From b27a3b5e810d8edbd44884223a9210d84c7901dd Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Yi=C4=9Fit=20ERDO=C4=9EAN?= <yigiterdogan023@gmail.com>
Date: Tue, 7 Jul 2026 20:40:32 +0300
Subject: [PATCH] fix(linkedin-search): decode hex HTML entities in CLI output
 (#55)

decodeHtmlEntities only handled decimal numeric character references
(&#233;); the equally valid hexadecimal form (&#xE9;) fell through
undecoded and surfaced as raw text in titles, companies, locations and
descriptions. 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. Add
network-free unit tests covering hex, uppercase-X hex, decimal
(regression) and astral code points via the exported parse functions.
---
 .../skills/linkedin-search/cli/src/helpers.ts | 13 ++++-
 .../linkedin-search/cli/tests/parsing.test.ts | 55 +++++++++++++++++++
 2 files changed, 67 insertions(+), 1 deletion(-)
 create mode 100644 .agents/skills/linkedin-search/cli/tests/parsing.test.ts

diff --git a/.agents/skills/linkedin-search/cli/src/helpers.ts b/.agents/skills/linkedin-search/cli/src/helpers.ts
index 56308b3..19e0200 100644
--- a/.agents/skills/linkedin-search/cli/src/helpers.ts
+++ b/.agents/skills/linkedin-search/cli/src/helpers.ts
@@ -67,6 +67,15 @@ export interface JobDetail extends JobCard {
   applyUrl: 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) : ""
+}
+
 function decodeHtmlEntities(text: string): string {
   return text
     .replace(/&amp;/g, "&")
@@ -75,7 +84,9 @@ 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, " ")
 }
 
diff --git a/.agents/skills/linkedin-search/cli/tests/parsing.test.ts b/.agents/skills/linkedin-search/cli/tests/parsing.test.ts
new file mode 100644
index 0000000..49d3115
--- /dev/null
+++ b/.agents/skills/linkedin-search/cli/tests/parsing.test.ts
@@ -0,0 +1,55 @@
+import { describe, test, expect } from "bun:test";
+import { parseJobCards, parseJobDetail } from "../src/helpers";
+
+// Minimal search-card markup: parseJobCards splits on the job-posting URN and
+// needs an id, a base-search-card__title, and a full-link. Everything else is
+// optional. We inject HTML entities into the title/company to exercise decoding.
+function searchCard(id: string, title: string, company = "Acme"): string {
+  return `<li>
+    <div data-entity-urn="urn:li:jobPosting:${id}">
+      <a class="base-card__full-link" href="https://www.linkedin.com/jobs/view/${id}"></a>
+      <h3 class="base-search-card__title">${title}</h3>
+      <h4 class="base-search-card__subtitle"><a href="https://www.linkedin.com/company/acme">${company}</a></h4>
+    </div>
+  </li>`;
+}
+
+describe("decodeHtmlEntities (via parseJobCards)", () => {
+  test("decodes hexadecimal numeric entities (&#xE9;)", () => {
+    const [card] = parseJobCards(searchCard("123", "Caf&#xE9; Manager"));
+    expect(card.title).toBe("Café Manager");
+  });
+
+  test("decodes uppercase-X hexadecimal entities (&#X...;)", () => {
+    const [card] = parseJobCards(searchCard("124", "Deb&#XFC;t Role")); // &#XFC; = ü
+    expect(card.title).toBe("Debüt Role");
+  });
+
+  test("still decodes decimal numeric entities (&#233;) — regression", () => {
+    const [card] = parseJobCards(searchCard("125", "Caf&#233; Lead"));
+    expect(card.title).toBe("Café Lead");
+  });
+
+  test("decodes supplementary-plane code points with fromCodePoint (&#128512;)", () => {
+    const [card] = parseJobCards(searchCard("126", "Growth &#128512;"));
+    expect(card.title).toBe("Growth 😀");
+  });
+
+  test("decodes hex supplementary-plane code points (&#x1F600;)", () => {
+    const [card] = parseJobCards(searchCard("127", "Growth &#x1F600;"));
+    expect(card.title).toBe("Growth 😀");
+  });
+
+  test("decodes hex entities in the company subtitle too", () => {
+    const [card] = parseJobCards(searchCard("128", "Engineer", "N&#xF8;rrebro ApS"));
+    expect(card.company).toBe("Nørrebro ApS");
+  });
+});
+
+describe("decodeHtmlEntities (via parseJobDetail)", () => {
+  test("decodes hex entities inside the job title", () => {
+    const html = `<h1 class="topcard__title">Se&#xF1;or Engineer</h1>`;
+    const job = parseJobDetail(html, "999");
+    expect(job.title).toBe("Señor Engineer");
+  });
+});