#!/usr/bin/env python3
"""Local server for the L2 lyric review dashboard."""

from __future__ import annotations

import argparse
import csv
import json
import mimetypes
import subprocess
import sys
import time
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
from pathlib import Path
from urllib.parse import parse_qs, unquote, urlparse


ROOT = Path(__file__).resolve().parent
REPORT_DIR = ROOT / "output" / "reports"
DASHBOARD = ROOT / "l2_review_dashboard.html"
REPORT_DIR.mkdir(parents=True, exist_ok=True)
GROUP_INDEX_CACHE: dict[tuple[str, int, int, str], list[dict[str, object]]] = {}


def _json_response(handler: BaseHTTPRequestHandler, payload: object, status: int = 200) -> None:
    body = json.dumps(payload, ensure_ascii=False).encode("utf-8")
    try:
        handler.send_response(status)
        handler.send_header("Content-Type", "application/json; charset=utf-8")
        handler.send_header("Content-Length", str(len(body)))
        handler.end_headers()
        handler.wfile.write(body)
    except (BrokenPipeError, ConnectionResetError):
        return


def _error(handler: BaseHTTPRequestHandler, message: str, status: int = 400) -> None:
    _json_response(handler, {"error": message}, status=status)


def _safe_path(raw_path: str) -> Path:
    path = Path(unquote(raw_path)).expanduser()
    if not path.is_absolute():
        path = ROOT / path
    resolved = path.resolve()
    allowed_roots = [ROOT.resolve(), REPORT_DIR.resolve()]
    if not any(resolved == base or base in resolved.parents for base in allowed_roots):
        raise ValueError(f"path is outside workspace: {raw_path}")
    if not resolved.exists() or not resolved.is_file():
        raise FileNotFoundError(str(resolved))
    return resolved


def _read_csv(path: Path) -> list[dict[str, str]]:
    with open(path, "r", encoding="utf-8-sig", newline="") as f:
        return list(csv.DictReader(f))


def _iter_csv(path: Path):
    with open(path, "r", encoding="utf-8-sig", newline="") as f:
        yield from csv.DictReader(f)


def _report_runs() -> list[dict[str, str]]:
    summaries = {
        path.name.replace("l2_topk_benchmark_summary_", "").removesuffix(".csv"): path
        for path in REPORT_DIR.glob("l2_topk_benchmark_summary_*.csv")
    }
    retrievals = {
        path.name.replace("l2_topk_retrieval_top10_", "").removesuffix(".csv"): path
        for path in REPORT_DIR.glob("l2_topk_retrieval_top10_*.csv")
    }
    hits = {
        path.name.replace("l2_topk_duplicate_hits_", "").removesuffix(".csv"): path
        for path in REPORT_DIR.glob("l2_topk_duplicate_hits_*.csv")
    }
    run_ids = sorted(set(summaries) & set(retrievals) & set(hits), reverse=True)
    benchmark_runs = [
        {
            "id": run_id,
            "type": "benchmark",
            "summary": str(summaries[run_id]),
            "retrieval": str(retrievals[run_id]),
            "hits": str(hits[run_id]),
        }
        for run_id in run_ids
    ]
    review_runs = [
        {
            "id": path.name.replace("review_decisions_", "").removesuffix(".csv"),
            "type": "import",
            "summary": str(path),
            "retrieval": str(path),
            "hits": str(path),
            "review": str(path),
        }
        for path in sorted(REPORT_DIR.glob("review_decisions_*.csv"), reverse=True)
    ]
    return review_runs + benchmark_runs


def _row_decision(row: dict[str, str]) -> str:
    return row.get("action") or row.get("decision") or row.get("candidate_decision") or ""


def _is_import_review_row(row: dict[str, str]) -> bool:
    return "source_id" in row and "action" in row and "query_source_id" not in row


def _dashboard_row(row: dict[str, str]) -> dict[str, str]:
    if not _is_import_review_row(row):
        return row
    source_id = row.get("source_id", "")
    action = row.get("action", "")
    return {
        **row,
        "top_k": "import",
        "rank": "1",
        "query_source_id": source_id,
        "query_name": row.get("name", ""),
        "query_lyricist": row.get("lyricist", ""),
        "query_composer": row.get("composer", ""),
        "query_lyrics_path": row.get("query_lyrics_path", ""),
        "candidate_id": row.get("matched_id", ""),
        "candidate_name": row.get("matched_name", ""),
        "candidate_lyricist": row.get("matched_lyricist", ""),
        "candidate_composer": row.get("matched_composer", ""),
        "candidate_lyrics_path": row.get("matched_lyrics_path", ""),
        "candidate_decision": action,
        "candidate_confidence": row.get("confidence", ""),
        "candidate_reason": row.get("reason", ""),
        "decision": action,
        "l1_metadata_match": "1" if row.get("l1_matched_id") else "0",
        "l1_l2_conflict": "0",
    }


def _review_summary(path: Path) -> list[dict[str, str]]:
    counts = {"new": 0, "merge": 0, "review": 0}
    total = 0
    for row in _iter_csv(path):
        total += 1
        action = row.get("action", "")
        if action in counts:
            counts[action] += 1
    return [{
        "top_k": "import",
        "elapsed_seconds": "-",
        "throughput_per_second": "-",
        "avg_recalled_candidates": "-",
        "hit_count": str(counts["merge"] + counts["review"]),
        "duplicate_count": str(counts["merge"]),
        "review_count": str(counts["review"]),
        "new_count": str(counts["new"]),
        "total_count": str(total),
    }]


def _norm(value: str | None) -> str:
    return (value or "").strip().lower()


def _matches_term(row: dict[str, object], term: str) -> bool:
    if not term:
        return True
    haystack = " ".join(
        [
            row.get("query_source_id", ""),
            row.get("query_name", ""),
            row.get("query_lyricist", ""),
            row.get("query_composer", ""),
        ]
    ).lower()
    return term in haystack


def _group_index(path: Path, top_k: str) -> list[dict[str, object]]:
    stat = path.stat()
    cache_key = (str(path), stat.st_mtime_ns, stat.st_size, top_k)
    cached = GROUP_INDEX_CACHE.get(cache_key)
    if cached is not None:
        return cached

    groups_by_id: dict[str, dict[str, object]] = {}
    order = 0
    for raw_row in _iter_csv(path):
        row = _dashboard_row(raw_row)
        if top_k and str(row.get("top_k", "")) != top_k:
            continue
        query_id = row.get("query_source_id", "")
        if not query_id:
            continue

        group = groups_by_id.get(query_id)
        if group is None:
            group = {
                "id": query_id,
                "_order": order,
                "query_source_id": query_id,
                "query_name": row.get("query_name", ""),
                "query_lyricist": row.get("query_lyricist", ""),
                "query_composer": row.get("query_composer", ""),
                "count": 0,
                "has_hit": False,
                "has_conflict": False,
                "has_l1_hint": False,
            }
            groups_by_id[query_id] = group
            order += 1

        group["count"] = int(group["count"]) + 1
        decision = _row_decision(row)
        l1_match = row.get("l1_metadata_match") == "1"
        conflict = row.get("l1_l2_conflict") == "1"
        group["has_hit"] = bool(group["has_hit"]) or decision in {"duplicate", "review"}
        group["has_conflict"] = bool(group["has_conflict"]) or conflict
        group["has_l1_hint"] = bool(group["has_l1_hint"]) or (decision == "new" and l1_match)

    groups = sorted(
        groups_by_id.values(),
        key=lambda group: (
            0 if group["has_conflict"] else 1,
            0 if group["has_l1_hint"] else 1,
            0 if group["has_hit"] else 1,
            int(group["_order"]),
        ),
    )
    GROUP_INDEX_CACHE.clear()
    GROUP_INDEX_CACHE[cache_key] = groups
    return groups


def _groups_response(path: Path, top_k: str, term: str, page: int, page_size: int) -> dict[str, object]:
    filtered = [group for group in _group_index(path, top_k) if _matches_term(group, term)]
    start = max(0, (page - 1) * page_size)
    end = start + page_size
    page_groups = filtered[start:end]
    return {
        "total": len(filtered),
        "page": page,
        "page_size": page_size,
        "has_more": end < len(filtered),
        "groups": [{key: value for key, value in group.items() if not key.startswith("_")} for group in page_groups],
    }


def _query_rows_response(path: Path, top_k: str, query_id: str) -> dict[str, object]:
    rows = []
    found = False
    for raw_row in _iter_csv(path):
        row = _dashboard_row(raw_row)
        if str(row.get("top_k", "")) != top_k:
            continue
        current_query_id = row.get("query_source_id", "")
        if current_query_id == query_id:
            found = True
            rows.append(row)
            continue
        if found:
            break
    return {"rows": rows}


def _write_review_import_csv(rows: list[dict[str, str]]) -> Path:
    path = REPORT_DIR / f"review_import_approved_{time.strftime('%Y%m%d_%H%M%S')}.csv"
    with open(path, "w", encoding="utf-8", newline="") as f:
        writer = csv.DictWriter(f, fieldnames=["source_id", "review_decision", "review_note"])
        writer.writeheader()
        for row in rows:
            writer.writerow({
                "source_id": row.get("source_id", ""),
                "review_decision": row.get("review_decision", ""),
                "review_note": row.get("review_note", ""),
            })
    return path


def _run_import(review_csv: Path) -> dict[str, object]:
    cmd = [
        "uv",
        "run",
        "python",
        "import_hk_songs.py",
        "--review-result-csv",
        str(review_csv),
        "--load-existing-lyrics",
    ]
    result = subprocess.run(
        cmd,
        cwd=ROOT,
        text=True,
        stdout=subprocess.PIPE,
        stderr=subprocess.STDOUT,
        check=False,
    )
    return {
        "command": " ".join(cmd),
        "returncode": result.returncode,
        "output": result.stdout[-12000:],
    }


class Handler(BaseHTTPRequestHandler):
    def log_message(self, fmt: str, *args: object) -> None:
        print(f"{self.address_string()} - {fmt % args}")

    def do_GET(self) -> None:
        parsed = urlparse(self.path)
        if parsed.path == "/":
            self._serve_file(DASHBOARD)
            return
        if parsed.path == "/api/reports":
            _json_response(self, {"runs": _report_runs()})
            return
        if parsed.path == "/api/csv":
            params = parse_qs(parsed.query)
            raw_path = params.get("path", [""])[0]
            try:
                path = _safe_path(raw_path)
                if path.name.startswith("review_decisions_"):
                    _json_response(self, {"path": str(path), "rows": _review_summary(path)})
                else:
                    _json_response(self, {"path": str(path), "rows": _read_csv(path)})
            except Exception as exc:  # noqa: BLE001 - local diagnostic API
                _error(self, str(exc), status=404)
            return
        if parsed.path == "/api/groups":
            params = parse_qs(parsed.query)
            try:
                path = _safe_path(params.get("path", [""])[0])
                top_k = params.get("top_k", [""])[0]
                term = _norm(params.get("q", [""])[0])
                page = max(1, int(params.get("page", ["1"])[0]))
                page_size = min(200, max(10, int(params.get("page_size", ["50"])[0])))
                _json_response(self, _groups_response(path, top_k, term, page, page_size))
            except Exception as exc:  # noqa: BLE001 - local diagnostic API
                _error(self, str(exc), status=404)
            return
        if parsed.path == "/api/query":
            params = parse_qs(parsed.query)
            try:
                path = _safe_path(params.get("path", [""])[0])
                top_k = params.get("top_k", [""])[0]
                query_id = params.get("query_id", [""])[0]
                _json_response(self, _query_rows_response(path, top_k, query_id))
            except Exception as exc:  # noqa: BLE001 - local diagnostic API
                _error(self, str(exc), status=404)
            return
        if parsed.path == "/api/text":
            params = parse_qs(parsed.query)
            raw_path = params.get("path", [""])[0]
            try:
                path = _safe_path(raw_path)
                text = path.read_text(encoding="utf-8", errors="replace")
                _json_response(self, {"path": str(path), "text": text})
            except Exception as exc:  # noqa: BLE001 - local diagnostic API
                _error(self, str(exc), status=404)
            return
        if parsed.path.startswith("/static/"):
            self._serve_file(ROOT / parsed.path.lstrip("/"))
            return
        _error(self, "not found", status=404)

    def do_POST(self) -> None:
        parsed = urlparse(self.path)
        if parsed.path != "/api/import-reviewed":
            _error(self, "not found", status=404)
            return
        try:
            length = int(self.headers.get("Content-Length", "0"))
            payload = json.loads(self.rfile.read(length).decode("utf-8") or "{}")
            rows = payload.get("rows") or []
            if not isinstance(rows, list):
                raise ValueError("rows must be a list")
            approved = [
                {
                    "source_id": str(row.get("source_id", "")).strip(),
                    "review_decision": "import",
                    "review_note": str(row.get("review_note", "")).strip(),
                }
                for row in rows
                if str(row.get("source_id", "")).strip()
                and str(row.get("review_decision", "")).strip().lower() in {"import", "导入", "not_duplicate"}
            ]
            if not approved:
                raise ValueError("没有可入库的审核通过样本")
            review_csv = _write_review_import_csv(approved)
            result = _run_import(review_csv)
            status = 200 if result["returncode"] == 0 else 500
            _json_response(self, {"review_csv": str(review_csv), **result}, status=status)
        except Exception as exc:  # noqa: BLE001 - local diagnostic API
            _error(self, str(exc), status=400)

    def _serve_file(self, path: Path) -> None:
        if not path.exists() or not path.is_file():
            _error(self, "not found", status=404)
            return
        content_type = mimetypes.guess_type(path.name)[0] or "application/octet-stream"
        body = path.read_bytes()
        self.send_response(200)
        self.send_header("Content-Type", content_type)
        self.send_header("Content-Length", str(len(body)))
        self.end_headers()
        self.wfile.write(body)


def main() -> None:
    parser = argparse.ArgumentParser(description="Serve L2 lyric review dashboard")
    parser.add_argument("--host", default="127.0.0.1")
    parser.add_argument("--port", type=int, default=8765)
    args = parser.parse_args()

    server = ThreadingHTTPServer((args.host, args.port), Handler)
    print(f"L2 dashboard: http://{args.host}:{args.port}")
    server.serve_forever()


if __name__ == "__main__":
    try:
        main()
    except KeyboardInterrupt:
        sys.exit(0)