False
                v.pop("error", None)
                v.pop("ingested_at", None)
                reset_count += 1
        if reset_count > 0:
            save_manifest(manifest)
            print(f"Reset {reset_count} failed entries to pending.")
        else:
            print("No failed entries found.")
    elif args.check:
        run_check()
    elif args.sync:
        run_sync(dry_run=False, verbose=args.verbose, json_mode=args.json)
    else:
        parser.print_help()
        print("\n示例:")
        print("  python tools/sync.py --check       # 预览变化")
        print("  python tools/sync.py --sync        # 执行同步")
        print("  python tools/sync.py --sync -v      # 详细模式")
        print("  python tools/sync.py --rebuild     # 重建 index")