# -*- coding: utf-8 -*-
"""
将 v26/main_ai_discussion.md 转换为 main_ai_discussion.html（AI 讨论专用版）
设计要求：
- 与 v26 站点主题一致（深色标题区、阅读设置面板、主题切换）
- 简化结构（无侧边栏、无 TTS 面板）— 专为 AI 讨论场景
- 保持可读性（16:9 / 1280px 容器）
- 自动包含 main.js 以支持主题切换
"""
import re
import html
from pathlib import Path
ROOT = Path(r"E:\GitHub3\article\四把尺子理论\v26")
SOURCE_MD = ROOT / "main_ai_discussion.md"
TARGET_HTML = ROOT / "main_ai_discussion.html"
def load_markdown(path: Path) -> str:
"""读取 Markdown 文件。"""
return path.read_text(encoding="utf-8")
def preprocess_markdown(md: str) -> str:
"""预处理：合并被翻译或拷贝导致的标题符号问题。"""
import re as _re
md = _re.sub(r'(^|\n)(#(?: +#+)+#?)', lambda m: f"{m.group(1)}{'#' * m.group(2).count('#')}", md)
md = _re.sub(r'(^|\n)(#)(?:\s+#)+', lambda m: f"{m.group(1)}{'#' * m.group(2).count('#')}", md)
for _ in range(5):
new_md = _re.sub(r'\* \*', '*', md)
if new_md == md:
break
md = new_md
for _ in range(5):
new_md = _re.sub(r'\*\* \*\*', '**', md)
if new_md == md:
break
md = new_md
return md
def escape_html(text: str) -> str:
"""转义 HTML 特殊字符。"""
return html.escape(text, quote=True)
def format_inline(text: str) -> str:
"""处理行内 markdown 格式：加粗、代码、链接、斜体、图片。"""
code_blocks = {}
def save_code(match):
key = f"\x00CODE{len(code_blocks)}\x00"
code_blocks[key] = f"{escape_html(match.group(1))}"
return key
text = re.sub(r"`([^`\n]+)`", save_code, text)
images = {}
def save_image(match):
key = f"\x00IMG{len(images)}\x00"
alt = escape_html(match.group(1))
src = match.group(2)
images[key] = f''
return key
text = re.sub(r"!\[([^\]]*)\]\(([^)]+)\)", save_image, text)
links = {}
def save_link(match):
key = f"\x00LINK{len(links)}\x00"
text_part = match.group(1)
url_part = match.group(2)
links[key] = f'{escape_html(text_part)}'
return key
text = re.sub(r"\[([^\]]+)\]\(([^)]+)\)", save_link, text)
text = escape_html(text)
text = re.sub(r"\*\*([^*\n]+)\*\*", r"\1", text)
text = re.sub(r"(?\1", text)
for k, v in images.items():
text = text.replace(k, v)
for k, v in links.items():
text = text.replace(k, v)
for k, v in code_blocks.items():
text = text.replace(k, v)
return text
def md_to_html(md: str) -> str:
"""Markdown → HTML 转换（支持 H1-H6 / 列表 / 引用 / 表格 / 段落）。"""
md = preprocess_markdown(md)
lines = md.splitlines()
out = []
in_code = False
code_buf = []
in_list = None
list_buf = []
in_table = False
table_buf = []
def flush_list():
nonlocal list_buf, in_list
if in_list and list_buf:
tag = in_list
out.append(f"<{tag}>")
for item in list_buf:
out.append(f"
{format_inline(item)}
")
out.append(f"")
list_buf = []
in_list = None
def flush_table():
nonlocal table_buf, in_table
if not table_buf:
in_table = False
return
sep_re = re.compile(r"^\s*\|?\s*:?-{3,}:?\s*(\|\s*:?-{3,}:?\s*)+\|?\s*$")
if len(table_buf) >= 2 and sep_re.match(table_buf[1]):
header_cells = [c.strip() for c in table_buf[0].strip().strip("|").split("|")]
body_rows = table_buf[2:]
out.append("
")
out.append("
")
for cell in header_cells:
out.append(f"
{format_inline(cell)}
")
out.append("
")
if body_rows:
out.append("")
for row in body_rows:
cells = [c.strip() for c in row.strip().strip("|").split("|")]
out.append("
")
for cell in cells:
out.append(f"
{format_inline(cell)}
")
out.append("
")
out.append("")
out.append("
")
else:
for row in table_buf:
out.append(f"
{format_inline(row)}
")
table_buf = []
in_table = False
for raw in lines:
line = raw.rstrip()
if line.strip().startswith("```"):
flush_list()
flush_table()
if in_code:
out.append("
" + "\n".join(code_buf) + "
")
code_buf = []
in_code = False
else:
in_code = True
continue
if in_code:
code_buf.append(line)
continue
stripped = line.strip()
if not stripped:
flush_list()
flush_table()
out.append("")
continue
# 标题：支持 H1-H6
if stripped.startswith("######"):
flush_list()
flush_table()
out.append(f"
{format_inline(stripped[6:].strip())}
")
continue
if stripped.startswith("#####"):
flush_list()
flush_table()
out.append(f"
{format_inline(stripped[5:].strip())}
")
continue
if stripped.startswith("####"):
flush_list()
flush_table()
out.append(f"
{format_inline(stripped[4:].strip())}
")
continue
if stripped.startswith("###"):
flush_list()
flush_table()
out.append(f"
{format_inline(stripped[3:].strip())}
")
continue
if stripped.startswith("##"):
flush_list()
flush_table()
out.append(f"
{format_inline(stripped[2:].strip())}
")
continue
if stripped.startswith("# "):
flush_list()
flush_table()
out.append(f"
{format_inline(stripped[2:].strip())}
")
continue
if stripped == "---":
flush_list()
flush_table()
out.append("")
continue
if stripped.startswith("> "):
flush_list()
flush_table()
out.append(f"
{format_inline(stripped[2:])}
")
continue
# 表格
if stripped.startswith("|") and stripped.endswith("|"):
in_table = True
table_buf.append(stripped)
continue
if in_table:
flush_table()
# 列表
if stripped.startswith("- "):
if in_list != "ul":
flush_list()
in_list = "ul"
list_buf.append(stripped[2:])
continue
if re.match(r"^\d+\.\s", stripped):
if in_list != "ol":
flush_list()
in_list = "ol"
list_buf.append(re.sub(r"^\d+\.\s", "", stripped))
continue
# 段落
flush_list()
out.append(f"
{format_inline(stripped)}
")
flush_list()
flush_table()
if in_code and code_buf:
out.append("
" + "\n".join(code_buf) + "
")
return "\n".join(out)
def build_html() -> str:
"""构建完整 HTML 页面。"""
body = load_markdown(SOURCE_MD)
content = md_to_html(body)
# 提取主标题（第一行 H1）
title = "四把尺子理论 v26 — AI 讨论专用版（v26.1.7）"
# 统计字符数
char_count = len(body)
line_count = len(body.splitlines())
# 渲染页面
return f"""
{title}
🤖 AI 讨论专用版 v26.1.7
{title}
定位：v26 框架的"AI 可投喂"精简版 — 适用于发给 AI 讨论、复制到 path-finder、生成 PPT 提示词、跨理论项目做参考输入