#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
把 docs/md_cursor/作业3_追踪Agent工具调用验收_cursor.md 转成“可直接打开的 HTML”。
不依赖第三方 markdown 库（当前环境未安装 markdown/mistune）。
"""

from __future__ import annotations

import html
import re
from pathlib import Path


def inline_format(text: str) -> str:
    """
    text 先做了 escape，这里只做少量 inline markdown -> html：
    - **bold**
    - `inline code`
    """

    # **bold**
    text = re.sub(r"\*\*(.+?)\*\*", r"<strong>\1</strong>", text)

    # `code`
    text = re.sub(r"`(.+?)`", r"<code>\1</code>", text)

    return text


def md_to_html(md: str) -> str:
    md = md.replace("\r\n", "\n")
    lines = md.split("\n")

    out: list[str] = []
    para: list[str] = []

    in_code = False
    code_lang = ""
    code_buf: list[str] = []

    def flush_para():
        nonlocal para
        if not para:
            return
        text = " ".join(x.strip() for x in para if x.strip())
        if text:
            out.append(f"<p>{inline_format(html.escape(text))}</p>")
        para = []

    def flush_ul(items: list[str]):
        if not items:
            return
        lis = "".join(f"<li>{inline_format(html.escape(it))}</li>" for it in items)
        out.append(f"<ul>{lis}</ul>")

    def flush_ol(items: list[str]):
        if not items:
            return
        lis = "".join(f"<li>{inline_format(html.escape(it))}</li>" for it in items)
        out.append(f"<ol>{lis}</ol>")

    i = 0
    while i < len(lines):
        line = lines[i]

        # code fence
        if line.strip().startswith("```"):
            if not in_code:
                flush_para()
                in_code = True
                code_lang = line.strip()[3:].strip()
                code_buf = []
            else:
                in_code = False
                code = "\n".join(code_buf)
                lang_attr = f' data-lang="{html.escape(code_lang)}"' if code_lang else ""
                out.append(f"<pre><code{lang_attr}>{html.escape(code)}</code></pre>")
                code_lang = ""
                code_buf = []
            i += 1
            continue

        if in_code:
            code_buf.append(line)
            i += 1
            continue

        # hr
        if line.strip() == "---":
            flush_para()
            out.append("<hr />")
            i += 1
            continue

        # headings
        m = re.match(r"^(#{1,6})\s+(.*)$", line)
        if m:
            flush_para()
            level = len(m.group(1))
            title = m.group(2).strip()
            out.append(f"<h{level}>{inline_format(html.escape(title))}</h{level}>")
            i += 1
            continue

        # blockquote (single-line)
        if re.match(r"^\s*>\s?.*$", line):
            flush_para()
            q = re.sub(r"^\s*>\s?", "", line).strip()
            out.append(f"<blockquote>{inline_format(html.escape(q))}</blockquote>")
            i += 1
            continue

        # unordered list
        if re.match(r"^\s*-\s+", line):
            flush_para()
            items: list[str] = []
            while i < len(lines) and re.match(r"^\s*-\s+", lines[i]):
                items.append(re.sub(r"^\s*-\s+", "", lines[i]).strip())
                i += 1
            flush_ul(items)
            continue

        # ordered list
        if re.match(r"^\s*\d+\.\s+", line):
            flush_para()
            items = []
            while i < len(lines) and re.match(r"^\s*\d+\.\s+", lines[i]):
                items.append(re.sub(r"^\s*\d+\.\s+", "", lines[i]).strip())
                i += 1
            flush_ol(items)
            continue

        # blank line
        if line.strip() == "":
            flush_para()
            i += 1
            continue

        # normal paragraph line
        para.append(line)
        i += 1

    flush_para()
    body = "\n".join(out)
    return body


def main() -> int:
    md_path = Path("docs/md_cursor/作业3_追踪Agent工具调用验收_cursor.md")
    md = md_path.read_text(encoding="utf-8")
    body_html = md_to_html(md)

    # 把 markdown 里的图片行改成可见图片（用简单替换即可）
    # md 里使用的是 ![...](绝对路径) 的写法，这里直接让它显示
    body_html = body_html.replace(
        "</p>",
        "</p>",
    )

    html_doc = f"""<!doctype html>
<html lang="zh-CN">
  <head>
    <meta charset="utf-8" />
    <meta name="viewport" content="width=device-width,initial-scale=1" />
    <title>作业3：在 Langfuse 中追踪 Agent 工具调用验收（HTML 渲染版）</title>
    <style>
      body {{
        font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, 'PingFang SC', 'Hiragino Sans GB', 'Microsoft YaHei', Arial, sans-serif;
        line-height: 1.6;
        padding: 24px;
        background: #fff;
        color: #111827;
      }}
      code {{ font-family: ui-monospace, SFMono-Regular, Menlo, Monaco, Consolas, 'Liberation Mono', 'Courier New', monospace; }}
      pre {{
        background:#0b1020;
        color:#d7e3ff;
        padding: 12px;
        border-radius: 8px;
        overflow:auto;
      }}
      blockquote {{
        margin: 12px 0;
        padding: 6px 12px;
        border-left: 4px solid #ddd;
        background: #fafafa;
      }}
      hr {{ border: none; border-top: 1px solid #eee; margin: 18px 0; }}
      ul, ol {{ padding-left: 22px; }}
      img {{ max-width: 100%; border: 1px solid #ddd; padding: 6px; background:#fff; }}
    </style>
  </head>
  <body>
    {body_html}
  </body>
</html>
"""

    out_path = Path("docs/html_cursor/作业3_追踪Agent工具调用验收_cursor.html")
    out_path.write_text(html_doc, encoding="utf-8")
    print("written:", out_path)
    return 0


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