crypto_okx/lib/common/markdown_html_lib.py

"""Markdown → HTML for system guide / options docs."""

from __future__ import annotations

import re


def render_markdown_html(md_text: str) -> str:
    try:
        import markdown  # type: ignore

        return markdown.markdown(
            md_text,
            extensions=["tables", "fenced_code", "nl2br", "sane_lists"],
        )
    except Exception:
        return _simple_md_html(md_text)


def _simple_md_html(md_text: str) -> str:
    from html import escape

    lines = md_text.replace("\r\n", "\n").replace("\r", "\n").splitlines()
    out: list[str] = []
    i = 0
    in_code = False
    code_buf: list[str] = []
    list_buf: list[str] = []
    list_ordered = False

    def flush_list() -> None:
        nonlocal list_buf, list_ordered
        if not list_buf:
            return
        tag = "ol" if list_ordered else "ul"
        out.append(f"<{tag}>")
        for item in list_buf:
            out.append(f"<li>{_inline_md(item)}</li>")
        out.append(f"</{tag}>")
        list_buf = []

    def flush_code() -> None:
        nonlocal code_buf, in_code
        if not code_buf:
            return
        out.append(f"<pre><code>{escape(chr(10).join(code_buf))}</code></pre>")
        code_buf = []
        in_code = False

    while i < len(lines):
        line = lines[i]
        if line.strip().startswith("```"):
            flush_list()
            if in_code:
                flush_code()
            else:
                in_code = True
            i += 1
            continue
        if in_code:
            code_buf.append(line)
            i += 1
            continue
        if re.match(r"^\s*\|", line) and i + 1 < len(lines) and re.match(r"^\s*\|?\s*[-:| ]+\|", lines[i + 1]):
            flush_list()
            header = [c.strip() for c in line.strip().strip("|").split("|")]
            i += 2
            rows: list[list[str]] = []
            while i < len(lines) and re.match(r"^\s*\|", lines[i]):
                rows.append([c.strip() for c in lines[i].strip().strip("|").split("|")])
                i += 1
            out.append("<table><thead><tr>" + "".join(f"<th>{_inline_md(h)}</th>" for h in header) + "</tr></thead><tbody>")
            for row in rows:
                out.append("<tr>" + "".join(f"<td>{_inline_md(c)}</td>" for c in row) + "</tr>")
            out.append("</tbody></table>")
            continue
        if re.match(r"^#{1,3}\s+", line):
            flush_list()
            m = re.match(r"^(#{1,3})\s+(.*)$", line)
            if m:
                level = len(m.group(1))
                out.append(f"<h{level}>{_inline_md(m.group(2))}</h{level}>")
            i += 1
            continue
        if line.strip() == "---":
            flush_list()
            out.append("<hr>")
            i += 1
            continue
        if line.startswith(">"):
            flush_list()
            out.append(f"<blockquote>{_inline_md(line.lstrip('>').strip())}</blockquote>")
            i += 1
            continue
        m = re.match(r"^(\d+)\.\s+(.*)$", line.strip())
        if m:
            if list_buf and not list_ordered:
                flush_list()
            list_ordered = True
            list_buf.append(m.group(2))
            i += 1
            continue
        if re.match(r"^[-*]\s+", line.strip()):
            if list_buf and list_ordered:
                flush_list()
            list_ordered = False
            list_buf.append(re.sub(r"^[-*]\s+", "", line.strip()))
            i += 1
            continue
        if not line.strip():
            flush_list()
            i += 1
            continue
        flush_list()
        out.append(f"<p>{_inline_md(line.strip())}</p>")
        i += 1
    flush_list()
    flush_code()
    return "\n".join(out)


def _inline_md(text: str) -> str:
    from html import escape

    s = escape(text)
    s = re.sub(r"`([^`]+)`", r"<code>\1</code>", s)
    s = re.sub(r"\*\*([^*]+)\*\*", r"<strong>\1</strong>", s)
    return s