"""
TODO 解析器 — V2 修复 P1-8：列索引从表头推导，不再硬编码 cells[1]/cells[6]/cells[7]。
"""

from __future__ import annotations

import re
from dataclasses import dataclass
from pathlib import Path


@dataclass
class TodoTask:
    task_id: str
    task: str
    files_dirs: str = ""
    status: str = "TODO"
    done_when: str = ""
    validations: str = ""
    adr: str = ""


def parse_tasks(todo_path: Path) -> list[TodoTask]:
    """从 todo.md 解析任务列表，动态检测列索引。"""
    if not todo_path.exists():
        return []

    content = todo_path.read_text(encoding="utf-8")
    lines = [l.strip() for l in content.splitlines() if l.strip()]

    # 找到 Markdown 表格头
    header_idx = -1
    for i, line in enumerate(lines):
        if line.startswith("|") and "Task" in line and "Status" in line:
            header_idx = i
            break

    if header_idx < 0:
        return []

    # 解析列名
    header_line = lines[header_idx]
    header_cols = [c.strip() for c in header_line.split("|") if c.strip()]

    # 建立列名 → 索引映射
    col_map = {}
    for idx, col_name in enumerate(header_cols):
        col_name_lower = col_name.lower()
        if "task" in col_name_lower:
            col_map["task"] = idx
        elif "status" in col_name_lower:
            col_map["status"] = idx
        elif "files" in col_name_lower or "dir" in col_name_lower:
            col_map["files_dirs"] = idx
        elif "done" in col_name_lower or "when" in col_name_lower:
            col_map["done_when"] = idx
        elif "valid" in col_name_lower:
            col_map["validations"] = idx
        elif "adr" in col_name_lower:
            col_map["adr"] = idx

    # 跳过表头和分隔符
    tasks = []
    for line in lines[header_idx + 2:]:
        if not line.startswith("|"):
            continue
        cells = [c.strip() for c in line.split("|") if len(c.strip()) > 0]
        if not cells:
            continue

        task_cell = cells[col_map.get("task", 0)] if col_map.get("task", 0) < len(cells) else ""
        # 优先提取 [T-xxx] 方括号格式的 ID；若没有则尝试从开头提取 G-001/H-000 类短 ID
        tid_match = re.match(r"\[([A-Za-z0-9_\-\.]+)\]", task_cell)
        if tid_match:
            task_id = tid_match.group(1)
        else:
            short_match = re.match(r"^([A-Z]+-\d+[a-z]*)", task_cell)
            task_id = short_match.group(1) if short_match else task_cell
        task = task_cell
        status = cells[col_map.get("status", 1)] if col_map.get("status", 1) < len(cells) else "TODO"
        files_dirs = cells[col_map.get("files_dirs", 2)] if col_map.get("files_dirs", 2) < len(cells) else ""
        done_when = cells[col_map.get("done_when", 3)] if col_map.get("done_when", 3) < len(cells) else ""
        validations = cells[col_map.get("validations", 4)] if col_map.get("validations", 4) < len(cells) else ""
        adr = cells[col_map.get("adr", 5)] if col_map.get("adr", 5) < len(cells) else ""

        # 清理标记
        task_id = re.sub(r"^\[|\]$", "", task_id).strip()

        if task_id and task_id != "---":
            tasks.append(TodoTask(
                task_id=task_id,
                task=task,
                files_dirs=files_dirs,
                status=status.upper() if status else "TODO",
                done_when=done_when,
                validations=validations,
                adr=adr,
            ))

    return tasks