#!/usr/bin/env python3
"""Validate a tester CSV/YAML pair and summarize statuses from CSV only."""

from __future__ import annotations

import argparse
import csv
import sys
from collections import Counter
from pathlib import Path
from typing import Any

try:
    import yaml
except ImportError:  # pragma: no cover
    print("需要 PyYAML: python3 -m pip install pyyaml", file=sys.stderr)
    raise SystemExit(2)


RESULTS = ("pass", "fail", "environment-fail", "skipped", "not-run")
RESULT_SET = frozenset(RESULTS)


class SummaryError(ValueError):
    """Raised when the CSV/YAML pair cannot be safely summarized."""


def _format_ids(ids: set[str]) -> str:
    return ", ".join(sorted(ids)) or "(none)"


def _duplicate_ids(ids: list[str]) -> list[str]:
    counts = Counter(ids)
    return sorted(case_id for case_id, count in counts.items() if count > 1)


def load_csv(path: Path) -> list[dict[str, str]]:
    """Load CSV rows and reject malformed IDs/results with diagnostics."""
    try:
        handle = path.open(encoding="utf-8-sig", newline="")
    except OSError as exc:
        raise SummaryError(f"无法读取 CSV {path}: {exc}") from exc

    with handle:
        reader = csv.DictReader(handle)
        if not reader.fieldnames:
            raise SummaryError(f"CSV {path} 缺少表头")
        missing_fields = [field for field in ("id", "result") if field not in reader.fieldnames]
        if missing_fields:
            raise SummaryError(f"CSV {path} 缺少必需列: {', '.join(missing_fields)}")
        rows = list(reader)

    ids: list[str] = []
    errors: list[str] = []
    for line_number, row in enumerate(rows, start=2):
        case_id = (row.get("id") or "").strip()
        result = (row.get("result") or "").strip()
        ids.append(case_id)
        if not case_id:
            errors.append(f"CSV 第 {line_number} 行 testcase id 缺失")
        if not result:
            errors.append(f"CSV 第 {line_number} 行 result 缺失 (testcase id={case_id or '(missing)'})")
        elif result not in RESULT_SET:
            errors.append(
                f"CSV 第 {line_number} 行 result 未知: {result!r} "
                f"(testcase id={case_id or '(missing)'}; 允许值={', '.join(RESULTS)})"
            )

    duplicates = _duplicate_ids([case_id for case_id in ids if case_id])
    if duplicates:
        errors.append(f"CSV testcase id 重复: {_format_ids(set(duplicates))}")
    if errors:
        raise SummaryError("CSV 校验失败:\n- " + "\n- ".join(errors))
    return rows


def load_yaml_results(path: Path) -> list[dict[str, Any]]:
    """Load only YAML results structure needed for count/ID validation."""
    try:
        data = yaml.safe_load(path.read_text(encoding="utf-8"))
    except OSError as exc:
        raise SummaryError(f"无法读取 YAML {path}: {exc}") from exc
    except yaml.YAMLError as exc:
        raise SummaryError(f"YAML 解析失败 {path}: {exc}") from exc

    if not isinstance(data, dict) or not isinstance(data.get("results"), list):
        raise SummaryError(f"YAML {path} 缺少 results 列表")

    results = data["results"]
    ids: list[str] = []
    errors: list[str] = []
    for index, item in enumerate(results, start=1):
        if not isinstance(item, dict):
            errors.append(f"YAML results[{index}] 不是 mapping")
            continue
        case_id = str(item.get("id") or "").strip()
        ids.append(case_id)
        if not case_id:
            errors.append(f"YAML results[{index}] testcase id 缺失")

    duplicates = _duplicate_ids([case_id for case_id in ids if case_id])
    if duplicates:
        errors.append(f"YAML testcase id 重复: {_format_ids(set(duplicates))}")
    if errors:
        raise SummaryError("YAML 校验失败:\n- " + "\n- ".join(errors))
    issues = data.get("defects", data.get("test_issues"))
    if issues is not None:
        if not isinstance(issues, list):
            raise SummaryError("YAML defects/test_issues 必须是列表")
        result_ids = set(ids)
        issue_errors: list[str] = []
        for index, issue in enumerate(issues, start=1):
            if not isinstance(issue, dict):
                issue_errors.append(f"YAML defects[{index}] 不是 mapping")
                continue
            testcase = str(issue.get("testcase") or "")
            issue_type = str(issue.get("issue_type") or "")
            if not testcase or testcase not in result_ids:
                issue_errors.append(f"YAML defects[{index}] testcase 无效: {testcase or '(missing)'}")
            if issue_type not in {"product", "test"}:
                issue_errors.append(f"YAML defects[{index}] issue_type 无效: {issue_type or '(missing)'}")
            for field in ("expected", "observed", "artifact_hash", "environment", "evidence_path", "reproduction", "next_step"):
                if field not in issue:
                    issue_errors.append(f"YAML defects[{index}] 缺少 {field}")
        if issue_errors:
            raise SummaryError("YAML defects 校验失败:\n- " + "\n- ".join(issue_errors))
    return results


def summarize(csv_path: Path, yaml_path: Path) -> tuple[Counter[str], dict[str, int]]:
    """Validate the pair and return counts calculated from CSV result values."""
    rows = load_csv(csv_path)
    yaml_results = load_yaml_results(yaml_path)
    csv_ids = [(row.get("id") or "").strip() for row in rows]
    yaml_ids = [str(item.get("id") or "").strip() for item in yaml_results]
    csv_id_set = set(csv_ids)
    yaml_id_set = set(yaml_ids)
    diagnostics: list[str] = []

    if len(rows) != len(csv_id_set):
        diagnostics.append(
            f"CSV 数据行总数与唯一 testcase id 数不一致: rows={len(rows)} unique_ids={len(csv_id_set)}"
        )
    if len(rows) != len(yaml_results):
        diagnostics.append(
            f"CSV 数据行总数与 YAML results 数量不一致: csv_rows={len(rows)} yaml_results={len(yaml_results)}"
        )
    if csv_id_set != yaml_id_set:
        diagnostics.append(
            "CSV/YAML testcase id 集合不一致: "
            f"仅 CSV 有 [{_format_ids(csv_id_set - yaml_id_set)}]; "
            f"仅 YAML 有 [{_format_ids(yaml_id_set - csv_id_set)}]"
        )
    if diagnostics:
        raise SummaryError("CSV/YAML 汇总校验失败:\n- " + "\n- ".join(diagnostics))

    counts: Counter[str] = Counter((row.get("result") or "").strip() for row in rows)
    total = sum(counts[name] for name in RESULTS)
    if total != len(rows):
        raise SummaryError(
            "CSV 状态计数和不等于数据行总数: "
            f"count_sum={total} csv_rows={len(rows)}"
        )
    metadata = {
        "csv_rows": len(rows),
        "csv_unique_ids": len(csv_id_set),
        "yaml_results": len(yaml_results),
        "count_sum": total,
    }
    return counts, metadata


def main(argv: list[str] | None = None) -> int:
    parser = argparse.ArgumentParser(description="校验 tester CSV/YAML 并从 CSV result 汇总状态")
    parser.add_argument("--csv", required=True, type=Path, help="运行成绩单 CSV")
    parser.add_argument("--yaml", required=True, type=Path, help="对应运行快照 YAML")
    args = parser.parse_args(argv)
    try:
        counts, metadata = summarize(args.csv, args.yaml)
    except SummaryError as exc:
        print(f"汇总失败: {exc}", file=sys.stderr)
        return 1

    bits = " ".join(f"{name}={counts[name]}" for name in RESULTS)
    print(f"summary source=CSV.result {bits} total={metadata['count_sum']}")
    print(
        "validated "
        f"csv_rows={metadata['csv_rows']} "
        f"csv_unique_ids={metadata['csv_unique_ids']} "
        f"yaml_results={metadata['yaml_results']}"
    )
    return 0


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