"""进度状态与中文篇幅统计。

（旧版这里还有整套「按年代切章 → 写编年史」的逻辑；那条路径已经被人物主线取代，
相关代码与提示词一并删除，只留下仍然需要的东西。）
"""
from __future__ import annotations

import json
import re
import unicodedata
from dataclasses import dataclass, field
from pathlib import Path

from dfannals.config import DATA_DIR

STATE_FILE = DATA_DIR / "state.json"


@dataclass
class State:
    world: str = ""
    volume: int = 1
    done: list[str] = field(default_factory=list)

    @classmethod
    def load(cls, path: Path = STATE_FILE) -> State:
        if not path.is_file():
            return cls()
        try:
            data = json.loads(path.read_text(encoding="utf-8"))
        except (json.JSONDecodeError, OSError):
            return cls()
        if not isinstance(data, dict):
            return cls()
        return cls(
            world=data.get("world", ""),
            volume=data.get("volume", 1),
            done=list(data.get("done", [])),
        )

    def save(self, path: Path = STATE_FILE) -> None:
        path.parent.mkdir(parents=True, exist_ok=True)
        path.write_text(
            json.dumps({"world": self.world, "volume": self.volume, "done": self.done},
                       ensure_ascii=False, indent=2),
            encoding="utf-8",
        )

    def mark_done(self, key: str) -> None:
        if key not in self.done:
            self.done.append(key)


def cjk_length(text: str) -> int:
    """按中文习惯计字数：CJK 字符、拉丁字母数字、中文标点各算 1。

    统计前先去掉代码块与 Markdown 行首标记（标题、引用、列表符），
    使结果接近读者感知的"正文字数"。
    """
    without_code = re.sub(r"```.*?```", "", text, flags=re.DOTALL)
    without_meta = re.sub(r"^\s*[#>|\-*].*$", "", without_code, flags=re.MULTILINE)
    n = 0
    for ch in without_meta:
        if (
            unicodedata.east_asian_width(ch) in ("W", "F")
            or ch.isalnum()
            or ch in "，。！？；：、"
        ):
            n += 1
    return n