import re
from pathlib import Path

path = Path(__file__).resolve().parents[1] / "doc" / "企微客户服务-功能实现说明.md"
s = path.read_text(encoding="utf-8")

CHAPTER_CN = {1: "四", 2: "五", 3: "六", 4: "七", 5: "八", 6: "九", 7: "十", 8: "十一", 9: "十二", 10: "十三", 11: "十四"}


def slug_title(title: str) -> str:
    t = title.strip().lower()
    t = re.sub(r"[「」『』""''（）()、，。！？：:；;·]", "", t)
    t = re.sub(r"\s+", "-", t)
    t = re.sub(r"-+", "-", t).strip("-")
    return t


# Fix module chapter headers (all were incorrectly collapsed to 四)
for mod in range(1, 12):
    ch = CHAPTER_CN[mod]
    s = re.sub(
        rf"^## 四、模块 {mod}：",
        f"## {ch}、模块 {mod}：",
        s,
        count=1,
        flags=re.M,
    )

# Build anchor map from ### headers
anchors: dict[str, str] = {}
for m in re.finditer(r"^### (\d+)\.(\d+) (.+)$", s, re.M):
    ch, sec, title = m.group(1), m.group(2), m.group(3)
    key = f"{ch}.{sec}"
    anchors[key] = f"#{ch}{sec}-{slug_title(title)}"


def fix_toc_link(m: re.Match) -> str:
    ch, sec = m.group(1), m.group(2)
    key = f"{ch}.{sec}"
    if key not in anchors:
        return m.group(0)
    return f"[§{ch}.{sec}]({anchors[key]})"


s = re.sub(r"\[§(\d+)\.(\d+)\]\(#[^)]+\)", fix_toc_link, s)

# Intro cleanup
s = s.replace(
    "为开发人员补充：**每条功能的详细实现流程**、**需实现的 QiWe 官方接口**（对照已爬取官方文档）、**项目需产出的文档清单**。",
    "为开发人员补充：**每条功能的详细实现流程**、**需实现的 QiWe 官方接口**（对照已爬取官方文档）。",
)

path.write_text(s, encoding="utf-8")
print("fixed", path, "anchors", len(anchors))