fix(jobindex-search): decode hex HTML entities in CLI output (#56)

decodeHtmlEntities (duplicated in src/helpers.ts and
src/commands/detail.ts) only handled decimal numeric character
references (é); the equally valid hexadecimal form (é) fell
through undecoded and surfaced as raw text in titles, companies,
locations and descriptions. This bites Danish content especially
(ae/o/aa often arrive as entities). It also used String.fromCharCode,
which corrupts supplementary-plane code points (e.g. emoji, U+1F600).

Add a hexadecimal numeric-entity rule and route both decimal and hex
through a fromCodePoint-based helper with a valid-range guard, in both
copies. Add network-free unit tests via the exported parseJobCards.

.agents/skills/jobindex-search/cli/src/commands/detail.ts

@@ -19,6 +19,15 @@ interface DetailResult {
   description: string | null
 }
 
+/**
+ * Convert a Unicode code point to a string. Uses `fromCodePoint` (not
+ * `fromCharCode`) so supplementary-plane code points (e.g. emoji, U+1F600)
+ * decode correctly, and drops out-of-range values instead of throwing.
+ */
+function numericEntity(cp: number): string {
+  return cp >= 0 && cp <= 0x10ffff ? String.fromCodePoint(cp) : ""
+}
+
 /**
  * Decode HTML entities in text
  */
@@ -30,7 +39,9 @@ function decodeHtmlEntities(text: string): string {
     .replace(/&quot;/g, '"')
     .replace(/&#39;/g, "'")
     .replace(/&apos;/g, "'")
-    .replace(/&#(\d+);/g, (_, code) => String.fromCharCode(parseInt(code, 10)))
+    // Numeric character references: decimal (&#233;) and hexadecimal (&#xE9;).
+    .replace(/&#(\d+);/g, (_, dec) => numericEntity(parseInt(dec, 10)))
+    .replace(/&#[xX]([0-9a-fA-F]+);/g, (_, hex) => numericEntity(parseInt(hex, 16)))
     .replace(/&nbsp;/g, " ")
 }
 

.agents/skills/jobindex-search/cli/src/helpers.ts

@@ -180,6 +180,15 @@ export function parseSearchPage(html: string): SearchPageResult {
   return { total, results }
 }
 
+/**
+ * Convert a Unicode code point to a string. Uses `fromCodePoint` (not
+ * `fromCharCode`) so supplementary-plane code points (e.g. emoji, U+1F600)
+ * decode correctly, and drops out-of-range values instead of throwing.
+ */
+function numericEntity(cp: number): string {
+  return cp >= 0 && cp <= 0x10ffff ? String.fromCodePoint(cp) : ""
+}
+
 /**
  * Decode HTML entities in text
  */
@@ -191,7 +200,9 @@ function decodeHtmlEntities(text: string): string {
     .replace(/&quot;/g, '"')
     .replace(/&#39;/g, "'")
     .replace(/&apos;/g, "'")
-    .replace(/&#(\d+);/g, (_, code) => String.fromCharCode(parseInt(code, 10)))
+    // Numeric character references: decimal (&#233;) and hexadecimal (&#xE9;).
+    .replace(/&#(\d+);/g, (_, dec) => numericEntity(parseInt(dec, 10)))
+    .replace(/&#[xX]([0-9a-fA-F]+);/g, (_, hex) => numericEntity(parseInt(hex, 16)))
     .replace(/&nbsp;/g, " ")
 }
 

.agents/skills/jobindex-search/cli/tests/parsing.test.ts

@@ -0,0 +1,46 @@
+import { describe, test, expect } from "bun:test";
+import { parseJobCards } from "../src/helpers";
+
+// Minimal jobad-wrapper markup: parseJobCards splits on `jobad-wrapper-<id>`
+// and reads the title from the <h4><a href>…</a></h4> and the company from the
+// jix-toolbar-top__company link. We inject HTML entities to exercise decoding.
+function card(id: string, title: string, company = "Acme A/S"): string {
+  return `<div id="jobad-wrapper-${id}" class="PaidJob">
+    <h4><a href="https://www.jobindex.dk/jobannonce/${id}">${title}</a></h4>
+    <div class="jix-toolbar-top__company">
+      <a href="https://www.jobindex.dk/virksomhed/acme">${company}</a>
+    </div>
+  </div>`;
+}
+
+describe("decodeHtmlEntities (via parseJobCards)", () => {
+  test("decodes hexadecimal numeric entities (&#xF8; -> ø)", () => {
+    const [c] = parseJobCards(card("h1", "Sm&#xF8;rrebro Chef"));
+    expect(c.title).toBe("Smørrebro Chef");
+  });
+
+  test("decodes uppercase-X hexadecimal entities (&#XE6; -> æ)", () => {
+    const [c] = parseJobCards(card("h2", "K&#XE6;re Kollega"));
+    expect(c.title).toBe("Kære Kollega");
+  });
+
+  test("still decodes decimal numeric entities (&#229; -> å) — regression", () => {
+    const [c] = parseJobCards(card("h3", "&#229;rhus Lead"));
+    expect(c.title).toBe("århus Lead");
+  });
+
+  test("decodes supplementary-plane code points with fromCodePoint (&#128512;)", () => {
+    const [c] = parseJobCards(card("h4", "Growth &#128512;"));
+    expect(c.title).toBe("Growth 😀");
+  });
+
+  test("decodes hex supplementary-plane code points (&#x1F600;)", () => {
+    const [c] = parseJobCards(card("h5", "Growth &#x1F600;"));
+    expect(c.title).toBe("Growth 😀");
+  });
+
+  test("decodes hex entities in the company name too", () => {
+    const [c] = parseJobCards(card("h6", "Engineer", "N&#xF8;rrebro ApS"));
+    expect(c.company).toBe("Nørrebro ApS");
+  });
+});