#!/usr/bin/env python3
"""校验 ~/.local/share/todo/tasks.json 的格式、结构和完整性。

退出码:
  0 - 校验通过
  1 - 校验失败（错误信息输出到 stderr）

用法:
  python3 validate.py [文件路径]
  默认路径: ~/.local/share/todo/tasks.json
"""

import json
import os
import sys
from pathlib import Path

DEFAULT_PATH = Path.home() / ".local" / "share" / "todo" / "tasks.json"
SCHEMA_PATH = Path(__file__).parent.parent / "schema" / "tasks.schema.json"


def load_json(path: Path) -> tuple[dict | None, str | None]:
    """加载并解析 JSON 文件。"""
    if not path.exists():
        return None, f"文件不存在: {path}"
    try:
        with open(path, "r", encoding="utf-8") as f:
            data = json.load(f)
        return data, None
    except json.JSONDecodeError as e:
        return None, f"JSON 格式错误: {e}"


def load_schema() -> tuple[dict | None, str | None]:
    """加载 JSON Schema。"""
    if not SCHEMA_PATH.exists():
        return None, f"Schema 文件不存在: {SCHEMA_PATH}"
    try:
        with open(SCHEMA_PATH, "r", encoding="utf-8") as f:
            return json.load(f), None
    except json.JSONDecodeError as e:
        return None, f"Schema 格式错误: {e}"


def validate_structure(data: dict) -> list[str]:
    """校验数据结构。"""
    errors = []

    if not isinstance(data, dict):
        errors.append("顶层必须是对象")
        return errors

    if "tasks" not in data:
        errors.append("缺少必需字段 'tasks'")
        return errors

    tasks = data["tasks"]
    if not isinstance(tasks, list):
        errors.append("'tasks' 必须是数组")
        return errors

    for i, item in enumerate(tasks):
        if not isinstance(item, str):
            errors.append(f"tasks[{i}] 必须是字符串，实际类型: {type(item).__name__}")
        elif len(item.strip()) == 0:
            errors.append(f"tasks[{i}] 不能为空字符串")

    return errors


def validate_duplicates(tasks: list[str]) -> list[str]:
    """校验任务是否有重复（大小写不敏感）。"""
    errors = []
    seen = {}
    for i, task in enumerate(tasks):
        key = task.strip().lower()
        if key in seen:
            errors.append(f"tasks[{i}] '{task}' 与 tasks[{seen[key]}] 重复")
        else:
            seen[key] = i
    return errors


def validate_schema(data: dict) -> list[str]:
    """使用 JSON Schema 校验（如果 jsonschema 可用）。"""
    try:
        import jsonschema
    except ImportError:
        # jsonschema 未安装，跳过 schema 校验
        return []

    schema, err = load_schema()
    if err:
        return [f"Schema 校验跳过: {err}"]

    errors = []
    try:
        jsonschema.validate(instance=data, schema=schema)
    except jsonschema.ValidationError as e:
        errors.append(f"Schema 校验失败: {e.message}")
    except jsonschema.SchemaError as e:
        errors.append(f"Schema 定义错误: {e.message}")

    return errors


def main() -> int:
    path = Path(sys.argv[1]) if len(sys.argv) > 1 else DEFAULT_PATH

    # 1. JSON 格式校验
    data, err = load_json(path)
    if err:
        print(err, file=sys.stderr)
        return 1

    # 2. 结构校验
    errors = validate_structure(data)
    if errors:
        for e in errors:
            print(f"结构错误: {e}", file=sys.stderr)
        return 1

    # 3. JSON Schema 校验
    schema_errors = validate_schema(data)
    if schema_errors:
        for e in schema_errors:
            print(f"Schema 错误: {e}", file=sys.stderr)
        return 1

    # 4. 去重校验
    dup_errors = validate_duplicates(data["tasks"])
    if dup_errors:
        for e in dup_errors:
            print(f"重复错误: {e}", file=sys.stderr)
        return 1

    print(f"校验通过: {path} ({len(data['tasks'])} 个任务)")
    return 0


if __name__ == "__main__":
    sys.exit(main())