fix: raise citation markers and stop adjacent ones merging (#22)

src/lib/citations.ts

@@ -104,13 +104,46 @@ export interface CitationResult {
 }
 
 /**
- * A citation marker the model wrote, in the two shapes it reaches for.
+ * One citation marker, in the two shapes a model reaches for, plus any markers
+ * written straight after it.
+ *
+ * Adjacent markers are matched as a single run, because a raised digit carries no
+ * separator of its own: `[1][2]` drawn as `¹²` reads as twelve, or as twenty one, and
+ * either way as one number rather than as two sources.
  *
  * The trailing guards are what keep this off markdown the model wrote on purpose:
  * `](` starts a link, and `]:` is a reference definition. The digit list allows
- * `[1, 3]`, which is how a sentence resting on two sources is usually written.
+ * `[1, 3]`, which is how a sentence resting on two sources is often written.
  */
-const CITATION_MARKER = /\[\^?(\d+(?:\s*,\s*\d+)*)\](?![(:])/g;
+const CITATION_RUN = /\[\^?\d+(?:\s*,\s*\d+)*\](?![(:])(?:[ \t]*\[\^?\d+(?:\s*,\s*\d+)*\](?![(:]))*/g;
+
+/** The numbers inside one run, in the order they were written. */
+const RUN_NUMBERS = /\d+/g;
+
+/** The digits a superscript marker is built from, in order. */
+const DIGITS = "0123456789";
+const SUPERSCRIPT = "⁰¹²³⁴⁵⁶⁷⁸⁹";
+
+/**
+ * A number as a superscript, which is what a citation mark is.
+ *
+ * Unicode rather than a `<sup>` tag on purpose. This is the label of a markdown
+ * link, and a plain label cannot be broken by any part of the pipeline, while
+ * inline HTML in a label asks two renderers to agree about something neither this
+ * extension nor its tests can see. The glyphs are raised by design, so the mark
+ * still reads as a superscript even when a font lacks the rarer ones and Qt falls
+ * back for them.
+ */
+function superscript(index: number): string {
+  let out = "";
+
+  for (const digit of String(index)) {
+    const at = DIGITS.indexOf(digit);
+    out += at >= 0 ? SUPERSCRIPT[at] : digit;
+  }
+
+  return out;
+}
 
 /**
  * A footnote definition line, which is `[^1]: title, url` on a line of its own.
@@ -165,7 +198,8 @@ function stripDefinitions(text: string, known: Set<number>): string {
 }
 
 /**
- * `[1]`, `[^1]` and `[1, 3]` as links, plus the numbers that became links.
+ * `[1]`, `[^1]`, `[1, 3]` and `[1][2]` as superscript links, plus the numbers that
+ * became links.
  *
  * One run of prose only: fences are the caller's business, because the caller
  * already walks the document in segments for the maths pass and there is no
@@ -179,8 +213,8 @@ export function linkCitations(text: string, sources: Source[]): CitationResult {
   const prose = stripDefinitions(text, new Set(byIndex.keys()));
 
   const linked = mapOutsideCodeSpans(prose, (chunk) =>
-    chunk.replace(CITATION_MARKER, (whole: string, digits: string) => {
-      const wanted = digits.split(",").map((part) => Number(part.trim()));
+    chunk.replace(CITATION_RUN, (whole: string) => {
+      const wanted = [...whole.matchAll(RUN_NUMBERS)].map((match) => Number(match[0]));
       const links: string[] = [];
 
       for (const index of wanted) {
@@ -190,10 +224,12 @@ export function linkCitations(text: string, sources: Source[]): CitationResult {
         // marker that is partly a link reads as a citation that works.
         if (!href) return whole;
 
-        links.push(markdownLink(`[${index}]`, href));
+        links.push(markdownLink(superscript(index), href));
       }
 
       for (const index of wanted) cited.add(index);
+      // Separated even when the model wrote them touching: `¹, ²` is two citations,
+      // where `¹²` is a number, and the reader has no way to tell it from a real one.
       return links.join(", ");
     }),
   );