Add Markdown to Telegram HTML converter

Claude-Session: https://claude.ai/code/session_01JtuZTCMW9TyogEmBgGf8JT

src/telegram/markdown.test.ts

@@ -0,0 +1,57 @@
+import { describe, expect, it } from "vitest";
+import { escapeHtml, markdownToTelegramHtml } from "./markdown.js";
+
+describe("escapeHtml", () => {
+  it("escapes the three HTML specials", () => {
+    expect(escapeHtml("a < b && c > d")).toBe("a &lt; b &amp;&amp; c &gt; d");
+  });
+});
+
+describe("markdownToTelegramHtml", () => {
+  it("escapes plain text", () => {
+    expect(markdownToTelegramHtml("1 < 2 & 3 > 2")).toBe("1 &lt; 2 &amp; 3 &gt; 2");
+  });
+
+  it("renders inline formatting", () => {
+    expect(markdownToTelegramHtml("**bold** __bold2__ *it* _it2_ ~~gone~~ `co<de>`")).toBe(
+      "<b>bold</b> <b>bold2</b> <i>it</i> <i>it2</i> <s>gone</s> <code>co&lt;de&gt;</code>",
+    );
+  });
+
+  it("leaves snake_case words and lone asterisks alone", () => {
+    expect(markdownToTelegramHtml("use snake_case_names and 2 * 3")).toBe("use snake_case_names and 2 * 3");
+  });
+
+  it("does not format inside inline code", () => {
+    expect(markdownToTelegramHtml("run `**not bold**`")).toBe("run <code>**not bold**</code>");
+  });
+
+  it("renders links", () => {
+    expect(markdownToTelegramHtml("see [docs](https://x.y/a?b=1&c=2)")).toBe(
+      'see <a href="https://x.y/a?b=1&amp;c=2">docs</a>',
+    );
+  });
+
+  it("renders headings as bold lines", () => {
+    expect(markdownToTelegramHtml("# Title\n\ntext")).toBe("<b>Title</b>\n\ntext");
+  });
+
+  it("renders bullet and ordered lists", () => {
+    expect(markdownToTelegramHtml("- one\n* two\n1. three\n  - nested")).toBe("• one\n• two\n1. three\n  • nested");
+  });
+
+  it("renders fenced code with and without language, escaped and unformatted", () => {
+    const md = "```ts\nconst a = 1 < 2; // **x**\n```\n\n```\nplain\n```";
+    expect(markdownToTelegramHtml(md)).toBe(
+      '<pre><code class="language-ts">const a = 1 &lt; 2; // **x**</code></pre>\n\n<pre>plain</pre>',
+    );
+  });
+
+  it("merges consecutive blockquote lines and renders rules", () => {
+    expect(markdownToTelegramHtml("> a\n> b\n\n---\n\nc")).toBe("<blockquote>a\nb</blockquote>\n\n───\n\nc");
+  });
+
+  it("collapses runs of blank lines and trims", () => {
+    expect(markdownToTelegramHtml("\n\na\n\n\n\nb\n\n")).toBe("a\n\nb");
+  });
+});

src/telegram/markdown.ts

@@ -0,0 +1,81 @@
+export function escapeHtml(text: string): string {
+  return text.replace(/&/g, "&amp;").replace(/</g, "&lt;").replace(/>/g, "&gt;");
+}
+
+const FENCE = /```([\w+-]*)[ \t]*\n([\s\S]*?)\n?```/g;
+
+/** Convert a Markdown subset to Telegram HTML. Unknown constructs are passed through escaped. */
+export function markdownToTelegramHtml(markdown: string): string {
+  const out: string[] = [];
+  let last = 0;
+  for (const m of markdown.matchAll(FENCE)) {
+    out.push(renderBlocks(markdown.slice(last, m.index)));
+    const lang = m[1];
+    const code = escapeHtml(m[2]);
+    out.push(lang ? `<pre><code class="language-${lang}">${code}</code></pre>` : `<pre>${code}</pre>`);
+    last = m.index + m[0].length;
+  }
+  out.push(renderBlocks(markdown.slice(last)));
+  return out.join("").replace(/\n{3,}/g, "\n\n").trim();
+}
+
+function renderBlocks(text: string): string {
+  const lines = text.split("\n");
+  const out: string[] = [];
+  let quote: string[] | null = null;
+  const flushQuote = () => {
+    if (quote) out.push(`<blockquote>${quote.join("\n")}</blockquote>`);
+    quote = null;
+  };
+
+  for (const line of lines) {
+    const q = /^\s{0,3}>\s?(.*)$/.exec(line);
+    if (q) {
+      (quote ??= []).push(renderInline(q[1]));
+      continue;
+    }
+    flushQuote();
+
+    const heading = /^\s{0,3}#{1,6}\s+(.*?)\s*#*\s*$/.exec(line);
+    if (heading) {
+      out.push(`<b>${renderInline(heading[1])}</b>`);
+      continue;
+    }
+    if (/^\s{0,3}([-*_])(\s*\1){2,}\s*$/.test(line)) {
+      out.push("───");
+      continue;
+    }
+    const bullet = /^(\s*)[-*+]\s+(.*)$/.exec(line);
+    if (bullet) {
+      out.push(`${bullet[1]}• ${renderInline(bullet[2])}`);
+      continue;
+    }
+    const ordered = /^(\s*)(\d+)[.)]\s+(.*)$/.exec(line);
+    if (ordered) {
+      out.push(`${ordered[1]}${ordered[2]}. ${renderInline(ordered[3])}`);
+      continue;
+    }
+    out.push(renderInline(line));
+  }
+  flushQuote();
+  return out.join("\n");
+}
+
+function renderInline(text: string): string {
+  const codes: string[] = [];
+  let s = text.replace(/`([^`\n]+)`/g, (_m, code: string) => {
+    codes.push(`<code>${escapeHtml(code)}</code>`);
+    return `\u0000${codes.length - 1}\u0000`;
+  });
+  s = escapeHtml(s);
+  s = s.replace(
+    /\[([^\]\n]+)\]\((https?:\/\/[^\s)]+)\)/g,
+    (_m, label: string, url: string) => `<a href="${url.replace(/"/g, "&quot;")}">${label}</a>`,
+  );
+  s = s.replace(/\*\*(.+?)\*\*/g, "<b>$1</b>");
+  s = s.replace(/__(.+?)__/g, "<b>$1</b>");
+  s = s.replace(/~~(.+?)~~/g, "<s>$1</s>");
+  s = s.replace(/(^|[^*\w])\*(?!\s)([^*\n]+?)(?<!\s)\*(?!\w)/g, "$1<i>$2</i>");
+  s = s.replace(/(^|[^_\w])_(?!\s)([^_\n]+?)(?<!\s)_(?!\w)/g, "$1<i>$2</i>");
+  return s.replace(/\u0000(\d+)\u0000/g, (_m, i: string) => codes[Number(i)]);
+}