fix: order a citation run ascending, and name each page once (#24)

src/__tests__/citations.test.ts

@@ -170,6 +170,20 @@ describe("linkCitations", () => {
     );
   });
 
+  it("orders a run ascending, because a model lists by rank and a reader reads by number", () => {
+    // A real answer sent [2][1] for a sentence resting on both, which drew as
+    // "two, one" and left the reader to work out that it meant the first two sources.
+    expect(linkCitations("Both [3][1] agree.", sources).text).toBe(
+      "Both [¹](https://first.example) [³](https://third.example) agree.",
+    );
+  });
+
+  it("cites one page once, however often a run names it", () => {
+    expect(linkCitations("Both [3][1][3] agree.", sources).text).toBe(
+      "Both [¹](https://first.example) [³](https://third.example) agree.",
+    );
+  });
+
   it("leaves a marker alone when the destination is not one this window should open", () => {
     const unsafe = [{ index: 1, title: "Nasty", url: "javascript:alert(1)" }];
     const result = linkCitations("See [1].", unsafe);

src/lib/citations.ts

@@ -198,8 +198,8 @@ function stripDefinitions(text: string, known: Set<number>): string {
 }
 
 /**
- * `[1]`, `[^1]`, `[1, 3]` and `[1][2]` as superscript links, plus the numbers that
- * became links.
+ * `[1]`, `[^1]`, `[1, 3]` and `[1][2]` as superscript links, ordered ascending and
+ * each page once, 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
@@ -214,7 +214,17 @@ export function linkCitations(text: string, sources: Source[]): CitationResult {
 
   const linked = mapOutsideCodeSpans(prose, (chunk) =>
     chunk.replace(CITATION_RUN, (whole: string) => {
-      const wanted = [...whole.matchAll(RUN_NUMBERS)].map((match) => Number(match[0]));
+      /**
+       * Ascending, and each page once.
+       *
+       * A run is a set of sources, and a model lists them in the order it thought of
+       * them rather than by number: a real answer sent `[2][1]` for a sentence resting
+       * on both, which drew as "two, one", and `[8][4]` for another. The numbers
+       * themselves are never renumbered, so `[3]` is still the third source the turn
+       * found and the reader can find it in the list.
+       */
+      const named = [...whole.matchAll(RUN_NUMBERS)].map((match) => Number(match[0]));
+      const wanted = [...new Set(named)].sort((left, right) => left - right);
       const links: string[] = [];
 
       for (const index of wanted) {