feat: improve worksheet

src/util/markup.rs

@@ -113,6 +113,32 @@ pub fn to_plain(src: &str) -> String {
     out.trim().to_string()
 }
 
+/// Converts authoring markup to Pandoc-flavoured Markdown, for a Quarto document.
+///
+/// Subscripts and superscripts become Pandoc's `~x~` and `^x^`, the symbol table
+/// renders as Unicode, and the bold, italic, and inline-code spans are already
+/// Markdown, so they pass through unchanged. Paragraph breaks are kept. Nothing is
+/// HTML-escaped, because the consumer is a Markdown renderer rather than a page.
+///
+/// # Arguments
+///
+/// * `src` - the authoring source.
+///
+/// # Returns
+///
+/// Pandoc Markdown, trimmed, with paragraph breaks preserved.
+pub fn to_markdown(src: &str) -> String {
+    let symbolized = apply_symbols(src, false);
+    let mut out = wrap_bracket(&symbolized, "#sub[", "~", "~");
+    out = wrap_bracket(&out, "#sup[", "^", "^");
+    out.lines()
+        .map(|l| l.trim_end())
+        .collect::<Vec<_>>()
+        .join("\n")
+        .trim()
+        .to_string()
+}
+
 /// Passes authoring markup through for Typst.
 ///
 /// The markup is already a Typst subset, so this only normalizes whitespace and
@@ -379,4 +405,21 @@ mod tests {
         assert_eq!(to_typst("a @ b"), "a \\@ b");
         assert_eq!(to_typst("x < y"), "x \\< y");
     }
+
+    #[test]
+    fn markdown_uses_pandoc_scripts_and_unicode_symbols() {
+        assert_eq!(to_markdown("H#sub[2]O"), "H~2~O");
+        assert_eq!(to_markdown("x#sup[2]"), "x^2^");
+        assert_eq!(
+            to_markdown("K#sub[m] #sym.approx 5 mM"),
+            "K~m~ \u{2248} 5 mM"
+        );
+        // Bold, italic, and code are already Markdown.
+        assert_eq!(
+            to_markdown("**bold** and *em* and `code`"),
+            "**bold** and *em* and `code`"
+        );
+        // Paragraph breaks survive.
+        assert_eq!(to_markdown("one\n\ntwo"), "one\n\ntwo");
+    }
 }